Compare commits

...
Author SHA1 Message Date
github-actions[bot] 448a99464d chore: sync CLIProxyAPI v6.9.1-v6.9.2 2026-03-26 09:03:51 +00:00
RCD fc9616026b chore: merge upstream CLIProxyAPI v6.9.2 2026-03-25 09:38:44 +07:00
Luis Pater 76c064c729 Merge pull request #2335 from router-for-me/auth
Support batch upload and delete for auth files
2026-03-25 09:34:44 +08:00
Luis Pater d2f652f436 Merge pull request #2333 from router-for-me/codex
feat(codex): pass through codex client identity headers
2026-03-25 09:34:09 +08:00
Luis Pater 6a452a54d5 Merge pull request #2316 from router-for-me/openai
Add per-model thinking support for OpenAI compatibility
2026-03-25 09:31:28 +08:00
hkfires 9e5693e74f feat(api): support batch auth file upload and delete 2026-03-25 09:20:17 +08:00
hkfires 528b1a2307 feat(codex): pass through codex client identity headers 2026-03-25 08:48:18 +08:00
Luis Pater 0cc978ec1d Merge pull request #2297 from router-for-me/readme
docs(readme): update japanese documentation links
2026-03-25 03:11:24 +08:00
hkfires fee736933b feat(openai-compat): add per-model thinking support 2026-03-24 14:21:12 +08:00
RCD a2a4fba626 chore: merge upstream CLIProxyAPI v6.9.1 2026-03-24 09:41:49 +07:00
hkfires 5c99846ecf docs(readme): update japanese documentation links 2026-03-24 09:47:01 +08:00
Luis Pater d475aaba96 Fixed: #2274
fix(translator): omit null content fields in Codex OpenAI tool call responses
2026-03-24 01:00:57 +08:00
Luis Pater 96f55570f7 Merge pull request #2282 from eltociear/add-ja-doc
docs: add Japanese README
2026-03-24 00:40:58 +08:00
Luis Pater 0906aeca87 Merge pull request #2254 from clcc2019/main
refactor: streamline usage reporting by consolidating record publishi…
2026-03-24 00:39:31 +08:00
Luis Pater 97c0487add Merge pull request #2223 from cnrpman/fix/codex-responses-web-search-preview-compat
fix: normalize web_search_preview for codex responses
2026-03-24 00:25:37 +08:00
Luis Pater a576088d5f Merge pull request #2222 from kaitranntt/kai/fix/758-openai-proxy-alternating-model-support
fix: fall back on model support errors during auth rotation
2026-03-24 00:03:28 +08:00
Luis Pater 66ff916838 Merge pull request #2220 from xulongwu4/main
fix: normalize model name in TranslateRequest fallback to prevent prefix leak
2026-03-23 23:56:15 +08:00
Luis Pater 7b0453074e Merge pull request #2219 from beck-8/fix/context-done-race
fix: avoid data race when watching request cancellation
2026-03-23 22:57:21 +08:00
Luis Pater a000eb523d Merge pull request #2213 from TTTPOB/ua-fix
feat(claude): stabilize device fingerprint across mixed Claude Code and cloaked clients
2026-03-23 22:53:51 +08:00
Luis Pater 18a4fedc7f Merge pull request #2126 from ailuntz/fix/watcher-auth-cache-memory
perf(watcher): reduce auth cache memory
2026-03-23 22:47:34 +08:00
Luis Pater 5d6cdccda0 Merge pull request #2268 from sususu98/fix/sanitize-tool-names
fix(translator): sanitize tool names for Gemini function_declarations compatibility
2026-03-23 21:42:22 +08:00
Luis Pater 1b7f4ac3e1 Merge pull request #2252 from sususu98/fix/antigravity-empty-thought-text
fix(antigravity): always include text field in thought parts to prevent Google 500
2026-03-23 21:41:25 +08:00
Luis Pater afc1a5b814 Fixed: #2281
refactor(claude): centralize usage token calculation logic and add tests for cached token handling
2026-03-23 21:30:03 +08:00
Ikko Eltociear Ashimineandgemini-code-assist[bot] 7ed38db54f docs: update README_JA.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 16:57:43 +09:00
Ikko Eltociear Ashimineandgemini-code-assist[bot] 28c10f4e69 docs: update README_JA.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 16:57:32 +09:00
Ikko Eltociear Ashimineandgemini-code-assist[bot] 6e12441a3b Update README_JA.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 16:57:19 +09:00
Ikko Ashimine 65c439c18d docs: add Japanese README 2026-03-23 15:23:18 +09:00
dslife2025 0ed2d16596 Merge branch 'router-for-me:main' into main 2026-03-23 09:50:43 +08:00
Supra4E8C db335ac616 Merge pull request #2269 from router-for-me/auth-fix
fix(auth): ensure absolute paths for auth file handling
2026-03-22 22:53:44 +08:00
sususu98 e8bb350467 fix: extend tool name sanitization to all remaining Gemini-bound translators
Apply SanitizeFunctionName on request and RestoreSanitizedToolName on
response for: gemini/claude, gemini/openai/chat-completions,
gemini/openai/responses, antigravity/openai/chat-completions,
gemini-cli/openai/chat-completions.

Also update SanitizedToolNameMap to handle OpenAI format
(tools[].function.name) in addition to Claude format (tools[].name).
2026-03-22 14:06:46 +08:00
Supra4E8C 5331d51f27 fix(auth): ensure absolute paths for auth file handling 2026-03-22 13:58:16 +08:00
sususu98 755ca75879 fix: address review feedback - init ToolNameMap eagerly, log collisions, add collision test 2026-03-22 13:24:03 +08:00
sususu98 2398ebad55 fix(translator): sanitize tool names for Gemini function_declarations compatibility
Claude Code and MCP clients may send tool names containing characters
invalid for Gemini's function_declarations (e.g. '/', '@', spaces).
Sanitize on request via SanitizeFunctionName and restore original names
on response for both antigravity/claude and gemini-cli/claude translators.
2026-03-22 13:10:53 +08:00
clcc2019 c1bf298216 refactor: streamline usage reporting by consolidating record publishing logic
- Introduced a new method `buildRecord` in `usageReporter` to encapsulate record creation, improving code readability and maintainability.
- Added latency tracking to usage records, ensuring accurate reporting of request latencies.
- Updated tests to validate the inclusion of latency in usage records and ensure proper functionality of the new reporting structure.
2026-03-20 19:44:26 +08:00
sususu e005208d76 fix(antigravity): always include text field in thought parts to prevent Google 500
When Claude sends redacted thinking with empty text, the translator
was omitting the "text" field from thought parts. Google Antigravity
API requires this field, causing 500 "Unknown Error" responses.

Verified: 129/129 error logs with empty thought → 500, 0/97 success
logs had empty thought. After fix: 0 new "Unknown Error" 500s.
2026-03-20 18:59:25 +08:00
Junyi Du d1df70d02f chore: add codex builtin tool normalization logging 2026-03-20 14:08:37 +08:00
Luis Pater f81acd0760 Merge pull request #2243 from router-for-me/oauth
Improve OAuth callback handling with async prompts
2026-03-20 12:35:44 +08:00
hkfires 636da4c932 refactor(auth): replace manual input handling with AsyncPrompt for callback URLs 2026-03-20 12:24:27 +08:00
hkfires cccb77b552 fix(auth): avoid blocking oauth callback wait on prompt 2026-03-20 11:48:30 +08:00
Luis Pater 2bd646ad70 refactor: replace sjson.Set usage with sjson.SetBytes to optimize mutable JSON transformations 2026-03-19 17:58:54 +08:00
tpob 52c1fa025e fix(claude): learn official fingerprints after custom baselines 2026-03-19 13:59:41 +08:00
tpob 680105f84d fix(claude): refresh cached fingerprint after baseline upgrades 2026-03-19 13:28:58 +08:00
tpob f7069e9548 fix(claude): pin stabilized OS arch to baseline 2026-03-19 13:07:16 +08:00
Junyi Du 793840cdb4 fix: cover dated and nested codex web search aliases 2026-03-19 03:41:12 +08:00
Junyi Du 8f421de532 fix: handle sjson errors in codex tool normalization 2026-03-19 03:36:06 +08:00
Junyi Du be2dd60ee7 fix: normalize web_search_preview for codex responses 2026-03-19 03:23:14 +08:00
Tam Nhu Tran ea3e0b713e fix: harden pooled model-support fallback state 2026-03-18 13:19:20 -04:00
tpob 8179d5a8a4 fix(claude): avoid racy fingerprint downgrades 2026-03-19 01:03:41 +08:00
tpob 6fa7abe434 fix(claude): keep configured baseline above older fingerprints 2026-03-19 01:02:04 +08:00
Tam Nhu Tran 5135c22cd6 fix: fall back on model support errors during auth rotation 2026-03-18 12:43:45 -04:00
Longwu Ou 1e27990561 address PR review: log sjson error and add unit tests
- Log a warning instead of silently ignoring sjson.SetBytes errors in the TranslateRequest fallback path
  - Add registry_test.go with tests covering the fallback model normalization and verifying registered transforms take precedence
2026-03-18 12:43:40 -04:00
Longwu Ou e1e9fc43c1 fix: normalize model name in TranslateRequest fallback to prevent prefix leak
When no request translator is registered for a format pair (e.g.
        openai-response → openai-response), TranslateRequest returned the raw
        payload unchanged. This caused client-side model prefixes (e.g.
        "copilot/gpt-5-mini") to leak into upstream requests, resulting in
        "The requested model is not supported" errors from providers.

        The fallback path now updates the "model" field in the payload to
        match the resolved model name before returning.
2026-03-18 12:30:22 -04:00
beck-8 b2921518ac fix: avoid data race when watching request cancellation 2026-03-19 00:15:52 +08:00
tpob dd64adbeeb fix(claude): preserve legacy user agent overrides 2026-03-19 00:03:09 +08:00
tpob 616d41c06a fix(claude): restore legacy runtime OS arch fallback 2026-03-19 00:01:50 +08:00
tpob e0e337aeb9 feat(claude): add switch for device profile stabilization 2026-03-18 19:31:59 +08:00
tpob d52839fced fix: stabilize claude device fingerprint 2026-03-18 18:46:54 +08:00
Luis Pater 56073ded69 Merge pull request #2200 from sususu98/feat/local-model-flag
feat: add -local-model flag to skip remote model catalog fetching
2026-03-18 10:58:07 +08:00
sususu98 9738a53f49 feat: add -local-model flag to skip remote model catalog fetching
When enabled, the server uses only the embedded models.json loaded at
init() and skips registry.StartModelsUpdater(), disabling the initial
remote fetch and 3-hour periodic refresh. The management panel
auto-updater (managementasset.StartAutoUpdater) is unaffected.
2026-03-18 10:48:03 +08:00
Luis Pater be3f8dbf7e Merge pull request #2187 from Darley-Wey/fix/claude-disable-parallel-tool-calls
fix(claude): honor disable_parallel_tool_use
2026-03-17 21:06:08 +08:00
Darley 9c6c3612a8 fix(claude): read disable_parallel_tool_use from tool_choice 2026-03-17 19:35:41 +08:00
Darley 19e1a4447a fix(claude): honor disable_parallel_tool_use 2026-03-17 19:17:41 +08:00
RCD 3595d47a9d docs: record v0.3.0-dev-0.43 release 2026-03-17 02:29:57 +07:00
RCD 82a00093b6 chore: merge upstream CLIProxyAPI v6.8.55 2026-03-17 02:25:21 +07:00
Luis Pater fb95813fbf Merge pull request #2142 from Muran-prog/fix/strip-uniqueItems-gemini-2123
fix: strip uniqueItems from Gemini function_declarations (#2123)
2026-03-16 20:34:28 +08:00
Luis Pater db63f9b5d6 Merge pull request #2162 from enieuwy/fix/responses-api-json-valid-check
fix: validate JSON before raw-embedding function call outputs in Responses API
2026-03-16 18:42:31 +08:00
Luis Pater 25f6c4a250 Merge pull request #2158 from sususu98/fix/antigravity-functionresponse-name
fix(antigravity): resolve empty functionResponse.name for toolu_* tool_use_id format
2026-03-16 18:39:40 +08:00
enieuwy b24ae74216 fix: validate JSON before raw-embedding function call outputs in Responses API
gjson.Parse() marks any string starting with { or [ as gjson.JSON type,
even when the content is not valid JSON (e.g. macOS plist format, truncated
tool results). This caused sjson.SetRaw to embed non-JSON content directly
into the Gemini API request payload, producing 400 errors.

Add json.Valid() check before using SetRaw to ensure only actually valid
JSON is embedded raw. Non-JSON content now falls through to sjson.Set
which properly escapes it as a JSON string.

Fixes #2161
2026-03-16 15:29:18 +08:00
Luis Pater 59ad8f40dc Merge pull request #2124 from RGBadmin/feat/auth-list-priority-note
feat(api): expose priority and note in GET /auth-files response
2026-03-16 12:31:11 +08:00
sususu98 ff03dc6a2c fix(antigravity): resolve empty functionResponse.name for toolu_* tool_use_id format
The Claude-to-Gemini translator derived function names by splitting
tool_use_id on "-", which produced empty strings for IDs with exactly
2 segments (e.g. toolu_tool-<uuid>). Replace the string-splitting
heuristic with a lookup map built from tool_use blocks during the
main processing loop, with fallback to the raw ID on miss.
2026-03-16 11:18:29 +08:00
Luis Pater dc7187ca5b fix(websocket): pin only websocket-capable auth IDs and add corresponding test 2026-03-16 09:57:38 +08:00
Luis Pater b1dcff778c Merge pull request #2141 from Muran-prog/fix/tool-calling-translation-2132
fix: skip empty assistant message in tool call translation (#2132)
2026-03-16 01:42:27 +08:00
Luis Pater 198b3f4a40 chore(ci): update build metadata to use GITHUB_REF_NAME in workflows 2026-03-16 00:30:44 +08:00
Luis Pater 9fee7f488e chore(ci): update GoReleaser config and release workflow to skip validation step 2026-03-16 00:16:25 +08:00
RGBadminandClaude Opus 4.6 c1241a98e2 fix(api): restrict fallback note to string-typed JSON values
Only emit note in listAuthFilesFromDisk when the JSON value is actually
a string (gjson.String), matching the synthesizer/buildAuthFileEntry
behavior. Non-string values like numbers or booleans are now ignored
instead of being coerced via gjson.String().

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 23:00:17 +08:00
RGBadminandClaude Opus 4.6 8d8f5970ee fix(api): fallback to Metadata for priority/note on uploaded auths
buildAuthFileEntry now falls back to reading priority/note from
auth.Metadata when Attributes lacks them. This covers auths registered
via UploadAuthFile which bypass the synthesizer and only populate
Metadata from the raw JSON.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 17:36:11 +08:00
RGBadminandClaude Opus 4.6 f90120f846 fix(api): propagate note to Gemini virtual auths and align priority parsing
- Read note from Attributes (consistent with priority) in buildAuthFileEntry,
  fixing missing note on Gemini multi-project virtual auth cards.
- Propagate note from primary to virtual auths in SynthesizeGeminiVirtualAuths,
  mirroring existing priority propagation.
- Sync note/priority writes to both Metadata and Attributes in PatchAuthFileFields,
  with refactored nil-check to reduce duplication (review feedback).
- Validate priority type in fallback disk-read path instead of coercing all values
  to 0 via gjson.Int(), aligning with the auth-manager code path.
- Add regression tests for note synthesis, virtual-auth note propagation, and
  end-to-end multi-project Gemini note inheritance.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 16:47:01 +08:00
Muran-prog 0b94d36c4a test: use exact match for tool name assertion
Address review feedback - drop function.name fallback and
strings.Contains in favor of direct == comparison.
2026-03-14 21:45:28 +02:00
Muran-prog 152c310bb7 test: add uniqueItems stripping test
Covers the fix from the previous commit — verifies uniqueItems is
removed from the schema and moved to the description hint.
2026-03-14 21:22:14 +02:00
Muran-prog f6bbca35ab fix: strip uniqueItems from Gemini function_declarations (#2123)
Gemini API rejects uniqueItems in tool schemas with 400. Add it to
unsupportedConstraints alongside minItems/maxItems where it belongs.

Same class of fix as #1424 and #1531.
2026-03-14 21:18:06 +02:00
Muran-prog c8cee6a209 fix: skip empty assistant message in tool call translation (#2132)
When assistant has tool_calls but no text content, the translator
emitted an empty message into the Responses API input array before
function_call items. The API then couldn't match function_call_output
to its function_call by call_id, returning:

  No tool output found for function call ...

Only emit assistant messages that have content parts. Tool-call-only
messages now produce function_call items directly.

Added 9 tests for tool calling translation covering single/parallel
calls, multi-turn conversations, name shortening, empty content
edge cases, and call_id integrity.
2026-03-14 21:01:01 +02:00
Luis Pater b5701f416b Fixed: #2102
fix(auth): ensure unique auth index for shared API keys across providers and credential identities
2026-03-15 02:48:54 +08:00
Luis Pater 4b1a404fcb Fixed: #1936
feat(translator): add image type handling in ConvertClaudeRequestToGemini
2026-03-15 02:18:28 +08:00
Luis Pater 67669196ed Merge pull request #2131 from HEUDavid/docs/add-who-is-with-us
docs: Add Shadow AI to 'Who is with us?' section
2026-03-15 01:44:46 +08:00
hkfires 58fd9bf964 fix(codex): add 'go' plan_type in registerModelsForAuth 2026-03-14 22:09:14 +08:00
HEUDavid 7b3dfc67bc docs: Add Shadow AI to 'Who is with us?' section 2026-03-14 21:01:07 +08:00
HEUDavid cdd24052d3 docs: Add Shadow AI to 'Who is with us?' section 2026-03-14 20:53:43 +08:00
Luis Pater 733fd8edab Merge pull request #2111 from qzydustin/main
Fix missing streaming usage tracking for OpenAI-compatible providers
2026-03-14 18:17:08 +08:00
Luis Pater af27f2b8bc Merge pull request #2110 from router-for-me/codex
feat(service): extend model registration for team and business types
2026-03-14 18:10:01 +08:00
Luis Pater 2e1925d762 Merge pull request #2108 from sususu98/fix/gemini-cli-tool-schema-and-empty-parts
fix(gemini-cli): sanitize tool schemas and filter empty parts
2026-03-14 18:02:52 +08:00
Luis Pater 77254bd074 Merge pull request #2116 from router-for-me/vertex
fix(config): allow vertex keys without base-url
2026-03-14 17:27:48 +08:00
RGBadminandClaude Opus 4.6 5b6342e6ac feat(api): expose priority and note fields in GET /auth-files list response
The list endpoint previously omitted priority and note, which are stored
inside each auth file's JSON content. This adds them to both the normal
(auth-manager) and fallback (disk-read) code paths, and extends
PATCH /auth-files/fields to support writing the note field.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 14:47:31 +08:00
hkfires 560c020477 fix(config): allow vertex keys without base-url 2026-03-13 19:09:26 +08:00
Zhenyu Qi aec65e3be3 fix(openai_compat): add stream_options.include_usage for streaming usage tracking 2026-03-13 00:48:17 -07:00
hkfires f44f0702f8 feat(service): extend model registration for team and business types 2026-03-13 14:12:19 +08:00
sususu98 b76b79068f fix(gemini-cli): sanitize tool schemas and filter empty parts
1. Claude translator: add CleanJSONSchemaForGemini() to sanitize tool
   input schemas (removes $schema, anyOf, const, format, etc.) and
   delete eager_input_streaming from tool declarations. Remove fragile
   bytes.Replace for format:"uri" now covered by schema cleaner.

2. Gemini native translator: filter out content entries with empty or
   missing parts arrays to prevent Gemini API 400 error "required
   oneof field 'data' must have one initialized field".

Both fixes align gemini-cli with protections already present in the
antigravity translator.
2026-03-13 12:37:37 +08:00
Luis Pater 1db23979e8 Merge pull request #2106 from router-for-me/model
feat(model_registry): enhance model registration and refresh mechanisms
2026-03-13 11:18:51 +08:00
hkfires c3d5dbe96f feat(model_registry): enhance model registration and refresh mechanisms 2026-03-13 10:56:39 +08:00
RCD 3a828bb14c docs: record maintenance fix rollout 2026-03-12 12:55:04 +07:00
RCD c93f57a02a fix(translator): align tool and gemini semantics 2026-03-12 12:54:50 +07:00
RCD dd0d99e64b fix(management): harden handler state and paths 2026-03-12 12:54:33 +07:00
RCD 96f28fc5d5 fix(auth): harden token persistence and refresh 2026-03-12 12:54:14 +07:00
RCD 85f6a29477 docs: record maintenance review findings 2026-03-12 12:02:21 +07:00
RCD 13a1fbe946 fix(auth): resolve nested filestore deletes 2026-03-12 11:20:51 +07:00
RCD 1f82eedbef chore: switch releases to manual publishing 2026-03-12 11:07:03 +07:00
RCD d9e5506949 docs: track CLIProxyAPI v6.8.51 sync 2026-03-12 11:00:53 +07:00
RCD 6628e20d8c fix(cmd): align model listing with codex tiers 2026-03-12 11:00:16 +07:00
RCD 64e2a43259 chore: merge upstream CLIProxyAPI v6.8.51 2026-03-12 10:58:52 +07:00
RCD febd409cca Merge tag 'v6.8.50' 2026-03-12 10:53:58 +07:00
Luis Pater 5484489406 chore(ci): update model catalog fetch method in workflows 2026-03-12 11:19:24 +08:00
Luis Pater 0ac52da460 chore(ci): update model catalog fetch method in release workflow 2026-03-12 10:50:46 +08:00
Luis Pater 817cebb321 Merge pull request #2082 from router-for-me/antigravity
Refactor Antigravity model handling and improve logging
2026-03-12 10:39:13 +08:00
Luis Pater 683f3709d6 Merge pull request #2076 from aikins01/fix/backfill-empty-function-response-names
fix: backfill empty functionResponse.name from preceding functionCall
2026-03-12 10:35:44 +08:00
hkfires dbd42a42b2 fix(model_updater): clarify log message for model refresh failure 2026-03-12 10:32:04 +08:00
hkfires ec24baf757 feat(fetch_antigravity_models): add command to fetch and save Antigravity model list 2026-03-12 10:21:09 +08:00
hkfires dea3e74d35 feat(antigravity): refactor model handling and remove unused code 2026-03-12 09:24:45 +08:00
Aikins Laryea a6c3042e34 refactor: remove redundant bounds checks per code review 2026-03-12 00:12:43 +00:00
Aikins Laryea 861537c9bd fix: backfill empty functionResponse.name from preceding functionCall
when Amp or Claude Code sends functionResponse with an empty name in Gemini
conversation history, the Gemini API rejects the request with 400
"Name cannot be empty". this fix backfills empty names from the
corresponding preceding functionCall parts using positional matching.

covers all three Gemini translator paths:
- gemini/gemini (direct API key)
- antigravity/gemini (OAuth)
- gemini-cli/gemini (Gemini CLI)

also switches fixCLIToolResponse pending group matching from LIFO to
FIFO to correctly handle multiple sequential tool call groups.

fixes #1903
2026-03-12 00:00:38 +00:00
Luis Pater 8c92cb0883 Merge pull request #2056 from lang-911/codex/custom-useragent-request
feat(config/codex): Add Codex header defaults (`user-agent`: override; `beta-features`: default)
2026-03-11 22:56:36 +08:00
Luis Pater 89d7be9525 Merge branch 'dev' into codex/custom-useragent-request 2026-03-11 22:55:50 +08:00
lang-911 2b79d7f22f fix: restore double quotes style in config.example.yaml for consistency and readability 2026-03-11 06:59:26 -07:00
lang-911 163fe287ce fix: codex header defaults example 2026-03-11 06:55:03 -07:00
lang-911 70988d387b Add Codex websocket header defaults 2026-03-11 00:34:57 -07:00
Luis Pater ddaa9d2436 Fixed: #2034
feat(proxy): centralize proxy handling with `proxyutil` package and enhance test coverage

- Added `proxyutil` package to simplify proxy handling across the codebase.
- Refactored various components (`executor`, `cliproxy`, `auth`, etc.) to use `proxyutil` for consistent and reusable proxy logic.
- Introduced support for "direct" proxy mode to explicitly bypass all proxies.
- Updated tests to validate proxy behavior (e.g., `direct`, HTTP/HTTPS, and SOCKS5).
- Enhanced YAML configuration documentation for proxy options.
2026-03-11 11:08:02 +08:00
Luis Pater 7b7b258c38 Fixed: #2022
test(translator): add tests for handling Claude system messages as string and array
2026-03-11 10:47:33 +08:00
Luis Pater cf74ed2f0c Merge pull request #2013 from router-for-me/model
Fetch model catalog from network
2026-03-10 19:07:23 +08:00
ailuntz c3762328a5 perf(watcher): reduce auth cache memory 2026-03-10 16:27:10 +08:00
hkfires e333fbea3d feat(updater): update StartModelsUpdater to block until models refresh completes 2026-03-10 14:41:58 +08:00
hkfires efbe36d1d4 feat(updater): change models refresh to one-time fetch on startup 2026-03-10 14:18:54 +08:00
hkfires 8553cfa40e feat(workflows): refresh models catalog in workflows 2026-03-10 14:03:31 +08:00
hkfires 30d5c95b26 feat(registry): refresh model catalog from network 2026-03-10 14:02:54 +08:00
hkfires d1e3195e6f feat(codex): register models by plan tier 2026-03-10 11:20:37 +08:00
Luis Pater ce53d3a287 Fixed: #1997
test(auth-scheduler): add benchmarks and priority-based scheduling improvements

- Added `BenchmarkManagerPickNextMixedPriority500` for mixed-priority performance assessment.
- Updated `pickNextMixed` to prioritize highest ready priority tiers.
- Introduced `highestReadyPriorityLocked` and `pickReadyAtPriorityLocked` for better scheduling logic.
- Added unit test to validate selection of highest priority tiers in mixed provider scenarios.
2026-03-09 22:27:15 +08:00
Luis Pater 4cc99e7449 Merge pull request #1992 from dcrdev/main
System prompt silently dropped when sent as a string
2026-03-09 21:03:15 +08:00
Luis Pater 71773fe032 Merge pull request #1996 from router-for-me/codex/fix-unbounded-websocket-log-buffering
fix: cap websocket body log growth in responses handler
2026-03-09 20:50:38 +08:00
Dominic Robinson a1e0fa0f39 test(executor): cover string system prompt handling in checkSystemInstructionsWithMode 2026-03-09 12:40:27 +00:00
Supra4E8C fc2f0b6983 fix: cap websocket body log growth 2026-03-09 17:48:30 +08:00
Dominic Robinson 5c9997cdac fix: Preserve system prompt when sent as a string instead of content block array 2026-03-09 07:38:11 +00:00
RCD 23e9dda036 docs: track CLIProxyAPI v6.8.49 sync 2026-03-09 09:05:54 +07:00
RCD af4affc150 fix(update): point release checks at ProxyPilot 2026-03-09 09:05:44 +07:00
RCD bd11f5372d chore: merge upstream CLIProxyAPI v6.8.49
# Conflicts:
#	README.md
#	README_CN.md
2026-03-09 09:02:25 +07:00
RCD 98247b0b8d chore: merge upstream CLIProxyAPI v6.8.48 2026-03-09 09:01:45 +07:00
RCD 691aeb78fe chore: merge upstream CLIProxyAPI v6.8.47 2026-03-09 09:01:41 +07:00
Luis Pater f5941a411c test(auth): cover scheduler refresh regression paths 2026-03-09 09:27:56 +08:00
Luis Pater ba672bbd07 Merge PR #1969 into dev 2026-03-09 09:25:06 +08:00
Luis Pater d9c6627a53 Merge pull request #1963 from qixing-jk/docs/add-all-api-hub-showcase
docs: add All API Hub to related projects list
2026-03-09 09:16:41 +08:00
Luis Pater 2e9907c3ac Merge pull request #1959 from thebtf/fix/system-instruction-camelcase
fix: use camelCase systemInstruction in OpenAI-to-Gemini translators
2026-03-09 09:09:03 +08:00
DragonFSKY 90afb9cb73 fix(auth): new OAuth accounts invisible to scheduler after dynamic registration
When new OAuth auth files are added while the service is running,
`applyCoreAuthAddOrUpdate` calls `coreManager.Register()` (which upserts
into the scheduler) BEFORE `registerModelsForAuth()`. At upsert time,
`buildScheduledAuthMeta` snapshots `supportedModelSetForAuth` from the
global model registry — but models haven't been registered yet, so the
set is empty. With an empty `supportedModelSet`, `supportsModel()`
always returns false and the new auth is never added to any model shard.

Additionally, when all existing accounts are in cooldown, the scheduler
returns `modelCooldownError`, but `shouldRetrySchedulerPick` only
handles `*Error` types — so the `syncScheduler` safety-net rebuild
never triggers and the new accounts remain invisible.

Fix:
1. Add `RefreshSchedulerEntry()` to re-upsert a single auth after its
   models are registered, rebuilding `supportedModelSet` from the
   now-populated registry.
2. Call it from `applyCoreAuthAddOrUpdate` after `registerModelsForAuth`.
3. Make `shouldRetrySchedulerPick` also match `*modelCooldownError` so
   the full scheduler rebuild triggers when all credentials are cooling
   down — catching any similar stale-snapshot edge cases.
2026-03-09 03:11:47 +08:00
anime d0cc0cd9a5 docs: add All API Hub to related projects list
- Update README.md with All API Hub entry in English
- Update README_CN.md with All API Hub entry in Chinese
2026-03-09 02:00:16 +08:00
Kirill Turanskiy 338321e553 fix: use camelCase systemInstruction in OpenAI-to-Gemini translators
The Gemini v1internal (cloudcode-pa) and Antigravity Manager endpoints
require camelCase "systemInstruction" in request JSON. The current
snake_case "system_instruction" causes system prompts to be silently
ignored when routing through these endpoints.

Replace all "system_instruction" JSON keys with "systemInstruction" in
chat-completions and responses request translators.
2026-03-08 15:59:13 +03:00
Luis Pater 4f48e5254a Merge pull request #1957 from router-for-me/thinking
fix(translator): pass through adaptive thinking effort
2026-03-08 20:46:58 +08:00
Luis Pater 15dd5db1d7 Merge pull request #1956 from router-for-me/vertex
fix(executor): use aiplatform base url for vertex api key calls
2026-03-08 20:46:28 +08:00
hkfires 424711b718 fix(executor): use aiplatform base url for vertex api key calls 2026-03-08 20:13:12 +08:00
Luis Pater 2b134fc378 test(auth-scheduler): add unit tests and scheduler implementation
- Added comprehensive unit tests for `authScheduler` and related components.
- Implemented `authScheduler` with support for Round Robin, Fill First, and custom selector strategies.
- Improved tracking of auth states, cooldowns, and recovery logic in scheduler.
2026-03-08 05:52:55 +08:00
Luis Pater b9153719b0 Merge pull request #1925 from shenshuoyaoyouguang/pr/openai-compat-pool-thinking
fix(openai-compat): improve pool fallback and preserve adaptive thinking
2026-03-08 01:05:05 +08:00
Luis Pater 631e5c8331 Merge pull request #1922 from shenshuoyaoyouguang/pr/model-registry-safety
fix(registry): clone model snapshots and invalidate available-model cache
2026-03-07 23:01:42 +08:00
Luis Pater e9c60a0a67 Merge pull request #1910 from thebtf/fix/gemini-oauth-error-messages
fix: surface upstream error details in Gemini CLI OAuth onboarding UI
2026-03-07 22:25:18 +08:00
Luis Pater 98a1bb5a7f Merge pull request #1900 from rex-zsd/feature/add-gemini-3.1-flash-image-preview
feat(registry): add gemini-3.1-flash-image-preview model definition
2026-03-07 22:17:10 +08:00
Luis Pater ca90487a8c Merge branch 'main' into feature/add-gemini-3.1-flash-image-preview 2026-03-07 22:16:09 +08:00
Luis Pater 1042489f85 Merge pull request #1893 from thebtf/fix/normalize-ttl-byte-preservation-mainline
fix: preserve original JSON bytes in normalizeCacheControlTTL
2026-03-07 22:14:13 +08:00
Luis Pater 38277c1ea6 Merge pull request #1875 from woqiqishi/fix/tool-use-id-sanitize
fix: sanitize tool_use.id to comply with Claude API regex ^[a-zA-Z0-9_-]+$
2026-03-07 22:06:36 +08:00
RCD cc0156f28c Merge pull request #8 from Finesssee/sync-upstream-v6.8.40-to-v6.8.46
chore: sync CLIProxyAPI v6.8.40-v6.8.46
2026-03-07 19:11:59 +07:00
RCD 6d89800038 docs: track CLIProxyAPI v6.8.46 sync 2026-03-07 19:08:42 +07:00
RCD 165de06c69 chore: merge upstream CLIProxyAPI v6.8.46 2026-03-07 19:07:10 +07:00
RCD b402506252 chore: merge upstream CLIProxyAPI v6.8.45 2026-03-07 19:06:38 +07:00
RCD 4a13c2e269 chore: merge upstream CLIProxyAPI v6.8.44 2026-03-07 19:06:18 +07:00
RCD 8ad863a4a2 chore: merge upstream CLIProxyAPI v6.8.43 2026-03-07 19:05:56 +07:00
RCD 08fb275fb6 chore: merge upstream CLIProxyAPI v6.8.42 2026-03-07 19:05:11 +07:00
RCD a445780e43 chore: merge upstream CLIProxyAPI v6.8.41 2026-03-07 19:04:31 +07:00
RCD 3d26dbadb0 Merge upstream CLIProxyAPI v6.8.40 2026-03-07 19:03:29 +07:00
chujian 3a18f6fcca fix(registry): clone slice fields in model map output 2026-03-07 18:53:56 +08:00
chujian 099e734a02 fix(registry): always clone available model snapshots 2026-03-07 18:40:02 +08:00
chujian a52da26b5d fix(auth): stop draining stream pool goroutines after context cancellation 2026-03-07 18:30:33 +08:00
chujian 522a68a4ea fix(openai-compat): retry empty bootstrap streams 2026-03-07 18:08:13 +08:00
chujian a02eda54d0 fix(openai-compat): address review feedback 2026-03-07 17:39:42 +08:00
chujian 97ef633c57 fix(registry): address review feedback 2026-03-07 17:36:57 +08:00
chujian dae8463ba1 fix(registry): clone model snapshots and invalidate available-model cache 2026-03-07 16:59:23 +08:00
chujian 7c1299922e fix(openai-compat): improve pool fallback and preserve adaptive thinking 2026-03-07 16:54:28 +08:00
Luis Pater ddcf1f279d Fixed: #1901
test(websocket): add tests for incremental input and prewarm handling logic

- Added test cases for incremental input support based on upstream capabilities.
- Introduced validation for prewarm handling of `response.create` messages locally.
- Enhanced test coverage for websocket executor behavior, including payload forwarding checks.
- Updated websocket implementation with prewarm and incremental input logic for better testability.
2026-03-07 13:11:28 +08:00
Luis Pater 7e6bb8fdc5 Merge origin/dev into pr-1774-review and resolve watcher conflicts 2026-03-07 11:12:42 +08:00
Luis Pater 9cee8ef87b Merge pull request #1684 from alexey-yanchenko/fix/input-audio-from-openai-to-antigravity
fix: preserve input_audio content parts when proxying to Antigravity
2026-03-07 10:12:28 +08:00
Luis Pater 93fb841bcb Fixed: #1670
test(translator): add unit tests for OpenAI to Claude requests and tool result handling

- Introduced tests for converting OpenAI requests to Claude with text, base64 images, and URL images in tool results.
- Refactored `convertClaudeToolResultContent` and related functionality to properly handle raw content with images and text.
- Updated conversion logic to streamline image handling for both base64 and URL formats.
2026-03-07 09:25:22 +08:00
Luis Pater 5ebc58fab4 refactor(executor): remove legacy connCreateSent logic and standardize response.create usage for all websocket events
- Simplified connection logic by removing `connCreateSent` and related state handling.
- Updated `buildCodexWebsocketRequestBody` to always use `response.create`.
- Added unit tests to validate `response.create` behavior and beta header preservation.
- Dropped unsupported `response.append` and outdated `response.done` event types.
2026-03-07 09:07:23 +08:00
Luis Pater 2b609dd891 Merge pull request #1912 from FradSer/main
feat(registry): add gemini 3.1 flash lite preview
2026-03-07 05:41:31 +08:00
Frad LEEandClaude Sonnet 4.6 a8cbc68c3e feat(registry): add gemini 3.1 flash lite preview
- Add model to GetGeminiModels()
- Add model to GetGeminiVertexModels()
- Add model to GetGeminiCLIModels()
- Add model to GetAIStudioModels()
- Add to AntigravityModelConfig with thinking levels
- Update gemini-3-flash-preview description

Registers the new lightweight Gemini model across all provider
endpoints for cost-effective high-volume usage scenarios.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-06 20:52:28 +08:00
Kirill Turanskiy 11a795a01c fix: surface upstream error details in Gemini CLI OAuth onboarding UI
SetOAuthSessionError previously sent generic messages to the management
panel (e.g. "Failed to complete Gemini CLI onboarding"), hiding the
actual error returned by Google APIs. The specific error was only
written to the server log via log.Errorf, which is often inaccessible
in headless/Docker deployments.

Include the upstream error in all 8 OAuth error paths so the
management panel shows actionable messages like "no Google Cloud
projects available for this account" instead of a generic failure.
2026-03-06 13:06:37 +03:00
Luis Pater 2695a99623 fix(translator): conditionally remove service_tier from OpenAI response processing 2026-03-06 11:07:22 +08:00
zhongnan.rex 242aecd924 feat(registry): add gemini-3.1-flash-image-preview model definition 2026-03-06 10:50:04 +08:00
KT-lcz 8e1acbf5d0 Update dashboard URL in README 2026-03-06 09:32:20 +08:00
hkfires ce8cc1ba33 fix(translator): pass through adaptive thinking effort 2026-03-06 09:13:32 +08:00
Kirill Turanskiy 97fdd2e088 fix: preserve original JSON bytes in normalizeCacheControlTTL when no TTL change needed
normalizeCacheControlTTL unconditionally re-serializes the entire request
body through json.Unmarshal/json.Marshal even when no TTL normalization
is needed. Go's json.Marshal randomizes map key order and HTML-escapes
<, >, & characters (to \u003c, \u003e, \u0026), producing different raw
bytes on every call.

Anthropic's prompt caching uses byte-prefix matching, so any byte-level
difference causes a cache miss. This means the ~119K system prompt and
tools are re-processed on every request when routed through CPA.

The fix adds a bool return to normalizeTTLForBlock to indicate whether
it actually modified anything, and skips the marshal step in
normalizeCacheControlTTL when no blocks were changed.
2026-03-05 22:28:01 +03:00
Luis Pater 9397f7049f fix(registry): simplify GPT 5.4 model description in static data 2026-03-06 02:32:56 +08:00
Luis Pater 8822f20d17 feat(registry): add GPT 5.4 model definition to static data 2026-03-06 02:23:53 +08:00
Xu Hong 553d6f50ea fix: sanitize tool_use.id to comply with Claude API regex ^[a-zA-Z0-9_-]+$
Add util.SanitizeClaudeToolID() to replace non-conforming characters in
tool_use.id fields across all five response translators (gemini, codex,
openai, antigravity, gemini-cli).

Upstream tool names may contain dots or other special characters
(e.g. "fs.readFile") that violate Claude's ID validation regex.
The sanitizer replaces such characters with underscores and provides
a generated fallback for empty IDs.

Fixes #1872, Fixes #1849

Made-with: Cursor
2026-03-06 00:10:09 +08:00
Luis Pater f0e5a5a367 test(watcher): add unit test for server update timer cancellation and immediate reload logic
- Add `TestTriggerServerUpdateCancelsPendingTimerOnImmediate` to verify proper handling of server update debounce and timer cancellation.
- Fix logic in `triggerServerUpdate` to prevent duplicate timers and ensure proper cleanup of pending state.
2026-03-05 23:48:50 +08:00
Luis Pater f6dfea9357 Merge pull request #1874 from constansino/fix/watcher-auth-event-storm-debounce
fix(watcher): 合并 auth 事件风暴下的回调触发,降低高 CPU
2026-03-05 23:29:56 +08:00
Luis Pater cc8dc7f62c Merge branch 'main' into dev 2026-03-05 23:13:21 +08:00
Luis Pater a3846ea513 Merge pull request #1870 from sususu98/fix/remove-instructions-restore
cleanup(translator): remove leftover instructions restore in codex responses
2026-03-05 23:12:31 +08:00
Luis Pater 8d44be858e Merge pull request #1834 from DragonFSKY/fix/sse-streaming-accept-encoding
fix(claude): extend gzip fix to SSE success path and header-absent compression (#1763)
2026-03-05 22:57:27 +08:00
Luis Pater 0e6bb076e9 fix(translator): comment out service_tier removal from OpenAI response processing 2026-03-05 22:49:38 +08:00
Luis Pater ac135fc7cb Fixed: #1815
**test(executor): add unit tests for prompt cache key generation in OpenAI `cacheHelper`**
2026-03-05 22:49:23 +08:00
Luis Pater 4e1d09809d Fixed: #1741
fix(translator): handle tool name mappings and improve tool call handling in OpenAI and Claude integrations
2026-03-05 22:24:50 +08:00
constansino ac95e92829 fix(watcher): guard debounced callback after Stop 2026-03-05 19:25:57 +08:00
constansino 8526c2da25 fix(watcher): debounce auth event callback storms 2026-03-05 19:12:57 +08:00
sususu98 68a6cabf8b style: blank unused params in codex responses translator 2026-03-05 16:42:48 +08:00
sususu98 ac0e387da1 cleanup(translator): remove leftover instructions restore in codex responses
The instructions restore logic was originally needed when the proxy
injected custom instructions (per-model system prompts) into requests.
Since ac802a46 removed the injection system, the proxy no longer
modifies instructions before forwarding. The upstream response's
instructions field now matches the client's original value, making
the restore a no-op.

Also removes unused sjson import.

Closes router-for-me/CLIProxyAPI#1868
2026-03-05 16:34:55 +08:00
Luis Pater 5850492a93 Fixed: #1548
test(translator): add unit tests for fallback logic in `ConvertCodexResponseToOpenAI` model assignment
2026-03-05 12:11:54 +08:00
Luis Pater fdbd4041ca Fixed: #1531
fix(gemini): add `deprecated` to unsupported schema keywords

Add `deprecated` to the list of unsupported schema metadata fields in Gemini and update tests to verify its removal.
2026-03-05 11:48:15 +08:00
Luis Pater ebef1fae2a Merge pull request #1511 from stondy0103/fix/responses-nullable-type-array
fix(translator): fix nullable type arrays breaking Gemini/Antigravity API
2026-03-05 11:30:09 +08:00
DragonFSKY 419bf784ab fix(claude): prevent compressed SSE streams and add magic-byte decompression fallback
- Set Accept-Encoding: identity for SSE streams; upstream must not compress
  line-delimited SSE bodies that bufio.Scanner reads directly
- Re-enforce identity after ApplyCustomHeadersFromAttrs to prevent auth
  attribute injection from re-enabling compression on the stream path
- Add peekableBody type wrapping bufio.Reader for non-consuming magic-byte
  inspection of the first 4 bytes without affecting downstream readers
- Detect gzip (0x1f 0x8b) and zstd (0x28 0xb5 0x2f 0xfd) by magic bytes
  when Content-Encoding header is absent, covering misbehaving upstreams
- Remove if-Content-Encoding guard on all three error paths (Execute,
  ExecuteStream, CountTokens); unconditionally delegate to decodeResponseBody
  so magic-byte detection applies consistently to all response paths
- Add 10 tests covering stream identity enforcement, compressed success bodies,
  magic-byte detection without headers, error path decoding, and
  auth attribute override prevention
2026-03-05 06:38:38 +08:00
FSOS a0b068756c fix: remove duplicate 'tui' flag definition causing startup panic
Fixes #5 - The 'tui' flag was registered twice via flag.BoolVar(),
causing a 'panic: flag redefined: tui' crash on startup.
Removed the duplicate at line 208, keeping the original at line 181.
2026-03-05 05:03:16 +07:00
Luis Pater 4bbeb92e9a Fixed: #1135
**test(translator): add tests for `tool_choice` handling in Claude request conversions**
2026-03-04 22:28:26 +08:00
Luis Pater b436dad8bc Merge pull request #1822 from sususu98/fix/strip-defer-loading
fix(translator): strip defer_loading from Claude tool declarations in Codex and Gemini translators
2026-03-04 20:49:48 +08:00
Luis Pater 6ae15d6c44 Merge pull request #1816 from sususu98/fix/antigravity-adaptive-effort
fix(antigravity): pass through adaptive thinking effort level instead of always mapping to high
2026-03-04 20:48:38 +08:00
Luis Pater 0468bde0d6 Merge branch 'dev' into fix/antigravity-adaptive-effort 2026-03-04 20:48:26 +08:00
Luis Pater 1d7329e797 Merge pull request #1825 from router-for-me/vertex
feat(config): support excluded vertex models in config
2026-03-04 20:44:41 +08:00
hkfires 48ffc4dee7 feat(config): support excluded vertex models in config 2026-03-04 18:47:42 +08:00
Luis Pater b680c146c1 chore(docs): update sponsor image links in README files 2026-03-04 18:29:23 +08:00
sususu98 d26ad8224d fix(translator): strip defer_loading from Claude tool declarations in Codex and Gemini translators
Claude's Tool Search feature (advanced-tool-use-2025-11-20 beta) adds
defer_loading field to tool definitions. When proxying Claude requests
to Codex or Gemini, this unknown field causes 400 errors upstream.

Strip defer_loading (and cache_control where missing) in all three
Claude-to-upstream translation paths:
- codex/claude: defer_loading + cache_control
- gemini-cli/claude: defer_loading
- gemini/claude: defer_loading

Fixes #1725, Fixes #1375
2026-03-04 14:21:30 +08:00
hkfires 5c84d69d42 feat(translator): map output_config.effort to adaptive thinking level in antigravity 2026-03-04 13:11:07 +08:00
sususu98 527e4b7f26 fix(antigravity): pass through adaptive thinking effort level instead of always mapping to high 2026-03-04 10:12:45 +08:00
Luis Pater b48485b42b Fixed: #822
**fix(auth): normalize ID casing on Windows to prevent duplicate entries due to case-insensitive paths**
2026-03-04 02:31:20 +08:00
Luis Pater 79009bb3d4 Fixed: #797
**test(auth): add test for preserving ModelStates during auth updates**
2026-03-04 02:06:24 +08:00
Luis Pater 9f95b31158 **fix(translator): enhance handling of mixed output content in Claude requests** 2026-03-03 21:49:41 +08:00
Luis Pater 5da07eae4c Merge pull request #1805 from router-for-me/thinking
Add adaptive thinking support for Claude models
2026-03-03 20:31:31 +08:00
hkfires 835ae178d4 feat(thinking): rename isBudgetBasedProvider to isBudgetCapableProvider and update logic for provider checks 2026-03-03 19:49:51 +08:00
hkfires c80ab8bf0d feat(thinking): improve provider family checks and clamp unsupported levels 2026-03-03 19:05:15 +08:00
hkfires ce87714ef1 feat(thinking): normalize effort levels in adaptive thinking requests to prevent validation errors 2026-03-03 15:10:47 +08:00
hkfires 0452b869e8 feat(thinking): add HasLevel and MapToClaudeEffort functions for adaptive thinking support 2026-03-03 14:16:36 +08:00
hkfires d2e5857b82 feat(thinking): enhance adaptive thinking support across models and update test cases 2026-03-03 13:00:24 +08:00
Luis Pater f9b005f21f Fixed: #1799
**test(auth): add tests for auth file deletion logic with manager and fallback scenarios**
2026-03-03 09:37:24 +08:00
hkfires 532107b4fa test(auth): add global model registry usage to conductor override tests 2026-03-03 09:18:56 +08:00
hkfires c44793789b feat(thinking): add adaptive thinking support for Claude models
Add support for Claude's "adaptive" and "auto" thinking modes using `output_config.effort`. Introduce support for new effort level "max" in adaptive thinking. Update thinking logic, validate model capabilities, and extend converters and handling to ensure compatibility with adaptive modes. Adjust static model data with supported levels and refine handling across translators and executors.
2026-03-03 09:05:31 +08:00
RCD 960422f715 Merge upstream CLIProxyAPI v6.8.38–v6.8.39
Upstream changes:
- Antigravity v1.19.5→1.19.6: Claude 4-6 migration, new models, image_gen payload
- Comprehensive browser fingerprint and proxy tracing header scrubbing
- Whitelist-based header filtering (replaces blacklist approach)
- Singleton HTTP transport to prevent OOM from connection pool leaks
- Disable HTTP/2 ALPN in Antigravity client (fixes connection resets)
- Gemini: route gemini-3.1-flash-image, custom generationConfig passthrough
- GeminiCLI versioning and User-Agent streamlining
- Model registry: input/output modalities, token limits, generation methods
- Removed oauth-model-alias migration logic

Fork resolution:
- Keep both SupportedEndpoints (fork) and modality fields (upstream) in ModelInfo
- Keep our README, delete README_CN.md
2026-03-02 19:51:13 +07:00
Luis Pater 09fec34e1c chore(docs): update sponsor info and GLM model details in README files 2026-03-02 20:30:07 +08:00
hkfires 9229708b6c revert(executor): re-apply PR #1735 antigravity changes with cleanup 2026-03-02 19:30:32 +08:00
hkfires 914db94e79 refactor(headers): streamline User-Agent handling and introduce GeminiCLI versioning 2026-03-02 13:04:30 +08:00
hkfires 660bd7eff5 refactor(config): remove oauth-model-alias migration logic and related tests 2026-03-02 13:02:15 +08:00
hkfires b907d21851 revert(executor): revert antigravity_executor.go changes from PR #1735 2026-03-02 12:54:15 +08:00
lyd123qw2008 dd44413ba5 refactor(watcher): make authSliceToMap always return map 2026-03-02 10:09:56 +08:00
lyd123qw2008 10fa0f2062 refactor(watcher): dedupe auth map conversion in incremental flow 2026-03-02 10:03:42 +08:00
Luis Pater d6cc976d1f chore(executor): remove unused header scrubbing function 2026-03-02 03:40:54 +08:00
Luis Pater 8aa2cce8c5 Merge PR #1735 into dev with conflict resolution and fixes 2026-03-02 03:22:51 +08:00
RCD 6d47c30305 Merge upstream CLIProxyAPI v6.8.33–v6.8.37
Upstream changes:
- Claude Code 2.1.63 fingerprint cloaking alignment
- X-CPA-CLAUDE-1M header handling and beta merging logic
- Claude cache-control guardrails and gzip error decoding
- Antigravity model updates and thinkingBudget default 64000
- Thinking type "auto" support (Amp client → adaptive translation)
- Kimi thinking provider improvements
- .idea directory gitignore

Fork resolution:
- Update SetRetryConfig calls (new maxRetryCredentials param)
- Update retrySettings() destructuring (now returns 3 values)
2026-03-02 02:10:16 +07:00
RCD dfd2e09898 Merge remote-tracking branch 'upstream/main' 2026-03-02 02:08:44 +07:00
Luis Pater 77b42c6165 fix(claude): handle X-CPA-CLAUDE-1M header and ensure proper beta merging logic 2026-03-01 21:39:33 +08:00
Luis Pater 1cbc4834e1 Merge pull request #1771 from edlsh/fix/claude-cache-control-1769
Fix Claude OAuth cache_control regressions and gzip error decoding
2026-03-01 20:17:22 +08:00
lyd123qw2008 30338ecec4 perf(watcher): remove redundant auth clones in incremental path 2026-03-01 14:05:11 +08:00
lyd123qw2008 9a37defed3 test(watcher): restore main test names and max-retry callback coverage 2026-03-01 13:54:03 +08:00
lyd123qw2008 c83a057996 refactor(watcher): make auth file events fully incremental 2026-03-01 13:42:42 +08:00
hkfires a8a5d03c33 chore: ignore .idea directory in git and docker builds 2026-03-01 12:42:59 +08:00
edlsh 76aa917882 Optimize cache-control JSON mutations in Claude executor 2026-02-28 22:47:04 -05:00
edlsh 6ac9b31e4e Handle compressed error decode failures safely 2026-02-28 22:43:46 -05:00
edlsh 0ad3e8457f Clarify cloaking system block cache-control comments 2026-02-28 22:34:14 -05:00
edlsh 444a47ae63 Fix Claude cache-control guardrails and gzip error decoding 2026-02-28 22:32:33 -05:00
Luis Pater 725f4fdff4 Merge pull request #1768 from router-for-me/claude
fix(translator): handle Claude thinking type "auto" like adaptive
2026-03-01 11:03:13 +08:00
Luis Pater c23e46f45d Merge pull request #1767 from router-for-me/antigravity
fix(antigravity): update model configurations and add new models for Antigravity
2026-03-01 11:02:20 +08:00
hkfires b148820c35 fix(translator): handle Claude thinking type "auto" like adaptive 2026-03-01 10:30:19 +08:00
hkfires 134f41496d fix(antigravity): update model configurations and add new models for Antigravity 2026-03-01 10:05:29 +08:00
Luis Pater 1ae994b4aa fix(antigravity): adjust thinkingBudget default to 64000 and update model definitions for Claude 2026-03-01 09:39:39 +08:00
Luis Pater cc1d8f6629 Fixed: #1747
feat(auth): add configurable max-retry-credentials for finer control over cross-credential retries
2026-03-01 02:42:36 +08:00
Luis Pater 5446cd2b02 Merge pull request #1761 from margbug01/fix/thinking-chain-display
fix: support thinking.type=auto from Amp client and decouple thinking translation from unsigned history
2026-03-01 02:30:42 +08:00
margbug01andAmp 8de0885b7d fix: support thinking.type="auto" from Amp client for Antigravity Claude models
## Problem

When using Antigravity Claude models through CLIProxyAPI, the thinking
chain (reasoning content) does not display in the Amp client.

## Root Cause

The Amp client sends `thinking: {"type": "auto"}` in its requests,
but `ConvertClaudeRequestToAntigravity` only handled `"enabled"` and
`"adaptive"` types in its switch statement. The `"auto"` type was
silently ignored, resulting in no `thinkingConfig` being set in the
translated Gemini request. Without `thinkingConfig`, the Antigravity
API returns responses without any thinking content.

Additionally, the Antigravity API for Claude models does not support
`thinkingBudget: -1` (auto mode sentinel). It requires a concrete
positive budget value. The fix uses 128000 as the budget for "auto"
mode, which `ApplyThinking` will then normalize to stay within the
model's actual limits (e.g., capped to `maxOutputTokens - 1`).

## Changes

### internal/translator/antigravity/claude/antigravity_claude_request.go

1. **Add "auto" case** to the thinking type switch statement.
   Sets `thinkingBudget: 128000` and `includeThoughts: true`.
   The budget is subsequently normalized by `ApplyThinking` based
   on model-specific limits.

2. **Add "auto" to hasThinking check** so that interleaved thinking
   hints are injected for tool-use scenarios when Amp sends
   `thinking.type="auto"`.

### internal/registry/model_definitions_static_data.go

3. **Add Thinking configuration** for `claude-sonnet-4-6`,
   `claude-sonnet-4-5`, and `claude-opus-4-6` in
   `GetAntigravityModelConfig()` -- these were previously missing,
   causing `ApplyThinking` to skip thinking config entirely.

## Testing

- Deployed to Railway test instance (cpa-thinking-test)
- Verified via debug logging that:
  - Amp sends `thinking: {"type": "auto"}`
  - CPA now translates this to `thinkingConfig: {thinkingBudget: 128000, includeThoughts: true}`
  - `ApplyThinking` normalizes the budget to model-specific limits
  - Antigravity API receives the correct thinkingConfig

Amp-Thread-ID: https://ampcode.com/threads/T-019ca511-710d-776d-a07c-4b750f871a93
Co-authored-by: Amp <amp@ampcode.com>
2026-03-01 02:18:43 +08:00
Luis Pater a6ce5f36e6 Fixed: #1758
fix(codex): filter billing headers from system result text and update template logic
2026-03-01 01:45:35 +08:00
Luis Pater e73cf42e28 Merge pull request #1750 from tpm2dot0/fix/claude-code-request-fingerprint-alignment
fix(cloak): align outgoing requests with real Claude Code 2.1.63
2026-03-01 01:27:28 +08:00
exe.dev userandClaude Opus 4.6 b45343e812 fix(cloak): align outgoing requests with real Claude Code 2.1.63 fingerprint
Captured and compared outgoing requests from CLIProxyAPI against real
Claude Code 2.1.63 and fixed all detectable differences:

Headers:
- Update anthropic-beta to match 2.1.63: replace fine-grained-tool-streaming
  and prompt-caching-2024-07-31 with context-management-2025-06-27 and
  prompt-caching-scope-2026-01-05
- Remove X-Stainless-Helper-Method header (real Claude Code does not send it)
- Update default User-Agent from "claude-cli/2.1.44 (external, sdk-cli)" to
  "claude-cli/2.1.63 (external, cli)"
- Force Claude Code User-Agent for non-Claude clients to avoid leaking
  real client identity (e.g. curl, OpenAI SDKs) during cloaking

Body:
- Inject x-anthropic-billing-header as system[0] (matches real format)
- Change system prompt identifier from "You are Claude Code..." to
  "You are a Claude agent, built on Anthropic's Claude Agent SDK."
- Add cache_control with ttl:"1h" to match real request format
- Fix user_id format: user_[64hex]_account_[uuid]_session_[uuid]
  (was missing account UUID)
- Disable tool name prefix (set claudeToolPrefix to empty string)

TLS:
- Switch utls fingerprint from HelloFirefox_Auto to HelloChrome_Auto
  (closer to Node.js/OpenSSL used by real Claude Code)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 09:19:06 +00:00
Luis Pater 8599b1560e Fixed: #1716
feat(kimi): add support for explicit disabled thinking and reasoning effort handling
2026-02-28 05:29:07 +08:00
Luis Pater 8bde8c37c0 Fixed: #1711
fix(server): use resolved log directory for request logger initialization and test fallback logic
2026-02-28 05:21:01 +08:00
RCD 0af0ad14e5 Merge upstream CLIProxyAPI v6.8.28–v6.8.32
Upstream changes:
- Codex responses compaction payload compatibility
- Codex usage_limit_reached retry-after, deterministic parsing
- Codex refresh_token_reused non-retryable fix
- Qwen rate limiting and quota error handling
- Context management compatibility simplification
- Antigravity tool_result image fix, model list backfill, deep copy cache
- Auth auto-refresh interval/concurrency limiting
- Auth hook OnResult refactor (replaces MarkResult)
- Gemini-3.1-flash-image support
- Registry cleanup of outdated model definitions

Fork resolution:
- Accept upstream's consolidated conductor.go (auto-refresh, round-tripper)
- Delete stale conductor_oauth.go, conductor_token.go (upstream reversed split)
- Delete stale provider_rotation_test.go (references removed method)
2026-02-27 20:58:16 +07:00
RCD a82585ba21 chore: add .gitallowed for upstream OAuth credentials
Public Google OAuth client IDs and secrets from upstream CLIProxyAPI.
These are intentionally embedded (installed/CLI app OAuth flow) and
identical to the upstream public repo. Allowlisting prevents GitHub
push protection from blocking merges.
2026-02-27 20:50:23 +07:00
Luis Pater 27c68f5bb2 fix(auth): replace MarkResult with hook OnResult for result handling 2026-02-27 20:47:46 +08:00
maplelove 68dd2bfe82 fix(translator): allow passthrough of custom generationConfig for all Gemini-like providers 2026-02-27 17:13:42 +08:00
Luis Pater 41b1cf2273 Merge pull request #1734 from huangusaki/main
feat(registry): add gemini-3.1-flash-image support
2026-02-27 16:12:05 +08:00
maplelove 2baf35b3ef fix(executor): bump antigravity UA to 1.19.6 and align image_gen payload 2026-02-27 14:09:37 +08:00
maplelove 846e75b893 feat(gemini): route gemini-3.1-flash-image identically to gemini-3-pro-image 2026-02-27 13:32:06 +08:00
maplelove fc0257d6d9 refactor: consolidate duplicate UA and header scrubbing into shared misc functions 2026-02-27 10:57:13 +08:00
maplelove f3c164d345 feat(antigravity): update to v1.19.5 with new models and Claude 4-6 migration 2026-02-27 10:34:27 +08:00
maplelove 4040b1e766 Merge remote-tracking branch 'upstream/dev' into dev
# Conflicts:
#	internal/runtime/executor/antigravity_executor.go
2026-02-27 10:29:50 +08:00
huang_usaki 3b4f9f43db feat(registry): add gemini-3.1-flash-image support 2026-02-27 10:20:46 +08:00
Luis Pater 0da34d3c2d Merge pull request #1668 from lyd123qw2008/fix/codex-usage-limit-retry-after
fix(codex): honor usage_limit_reached resets_at for retry_after
2026-02-27 06:01:44 +08:00
Luis Pater 74bf7eda8f Merge pull request #1686 from lyd123qw2008/fix/auth-refresh-concurrency-limit
fix(auth): limit auto-refresh concurrency to prevent refresh storms
2026-02-27 05:59:20 +08:00
Luis Pater 8c6c90da74 fix(registry): clean up outdated model definitions in static data 2026-02-26 23:12:40 +08:00
Luis Pater 24bcfd9c03 Merge pull request #1699 from 123hi123/fix/antigravity-primary-model-fallback
fix(antigravity): keep primary model list and backfill empty auths
2026-02-26 04:28:29 +08:00
Luis Pater 816fb4c5da Merge pull request #1682 from sususu98/fix/tool-result-image-parts
fix(antigravity): place tool_result images in functionResponse.parts and unify mimeType
2026-02-25 23:14:35 +08:00
RCD 6ffc26271c Merge upstream CLIProxyAPI v6.8.27
Upstream changes:
- Post-auth hook system (RequestInfo refactor + hook chain)
- Credential-based round-robin for gemini-cli virtual auths
- Codex additive device-code login flow
- File input passthrough for /chat/completions and /responses
- Gemini → OpenAI usage conversion fix
- Responses stream: model/usage in translated streams, valid SSE error chunks
- Revert reasoning effort clamping

Fork resolution:
- Keep both integrationManager (fork) and postAuthHook (upstream) in handler struct
2026-02-25 14:49:42 +07:00
Luis Pater d24ea4ce2a Merge pull request #1664 from ciberponk/pr/responses-compaction-compat
feat: add codex responses compatibility for compaction payloads
2026-02-25 01:21:59 +08:00
Luis Pater 2c30c981ae Merge pull request #1687 from lyd123qw2008/fix/codex-refresh-token-reused-no-retry
fix(codex): stop retrying refresh_token_reused errors
2026-02-25 01:19:30 +08:00
Luis Pater aa1da8a858 Merge pull request #1685 from lyd123qw2008/fix/auth-auto-refresh-interval
fix(auth): respect configured auto-refresh interval
2026-02-25 01:13:47 +08:00
Luis Pater f1e9a787d7 Merge pull request #1676 from piexian/feat/qwen-quota-handling-clean
feat(qwen): add rate limiting and quota error handling
2026-02-25 01:07:55 +08:00
Luis Pater c66cb0afd2 Merge pull request #1683 from dusty-du/codex/device-login-flow
Add additive Codex device-code login flow
2026-02-25 00:50:48 +08:00
Luis Pater fb48eee973 Merge pull request #1680 from canxin121/fix/responses-stream-error-chunks
fix(responses): emit schema-valid SSE chunks
2026-02-25 00:49:06 +08:00
Luis Pater bb44e5ec44 Merge pull request #1701 from router-for-me/openai
Revert "Merge pull request #1627 from thebtf/fix/reasoning-effort-clamping"
2026-02-25 00:46:13 +08:00
comalot 514ae341c8 fix(antigravity): deep copy cached model metadata 2026-02-24 20:14:01 +08:00
hkfires 0659ffab75 Revert "Merge pull request #1627 from thebtf/fix/reasoning-effort-clamping" 2026-02-24 19:47:53 +08:00
comalot 8ce07f38dd fix(antigravity): keep primary model list and backfill empty auths 2026-02-24 16:16:44 +08:00
Luis Pater 7cb398d167 Merge pull request #1663 from rensumo/main
feat: implement credential-based round-robin for gemini-cli
2026-02-24 06:02:50 +08:00
Luis Pater c3e12c5e58 Merge pull request #1654 from alexey-yanchenko/feature/pass-file-inputs
Pass file input from /chat/completions and /responses to codex and claude
2026-02-24 05:53:11 +08:00
Luis Pater 1825fc7503 Merge pull request #1643 from alexey-yanchenko/fix/gemini-prompt-tokens
Fix usage convertation from gemini response to openai format
2026-02-24 05:46:13 +08:00
Luis Pater 48732ba05e Merge pull request #1527 from HEUDavid/feat/auth-hook
feat(auth): add post-auth hook mechanism
2026-02-24 05:33:13 +08:00
canxin121 acf483c9e6 fix(responses): reject invalid SSE data JSON
Guard the openai-response streaming path against truncated/invalid SSE data payloads by validating data: JSON before forwarding; surface a 502 terminal error instead of letting clients crash with JSON parse errors.
2026-02-24 01:42:54 +08:00
lyd123qw2008 3b3e0d1141 test(codex): log non-retryable refresh error and cover single-attempt behavior 2026-02-23 22:41:33 +08:00
lyd123qw2008 7acd428507 fix(codex): stop retrying refresh_token_reused errors 2026-02-23 22:31:30 +08:00
lyd123qw2008 0aaf177640 fix(auth): limit auto-refresh concurrency to prevent refresh storms 2026-02-23 22:28:41 +08:00
lyd123qw2008 450d1227bd fix(auth): respect configured auto-refresh interval 2026-02-23 22:07:50 +08:00
Alexey Yanchenko b7588428c5 fix: preserve input_audio content parts when proxying to Antigravity
- Add input_audio handling in chat/completions translator (antigravity_openai_request.go)
- Add input_audio handling in responses translator (gemini_openai-responses_request.go)
- Map OpenAI audio formats (mp3, wav, ogg, flac, aac, webm, pcm16, g711_ulaw, g711_alaw) to correct MIME types for Gemini inlineData
2026-02-23 20:50:28 +07:00
test 492b9c46f0 Add additive Codex device-code login flow 2026-02-23 06:30:04 -05:00
RCD dd41652e99 feat: add CODEOWNERS, PR template, and /health endpoint 2026-02-23 15:38:56 +07:00
RCD f4f66ad0d3 feat: add pre-commit hooks, go vet, and test coverage threshold (30%) in CI 2026-02-23 15:33:43 +07:00
sususu98 4e26182d14 fix(antigravity): place tool_result images in functionResponse.parts and unify mimeType
Move base64 image data from Claude tool_result into functionResponse.parts
as inlineData instead of outer sibling parts, preventing context bloat.
Unify all inlineData field naming to camelCase mimeType across Claude,
OpenAI, and Gemini translators. Add comprehensive edge case tests and
Gemini-side regression test for functionResponse.parts preservation.
2026-02-23 13:38:21 +08:00
maplelove 8f97a5f77c feat(registry): expose input modalities, token limits, and generation methods for Antigravity models 2026-02-23 13:33:51 +08:00
canxin121 eb7571936c revert: translator changes (path guard)
CI blocks PRs that modify internal/translator. Revert translator edits and keep only the /v1/responses streaming error-chunk fix; file an issue for translator conformance work.
2026-02-23 13:30:43 +08:00
canxin121 5382764d8a fix(responses): include model and usage in translated streams
Ensure response.created and response.completed chunks produced by the OpenAI/Gemini/Claude translators always include required fields (response.model and response.usage) so clients validating Responses SSE do not fail schema validation.
2026-02-23 13:22:06 +08:00
canxin121 49c8ec69d0 fix(openai): emit valid responses stream error chunks
When /v1/responses streaming fails after headers are sent, we now emit a type=error chunk instead of an HTTP-style {error:{...}} payload, preventing AI SDK chunk validation errors.
2026-02-23 12:59:50 +08:00
RCD cf558dd166 Merge upstream CLIProxyAPI v6.8.18–v6.8.26
Upstream changes:
- Codex WebSocket executor and Codex response handlers
- Header passthrough (upstream response headers forwarded to clients)
- ExecuteStream returns *StreamResult (wraps channel + headers)
- Embeddings handler with synthetic fallback
- User ID cache for executors
- Gemini schema/request fixes
- New test coverage for bootstrap retries, error responses

Fork resolution:
- Delete upstream's modular TUI files (app.go, styles.go, dashboard.go,
  auth_tab.go, config_tab.go, keys_tab.go, logs_tab.go, oauth_tab.go,
  usage_tab.go, i18n.go, loghook.go) — keep fork's Flight Deck tui.go
- Add PassthroughHeaders field to SDKConfig
- Fix embeddings handler to capture 3-value ExecuteWithAuthManager return
- Update test mocks (conductor_test, auth_flow_test, multi_provider_test,
  gemini_executor_test) for new ExecuteStream signature
- Fix tuiMode → launchTUI flag variable reference
- Remove unused "io" import from main.go
2026-02-23 11:58:54 +07:00
piexian 3b421c8181 feat(qwen): add rate limiting and quota error handling
- Add 60 requests/minute rate limiting per credential using sliding window
- Detect insufficient_quota errors and set cooldown until next day (Beijing time)
- Map quota errors (HTTP 403/429) to 429 with retryAfter for conductor integration
- Cache Beijing timezone at package level to avoid repeated syscalls
- Add redactAuthID function to protect credentials in logs
- Extract wrapQwenError helper to consolidate error handling
2026-02-23 00:38:46 +08:00
Luis Pater 713388dd7b Fixed: #1675
fix(gemini): add model definitions for Gemini 3.1 Pro High and Image
2026-02-23 00:12:57 +08:00
maplelove 2a4d3e60f3 Merge remote-tracking branch 'upstream/dev' into dev 2026-02-23 00:01:47 +08:00
maplelove 8b5af2ab84 fix(executor): match real Antigravity OAuth UA, remove redundant header scrubbing on new requests 2026-02-22 23:20:12 +08:00
Luis Pater e6c7af0fa9 Merge pull request #1522 from soilSpoon/feature/canceled
feature(proxy): Adds special handling for client cancellations in proxy error handler
2026-02-22 22:02:59 +08:00
Luis Pater d210be06c2 fix(gemini): update min Thinking value and add Gemini 3.1 Pro Preview model definition 2026-02-22 21:51:32 +08:00
maplelove d887716ebd refactor(executor): switch HttpRequest to whitelist-based header filtering 2026-02-22 21:00:12 +08:00
maplelove 5dc1848466 feat(scrub): add comprehensive browser fingerprint and client identity header scrubbing 2026-02-22 20:51:00 +08:00
maplelove 9491517b26 fix(executor): use singleton transport to prevent OOM from connection pool leaks 2026-02-22 20:17:30 +08:00
maplelove 9370b5bd04 fix(executor): completely scrub all proxy tracing headers in executor 2026-02-22 19:43:10 +08:00
maplelove abb51a0d93 fix(executor): correctly disable http2 ALPN in Antigravity client to resolve connection reset errors 2026-02-22 19:23:48 +08:00
maplelove c8d809131b fix(executor): improve antigravity reverse proxy emulation
- force http/1.1 instead of http/2

- explicit connection close

- strip proxy headers X-Forwarded-For and X-Real-IP

- add project id to fetch models payload
2026-02-22 18:41:58 +08:00
maplelove dd71c73a9f fix: align gemini-cli upstream communication headers
Removed legacy Client-Metadata and explicit API-Client headers. Dynamically generating accurate User-Agent strings matching the official cli.
2026-02-22 17:07:17 +08:00
fan afc8a0f9be refactor: simplify context_management compatibility handling 2026-02-21 22:20:48 +08:00
Luis Pater d6ec33e8e1 Merge pull request #1662 from matchch/contribute/cache-user-id
feat: add cache-user-id toggle for Claude cloaking
2026-02-21 20:51:30 +08:00
Luis Pater 081cfe806e fix(gemini): correct Created timestamps for Gemini 3.1 Pro Preview model definitions 2026-02-21 20:47:47 +08:00
hkfires c1c62a6c04 feat(gemini): add Gemini 3.1 Pro Preview model definitions 2026-02-21 20:42:29 +08:00
lyd123qw2008 a99522224f refactor(codex): make retry-after parsing deterministic for tests 2026-02-21 14:13:38 +08:00
lyd123qw2008 f5d46b9ca2 fix(codex): honor usage_limit_reached resets_at for retry_after 2026-02-21 13:50:23 +08:00
ciberponk d693d7993b feat: support responses compaction payload compatibility for codex translator 2026-02-21 12:56:10 +08:00
rensumo 5936f9895c feat: implement credential-based round-robin for gemini-cli virtual auths
Changes the RoundRobinSelector to use two-level round-robin when
gemini-cli virtual auths are detected (via gemini_virtual_parent attr):
- Level 1: cycle across credential groups (parent accounts)
- Level 2: cycle within each group's project auths

Credentials start from a random offset (rand.IntN) for fair distribution.
Non-virtual auths and single-credential scenarios fall back to flat RR.

Adds 3 test cases covering multi-credential grouping, single-parent
fallback, and mixed virtual/non-virtual fallback.
2026-02-21 12:49:48 +08:00
matchch 2fdf5d2793 feat: add cache-user-id toggle for Claude cloaking
Default to generating a fresh random user_id per request instead of
reusing cached IDs. Add cache-user-id config option to opt in to the
previous caching behavior.

- Add CacheUserID field to CloakConfig
- Extract user_id cache logic to dedicated file
- Generate fresh user_id by default, cache only when enabled
- Add tests for both paths
2026-02-21 12:31:20 +08:00
Luis Pater 7b0eb41ebc Merge pull request #1660 from Grivn/fix/claude-token-url
fix(claude): use api.anthropic.com for OAuth token exchange
2026-02-20 21:52:08 +08:00
GrivnandClaude Opus 4.6 ef5901c81b fix(claude): use api.anthropic.com for OAuth token exchange
console.anthropic.com is now protected by a Cloudflare managed challenge
that blocks all non-browser POST requests to /v1/oauth/token, causing
`-claude-login` to fail with a 403 error.

Switch to api.anthropic.com which hosts the same OAuth token endpoint
without the Cloudflare managed challenge.

Fixes #1659

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-20 20:11:27 +08:00
Luis Pater d4829c82f7 Merge pull request #1652 from thebtf/fix/claude-translator-arguments
fix(translator): handle tool call arguments in codex→claude streaming translator
2026-02-20 19:50:20 +08:00
Luis Pater a5f4166a9b Merge pull request #1644 from possible055/main
feat: add Gemini 3.1 Pro Preview model definition
2026-02-20 19:44:59 +08:00
Alexey Yanchenko 0cbfe7f457 Pass file input from /chat/completions and /responses to codex and claude 2026-02-20 10:25:44 +07:00
Kirill Turanskiy 1cc21cc45b fix: prevent duplicate function call arguments when delta events precede done
Non-spark codex models (gpt-5.3-codex, gpt-5.2-codex) stream function call
arguments via multiple delta events followed by a done event. The done handler
unconditionally emitted the full arguments, duplicating what deltas already
streamed. This produced invalid double JSON that Claude Code couldn't parse,
causing tool calls to fail with missing parameters and infinite retry loops.

Add HasReceivedArgumentsDelta flag to track whether delta events were received.
The done handler now only emits arguments when no deltas preceded it (spark
models), while delta-based streaming continues to work for non-spark models.
2026-02-19 23:18:14 +03:00
Kirill Turanskiy 07cf616e2b fix: handle response.function_call_arguments.done in codex→claude streaming translator
Some Codex models (e.g. gpt-5.3-codex-spark) send function call arguments
in a single "done" event without preceding "delta" events. The streaming
translator only handled "delta" events, causing tool call arguments to be
lost — resulting in empty tool inputs and infinite retry loops in clients
like Claude Code.

Emit the full arguments from the "done" event as a single input_json_delta
so downstream clients receive the complete tool input.
2026-02-19 23:18:14 +03:00
Luis Pater 4445a165e9 test(handlers): add tests for passthrough headers behavior in WriteErrorResponse 2026-02-19 21:49:44 +08:00
Luis Pater e92e2af71a Merge branch 'codex/pr-1626' into dev 2026-02-19 21:33:23 +08:00
Luis Pater a6bdd9a652 feat: add passthrough headers configuration
- Introduced `passthrough-headers` option in configuration to control forwarding of upstream response headers.
- Updated handlers to respect the passthrough headers setting.
- Added tests to verify behavior when passthrough is enabled or disabled.
2026-02-19 21:31:29 +08:00
Luis Pater 349a6349b3 Merge pull request #1645 from tinyc0der/fix/antigravity-tool-result-json
fix(antigravity): prevent invalid JSON when tool_result has no content
2026-02-19 21:01:25 +08:00
TinyCoder 00822770ec fix(antigravity): prevent invalid JSON when tool_result has no content
sjson.SetRaw with an empty string produces malformed JSON (e.g. "result":}).
This happens when a Claude tool_result block has no content field, causing
functionResponseResult.Raw to be "". Guard against this by falling back to
sjson.Set with an empty string only when .Raw is empty.
2026-02-19 17:08:39 +07:00
apparition 1a0ceda0fc feat: add Gemini 3.1 Pro Preview model definition 2026-02-19 17:43:08 +08:00
Alexey Yanchenko b9ae4ab803 Fix usage convertation from gemini response to openai format 2026-02-19 15:34:59 +07:00
Luis Pater 72add453d2 docs: add OmniRoute to README 2026-02-19 13:23:25 +08:00
Luis Pater 2789396435 fix: ensure connection-scoped headers are filtered in upstream requests
- Added `connectionScopedHeaders` utility to respect "Connection" header directives.
- Updated `FilterUpstreamHeaders` to remove connection-scoped headers dynamically.
- Refactored and tested upstream header filtering with additional validations.
- Adjusted upstream header handling during retries to replace headers safely.
2026-02-19 13:19:10 +08:00
Luis Pater 61da7bd981 Merge PR #1626 into codex/pr-1626 2026-02-19 04:49:14 +08:00
Luis Pater 9c040445af Merge pull request #1635 from thebtf/fix/openai-translator-tool-streaming
fix: handle tool call argument streaming in Codex→OpenAI translator
2026-02-19 04:22:12 +08:00
Luis Pater fff866424e Merge pull request #1628 from thebtf/fix/masquerading-headers
fix: update Claude masquerading headers and configurable defaults
2026-02-19 04:19:59 +08:00
Luis Pater 2d12becfd6 Merge pull request #1627 from thebtf/fix/reasoning-effort-clamping
fix: clamp reasoning_effort to valid OpenAI-format values
2026-02-19 04:15:19 +08:00
Luis Pater 252f7e0751 Merge pull request #1625 from thebtf/feat/tool-prefix-config
feat: add per-auth tool_prefix_disabled option
2026-02-19 04:07:22 +08:00
Luis Pater b2b17528cb Merge branch 'pr-1624' into dev
# Conflicts:
#	internal/runtime/executor/claude_executor.go
#	internal/runtime/executor/claude_executor_test.go
2026-02-19 04:05:04 +08:00
Luis Pater 55f938164b Merge pull request #1618 from alexey-yanchenko/fix/completions-usage
Fix empty usage in /v1/completions
2026-02-19 03:57:11 +08:00
Luis Pater 76294f0c59 Merge pull request #1608 from thebtf/fix/tool-reference-proxy-prefix-mainline
fix: add proxy_ prefix handling for tool_reference content blocks
2026-02-19 03:50:34 +08:00
Luis Pater 2bcee78c6e feat(tui): add standalone mode and API-based log polling
- Implemented `--standalone` mode to launch an embedded server for TUI.
- Enhanced TUI client to support API-based log polling when log hooks are unavailable.
- Added authentication gate for password input and connection handling.
- Improved localization and UX for logs, authentication, and status bar rendering.
2026-02-19 03:19:18 +08:00
Luis Pater 7fe8246a9f Merge branch 'tui' into dev 2026-02-19 03:18:24 +08:00
Luis Pater 93fe58e31e feat(tui): add standalone mode and API-based log polling
- Implemented `--standalone` mode to launch an embedded server for TUI.
- Enhanced TUI client to support API-based log polling when log hooks are unavailable.
- Added authentication gate for password input and connection handling.
- Improved localization and UX for logs, authentication, and status bar rendering.
2026-02-19 03:18:08 +08:00
Luis Pater e5b5dc870f chore(executor): remove unused Openai-Beta header from Codex executor 2026-02-19 02:19:48 +08:00
Luis Pater a54877c023 Merge branch 'dev' 2026-02-19 02:03:41 +08:00
Luis Pater bb86a0c0c4 feat(logging, executor): add request logging tests and WebSocket-based Codex executor
- Introduced unit tests for request logging middleware to enhance coverage.
- Added WebSocket-based Codex executor to support Responses API upgrade.
- Updated middleware logic to selectively capture request bodies for memory efficiency.
- Enhanced Codex configuration handling with new WebSocket attributes.
2026-02-19 01:57:02 +08:00
Kirill Turanskiy 5fa23c7f41 fix: handle tool call argument streaming in Codex→OpenAI translator
The OpenAI Chat Completions translator was silently dropping
response.function_call_arguments.delta and
response.function_call_arguments.done Codex SSE events, meaning
tool call arguments were never streamed incrementally to clients.

Add proper handling mirroring the proven Claude translator pattern:

- response.output_item.added: announce tool call (id, name, empty args)
- response.function_call_arguments.delta: stream argument chunks
- response.function_call_arguments.done: emit full args if no deltas
- response.output_item.done: defensive fallback for backward compat

State tracking via HasReceivedArgumentsDelta and HasToolCallAnnounced
ensures no duplicate argument emission and correct behavior for models
like codex-spark that skip delta events entirely.
2026-02-18 19:09:05 +03:00
Kirill Turanskiy 73dc0b10b8 fix: update Claude masquerading headers and make them configurable
Update hardcoded X-Stainless-* and User-Agent defaults to match
Claude Code 2.1.44 / @anthropic-ai/sdk 0.74.0 (verified via
diagnostic proxy capture 2026-02-17).

Changes:
- X-Stainless-Os/Arch: dynamic via runtime.GOOS/GOARCH
- X-Stainless-Package-Version: 0.55.1 → 0.74.0
- X-Stainless-Timeout: 60 → 600
- User-Agent: claude-cli/1.0.83 (external, cli) → claude-cli/2.1.44 (external, sdk-cli)

Add claude-header-defaults config section so values can be updated
without recompilation when Claude Code releases new versions.
2026-02-18 03:38:51 +03:00
Kirill Turanskiy 2ea95266e3 fix: clamp reasoning_effort to valid OpenAI-format values
CPA-internal thinking levels like 'xhigh' and 'minimal' are not accepted
by OpenAI-format providers (MiniMax, etc.). The OpenAI applier now maps
non-standard levels to the nearest valid reasoning_effort value before
writing to the request body:

  xhigh   → high
  minimal → low
  auto    → medium
2026-02-18 03:36:42 +03:00
Kirill Turanskiy 1f8f198c45 feat: passthrough upstream response headers to clients
CPA previously stripped ALL response headers from upstream AI provider
APIs, preventing clients from seeing rate-limit info, request IDs,
server-timing and other useful headers.

Changes:
- Add Headers field to Response and StreamResult structs
- Add FilterUpstreamHeaders helper (hop-by-hop + security denylist)
- Add WriteUpstreamHeaders helper (respects CPA-set headers)
- ExecuteWithAuthManager/ExecuteCountWithAuthManager now return headers
- ExecuteStreamWithAuthManager returns headers from initial connection
- All 11 provider executors populate Response.Headers
- All handler call sites write filtered upstream headers before response

Filtered headers (not forwarded):
- RFC 7230 hop-by-hop: Connection, Transfer-Encoding, Keep-Alive, etc.
- Security: Set-Cookie
- CPA-managed: Content-Length, Content-Encoding
2026-02-18 00:16:22 +03:00
Kirill Turanskiy 9261b0c20b feat: add per-auth tool_prefix_disabled option
Allow disabling the proxy_ tool name prefix on a per-account basis.
Users who route their own Anthropic account through CPA can set
"tool_prefix_disabled": true in their OAuth auth JSON to send tool
names unchanged to Anthropic.

Default behavior is fully preserved — prefix is applied unless
explicitly disabled.

Changes:
- Add ToolPrefixDisabled() accessor to Auth (reads metadata key
  "tool_prefix_disabled" or "tool-prefix-disabled")
- Gate all 6 prefix apply/strip points with the new flag
- Add unit tests for the accessor
2026-02-17 21:48:19 +03:00
Kirill Turanskiy 7cc725496e fix: skip proxy_ prefix for built-in tools in message history
The proxy_ prefix logic correctly skips built-in tools (those with a
non-empty "type" field) in tools[] definitions but does not skip them
in messages[].content[] tool_use blocks or tool_choice. This causes
web_search in conversation history to become proxy_web_search, which
Anthropic does not recognize.

Fix: collect built-in tool names from tools[] into a set and also
maintain a hardcoded fallback set (web_search, code_execution,
text_editor, computer) for cases where the built-in tool appears in
history but not in the current request's tools[] array. Skip prefixing
in messages and tool_choice when name matches a built-in.
2026-02-17 21:42:32 +03:00
Alexey Yanchenko 709d999f9f Add usage to /v1/completions 2026-02-17 17:21:03 +07:00
Kirill Turanskiy 24c18614f0 fix: skip built-in tools in tool_reference prefix + refactor to switch
- Collect built-in tool names (those with a "type" field like
  web_search, code_execution) and skip prefixing tool_reference
  blocks that reference them, preventing name mismatch.
- Refactor if-else if chains to switch statements in all three
  prefix functions for idiomatic Go style.
2026-02-16 19:37:11 +03:00
Kirill Turanskiy 603f06a762 fix: handle tool_reference nested inside tool_result.content[]
tool_reference blocks can appear nested inside tool_result.content[]
arrays, not just at the top level of messages[].content[]. The prefix
logic now iterates into tool_result blocks with array content to find
and prefix/strip nested tool_reference.tool_name fields.
2026-02-16 19:06:24 +03:00
Kirill TuranskiyandKirill Turanskiy 98f0a3e3bd fix: add proxy_ prefix handling for tool_reference content blocks (#1)
applyClaudeToolPrefix, stripClaudeToolPrefixFromResponse, and
stripClaudeToolPrefixFromStreamLine now handle "tool_reference" blocks
(field "tool_name") in addition to "tool_use" blocks (field "name").

Without this fix, tool_reference blocks in conversation history retain
their original unprefixed names while tool definitions carry the proxy_
prefix, causing Anthropic API 400 errors: "Tool reference 'X' not found
in available tools."

Co-authored-by: Kirill Turanskiy <kt@novamedia.ru>
2026-02-16 19:06:24 +03:00
Luis Pater 453aaf8774 chore(runtime): update Qwen executor user agent and headers for compatibility with new runtime standards 2026-02-16 23:29:47 +08:00
Supra4E8C 1b1ab1fb9b Merge pull request #1606 from router-for-me/add-qwen-3.5
feat(registry): add Qwen 3.5 Plus model definitions
2026-02-16 23:10:53 +08:00
Supra4E8C a9d0bb72da feat(registry): add Qwen 3.5 Plus model definitions 2026-02-16 22:55:37 +08:00
RCD 4cf25c05ce Merge upstream CLIProxyAPI v6.8.15–v6.8.17
Upstream changes:
- feat: add Google One login and improve Gemini CLI auto-discovery
- feat: add gpt-5.3-codex-spark model definition
- feat: add 'kimi' channel support in model definitions
- feat: pass cache usage from codex to openai chat completions
- fix: normalize Gemini credential file prefix for consistency
- refactor: replace manual pointer assignments with new()
- chore: update Go to 1.26, update Codex client version

Fork fixes:
- Bump mise Go pin to 1.26.0
- Remove stale .syso resource files (incompatible with Go 1.26 linker)
2026-02-16 08:01:38 +07:00
lhpqaq 2c8821891c fix(tui): update with review 2026-02-16 00:24:25 +08:00
haopengandgemini-code-assist[bot] 0a2555b0f3 Update internal/tui/auth_tab.go
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-16 00:11:31 +08:00
lhpqaq 020df41efe chore(tui): update readme, fix usage 2026-02-16 00:04:04 +08:00
lhpqaq f31f7f701a feat(tui): add i18n 2026-02-15 15:42:59 +08:00
Supra4E8C b5fe78eb70 Merge pull request #1597 from router-for-me/kimi-fix
feat(registry): add support for 'kimi' channel in model definitions
2026-02-15 15:35:17 +08:00
Supra4E8C d1f667cf8d feat(registry): add support for 'kimi' channel in model definitions 2026-02-15 15:21:33 +08:00
lhpqaq 54ad7c1b6b feat(tui): add manager tui 2026-02-15 14:52:40 +08:00
Luis Pater 55789df275 chore(docker): update Go base image to 1.26-alpine 2026-02-15 14:26:44 +08:00
Luis Pater 46a6782065 refactor(all): replace manual pointer assignments with new to enhance code readability and maintainability 2026-02-15 14:10:10 +08:00
Luis Pater c359f61859 fix(auth): normalize Gemini credential file prefix for consistency 2026-02-15 13:59:33 +08:00
Luis Pater 908c8eab5b Merge pull request #1543 from sususu98/feat/gemini-cli-google-one
feat(gemini-cli): add Google One login and improve auto-discovery
2026-02-15 13:58:21 +08:00
Luis Pater f5f2c69233 Merge pull request #1595 from alexey-yanchenko/feature/cache-usage-from-codex-to-chat-completions
Pass cache usage from codex to openai chat completions
2026-02-15 13:56:46 +08:00
Alexey Yanchenko 63d4de5eea Pass cache usage from codex to openai chat completions 2026-02-15 12:04:15 +07:00
이대희 a45c6defa7 Merge remote-tracking branch 'upstream/main' into feature/canceled 2026-02-13 15:07:32 +09:00
Luis Pater ae1e8a5191 chore(runtime, registry): update Codex client version and GPT-5.3 model creation date 2026-02-13 12:47:48 +08:00
Luis Pater b3ccc55f09 Merge pull request #1574 from fbettag/feat/gpt-5.3-codex-spark
feat(registry): add gpt-5.3-codex-spark model definition
2026-02-13 12:46:08 +08:00
이대희 40bee3e8d9 Merge branch 'main' into feature/canceled 2026-02-13 13:37:55 +09:00
Franz Bettagandgemini-code-assist[bot] 1ce56d7413 Update internal/registry/model_definitions_static_data.go
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-12 23:37:27 +01:00
Franz Bettag 41a78be3a2 feat(registry): add gpt-5.3-codex-spark model definition 2026-02-12 23:24:08 +01:00
Luis Pater 1ff5de9a31 docs(readme): add CLIProxyAPI Dashboard to project list 2026-02-13 00:40:39 +08:00
Luis Pater 46a6853046 Merge pull request #1568 from itsmylife44/add-cliproxyapi-dashboard
Add CLIProxyAPI Dashboard to 'Who is with us?' section
2026-02-13 00:37:41 +08:00
xSpaM 4b2d40bd67 Add CLIProxyAPI Dashboard to 'Who is with us?' section 2026-02-12 17:15:46 +01:00
RCD 064f2e6b8d Merge remote-tracking branch 'upstream/main' 2026-02-12 22:26:45 +07:00
Luis Pater 575881cb59 feat(registry): add new model definition for MiniMax-M2.5 2026-02-12 22:43:01 +08:00
hkfires f361b2716d feat(registry): add glm-5 model to iflow 2026-02-12 11:13:28 +08:00
이대희 93147dddeb Improves error handling for canceled requests
Adds explicit handling for context.Canceled errors in the reverse proxy error handler to return 499 status code without logging, which is more appropriate for client-side cancellations during polling.

Also adds a test case to verify this behavior.
2026-02-12 10:39:45 +09:00
이대희 c0f9b15a58 Merge remote-tracking branch 'upstream/main' into feature/canceled 2026-02-12 10:33:49 +09:00
이대희andgemini-code-assist[bot] 6f2fbdcbae Update internal/api/modules/amp/proxy.go
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-12 10:30:05 +09:00
HEUDavid 65debb874f feat/auth-hook: refactor RequstInfo to preserve original HTTP semantics 2026-02-12 07:11:17 +08:00
HEUDavid 3caadac003 feat/auth-hook: add post auth hook [CR] 2026-02-12 07:11:17 +08:00
HEUDavid 6a9e3a6b84 feat/auth-hook: add post auth hook 2026-02-12 07:11:17 +08:00
HEUDavid 269972440a feat/auth-hook: add post auth hook 2026-02-12 07:11:17 +08:00
HEUDavid cce13e6ad2 feat/auth-hook: add post auth hook 2026-02-12 07:11:17 +08:00
HEUDavid 8a565dcad8 feat/auth-hook: add post auth hook 2026-02-12 07:11:17 +08:00
HEUDavid d536110404 feat/auth-hook: add post auth hook 2026-02-12 07:11:17 +08:00
HEUDavid 48e957ddff feat/auth-hook: add post auth hook 2026-02-12 07:11:17 +08:00
HEUDavid 94563d622c feat/auth-hook: add post auth hook 2026-02-12 07:11:17 +08:00
RCD 9ee4e17e6d Merge remote-tracking branch 'upstream/main' 2026-02-12 04:36:28 +07:00
Luis Pater 58e09f8e5f Merge pull request #1542 from APE-147/fix/gemini-antigravity-schema-sanitization
fix(schema): sanitize Gemini-incompatible tool metadata fields
2026-02-11 21:34:04 +08:00
Luis Pater a146c6c0aa Merge pull request #1523 from xxddff/feature/removeUserField
fix(codex): remove unsupported 'user' field from /v1/responses payload
2026-02-11 20:38:16 +08:00
Luis Pater 4c133d3ea9 test(sdk/watcher): add tests for excluded models merging and priority parsing logic
- Added unit tests for combining OAuth excluded models across global and attribute-specific scopes.
- Implemented priority attribute parsing with support for different formats and trimming.
2026-02-11 20:35:13 +08:00
RCD 9809985f91 remove(docs): drop Chinese README translation 2026-02-11 19:06:29 +07:00
RCD a987b9fb83 Merge upstream CLIProxyAPI v6.8.11 into ProxyPilot
Upstream changes (v6.8.0–v6.8.11):
- feat: add Kimi (Moonshot AI) provider support with OAuth
- feat: add iFlow provider with OAuth and cookie auth
- feat: support Claude thinking type adaptive
- feat: capture cached token count in usage metadata
- fix: correct max completion tokens for opus 4.6 thinking
- fix: improve content handling for system and user messages
- fix: rewrite model name in response.model for Responses API SSE
- refactor: simplify provider lifecycle and registration logic
- refactor: migrate config-access to internal package

Fork integration:
- Migrate configaccess from sdk/access/config to internal/access/config_access
- Update reconcile.go to use internalconfig types directly
- Add Kimi and iFlow login flags to ProxyPilot CLI
- Integrate managementasset auto-updater
- Keep all ProxyPilot fork features (TUI, agent setup, service, etc.)
2026-02-11 19:03:07 +07:00
sususu98 f3ccd85ba1 feat(gemini-cli): add Google One login and improve auto-discovery
Add Google One personal account login to Gemini CLI OAuth flow:
- CLI --login shows mode menu (Code Assist vs Google One)
- Web management API accepts project_id=GOOGLE_ONE sentinel
- Auto-discover project via onboardUser without cloudaicompanionProject when project is unresolved

Improve robustness of auto-discovery and token handling:
- Add context-aware auto-discovery polling (30s timeout, 2s interval)
- Distinguish network errors from project-selection-required errors
- Refresh expired access tokens in readAuthFile before project lookup
- Extend project_id auto-fill to gemini auth type (was antigravity-only)

Unify credential file naming to geminicli- prefix for both CLI and web.

Add extractAccessToken unit tests (9 cases).
2026-02-11 17:53:03 +08:00
RGBadmin dc279de443 refactor: reduce code duplication in extractExcludedModelsFromMetadata 2026-02-11 15:57:16 +08:00
RGBadmin bf1634bda0 refactor: simplify per-account excluded_models merge in routing 2026-02-11 15:57:15 +08:00
NathanandClaude Opus 4.6 166d2d24d9 fix(schema): remove Gemini-incompatible tool metadata fields
Sanitize tool schemas by stripping prefill, enumTitles, $id, and patternProperties to prevent Gemini INVALID_ARGUMENT 400 errors, and add unit and executor-level tests to lock in the behavior.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-11 18:29:17 +11:00
RGBadmin 4cbcc835d1 feat: read per-account excluded_models at routing time 2026-02-11 15:21:19 +08:00
RGBadmin b93026d83a feat: merge per-account excluded_models with global config 2026-02-11 15:21:15 +08:00
RGBadmin 5ed2133ff9 feat: add per-account excluded_models and priority parsing 2026-02-11 15:21:12 +08:00
Luis Pater 1510bfcb6f fix(translator): improve content handling for system and user messages
- Added support for single and array-based `content` cases.
- Enhanced `system_instruction` structure population logic.
- Improved handling of user role assignment for string-based `content`.
2026-02-11 15:04:01 +08:00
Chén Mù c6bd91b86b Merge pull request #1519 from router-for-me/thinking
feat(translator): support Claude thinking type adaptive
2026-02-10 18:31:56 +08:00
이대희andCopilot ce0c6aa82b Update internal/api/modules/amp/proxy.go
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-02-10 19:07:49 +09:00
hkfires 349ddcaa89 fix(registry): correct max completion tokens for opus 4.6 thinking 2026-02-10 18:05:40 +08:00
xxddffandgemini-code-assist[bot] bb9fe52f1e Update internal/translator/codex/openai/responses/codex_openai-responses_request_test.go
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-10 18:24:58 +09:00
xxddffandgemini-code-assist[bot] afe4c1bfb7 更新internal/translator/codex/openai/responses/codex_openai-responses_request.go
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-10 18:24:26 +09:00
이대희 3c85d2a4d7 feature(proxy): Adds special handling for client cancellations in proxy error handler
Silences logging for client cancellations during polling to reduce noise in logs.
Client-side cancellations are common during long-running operations and should not be treated as errors.
2026-02-10 18:02:08 +09:00
xxddff 865af9f19e Implement test for user field deletion
Add test to verify deletion of user field in response
2026-02-10 17:38:49 +09:00
xxddff 2b97cb98b5 Delete 'user' field from raw JSON
Remove the 'user' field from the raw JSON as requested.
2026-02-10 17:35:54 +09:00
hkfires 938a799263 feat(translator): support Claude thinking type adaptive 2026-02-10 16:20:32 +08:00
Luis Pater 0040d78496 refactor(sdk): simplify provider lifecycle and registration logic 2026-02-10 15:39:26 +08:00
Finn PhillipsandClaude Opus 4.6 2615f489d6 fix(translator): remove broken type uppercasing in OpenAI Responses-to-Gemini translator
The `ConvertOpenAIResponsesRequestToGemini` function had code that attempted
to uppercase JSON Schema type values (e.g. "string" -> "STRING") for Gemini
compatibility. This broke nullable types because when `type` is a JSON array
like `["string", "null"]`:

1. `gjson.Result.String()` returns the raw JSON text `["string","null"]`
2. `strings.ToUpper()` produces `["STRING","NULL"]`
3. `sjson.Set()` stores it as a JSON **string** `"[\"STRING\",\"NULL\"]"`
   instead of a JSON array
4. The downstream `CleanJSONSchemaForGemini()` / `flattenTypeArrays()`
   cannot detect it (since `IsArray()` returns false on a string)
5. Gemini/Antigravity API rejects it with:
   `400 Invalid value at '...type' (Type), "["STRING","NULL"]"`

This was confirmed and tested with Droid Factory (Antigravity) Gemini models
where Claude Code sends tool schemas with nullable parameters.

The fix removes the uppercasing logic entirely and passes the raw schema
through to `parametersJsonSchema`. This is safe because:
- Antigravity executor already runs `CleanJSONSchemaForGemini()` which
  properly handles type arrays, nullable fields, and all schema cleanup
- Gemini/Vertex executors use `parametersJsonSchema` which accepts raw
  JSON Schema directly (no uppercasing needed)
- The uppercasing code also only iterated top-level properties, missing
  nested schemas entirely

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-10 09:29:09 +07:00
hkfires 896de027cc docs(config): reorder antigravity model alias example 2026-02-10 10:13:54 +08:00
hkfires fc329ebf37 docs(config): simplify oauth model alias example 2026-02-10 10:12:28 +08:00
Luis Pater eaab1d6824 Merge pull request #1506 from masrurimz/fix-sse-model-mapping
fix(amp): rewrite response.model in Responses API SSE events
2026-02-10 02:08:11 +08:00
Muhammad Zahid Masruri 0cfe310df6 ci: retrigger workflows
Amp-Thread-ID: https://ampcode.com/threads/T-019c264f-1cb9-7420-a68b-876030db6716
2026-02-10 00:09:11 +07:00
Muhammad Zahid Masruri 918b6955e4 fix(amp): rewrite model name in response.model for Responses API SSE events
The ResponseRewriter's modelFieldPaths was missing 'response.model',
causing the mapped model name to leak through SSE streaming events
(response.created, response.in_progress, response.completed) in the
OpenAI Responses API (/v1/responses).

This caused Amp CLI to report 'Unknown OpenAI model' errors when
model mapping was active (e.g., gpt-5.2-codex -> gpt-5.3-codex),
because the mapped name reached Amp's backend via telemetry.

Also sorted modelFieldPaths alphabetically per review feedback
and added regression tests for all rewrite paths.

Fixes #1463
2026-02-09 23:52:59 +07:00
Luis Pater 5a3eb08739 Merge pull request #1502 from router-for-me/iflow
feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests
2026-02-09 19:56:12 +08:00
Luis Pater 0dff329162 Merge pull request #1492 from router-for-me/management
fix(management): ensure management.html is available synchronously and improve asset sync handling
2026-02-09 19:55:21 +08:00
hkfires 49c1740b47 feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests 2026-02-09 19:29:42 +08:00
hkfires 3fbee51e9f fix(management): ensure management.html is available synchronously and improve asset sync handling 2026-02-09 08:32:58 +08:00
Luis Pater 63643c44a1 Fixed: #1484
fix(translator): restructure message content handling to support multiple content types

- Consolidated `input_text` and `output_text` handling into a single case.
- Added support for processing `input_image` content with associated URLs.
2026-02-09 02:05:38 +08:00
Luis Pater 3b34521ad9 Merge pull request #1479 from router-for-me/management
refactor(management): streamline control panel management and implement sync throttling
2026-02-08 20:37:29 +08:00
hkfires 7197fb350b fix(config): prune default descendants when merging new yaml nodes 2026-02-08 19:05:52 +08:00
RCD 7fd8acef64 chore: pin Go 1.25.6 via mise for local dev 2026-02-08 18:00:48 +07:00
RCD 85bf0bc9e0 update(agents): refresh Droid factory model list
Remove deprecated Amazon Q and GPT-5.1 Codex Max entries,
add GPT-5.3 Codex.
2026-02-08 18:00:31 +07:00
RCD e94805c460 remove(registry): drop deprecated Claude and OpenAI models
Claude: remove 3.5 Haiku, 3.7 Sonnet, Sonnet 4, Opus 4.1
OpenAI: remove GPT-5, 5-codex-mini, 5.1, 5.1-codex,
5.1-codex-mini, 5.1-codex-max
2026-02-08 17:59:42 +07:00
RCD 81f6c044f2 docs: remove Amazon Q CLI references 2026-02-08 17:59:23 +07:00
RCD ef84773394 remove(webui): drop Amazon Q provider from dashboard UI
Remove provider entry, auth file detection, import handler,
and usage color definition.
2026-02-08 17:59:07 +07:00
RCD 1a78f65cb0 remove(executor): drop Amazon Q endpoint and model mappings
Remove the q.us-east-1.amazonaws.com endpoint config, amazonq-
prefixed model mappings, and amazonq- tokenizer prefix check.
2026-02-08 17:58:44 +07:00
RCD 90625182f3 remove(registry): delete Amazon Q model definitions
Remove GetAmazonQModels and its entry in the model listing.
2026-02-08 17:58:16 +07:00
RCD 346d8d3fb6 remove(cli): drop --amazonq-import flag and import command
Remove the CLI flag, variable, and DoAmazonQImport function.
2026-02-08 17:57:55 +07:00
RCD 182b46bb5d remove(agents): delete Amazon Q CLI agent handler
Remove dedicated amazonq_cli.go and its registration in
the agent manager.
2026-02-08 17:57:27 +07:00
RCD f55574adcf remove(auth): delete Amazon Q CLI authentication files
Amazon Q CLI is deprecated. Remove the SQLite token reader
and SDK authenticator.
2026-02-08 17:57:11 +07:00
hkfires 6e349bfcc7 fix(config): avoid writing known defaults during merge 2026-02-08 18:47:44 +08:00
hkfires 234056072d refactor(management): streamline control panel management and implement sync throttling 2026-02-08 10:42:49 +08:00
Luis Pater 7e9d0db6aa Merge pull request #1467 from dusty-du/fix/kimi-toolcall-reasoning-content
Fix Kimi tool-call payload normalization for reasoning_content
2026-02-07 09:35:04 +08:00
Luis Pater 2f1874ede5 chore(docs): remove Cubence sponsorship from README files and delete related asset 2026-02-07 08:55:14 +08:00
Luis Pater 78ef04fcf1 fix(kimi): reduce redundant payload cloning and simplify translation calls 2026-02-07 08:51:48 +08:00
hkfires b7e4f00c5f fix(translator): correct gemini-cli log prefix 2026-02-07 08:40:09 +08:00
Luis Pater f7d0019df7 fix(kimi): update base URL and integrate ClaudeExecutor fallback
- Updated `KimiAPIBaseURL` to remove versioning from the root path.
- Integrated `ClaudeExecutor` fallback in `KimiExecutor` methods for compatibility with Claude requests.
- Simplified token counting by delegating to `ClaudeExecutor`.
2026-02-07 06:42:08 +08:00
test 52364af5bf Fix Kimi tool-call reasoning_content normalization 2026-02-06 14:46:16 -05:00
Luis Pater f410dd0440 Merge pull request #1390 from sususu98/fix/400-invalid-request-no-retry
fix(auth): 400 invalid_request_error 立即返回不再重试
2026-02-07 03:14:25 +08:00
Luis Pater eb5582c17c Merge pull request #1386 from shenshuoyaoyouguang/sync-auth-changes
fix(auth): normalize model key for thinking suffix in selectors
2026-02-07 03:12:01 +08:00
Luis Pater 1c6cb2bec3 Merge pull request #1239 from ThanhNguyxn/fix/gitstore-gc-after-squash
fix(store): run GC after squashing history to prevent loose object accumulation
2026-02-07 02:51:27 +08:00
Luis Pater 80b5e79e75 fix(translator): normalize and restrict stop_reason/finish_reason usage
- Standardized the handling of `stop_reason` and `finish_reason` across Codex and Gemini responses.
- Restricted pass-through of specific reasons (`max_tokens`, `stop`) for consistency.
- Enhanced fallback logic for undefined reasons.
2026-02-07 02:07:51 +08:00
Luis Pater 394497fb2f Merge pull request #1465 from router-for-me/kimi-fix
fix(kimi): add OAuth model-alias channel support and cover OAuth excl…
2026-02-07 01:27:30 +08:00
LTbinglingfeng fc7b6ef086 fix(kimi): add OAuth model-alias channel support and cover OAuth excluded-models with tests 2026-02-07 01:16:39 +08:00
Luis Pater 1187aa8222 feat(translator): capture cached token count in usage metadata and handle prompt caching
- Added support to extract and include `cachedContentTokenCount` in `usage.prompt_tokens_details`.
- Logged warnings for failures to set cached token count for better debugging.
2026-02-06 21:28:40 +08:00
Luis Pater dc9b4dd017 Merge branch 'kimi-provider-support-v2' into dev 2026-02-06 20:51:48 +08:00
Luis Pater 68cb81a258 feat: add Kimi authentication support and streamline device ID handling
- Introduced `RequestKimiToken` API for Kimi authentication flow.
- Integrated device ID management throughout Kimi-related components.
- Enhanced header management for Kimi API requests with device ID context.
2026-02-06 20:43:30 +08:00
RCD 38e7f28233 Merge upstream CLIProxyAPI v6.7.53 into ProxyPilot
Changes (v6.7.49 - v6.7.53):
- feat(registry): add Claude 4.6 (Opus) model
- feat(registry): add GPT 5.3 Codex model
- fix(registry): correct Claude Opus 4.6 model metadata
- fix: enable extended thinking support for Claude Haiku 4.5
- refactor(executor): centralize Codex client version and user agent
- refactor(translator, executor): remove redundant bytes.Clone calls
- refactor(util): optimize JSON schema processing

Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.53
2026-02-06 10:24:59 +07:00
hkfires c874f19f2a refactor(config): disable automatic migration during server startup 2026-02-06 09:57:47 +08:00
testandClaude Opus 4.6 f5f26f0cbe Add Kimi (Moonshot AI) provider support
- OAuth2 device authorization grant flow (RFC 8628) for authentication
- Streaming and non-streaming chat completions via OpenAI-compatible API
- Models: kimi-k2, kimi-k2-thinking, kimi-k2.5
- CLI `--kimi-login` command for device flow auth
- Token management with automatic refresh
- Thinking/reasoning effort support for thinking-enabled models

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-05 19:24:46 -05:00
Luis Pater 4b00312fef Merge pull request #1435 from tianyicui/fix/haiku-4-5-thinking-support
fix: Enable extended thinking support for Claude Haiku 4.5
2026-02-06 05:44:14 +08:00
Luis Pater c5fd3db01e Merge pull request #1446 from qyhfrank/fix-claude-opus-4-6-model-metadata
fix(registry): correct Claude Opus 4.6 model metadata
2026-02-06 05:43:32 +08:00
Frank Qing f870a9d2a7 fix(registry): correct Claude Opus 4.6 model metadata 2026-02-06 05:39:41 +08:00
Luis Pater b4e034be1c refactor(executor): centralize Codex client version and user agent constants
- Introduced `codexClientVersion` and `codexUserAgent` constants for better maintainability.
- Updated `EnsureHeader` calls to use the new constants.
2026-02-06 05:30:28 +08:00
Luis Pater a5a25dec57 refactor(translator, executor): remove redundant bytes.Clone calls for improved performance
- Replaced all instances of `bytes.Clone` with direct references to enhance efficiency.
- Simplified payload handling across executors and translators by eliminating unnecessary data duplication.
2026-02-06 03:26:29 +08:00
Luis Pater c71905e5e8 Merge pull request #1440 from kvokka/add-cc-opus-4-6
feat(registry): register Claude 4.6 static data
2026-02-06 03:23:59 +08:00
kvokka bc78d668ac feat(registry): register Claude 4.6 static data
Add model definition for Claude 4.6 Opus with 200k context length and thinking support capabilities.
2026-02-05 23:13:36 +04:00
Luis Pater 5bd0896ad7 feat(registry): add GPT 5.3 Codex model to static data 2026-02-06 01:52:41 +08:00
Luis Pater 09ecfbcaed refactor(executor): optimize payload cloning and streamline SDK translator usage
- Replaced unnecessary `bytes.Clone` calls for `opts.OriginalRequest` throughout executors.
- Introduced intermediate variable `originalPayloadSource` to simplify payload processing.
- Ensured better clarity and structure in request translation logic.
2026-02-06 01:44:20 +08:00
Luis Pater f0bd14b64f refactor(util): optimize JSON schema processing and keyword removal logic
- Consolidated path-finding logic into a new `findPathsByFields` helper function.
- Refactored repetitive loop structures to improve readability and performance.
- Added depth-based sorting for deletion paths to ensure proper removal order.
2026-02-06 00:19:56 +08:00
RCD 6c0c0b3a44 Merge upstream CLIProxyAPI v6.7.48 into ProxyPilot
Changes:
- feat(registry): add Kimi-K2.5 model to static data
- refactor(util, executor): optimize payload handling and schema processing
- fix(thinking): support user-defined includeThoughts setting (camelCase/snake_case)
- fix(thinking): ensure includeThoughts is false for ModeNone
- fix(gemini): support snake_case thinking config fields from Python SDK
- feat(gemini-cli): support image content in Claude request conversion
- fix(test): upstream fixed the builtin tools test we also fixed

Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.48
2026-02-05 21:39:14 +07:00
Luis Pater f7d82fda3f feat(registry): add Kimi-K2.5 model to static data 2026-02-05 19:48:04 +08:00
Tianyi Cui 706590c62a fix: Enable extended thinking support for Claude Haiku 4.5
Claude Haiku 4.5 (claude-haiku-4-5-20251001) supports extended thinking
according to Anthropic's official documentation:
https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking

The model was incorrectly marked as not supporting thinking in the static
model definitions. This fix adds ThinkingSupport with the same parameters
as other Claude 4.5 models (Sonnet, Opus):
- Min: 1024 tokens
- Max: 128000 tokens
- ZeroAllowed: true
- DynamicAllowed: false
2026-02-05 19:03:23 +08:00
Luis Pater 25c6b479c7 refactor(util, executor): optimize payload handling and schema processing
- Replaced repetitive string operations with a centralized `escapeGJSONPathKey` function.
- Streamlined handling of JSON schema cleaning for Gemini and Antigravity requests.
- Improved payload management by transitioning from byte slices to strings for processing.
- Removed unnecessary cloning of byte slices in several places.
2026-02-05 19:00:30 +08:00
Chén Mù 7cf9ff0345 Merge pull request #1429 from neavo/fix/gemini-python-sdk-thinking-fields
fix(gemini): support snake_case thinking config fields from Python SDK
2026-02-05 14:32:58 +08:00
hkfires 209d74062a fix(thinking): ensure includeThoughts is false for ModeNone in budget processing 2026-02-05 10:24:42 +08:00
hkfires d86b13c9cb fix(thinking): support user-defined includeThoughts setting with camelCase and snake_case variants
Fixes #1378
2026-02-05 10:07:41 +08:00
hkfires 075e3ab69e fix(test): rename test function to reflect behavior change for builtin tools 2026-02-05 09:25:34 +08:00
Luis Pater c1c9483752 Merge pull request #1422 from dannycreations/feat-gemini-cli-claude-mime
feat(gemini-cli): support image content in Claude request conversion
2026-02-05 01:21:09 +08:00
RCD a6e817b72f Merge upstream CLIProxyAPI v6.7.47 into ProxyPilot
Changes from v6.7.43-v6.7.47:
- fix(logging): expand tilde in auth-dir and log resolution errors
- feat(pprof): add configurable pprof HTTP debug server
- feat(watcher): log auth field changes on reload
- fix(cliproxy): update auth before model registration
- docs: README updates, AICodeMirror sponsorship

Fixed upstream test bug: TestOpenAIResponsesToOpenAI now correctly expects
built-in tools to be dropped (upstream intentionally changed this behavior).

Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.47
2026-02-04 22:50:54 +07:00
neavo 6c65fdf54b fix(gemini): support snake_case thinking config fields from Python SDK
Google official Gemini Python SDK sends thinking_level, thinking_budget,
and include_thoughts (snake_case) instead of thinkingLevel, thinkingBudget,
and includeThoughts (camelCase). This caused thinking configuration to be
ignored when using Python SDK.

Changes:
- Extract layer: extractGeminiConfig now reads snake_case as fallback
- Apply layer: Gemini/CLI/Antigravity appliers clean up snake_case fields
- Translator layer: Gemini->OpenAI/Claude/Codex translators support fallback
- Tests: Added 4 test cases for snake_case field coverage

Fixes #1426
2026-02-04 21:12:47 +08:00
Luis Pater 4874253d1e Merge pull request #1425 from router-for-me/auth
fix(cliproxy): update auth before model registration
2026-02-04 15:01:01 +08:00
Luis Pater b72250349f Merge pull request #1423 from router-for-me/watcher
feat(watcher): log auth field changes on reload
2026-02-04 15:00:38 +08:00
hkfires 116573311f fix(cliproxy): update auth before model registration 2026-02-04 14:03:15 +08:00
hkfires 4af712544d feat(watcher): log auth field changes on reload
Cache parsed auth contents and compute redacted diffs for prefix, proxy_url,
and disabled when auth files are added or updated.
2026-02-04 12:29:56 +08:00
dannycreations 3f9c9591bd feat(gemini-cli): support image content in Claude request conversion
- Add logic to handle `image` content type during request translation.
- Map Claude base64 image data to Gemini's `inlineData` structure.
- Support automatic extraction of `media_type` and `data` for image parts.
2026-02-04 11:00:37 +07:00
Luis Pater 1548c567ab feat(pprof): add support for configurable pprof HTTP debug server
- Introduced a new `pprof` server to enable/debug HTTP profiling.
- Added configuration options for enabling/disabling and specifying the server address.
- Integrated pprof server lifecycle management with `Service`.

#1287
2026-02-04 02:39:26 +08:00
Luis Pater 5b23fc570c Merge pull request #1396 from Xm798/fix/log-dir-tilde-expansion
fix(logging): expand tilde in auth-dir path for log directory
2026-02-04 02:00:13 +08:00
Luis Pater 04e1c7a05a docs: reorganize and update README entries for CLIProxyAPI projects 2026-02-04 01:49:27 +08:00
Luis Pater 9181e72204 Merge pull request #1409 from wangdabaoqq/main
docs: Add a new client application - Lin Jun
2026-02-04 01:47:31 +08:00
宝宝宝 4939865f6d Add a new client application - Lin Jun 2026-02-03 23:55:24 +08:00
宝宝宝 3da7f7482e Add a new client application - Lin Jun 2026-02-03 23:36:34 +08:00
宝宝宝 9072b029b2 Add a new client application - Lin Jun 2026-02-03 23:35:53 +08:00
宝宝宝 c296cfb8c0 docs: Add a new client application - Lin Jun 2026-02-03 23:32:50 +08:00
Luis Pater 2707377fcb docs: add AICodeMirror sponsorship details to README files 2026-02-03 22:34:50 +08:00
Luis Pater 259f586ff7 Fixed: #1398
fix(translator): use model group caching for client signature validation
2026-02-03 22:04:52 +08:00
Luis Pater d885b81f23 Fixed: #1403
fix(translator): handle "input" field transformation for OpenAI responses
2026-02-03 21:49:30 +08:00
Luis Pater fe6bffd080 fixed: #1407
fix(translator): adjust "developer" role to "user" and ignore unsupported tool types
2026-02-03 21:41:17 +08:00
RCD 7e3df456a5 Merge upstream CLIProxyAPI v6.7.42 into ProxyPilot
This merge brings in upstream changes from CLIProxyAPI v6.7.42 while
preserving ProxyPilot-specific customizations:

- Updated API server and executor modules
- New OAuth model alias functionality
- Enhanced thinking provider for iflow
- Updated model definitions and registry
- Improved docker build scripts

Conflicts were resolved by keeping ProxyPilot branding and merging
upstream improvements for translator and runtime components.
2026-02-03 11:08:58 +07:00
Luis Pater 250f212fa3 fix(executor): handle "global" location in AI platform URL generation 2026-02-03 01:39:57 +08:00
Cyrus a275db3fdb fix(logging): expand tilde in auth-dir and log resolution errors
- Use util.ResolveAuthDir to properly expand ~ to user home directory
- Fixes issue where logs were created in literal "~/.cli-proxy-api" folder
- Add warning log when auth-dir resolution fails for debugging

Bug introduced in 62e2b67 (refactor(logging): centralize log directory
resolution logic), where strings.TrimSpace was used instead of
util.ResolveAuthDir to process auth-dir path.
2026-02-03 00:02:54 +08:00
sususu98 233be6272a fix(auth): 400 invalid_request_error 立即返回不再重试
当上游返回 400 Bad Request 且错误消息包含 invalid_request_error 时,
表示请求本身格式错误,切换账户不会改变结果。

修改:
- 添加 isRequestInvalidError 判定函数
- 内层循环遇到此错误立即返回,不遍历其他账户
- 外层循环不再对此类错误进行重试
2026-02-02 17:35:51 +08:00
chujian 47cb52385e sdk/cliproxy/auth: update selector tests 2026-02-02 05:26:04 +08:00
hkfires 9861bf3ded fix(codex): convert system role to developer for codex input 2026-02-01 20:43:52 +07:00
hkfires 93e2e03793 docs(translator): update Codex Claude request transform docs 2026-02-01 20:43:45 +07:00
hkfires bc3bea72f3 refactor(codex): remove codex instructions injection support 2026-02-01 20:43:35 +07:00
hkfires 9eece2ea2a feat(config): track routing and cloak changes in config diff 2026-02-01 20:42:16 +07:00
hkfires 1f1160eb07 refactor(api): centralize config change logging 2026-02-01 20:42:09 +07:00
Luis Pater 157f16d3b2 Merge pull request #1380 from router-for-me/codex
refactor(codex): remove codex instructions injection support
2026-02-01 20:20:59 +08:00
Luis Pater b927b0cc6c Merge branch 'dev' into codex 2026-02-01 20:20:49 +08:00
Luis Pater 493969a742 Merge pull request #1379 from router-for-me/log
refactor(api): centralize config change logging
2026-02-01 20:19:55 +08:00
hkfires 354f6582b2 fix(codex): convert system role to developer for codex input 2026-02-01 15:37:37 +08:00
hkfires fe3ebe3532 docs(translator): update Codex Claude request transform docs 2026-02-01 14:55:41 +08:00
hkfires ac802a4646 refactor(codex): remove codex instructions injection support 2026-02-01 14:33:31 +08:00
RCDandClaude 2f72e9801a fix: address 6 issues from Codex code review
kiro_request.go:
- Fix panic: safely truncate tokenKey for logging (was slicing [:8] without length check)
- Fix order: check EventStreamError BEFORE string pattern matching in isRetryableError

kiro_auth.go:
- Fix logic: isTokenExpired now returns true on parse failures (matches function contract)

conductor_token.go:
- Fix ignored param: StartAutoRefresh now respects caller-provided interval
- Fix race condition: protect refreshCancel with mutex in Start/StopAutoRefresh
- Fix wrong key: refreshAuth now uses executorKeyFromAuth for compat auths

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 13:11:51 +07:00
RCDandClaude 3e4dccf857 fix(middleware): address remaining code review findings
MEDIUM: Return 400 on body read error instead of passing empty body
- Previously, on io.ReadAll error, body was consumed but c.Next()
  was called, causing downstream handlers to see empty body
- Now returns http.StatusBadRequest on read errors

MEDIUM: Recompute token analysis after scaffold injection
- Token analysis was computed before scaffold state was injected
- If scaffold pushed request over token threshold, trimming was skipped
- Now recomputes analyzeTokenBudget() after injection

LOW: Always strip X-CLIProxyAPI-Todo header
- Header was only stripped when memory store was available
- If memory disabled, internal header leaked upstream
- Now stripped immediately regardless of memory store state

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 12:52:57 +07:00
RCDandClaude 4491089ad1 fix(middleware): ensure prompt budget trimming loop executes
The trimming loop condition `for keep >= minKeep` was never true because
`keep` started at 20 while `minKeep` defaults to 25. Added clamp to ensure
`keep >= minKeep` at initialization, fixing prompt budget enforcement.

Affected functions:
- trimOpenAIChatCompletions
- trimOpenAIResponses
- trimOpenAIChatCompletionsWithMemory
- trimOpenAIResponsesWithMemory
- trimClaudeMessagesWithMemory

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 12:50:05 +07:00
RCDandClaude 7cc4e9d8f5 refactor(middleware): split codex_prompt_budget.go into logical modules
Split the 2,762 line codex_prompt_budget.go into focused modules:
- codex_prompt_budget.go (1,272 lines): Main middleware, scaffold injection
- codex_budget_types.go (498 lines): Constants, package vars, config functions
- codex_budget_calculator.go (944 lines): Token analysis, trim functions

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 12:28:00 +07:00
RCDandClaude 75ca091a73 refactor(executor): split kiro_executor.go into logical modules
Split the 3,891 line kiro_executor.go into focused modules:
- kiro_executor.go (966 lines): Main executor, public interface
- kiro_auth.go (462 lines): Authentication/credential logic
- kiro_request.go (422 lines): Request transformation and retry logic
- kiro_response.go (1,765 lines): Response handling/streaming

Fix: Corrected isRetryableError to use errors.As for EventStreamError
type assertion instead of errors.Is on string constants.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 12:09:33 +07:00
RCDandClaude 8927e6b71d test(auth): add unit tests for claude, codex, gemini auth packages
Add comprehensive unit tests for authentication packages:
- claude_auth_test.go: AuthBundle parsing, token serialization, validation
- codex_auth_test.go: token storage, expiry edge cases, refresh thresholds
- gemini_auth_test.go: token storage with any type, JSON field verification

Also add translator package tests for format conversion edge cases.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 12:08:53 +07:00
RCDandClaude ef60b1cd7e refactor(auth): split conductor.go into logical modules
Split the 2,280-line conductor.go into three focused files:
- conductor.go (1,416 lines): Core types, Manager struct, execution
- conductor_oauth.go (383 lines): OAuth/API key model alias resolution
- conductor_token.go (501 lines): Token refresh and HTTP request handling

This is a pure refactor with no logic changes.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 12:02:14 +07:00
RCDandClaude 3986099409 refactor: remove unused loop index variable
Replace `for i, part := range` with `for _, part := range` since the
index variable was captured but never used (just discarded with `_ = i`).

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:57:03 +07:00
RCDandClaude b4fd299fce refactor(modules): remove deprecated RouteModule interface
Remove the V1 RouteModule interface which was marked as deprecated.
All modules now use RouteModuleV2 exclusively. The RegisterModule
function signature is simplified to accept RouteModuleV2 directly
instead of interface{}.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:55:57 +07:00
RCDandClaude b5077879d0 chore: clarify GetRequestMonitor stub comment
Remove TODO marker and update comment to indicate the stub is
intentional for API compatibility, not incomplete work.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:54:32 +07:00
RCDandClaude 861c4c29d9 chore: sync version strings to 0.3.0
Update FileVersion and ProductVersion in versioninfo.json files
from 0.1.6 to 0.3.0 for both proxypilot-tray and server commands.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:53:41 +07:00
RCDandClaude 0db83010aa feat(config): add payload filter rules to remove JSON paths
Cherry-picked from upstream 6d8609e4

Allows configuring rules to remove specific JSON paths from request/response payloads.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:36:39 +07:00
RCDandClaude 977c5c18ad fix: handle issues #1372 #1366
Cherry-picked from upstream d216adef

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:36:17 +07:00
RCDandClaude 0801d1d101 fix(config): add codex instructions enabled change to config change details
Cherry-picked from upstream bb09708c

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:35:49 +07:00
RCDandClaude 993e6795c0 fix(misc): update opencode instructions
Cherry-picked from upstream 1150d972

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:35:26 +07:00
RCDandClaude 4ba0a04c37 feat(logging): make error-logs-max-files configurable
Cherry-picked from upstream 6db8d2a2

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:34:58 +07:00
RCDandClaude 006bd54c9a fix(misc): update user agent string for opencode
Cherry-picked from upstream 2854e04b

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:34:19 +07:00
RCDandClaude af48e0f37b fix(translator): handle stop_reason and MAX_TOKENS for Claude responses
Cherry-picked from upstream f99cddf9

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:33:36 +07:00
RCDandClaude 2f6fee08d4 fix(translator): include token usage in message_delta for Claude responses
Cherry-picked from upstream 550da0ce

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:33:20 +07:00
RCDandClaude 35b033ae06 fix(caching): ensure prompt-caching beta is always appended
Cherry-picked from upstream 7ff3936e

Adds multi-turn cache control tests.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:33:02 +07:00
RCDandClaude d9b3f07db3 feat(auth): add custom HTTP client with utls for Claude API authentication
Cherry-picked from upstream 6b6d030e

Adds uTLS-based HTTP transport to mimic browser TLS fingerprints for Claude API.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:32:40 +07:00
RCDandClaude 4a3996ca5c feat(translator): add code_execution and url_context tool passthrough
Cherry-picked from upstream 538039f5

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:31:18 +07:00
RCDandClaude 459997789e refactor(gemini): optimize removeExtensionFields with post-order traversal
Cherry-picked from upstream ca796510

Uses post-order traversal and DeleteBytes for better performance.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:30:57 +07:00
RCDandClaude 29f0da4942 fix(gemini): remove unsupported extension fields
Cherry-picked from upstream d0d66cdc

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:30:35 +07:00
RCDandClaude 39796063c5 feat(caching): implement Claude prompt caching with multi-turn support
Cherry-picked from upstream 3a43ecb1

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:30:10 +07:00
RCDandClaude a7fa518584 fix: skip empty text parts and messages for Gemini API
Cherry-picked from upstream 2666708c

When Claude API sends an assistant message with empty text content,
the translator was creating an empty part, causing Gemini API to return
"required oneof field 'data' must have one initialized field" error.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:29:47 +07:00
RCDandClaude 8473211ad6 fix(codex): avoid empty prompt_cache_key
Cherry-picked from upstream 04b22909

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:29:21 +07:00
RCDandClaude 4527e5a7e5 fix(openai): drop stream for responses/compact
Cherry-picked from upstream 53920b03

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:29:03 +07:00
RCDandClaude acdf099442 feat(openai): add responses/compact support
Cherry-picked from upstream 95096bc3

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:28:45 +07:00
RCDandClaude 1c9ade20f8 fix: change HTTP status code from 400 to 502 when no provider available
Cherry-picked from upstream 6da7ed53

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:28:20 +07:00
RCDandClaude 787af1fb12 fix(antigravity): preserve finish_reason tool_calls across streaming chunks
Cherry-picked from upstream fe6043ae

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:28:03 +07:00
RCDandClaude 070ddb0ff5 fix: prevent race condition in objectstore auth sync
Cherry-picked from upstream bc32096e

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-02-01 11:27:40 +07:00
ThanhNguyxn a406ca2d5a fix(store): add proper GC with Handler and interval gating
Address maintainer feedback on PR #1239:
- Add Handler: repo.DeleteObject to prevent nil panic in Prune
- Handle ErrLooseObjectsNotSupported gracefully
- Add 5-minute interval gating to avoid repack overhead on every write
- Remove sirupsen/logrus dependency (best-effort silent GC)

Fixes #1104
2026-02-01 11:19:43 +07:00
hkfires 6a258ff841 feat(config): track routing and cloak changes in config diff 2026-02-01 12:05:48 +08:00
hkfires 4649cadcb5 refactor(api): centralize config change logging 2026-02-01 11:31:44 +08:00
Luis Pater c82d8e250a Merge pull request #1174 from lieyan666/fix/issue-1082-change-error-status-code
fix: change HTTP status code from 400 to 502 when no provider available
2026-02-01 07:10:52 +08:00
Luis Pater 73db4e64f6 Merge pull request #874 from MohammadErfan-Jabbari/fix/streaming-finish-reason-tool-calls
fix(antigravity): preserve finish_reason tool_calls across streaming chunks
2026-02-01 07:05:39 +08:00
Luis Pater 69ca0a8fac Merge pull request #859 from shunkakinoki/fix/objectstore-sync-race-condition
fix: prevent race condition in objectstore auth sync
2026-02-01 07:01:43 +08:00
Luis Pater 3b04e11544 Merge pull request #1368 from sususu98/feat/configurable-error-logs-max-files
feat(logging): make error-logs-max-files configurable
2026-02-01 06:50:10 +08:00
Luis Pater e0927afa40 Merge pull request #1371 from kitephp/patch-2
Add CLIProxyAPI Tray section to README_CN.md
2026-02-01 06:47:36 +08:00
Luis Pater f97d9f3e11 Merge pull request #1370 from kitephp/patch-3
Add CLIProxyAPI Tray information to README
2026-02-01 06:46:39 +08:00
Luis Pater 6d8609e457 feat(config): add payload filter rules to remove JSON paths
Introduce `Filter` rules in the payload configuration to remove specified JSON paths from the payload. Update related helper functions and add examples to `config.example.yaml`.
2026-02-01 05:29:41 +08:00
Luis Pater d216adeffc Fixed: #1372 #1366
fix(caching): ensure unique cache_control injection using count validation
2026-01-31 23:48:50 +08:00
hkfires bb09708c02 fix(config): add codex instructions enabled change to config change details 2026-01-31 22:44:25 +08:00
hkfires 1150d972a1 fix(misc): update opencode instructions 2026-01-31 22:28:30 +08:00
kitephp 13bb7cf704 Add CLIProxyAPI Tray information to README
Added CLIProxyAPI Tray section with details about the application.
2026-01-31 20:28:16 +08:00
kitephp 8bce696a7c Add CLIProxyAPI Tray section to README_CN.md
Added information about CLIProxyAPI Tray application.
2026-01-31 20:26:52 +08:00
sususu98 6db8d2a28e feat(logging): make error-logs-max-files configurable
- Add ErrorLogsMaxFiles config field with default value 10
- Support hot-reload via config file changes
- Add Management API: GET/PUT/PATCH /v0/management/error-logs-max-files
- Maintain SDK backward compatibility with NewFileRequestLogger (3 params)
- Add NewFileRequestLoggerWithOptions for custom error log retention

When request logging is disabled, forced error logs are retained up to
the configured limit. Set to 0 to disable cleanup.
2026-01-31 17:48:40 +08:00
hkfires 2854e04bbb fix(misc): update user agent string for opencode 2026-01-31 11:23:08 +08:00
Luis Pater f99cddf97f fix(translator): handle stop_reason and MAX_TOKENS for Claude responses 2026-01-31 04:03:01 +08:00
Luis Pater f887f9985d Merge pull request #1248 from shekohex/feat/responses-compact
feat(openai): add responses/compact support
2026-01-31 03:12:55 +08:00
Luis Pater 550da0cee8 fix(translator): include token usage in message_delta for Claude responses 2026-01-31 02:55:27 +08:00
Luis Pater 7ff3936efe fix(caching): ensure prompt-caching beta is always appended and add multi-turn cache control tests 2026-01-31 01:42:58 +08:00
Luis Pater f36a5f5654 Merge pull request #1294 from Darley-Wey/fix/claude2gemini
fix: skip empty text parts and messages to avoid Gemini API error
2026-01-31 01:05:41 +08:00
Luis Pater c1facdff67 Merge pull request #1295 from SchneeMart/feature/claude-caching
feat(caching): implement Claude prompt caching with multi-turn support
2026-01-31 01:04:19 +08:00
Luis Pater 4ee46bc9f2 Merge pull request #1311 from router-for-me/fix/gemini-schema
fix(gemini): Removes unsupported extension fields
2026-01-30 23:55:56 +08:00
Luis Pater c3e94a8277 Merge pull request #1317 from yinkev/feat/gemini-tools-passthrough
feat(translator): add code_execution and url_context tool passthrough
2026-01-30 23:46:44 +08:00
Luis Pater 6b6d030ed3 feat(auth): add custom HTTP client with utls for Claude API authentication
Introduce a custom HTTP client utilizing utls with Firefox TLS fingerprinting to bypass Cloudflare fingerprinting on Anthropic domains. Includes support for proxy configuration and enhanced connection management for HTTP/2.
2026-01-30 21:29:41 +08:00
RCDandClaude ae7946402a fix(translator): validate complete JSON before using SetRaw for tool output
Tool outputs like "[1,2,3]\n\n[Process exited with code 0]" were being
partially parsed by gjson.Parse() which would extract just "[1,2,3]" and
lose the trailing text. This caused invalid JSON in the Gemini request.

Fix: Use gjson.Valid() to verify the ENTIRE string is valid JSON before
treating it as raw JSON. If validation fails, treat as a string with
proper escaping via sjson.Set().

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 17:19:56 +07:00
RCDandClaude a7b7856135 fix(tests): register test models in global registry for auth lookup
Tests were failing with "auth_not_found: no auth available" because the
conductor.pickNextMixed() function checks ClientSupportsModel() against
the global registry. Test auths weren't registered with their models.

Changes:
- sdk/cliproxy/auth/conductor_test.go: Add registry.RegisterClient calls
- internal/translator/gemini/.../gemini_openai-responses_request.go:
  Skip empty text parts to avoid invalid Gemini content

Note: Some pre-existing flaky tests remain in test/integration and
internal/translator/gemini (NonJSON tool output test).

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 16:07:03 +07:00
RCDandClaude c73b709a98 feat(registry): sync model definitions from plus remote
- Add SupportedEndpoints field to ModelInfo
- Add GetMiniMaxModels, GetZhipuModels stub functions
- Add GetGitHubCopilotModels, GetKiroModels, GetAmazonQModels
- Update model registry with new providers

Cherry-picked and merged from plus remote.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:44:20 +07:00
RCDandClaude 63e54f2ca4 chore(registry): disable gemini 2.5 flash image preview model
Cherry-picked from plus: 88a0f095

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:41:28 +07:00
RCDandClaude ac2d6df45e chore(registry): comment out rev19-uic3-1p model config
Cherry-picked from plus: c65f64dc

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:41:06 +07:00
RCDandClaude 6756600812 feat(api): add management model definitions endpoint
Cherry-picked from plus: d18cd217

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:40:44 +07:00
RCDandClaude 3a00e35a5a feat(auth): add support for request_retry and disable_cooling overrides
Cherry-picked from plus: 70897247

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:39:42 +07:00
RCDandClaude cb25c754ea feat(auth): add skip persistence context key for file watcher events
Cherry-picked from plus: 9c341f5a

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:39:20 +07:00
RCDandClaude a8592c8410 fix(claude): default Claude tool input schema
Cherry-picked from plus: e3e741d0

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:38:36 +07:00
RCDandClaude 9e53fc4540 fix(kiro): fix Kiro tool schema defaults
Cherry-picked from plus: 7c7c5fd9

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:38:17 +07:00
RCDandClaude e17990c2f8 fix(config): ensure empty mapping persists for oauth-model-alias deletions
When all oauth-model-alias entries are deleted, ensure an empty map
is persisted to config file rather than being omitted entirely.

Fixes #1305

Cherry-picked from upstream: a709e5a1

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:31:58 +07:00
RCDandClaude 71a502075e fix(logging): capture streaming TTFB on first chunk and make timestamps required
- Add firstChunkTimestamp field to ResponseWriterWrapper for sync capture
- Capture TTFB in Write() and WriteString() before async channel send
- Add SetFirstChunkTimestamp() to StreamingLogWriter interface
- Make requestTimestamp/apiResponseTimestamp required in LogRequest()
- Remove timestamp capture from WriteAPIResponse() (now via setter)
- Fix Gemini handler to set API_RESPONSE_TIMESTAMP before writing response

This ensures accurate TTFB measurement for all streaming API formats
(OpenAI, Gemini, Claude) by capturing timestamp synchronously when
the first response chunk arrives, not when the stream finalizes.

Cherry-picked from upstream: 295f34d7

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:31:30 +07:00
RCDandClaude bcd735b2a8 fix(logging): add API response timestamp and fix request timestamp timing
Previously:
- REQUEST INFO timestamp was captured at log write time (not request arrival)
- API RESPONSE had NO timestamp at all

This fix:
- Captures REQUEST INFO timestamp when request first arrives
- Adds API RESPONSE timestamp when upstream response arrives
- Add Timestamp field to RequestInfo, set at middleware initialization
- Set API_RESPONSE_TIMESTAMP in appendAPIResponse() and gemini handler
- Pass timestamps through logging chain to writeNonStreamingLog()
- Add timestamp output to API RESPONSE section

Cherry-picked from upstream: c41ce77e

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:30:56 +07:00
RCDandClaude 584648416a fix(translator): restore usageMetadata in Gemini responses from Antigravity
When using Gemini API format with Antigravity backend, the executor
renames usageMetadata to cpaUsageMetadata in non-terminal chunks.
The Gemini translator was returning this internal field name directly
to clients instead of the standard usageMetadata field.

Add restoreUsageMetadata() to rename cpaUsageMetadata back to
usageMetadata before returning responses to clients.

Cherry-picked from upstream: 9dc0e6d0

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-30 15:29:30 +07:00
kyinhubandClaude Opus 4.5 538039f583 feat(translator): add code_execution and url_context tool passthrough
Add support for Gemini's code_execution and url_context tools in the
request translators, enabling:

- Agentic Vision: Image analysis with Python code execution for
  bounding boxes, annotations, and visual reasoning
- URL Context: Live web page content fetching and analysis

Tools are passed through using the same pattern as google_search:
- code_execution: {} -> codeExecution: {}
- url_context: {} -> urlContext: {}

Tested with Gemini 3 Flash Preview agentic vision successfully.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-29 21:14:52 -08:00
이대희andAmp ca796510e9 refactor(gemini): optimize removeExtensionFields with post-order traversal and DeleteBytes
Amp-Thread-ID: https://ampcode.com/threads/T-019c0d09-330d-7399-b794-652b94847df1
Co-authored-by: Amp <amp@ampcode.com>
2026-01-30 13:02:58 +09:00
이대희andAmp d0d66cdcb7 fix(gemini): Removes unsupported extension fields
Removes x-* extension fields from JSON schemas to ensure compatibility with the Gemini API.

These fields, while valid in OpenAPI/JSON Schema, are not recognized by the Gemini API and can cause issues.
The change recursively walks the schema, identifies these extension fields, and removes them, except when they define properties.

Amp-Thread-ID: https://ampcode.com/threads/T-019c0cd1-9e59-722b-83f0-e0582aba6914
Co-authored-by: Amp <amp@ampcode.com>
2026-01-30 12:31:26 +09:00
Luis Pater d7d54fa2cc feat(ci): add cleanup step for temporary Docker tags in workflow 2026-01-30 09:15:00 +08:00
Luis Pater 31649325f0 feat(ci): add multi-arch Docker builds and manifest creation to workflow 2026-01-30 07:26:36 +08:00
Martin SchneeweissandClaude Opus 4.5 3a43ecb19b feat(caching): implement Claude prompt caching with multi-turn support
- Add ensureCacheControl() to auto-inject cache breakpoints
- Cache tools (last tool), system (last element), and messages (2nd-to-last user turn)
- Add prompt-caching-2024-07-31 beta header
- Return original payload on sjson error to prevent corruption
- Include verification test for caching logic

Enables up to 90% cost reduction on cached tokens.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-29 22:59:33 +01:00
Luis Pater a709e5a12d fix(config): ensure empty mapping persists for oauth-model-alias deletions #1305 2026-01-30 04:17:56 +08:00
Luis Pater f0ac77197b Merge pull request #1300 from sususu98/feat/log-api-response-timestamp
fix(logging): add API response timestamp and fix request timestamp timing
2026-01-30 03:27:17 +08:00
Luis Pater da0bbf2a3f Merge pull request #1298 from sususu98/fix/restore-usageMetadata-in-gemini-translator
fix(translator): restore usageMetadata in Gemini responses from Antigravity
2026-01-30 02:59:41 +08:00
sususu98 295f34d7f0 fix(logging): capture streaming TTFB on first chunk and make timestamps required
- Add firstChunkTimestamp field to ResponseWriterWrapper for sync capture
- Capture TTFB in Write() and WriteString() before async channel send
- Add SetFirstChunkTimestamp() to StreamingLogWriter interface
- Make requestTimestamp/apiResponseTimestamp required in LogRequest()
- Remove timestamp capture from WriteAPIResponse() (now via setter)
- Fix Gemini handler to set API_RESPONSE_TIMESTAMP before writing response

This ensures accurate TTFB measurement for all streaming API formats
(OpenAI, Gemini, Claude) by capturing timestamp synchronously when
the first response chunk arrives, not when the stream finalizes.
2026-01-29 22:32:24 +08:00
RCDandClaude 41b1ad654e feat(config): add oauth-model-alias migration support
Add migration logic for converting oauth-model-mappings to oauth-model-alias
with comprehensive test coverage.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:30:09 +07:00
RCDandClaude 7d1dc22657 feat(config): add AmpCode config and incognito browser option
- Add AmpCode configuration structure for Amp CLI proxy
- Add IncognitoBrowser option for OAuth flows
- Update SDK config mappings

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:29:39 +07:00
RCDandClaude 6b85dadce7 feat(interfaces): extend client models and types
Update interfaces with new fields for extended provider support.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:29:29 +07:00
RCDandClaude 24626d061d feat(constant): add Kiro and iFlow provider constants
Add new provider constants for Kiro and iFlow authentication.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:29:20 +07:00
RCDandClaude 3fc5b5a3b3 feat(auth): add empty token provider for unauthenticated requests
Add empty auth provider for handling requests that don't require authentication.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:23:46 +07:00
RCDandClaude 357eed3ec6 feat(auth): enhance Kiro authentication with rate limiting and metrics
Extend Kiro auth module with:
- Background token refresh
- Cooldown mechanism for failed requests
- Browser fingerprint generation
- Jitter utilities for request timing
- Metrics collection and reporting
- Rate limiter with singleton pattern
- Refresh manager for token lifecycle
- Token repository for persistent storage
- Usage checker for quota monitoring
- Web-based OAuth flow templates
- Updated AWS auth and SSO OIDC flows

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:23:31 +07:00
RCDandClaude d6104a0fca feat(auth): add iFlow authentication provider
Add iFlow auth module for cookie-based authentication:
- Cookie helper utilities
- iFlow auth client implementation
- Token management
- Local OAuth server for browser flow
- SDK auth integration

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:23:10 +07:00
RCDandClaude 45ba3b9c3f feat(auth): add GitHub Copilot OAuth authentication
Add complete Copilot authentication module:
- OAuth device flow for GitHub authentication
- Token management and storage
- Error handling for auth failures

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:22:38 +07:00
RCDandClaude 92bf72d8c5 feat(amp): add Amp CLI proxy module
Add complete Amp module for routing requests through the Amp CLI:
- Core module with lifecycle management
- Gemini bridge for model translation
- Model mapping configuration
- Proxy handler for request forwarding
- Response rewriter for format conversion
- Secret management for API keys
- Route definitions and fallback handlers
- Comprehensive test coverage

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 21:22:19 +07:00
sususu98 c41ce77eea fix(logging): add API response timestamp and fix request timestamp timing
Previously:
- REQUEST INFO timestamp was captured at log write time (not request arrival)
- API RESPONSE had NO timestamp at all

This fix:
- Captures REQUEST INFO timestamp when request first arrives
- Adds API RESPONSE timestamp when upstream response arrives

Changes:
- Add Timestamp field to RequestInfo, set at middleware initialization
- Set API_RESPONSE_TIMESTAMP in appendAPIResponse() and gemini handler
- Pass timestamps through logging chain to writeNonStreamingLog()
- Add timestamp output to API RESPONSE section

This enables accurate measurement of backend response latency in error logs.
2026-01-29 22:22:18 +08:00
RCDandClaude 1fa155621b feat: sync with upstream v6.7.28
Cherry-picked changes from CLIProxyAPI v6.7.28:

- feat(handlers): add test to verify no retries after partial stream response (4eb1e60)
- fix(config): prune oauth-model-alias when preserving config (d0bada7)

Note: fix(api): update amp module only on config changes (8510fc3) was skipped
as ProxyPilot does not have the Amp feature.

Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
2026-01-29 18:48:10 +07:00
Luis Pater 4eb1e6093f feat(handlers): add test to verify no retries after partial stream response
Introduce `TestExecuteStreamWithAuthManager_DoesNotRetryAfterFirstByte` to validate that stream executions do not retry after receiving partial responses. Implement `payloadThenErrorStreamExecutor` for test coverage of this behavior.
2026-01-29 17:30:48 +08:00
Luis Pater 189a066807 Merge pull request #1296 from router-for-me/log
fix(api): update amp module only on config changes
2026-01-29 17:27:52 +08:00
hkfires d0bada7a43 fix(config): prune oauth-model-alias when preserving config 2026-01-29 14:06:52 +08:00
sususu98 9dc0e6d08b fix(translator): restore usageMetadata in Gemini responses from Antigravity
When using Gemini API format with Antigravity backend, the executor
renames usageMetadata to cpaUsageMetadata in non-terminal chunks.
The Gemini translator was returning this internal field name directly
to clients instead of the standard usageMetadata field.

Add restoreUsageMetadata() to rename cpaUsageMetadata back to
usageMetadata before returning responses to clients.
2026-01-29 11:16:00 +08:00
hkfires 8510fc313e fix(api): update amp module only on config changes 2026-01-29 09:28:49 +08:00
Darley 2666708c30 fix: skip empty text parts and messages to avoid Gemini API error
When Claude API sends an assistant message with empty text content like:
{"role":"assistant","content":[{"type":"text","text":""}]}
The translator was creating a part object {} with no data field,
causing Gemini API to return error:
"required oneof field 'data' must have one initialized field"
This fix:
1. Skips empty text parts (text="") during translation
2. Skips entire messages when their parts array becomes empty
This ensures compatibility when clients send empty assistant messages
in their conversation history.
2026-01-29 04:13:07 +08:00
Luis Pater 9e5b1d24e8 Merge pull request #1276 from router-for-me/thinking
feat(thinking): enable thinking toggle for qwen3 and deepseek models
2026-01-28 11:16:54 +08:00
Luis Pater a7dae6ad52 Merge remote-tracking branch 'origin/dev' into dev 2026-01-28 10:59:00 +08:00
Luis Pater e93e05ae25 refactor: consolidate channel send logic with context-safe handlers
Optimize channel operations by introducing reusable context-aware send functions (`send` and `sendErr`) across `wsrelay`, `handlers`, and `cliproxy`. Ensure graceful handling of canceled contexts during stream operations.
2026-01-28 10:58:35 +08:00
hkfires c8c27325dc feat(thinking): enable thinking toggle for qwen3 and deepseek models
Fix #1245
2026-01-28 09:54:05 +08:00
hkfires c3b6f3918c chore(git): stop ignoring .idea and data directories 2026-01-28 09:52:44 +08:00
Luis Pater bbb55a8ab4 Merge pull request #1170 from BianBianY/main
feat: optimization enable/disable auth files
2026-01-28 09:34:35 +08:00
Shady Khalifa 04b2290927 fix(codex): avoid empty prompt_cache_key 2026-01-27 19:06:42 +02:00
Shady Khalifa 53920b0399 fix(openai): drop stream for responses/compact 2026-01-27 18:27:34 +02:00
RCD 1663148a32 feat: sync with upstream v6.7.25-26
Cherry-picked changes from CLIProxyAPI:
- fix(gemini): force type to string for enum fields (fixes Antigravity Gemini API error)
- feat(auth): add request_retry and disable_cooling per-auth overrides
- feat(auth): add skip persistence context key for file watcher events

Manually added RequestRetryOverride/DisableCoolingOverride methods to
types.go to preserve ProxyPilot's conductor.go compatibility while
gaining new functionality.
2026-01-27 22:08:43 +07:00
Luis Pater 7583193c2a Merge pull request #1257 from router-for-me/model
feat(api): add management model definitions endpoint
2026-01-27 20:32:04 +08:00
hkfires 7cc3bd4ba0 chore(deps): mark golang.org/x/text as indirect 2026-01-27 19:19:52 +08:00
hkfires 88a0f095e8 chore(registry): disable gemini 2.5 flash image preview model 2026-01-27 18:33:13 +08:00
hkfires c65f64dce0 chore(registry): comment out rev19-uic3-1p model config 2026-01-27 18:33:13 +08:00
hkfires d18cd217e1 feat(api): add management model definitions endpoint 2026-01-27 18:33:12 +08:00
Luis Pater ba4a1ab433 Merge pull request #1261 from Darley-Wey/fix/gemini_scheme
fix(gemini): force type to string for enum fields to fix Antigravity Gemini API error
2026-01-27 17:02:25 +08:00
Darley decddb521e fix(gemini): force type to string for enum fields to fix Antigravity Gemini API error (Relates to #1260) 2026-01-27 11:14:08 +03:30
Shady Khalifa 95096bc3fc feat(openai): add responses/compact support 2026-01-26 16:36:01 +02:00
Luis Pater 70897247b2 feat(auth): add support for request_retry and disable_cooling overrides
Implement `request_retry` and `disable_cooling` metadata overrides for authentication management. Update retry and cooling logic accordingly across `Manager`, Antigravity executor, and file synthesizer. Add tests to validate new behaviors.
2026-01-26 21:59:08 +08:00
RCD 1d29f18172 feat: sync with upstream v6.7.22-24
- Antigravity retry logic with improved error handling and capacity management
- Added request_id to error logs for better debugging
- Export OAuth constants from auth packages (antigravity, claude, codex, gemini)
- Added Antigravity AuthService in internal/auth/antigravity
- Updated Claude executor test expectations for system message handling
- Skip built-in tools in OAuth tool prefix
- Preserve displayName and description in Gemini models list
- Added Embed stubs for ProviderExecutor interface compliance
2026-01-26 20:22:43 +07:00
Luis Pater 9c341f5aa5 feat(auth): add skip persistence context key for file watcher events
Introduce `WithSkipPersist` to disable persistence during Manager Update/Register calls, preventing write-back loops caused by redundant file writes. Add corresponding tests and integrate with existing file store and conductor logic.
2026-01-26 18:20:19 +08:00
Luis Pater 2af4a8dc12 refactor(runtime): implement retry logic for Antigravity executor with improved error handling and capacity management 2026-01-26 06:22:46 +08:00
Luis Pater 0f53b952b2 Merge pull request #1225 from router-for-me/log
Add request_id to error logs and extract error messages
2026-01-25 22:08:46 +08:00
hkfires f30ffd5f5e feat(executor): add request_id to error logs
Extract error.message from JSON error responses when summarizing error bodies for debug logs
2026-01-25 21:31:46 +08:00
Luis Pater bc9a24d705 docs(readme): reposition CPA-XXX Panel section for improved visibility 2026-01-25 18:58:32 +08:00
Luis Pater 2c879f13ef Merge pull request #1216 from ferretgeek/add-cpa-xxx-panel
docs: 新增 CPA-XXX 社区面板项目
2026-01-25 18:57:32 +08:00
Gemini 07b4a08979 docs: translate CPA-XXX description to English 2026-01-25 18:00:28 +08:00
Geminiandfactory-droid[bot] 7f612bb069 docs: add CPA-XXX panel to community list
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-01-25 10:45:51 +08:00
hkfires 5743b78694 test(claude): update expectations for system message handling 2026-01-25 08:31:29 +08:00
Luis Pater 2e6a2b655c Merge pull request #1132 from XYenon/fix/gemini-models-displayname-override
fix(gemini): preserve displayName and description in models list
2026-01-25 03:40:04 +08:00
Luis Pater cb47ac21bf Merge pull request #1179 from mallendeo/main
fix(claude): skip built-in tools in OAuth tool prefix
2026-01-25 03:31:58 +08:00
Luis Pater a1394b4596 Merge pull request #1183 from Darley-Wey/fix/api-align
fix(api): enhance ClaudeModels response to align with api.anthropic.com
2026-01-25 03:30:14 +08:00
Luis Pater 9e97948f03 Merge pull request #1185 from router-for-me/auth
Refactor authentication handling for Antigravity, Claude, Codex, and Gemini
2026-01-25 03:28:53 +08:00
Yang Bian f7bfa8a05c Merge branch 'upstream-main' 2026-01-24 16:28:08 +08:00
RCD 5be8c90506 feat: sync with upstream v6.7.19-21
- Updated all executors with context cancellation handling
- Added payload rules using requested model
- Filter out Top_P when Temperature is set on Claude
- Remove empty system messages in translators
- Handle quota cooldown in retry logic
- Include requested model in executor metadata
- Normalize plan type filenames to lowercase
- Added Embed stubs for ProviderExecutor interface compliance
- Added payloadRequestedModel helper function
2026-01-24 11:17:03 +07:00
Darley 46c6fb1e7a fix(api): enhance ClaudeModels response to align with api.anthropic.com 2026-01-24 04:41:08 +03:30
hkfires 9f9fec5d4c fix(auth): improve antigravity token exchange errors 2026-01-24 09:04:15 +08:00
hkfires e95be10485 fix(auth): validate antigravity token userinfo email 2026-01-24 08:33:52 +08:00
hkfires f3d58fa0ce fix(auth): correct antigravity oauth redirect and expiry 2026-01-24 08:33:52 +08:00
hkfires 8c0eaa1f71 refactor(auth): export Gemini constants and use in handler 2026-01-24 08:33:52 +08:00
hkfires 405df58f72 refactor(auth): export Codex constants and slim down handler 2026-01-24 08:33:52 +08:00
hkfires e7f13aa008 refactor(api): slim down RequestAnthropicToken to use internal/auth 2026-01-24 08:33:51 +08:00
hkfires 7cb6a9b89a refactor(auth): export Claude OAuth constants for reuse 2026-01-24 08:33:51 +08:00
hkfires 9aa5344c29 refactor(api): slim down RequestAntigravityToken to use internal/auth 2026-01-24 08:33:51 +08:00
hkfires 8ba0ebbd2a refactor(sdk): slim down Antigravity authenticator to use internal/auth 2026-01-24 08:33:51 +08:00
hkfires c65407ab9f refactor(auth): extract Antigravity OAuth constants to internal/auth 2026-01-24 08:33:51 +08:00
hkfires 9e59685212 refactor(auth): implement Antigravity AuthService in internal/auth 2026-01-24 08:33:51 +08:00
hkfires 4a4dfaa910 refactor(auth): replace sanitizeAntigravityFileName with antigravity.CredentialFileName 2026-01-24 08:33:51 +08:00
Luis Pater 0d6ecb0191 Fixed: #1077
refactor(translator): improve tools handling by separating functionDeclarations and googleSearch nodes
2026-01-24 05:51:11 +08:00
Mauricio Allende f16461bfe7 fix(claude): skip built-in tools in OAuth tool prefix 2026-01-23 21:29:39 +00:00
Luis Pater c32e2a8196 fix(auth): handle context cancellation in executor methods 2026-01-24 04:56:55 +08:00
Luis Pater 873d41582f Merge pull request #1125 from NightHammer1000/dev
Filter out Top_P when Temp is set on Claude
2026-01-24 02:03:33 +08:00
Luis Pater 6fb7d85558 Merge pull request #1137 from augustVino/fix/remove_empty_systemmsg
fix(translator): ensure system message is only added if it contains c…
2026-01-24 02:02:18 +08:00
lieyan666 6da7ed53f2 fix: change HTTP status code from 400 to 502 when no provider available
Fixes #1082

When all Antigravity accounts are unavailable, the error response now returns
HTTP 502 (Bad Gateway) instead of HTTP 400 (Bad Request). This ensures that
NewAPI and other clients will retry the request on a different channel,
improving overall reliability.
2026-01-23 23:45:14 +08:00
RCD 377697331b feat: sync with upstream v6.7.17-18
- Updated gemini_schema.go with improved schema cleaning
- Refined signature caching logic (kept 1h TTL for memory efficiency)
- Enhanced Claude/Gemini translator tests
- Fixed Gemini function-calling INVALID_ARGUMENT via relaxed tool validation
2026-01-23 19:26:02 +07:00
hkfires d5e3e32d58 fix(auth): normalize plan type filenames to lowercase 2026-01-23 20:13:09 +08:00
Chén Mù f353a54555 Merge pull request #1171 from router-for-me/auth
refactor(auth): remove unused provider execution helpers
2026-01-23 19:43:42 +08:00
Chén Mù 1d6e2e751d Merge pull request #1140 from sxjeru/main
fix(auth): handle quota cooldown in retry logic for transient errors
2026-01-23 19:43:17 +08:00
hkfires cc50b63422 refactor(auth): remove unused provider execution helpers 2026-01-23 19:12:55 +08:00
Luis Pater 15ae83a15b Merge pull request #1169 from router-for-me/payload
feat(executor): apply payload rules using requested model
2026-01-23 18:41:31 +08:00
hkfires 81b369aed9 fix(auth): include requested model in executor metadata 2026-01-23 18:30:08 +08:00
Yang Bian c8620d1633 feat: optimization enable/disable auth files 2026-01-23 18:03:09 +08:00
hkfires ecc850bfb7 feat(executor): apply payload rules using requested model 2026-01-23 16:38:41 +08:00
Chén Mù 19b4ef33e0 Merge pull request #1102 from aldinokemal/main
feat(management): add PATCH endpoint to enable/disable auth files
2026-01-23 09:05:24 +08:00
hkfires 7ca045d8b9 fix(executor): adjust model-specific request payload 2026-01-22 20:28:08 +08:00
hkfires abfca6aab2 refactor(util): reorder gemini schema cleaner helpers 2026-01-22 18:38:48 +08:00
Chén Mù 3c71c075db Merge pull request #1131 from sowar1987/fix/gemini-malformed-function-call
Fix Gemini tool calling for Antigravity (malformed_function_call)
2026-01-22 18:07:03 +08:00
sowar1987andWarp 9c2992bfb2 test: align signature cache tests with cache behavior
Co-Authored-By: Warp <agent@warp.dev>
2026-01-22 17:12:47 +08:00
sowar1987andWarp 269a1c5452 refactor: reuse placeholder reason description
Co-Authored-By: Warp <agent@warp.dev>
2026-01-22 17:12:47 +08:00
sowar1987andWarp 22ce65ac72 test: update signature cache tests
Revert gemini translator changes for scheme A

Co-Authored-By: Warp <agent@warp.dev>
2026-01-22 17:12:47 +08:00
sowar1987 a2f8f59192 Fix Gemini function-calling INVALID_ARGUMENT by relaxing Gemini tool validation and cleaning schema 2026-01-22 17:11:07 +08:00
XYenon 8c7c446f33 fix(gemini): preserve displayName and description in models list
Previously GeminiModels handler unconditionally overwrote displayName
and description with the model name, losing the original values defined
in model definitions (e.g., 'Gemini 3 Pro Preview').

Now only set these fields as fallback when they are missing or empty.
2026-01-22 15:19:27 +08:00
sxjeru 30a59168d7 fix(auth): handle quota cooldown in retry logic for transient errors 2026-01-21 21:48:23 +08:00
hkfires c8884f5e25 refactor(translator): enhance signature handling in Claude and Gemini requests, streamline cache usage and remove unnecessary tests 2026-01-21 20:21:49 +08:00
Luis Pater d9c6317c84 refactor(cache, translator): refine signature caching logic and tests, replace session-based logic with model group handling 2026-01-21 18:30:05 +08:00
Vino d29ec95526 fix(translator): ensure system message is only added if it contains content 2026-01-21 16:45:50 +08:00
RCD e86d2b86d5 feat: sync with upstream v6.7.16
Major changes from upstream v6.7.16:
- Remove sessionID from signature caching API entirely
  - CacheSignature(modelName, text, sig) instead of 4 params
  - GetCachedSignature(modelName, text) instead of 3 params
  - HasValidSignature(modelName, sig) instead of 1 param
- Add Gemini fallback: returns "skip_thought_signature_validator" on cache miss
- Add sliding expiration (TTL refresh on cache access)
- Add GetModelGroup() for grouping cache keys by model family
- Simplify antigravity executor by removing project switch logic
- Fix OpenAI Responses request handler to skip empty assistant text
- Fix OpenAI Responses request to validate full JSON before parsing

Local fixes for compatibility:
- Add Embed stub method to AntigravityExecutor for interface compliance
- Update test to clear cache for isolation (ThinkingBlockWithoutSignature)
- Update Gemini test to expect thinking blocks to be annotated not removed
- Fix gjson.Valid check before treating tool output as raw JSON
2026-01-21 15:05:05 +07:00
Luis Pater ef4508dbc8 refactor(cache, translator): remove session ID from signature caching and clean up logic 2026-01-21 13:37:10 +08:00
Luis Pater f775e46fe2 refactor(translator): remove session ID logic from signature caching and associated tests 2026-01-21 12:45:07 +08:00
Luis Pater 65ad5c0c9d refactor(cache): simplify signature caching by removing sessionID parameter 2026-01-21 12:38:05 +08:00
Luis Pater 88bf4e77ec fix(translator): update HasValidSignature to require modelName parameter for improved validation 2026-01-21 11:31:37 +08:00
Luis Pater a4f8015caa test(logging): add unit tests for GinLogrusRecovery middleware panic handling 2026-01-21 10:57:27 +08:00
Luis Pater ffd129909e Merge pull request #1130 from router-for-me/agty
fix(executor): only strip maxOutputTokens for non-claude models
2026-01-21 10:50:39 +08:00
hkfires 9332316383 fix(translator): preserve thinking blocks by skipping signature 2026-01-21 10:49:20 +08:00
hkfires 6dcbbf64c3 fix(executor): only strip maxOutputTokens for non-claude models 2026-01-21 10:49:20 +08:00
Luis Pater 2ce3553612 feat(cache): handle gemini family in signature cache with fallback validator logic 2026-01-21 10:11:21 +08:00
Luis Pater 2e14f787d4 feat(translator): enhance ConvertGeminiRequestToAntigravity with model name and refine reasoning block handling 2026-01-21 08:31:23 +08:00
Luis Pater 523b41ccd2 test(responses): add comprehensive tests for SSE event ordering and response transformations 2026-01-21 07:08:59 +08:00
N1GHT 09970dc7af Accept Geminis Review Suggestion 2026-01-20 17:51:36 +01:00
N1GHT d81abd401c Returned the Code Comment I trashed 2026-01-20 17:36:27 +01:00
N1GHT a6cba25bc1 Small fix to filter out Top_P when Temperature is set on Claude to make requests go through 2026-01-20 17:34:26 +01:00
Luis Pater c6fa1d0e67 Merge pull request #1117 from router-for-me/cache
fix(translator): enhance signature cache clearing logic and update test cases with model name
2026-01-20 23:18:48 +08:00
Luis Pater ac56e1e88b Merge pull request #1116 from bexcodex/fix/antigravity
Fix antigravity malformed_function_call
2026-01-20 22:40:00 +08:00
hkfires 9b72ea9efa fix(translator): enhance signature cache clearing logic and update test cases with model name 2026-01-20 20:02:29 +08:00
bexcodex 9f364441e8 Fix antigravity malformed_function_call 2026-01-20 19:54:54 +08:00
Luis Pater e49a1c07bf chore(translator): update cache functions to include model name parameter in tests 2026-01-20 18:36:51 +08:00
RCD 3fb213d513 feat: sync with upstream v6.7.15
Port features from upstream CLIProxyAPI:

v6.7.13:
- Raw JSON payload rules (DefaultRaw, OverrideRaw)
- OpenCode instructions support with user agent detection

v6.7.14:
- Improve signature handling by associating with model name

v6.7.15:
- Unify model group references with GetModelGroup helper function
2026-01-20 16:49:13 +07:00
RCD e0fa10b669 feat: sync with upstream v6.7.13
Features ported from upstream:
- feat(claude): add native request cloaking support
- feat(translator): add candidate count (n param) support for Gemini
- fix(translator): consolidate multiple system messages into single message (#1064)
- feat(codex): add config toggle for codex instructions injection
- feat(auth): add hashed account ID to credential filenames for team plans
- feat(config): add support for raw JSON payload rules (default-raw, override-raw)
- feat(codex): add OpenCode instructions based on user agent

Also includes minor whitespace cleanup and code organization.
2026-01-20 14:08:05 +07:00
Luis Pater 8d9f4edf9b feat(translator): unify model group references by introducing GetModelGroup helper function 2026-01-20 13:45:25 +08:00
Luis Pater 020e61d0da feat(translator): improve signature handling by associating with model name in cache functions 2026-01-20 13:31:36 +08:00
RCD 4a0f8232d5 refactor(claude): remove redundant system instructions check
The checkSystemInstructions was being called on every request but the
cloaking/system prompt handling is now done elsewhere. This removes
redundant processing.

Cherry-picked from CLIProxyAPI: 7831cba9
2026-01-20 11:49:21 +07:00
RCD 3d4b723fb3 feat(translator): enhance session ID derivation with user_id parsing
Extract session ID from metadata.user_id field when available, using
the "session_" prefix marker. Falls back to first user message hash.

Cherry-picked from CLIProxyAPI: 6184c433 (Fixed: #1109)
2026-01-20 11:42:02 +07:00
RCD 5428a0ad74 test(antigravity): update tests to match cached-only signature behavior
Update tests to reflect the new signature handling behavior where only
cached signatures are used, not client-provided ones. This prevents
"Corrupted thought signature" errors when switching between Claude and
Gemini models.

Tests now properly cache signatures before testing conversion functions.
2026-01-20 11:39:56 +07:00
Luis Pater 6184c43319 Fixed: #1109
feat(translator): enhance session ID derivation with user_id parsing in Claude
2026-01-20 12:35:40 +08:00
RCD 02b0714e3a feat(vertex): add Imagen image generation model support
Add support for Imagen 3.0 and 4.0 image generation models in Vertex AI:

- Add 5 Imagen model definitions (4.0, 4.0-ultra, 4.0-fast, 3.0, 3.0-fast)
- Implement :predict action routing for Imagen models
- Convert Imagen request/response format to match Gemini structure
- Transform prompts to Imagen's instances/parameters format
- Convert base64 image responses to Gemini-compatible inline data

Cherry-picked from CLIProxyAPI: 8734d4cb
2026-01-20 11:31:07 +07:00
RCD 94088ea1de refactor(antigravity): remove legacy client signature comments
Cleanup dead code from signature handling in thinking blocks.
The actual fix was applied in commit 27b25bc0.
Cherry-picked from CLIProxyAPI: 5977af96
2026-01-20 11:25:37 +07:00
RCD e6e7e6db30 feat(registry): support provider-specific model info lookup
Add InfoByProvider map to ModelRegistration to store provider-specific
ModelInfo, enabling different capabilities for the same model across
providers (e.g., direct API vs OpenRouter).

Changes:
- Add InfoByProvider field to ModelRegistration struct
- Update GetModelInfo to accept provider parameter for provider-specific lookup
- Update LookupModelInfo to accept variadic provider parameter
- Add LookupStaticModelInfo for fallback to static model definitions
- Update ApplyThinking to pass providerKey for registry lookups
- Update all GetModelInfo callers to use new signature
- Remove ensureMaxTokensForThinking test (function moved to thinking package)

Ported from CLIProxyAPI e641fde2
2026-01-20 11:15:39 +07:00
RCD f528639f1c feat(claude): clamp thinking budget to max_tokens constraints
Improve budget normalization in Claude applier to handle edge cases
where budget exceeds or approaches max_tokens limits.

Cherry-picked from 239a2879.
2026-01-20 10:54:29 +07:00
RCD 5dd078ffb3 refactor(claude): move max_tokens constraint enforcement to Apply method
Move ensureMaxTokensForThinking logic from claude_executor to
thinking/provider/claude/apply.go. This centralizes Claude-specific
thinking budget constraints in the thinking package.

Cherry-picked from c421d653.
2026-01-20 10:53:37 +07:00
RCD 8d8a010577 feat(executor): enhance payload translation with original request context
Add 6th parameter 'original' to applyPayloadConfigWithRoot to support
checking defaults against the original payload. This enables proper
default rule validation when translating between formats.

Based on upstream 2a663d5c.
2026-01-20 10:49:30 +07:00
Luis Pater 2cbe4a790c chore(translator): remove unnecessary whitespace in gemini_openai_response code 2026-01-20 11:47:33 +08:00
RCD 27b25bc0d7 refactor(antigravity): remove unused client signature handling in thinking objects
- Comment out client signature extraction (incompatible across model families)
- Use only cached signatures for thinking blocks
- Switch to thinking.GetThinkingText for text extraction
- Add explanatory comment about cross-model signature issues

Cherry-picked from d4bb4e66.
2026-01-20 10:43:24 +07:00
Luis Pater 68b3565d7b Merge branch 'main' into dev (PR #961) 2026-01-20 11:42:22 +08:00
RCD 5a38b6bc04 fix(executor): stop rewriting thinkingLevel for gemini
Remove automatic thinkingLevel -> thinkingBudget:-1 conversion
for non-gemini-3 models in antigravity executor.

Cherry-picked from 1d2fe553.
2026-01-20 10:40:07 +07:00
RCD f1d05cc027 feat(registry): expand antigravity model config
- Remove static Name mapping from AntigravityModelConfig
- Add new model entries: claude-sonnet-4-5, gpt-oss-120b-medium, tab_flash_lite_preview
- Add model skip list for unlisted models
- Update thinking limits (Max: 128000, ZeroAllowed: true)

Cherry-picked from c175821c.
2026-01-20 10:39:00 +07:00
Luis Pater 3f385a8572 feat(auth): add "antigravity" provider to ignored access_token fields in filestore 2026-01-20 11:38:31 +08:00
Luis Pater 9823dc35e1 feat(auth): hash account ID for improved uniqueness in credential filenames 2026-01-20 11:37:52 +08:00
Luis Pater 059bfee91b feat(auth): add hashed account ID to credential filenames for team plans 2026-01-20 11:36:29 +08:00
RCD e80b531d68 fix(translator): avoid forcing RFC 8259 system prompt
Cherry-picked from 52e46ced.
2026-01-20 10:32:41 +07:00
RCD 8d737adaf1 feat(translator): report cached token usage in Claude output
Cherry-picked from cf9daf47.
2026-01-20 10:32:12 +07:00
Luis Pater 7beaf0eaa2 Merge pull request #869 2026-01-20 11:16:53 +08:00
Luis Pater 1fef90ff58 Merge pull request #877 from zhiqing0205/main
feat(codex): include plan type in auth filename
2026-01-20 11:11:25 +08:00
Luis Pater 8447fd27a0 fix(login): remove emojis from interactive prompt messages 2026-01-20 11:09:56 +08:00
Luis Pater 7831cba9f6 refactor(claude): remove redundant system instructions check in Claude executor 2026-01-20 11:02:52 +08:00
Luis Pater e02b2d58d5 Merge pull request #868 2026-01-20 10:57:24 +08:00
Luis Pater 28726632a9 Merge pull request #861 from umairimtiaz9/fix/gemini-cli-backend-project-id
fix(auth): use backend project ID for free tier Gemini CLI OAuth users
2026-01-20 10:32:17 +08:00
Luis Pater 3b26129c82 Merge pull request #1108 from router-for-me/modelinfo
feat(registry): support provider-specific model info lookup
2026-01-20 10:18:42 +08:00
Luis Pater d4bb4e6624 refactor(antigravity): remove unused client signature handling in thinking objects 2026-01-20 10:17:55 +08:00
Luis Pater 0766c49f93 Merge pull request #994 from adrenjc/fix/cross-model-thinking-signature
fix(antigravity): prevent corrupted thought signature when switching models
2026-01-20 10:14:05 +08:00
Luis Pater a7ffc77e3d Merge branch 'dev' into fix/cross-model-thinking-signature 2026-01-20 10:10:43 +08:00
hkfires e641fde25c feat(registry): support provider-specific model info lookup 2026-01-20 10:01:17 +08:00
Luis Pater 5717c7f2f4 Merge pull request #1103 from dinhkarate/feat/imagen
feat(vertex): add Imagen image generation model support
2026-01-20 07:11:18 +08:00
dinhkarate 8734d4cb90 feat(vertex): add Imagen image generation model support
Add support for Imagen 3.0 and 4.0 image generation models in Vertex AI:

- Add 5 Imagen model definitions (4.0, 4.0-ultra, 4.0-fast, 3.0, 3.0-fast)
- Implement :predict action routing for Imagen models
- Convert Imagen request/response format to match Gemini structure like gemini-3-pro-image
- Transform prompts to Imagen's instances/parameters format
- Convert base64 image responses to Gemini-compatible inline data
2026-01-20 01:26:37 +07:00
Aldino Kemal 2f6004d74a perf(management): optimize auth lookup in PatchAuthFileStatus
Use GetByID() for O(1) map lookup first, falling back to iteration
only for FileName matching. Consistent with pattern in disableAuth().
2026-01-19 20:05:37 +07:00
Luis Pater 5baa753539 Merge pull request #1099 from router-for-me/claude
refactor(claude): move max_tokens constraint enforcement to Apply method
2026-01-19 20:55:59 +08:00
Luis Pater ead98e4bca Merge pull request #1101 from router-for-me/argy
fix(executor): stop rewriting thinkingLevel for gemini
2026-01-19 20:55:22 +08:00
Aldino Kemal a1634909e8 feat(management): add PATCH endpoint to enable/disable auth files
Add new PATCH /v0/management/auth-files/status endpoint that allows
toggling the disabled state of auth files without deleting them.
This enables users to temporarily disable credentials from the
management UI.
2026-01-19 19:50:36 +07:00
hkfires 1d2fe55310 fix(executor): stop rewriting thinkingLevel for gemini 2026-01-19 19:49:39 +08:00
hkfires c175821cc4 feat(registry): expand antigravity model config
Remove static Name mapping and add entries for claude-sonnet-4-5,
tab_flash_lite_preview, and gpt-oss-120b-medium configs
2026-01-19 19:32:00 +08:00
hkfires 239a28793c feat(claude): clamp thinking budget to max_tokens constraints 2026-01-19 16:32:20 +08:00
hkfires c421d653e7 refactor(claude): move max_tokens constraint enforcement to Apply method 2026-01-19 15:50:35 +08:00
Luis Pater 2542c2920d Merge pull request #1096 from router-for-me/usage
feat(translator): report cached token usage in Claude output
2026-01-19 11:52:18 +08:00
hkfires 52e46ced1b fix(translator): avoid forcing RFC 8259 system prompt 2026-01-19 11:33:27 +08:00
hkfires cf9daf470c feat(translator): report cached token usage in Claude output 2026-01-19 11:23:44 +08:00
RCD 513594deb4 chore: add temp files to gitignore 2026-01-19 06:54:48 +07:00
RCD de766d80b3 refactor(translator): normalize includeThoughts field name
Rename include_thoughts to includeThoughts across all translator files
for consistency with the Gemini API field naming convention.

Cherry-picked key change from d5ef4a6d.
2026-01-19 06:54:38 +07:00
RCD eead4d59f4 fix(thinking): add original_mode to log field order
Cherry-picked from cb6caf3f. The main changes (fromSuffix parameter,
strictBudget logic) were already included in the thinking package port.
2026-01-19 06:50:42 +07:00
RCD f030ec3384 feat(thinking): add unified thinking configuration package
Port the internal/thinking package from CLIProxyAPI for unified thinking
configuration processing across all AI providers.

Features:
- Core types: ThinkingConfig, ThinkingMode, ThinkingLevel, SuffixResult
- Suffix parsing: model-name(16384) or model-name(high) syntax
- Validation: auto-conversion between budget/level formats, clamping
- Provider appliers: claude, gemini, antigravity, openai, codex
- Config extraction: extract thinking config from various request formats
- Stripping: remove thinking config for non-supporting models

Registry updates:
- Add UserDefined field to ModelInfo for passthrough behavior
- Add LookupModelInfo function for model capability lookup
2026-01-19 06:36:22 +07:00
RCD 22f91dc48e feat(translator): add reasoning state tracking and improve reasoning summary handling
Improves handling of reasoning summaries in OpenAI Responses API translation.
Cherry-picked from CLIProxyAPI.
2026-01-19 06:09:19 +07:00
RCD ed136fef5d refactor(logging): centralize log directory resolution logic
- Add ResolveLogDirectory() for consistent log path resolution
- Add SetLogLevel() for string-based log level configuration
- Update ConfigureLogOutput() to take *config.Config parameter
- Update all callers to use simplified API

Cherry-picked from CLIProxyAPI with adaptations.
2026-01-19 06:07:51 +07:00
RCD 630102632f fix(antigravity): convert non-string enum values to strings for Gemini API
Gemini API requires enum values to be strings. This adds NormalizeEnumValues
to convert numeric or boolean enum values to their string representations.
Cherry-picked from CLIProxyAPI.
2026-01-19 06:01:28 +07:00
RCD 2e490cf8f2 fix(translator): add check for empty text to prevent invalid serialization
Prevents sending empty text fields to Gemini and Antigravity APIs which
could cause invalid JSON serialization. Cherry-picked from CLIProxyAPI.
2026-01-19 06:00:12 +07:00
Luis Pater 140d6211cc feat(translator): add reasoning state tracking and improve reasoning summary handling
- Introduced `oaiToResponsesStateReasoning` to track reasoning data.
- Enhanced logic for emitting reasoning summary events and managing state transitions.
- Updated output generation to handle multiple reasoning entries consistently.
2026-01-19 03:58:28 +08:00
Luis Pater 60f9a1442c Merge pull request #1088 from router-for-me/thinking
Thinking
2026-01-18 17:01:59 +08:00
hkfires cb6caf3f87 fix(thinking): update ValidateConfig to include fromSuffix parameter and adjust budget validation logic 2026-01-18 16:37:14 +08:00
Luis Pater 99c7abbbf1 Merge pull request #1067 from router-for-me/auth-files
refactor(auth): simplify filename prefixes for qwen and iflow tokens
2026-01-18 13:41:59 +08:00
Luis Pater 8f511ac33c Merge pull request #1076 from sususu98/fix/antigravity-enum-string
fix(antigravity): convert non-string enum values to strings for Gemini API
2026-01-18 13:40:53 +08:00
Luis Pater 1046152119 Merge pull request #1068 from 0xtbug/dev
docs(readme): add ZeroLimit to projects based on CLIProxyAPI
2026-01-18 13:37:50 +08:00
Luis Pater f88228f1c5 Merge pull request #1081 from router-for-me/thinking
Refine thinking validation and cross‑provider payload conversion
2026-01-18 13:34:28 +08:00
Luis Pater 62e2b672d9 refactor(logging): centralize log directory resolution logic
- Introduced `ResolveLogDirectory` function in `logging` package to standardize log directory determination across components.
- Replaced redundant logic in `server`, `global_logger`, and `handlers` with the new utility function.
2026-01-18 12:40:57 +08:00
hkfires 03005b5d29 refactor(thinking): add Gemini family provider grouping for strict validation 2026-01-18 11:30:53 +08:00
hkfires c7e8830a56 refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation
Update ApplyThinking signature to accept fromFormat and toFormat parameters
instead of a single provider string. This enables:

- Proper level-to-budget conversion when source is level-based (openai/codex)
  and target is budget-based (gemini/claude)
- Strict budget range validation when source and target formats match
- Level clamping to nearest supported level for cross-format requests
- Format alias resolution in SDK translator registry for codex/openai-response

Also adds ErrBudgetOutOfRange error code and improves iflow config extraction
to fall back to openai format when iflow-specific config is not present.
2026-01-18 10:30:15 +08:00
hkfires d5ef4a6d15 refactor(translator): remove registry model lookups from thinking config conversions 2026-01-18 10:30:14 +08:00
hkfires 97b67e0e49 test(thinking): split E2E coverage into suffix and body parameter test functions
Refactor thinking configuration tests by separating model name suffix-based
scenarios from request body parameter-based scenarios into distinct test
functions with independent case numbering.

Architectural improvements:
- Extract thinkingTestCase struct to package level for shared usage
- Add getTestModels() helper returning complete model fixture set
- Introduce runThinkingTests() runner with protocol-specific field detection
- Register level-subset-model fixture with constrained low/high level support
- Extend iflow protocol handling for glm-test and minimax-test models
- Add same-protocol strict boundary validation cases (80-89)
- Replace error responses with clamped values for boundary-exceeding budgets
2026-01-18 10:30:14 +08:00
sususu98 dd6d78cb31 fix(antigravity): convert non-string enum values to strings for Gemini API
Gemini API requires all enum values in function declarations to be
strings. Some MCP tools (e.g., roxybrowser) define schemas with numeric
enums like `"enum": [0, 1, 2]`, causing INVALID_ARGUMENT errors.

Add convertEnumValuesToStrings() to automatically convert numeric and
boolean enum values to their string representations during schema
transformation.
2026-01-18 02:00:02 +00:00
RCD 7beb9b788a docs: add auto-update and rollback documentation
- Add Auto-Updates and Rollback Support features to Features list
- Add Auto-Updates section with configuration options
- Add Rollback Support section explaining crash detection and recovery
- Document tray menu options for updates and rollback
2026-01-18 08:22:20 +07:00
RCD e845700b9e test(updates): add unit tests for update system
11 tests covering:
- Poller creation, channel setting, start/stop
- Rollback data directory handling
- Rollback info save/load operations
- Health check recording and marking
- Asset platform detection
- Download progress reader
2026-01-18 07:39:02 +07:00
RCD 2913c4a20e feat(tray): integrate auto-update and rollback features
Tray app integration:
- Health check on startup with auto-rollback trigger
- Background update polling with configurable interval
- One-click update menu item (shown when available)
- Manual rollback menu item in Settings
- Mark healthy after 30s of stable operation
- Graceful cleanup on exit (stop engine, stop poller)
2026-01-18 07:38:37 +07:00
RCD cb53b9ca2a feat(tray): add stability improvements to embedded engine
Enhanced EmbeddedEngine with:
- Panic recovery to prevent tray crashes
- Graceful shutdown with 10s timeout
- Panic and restart counters for monitoring
- Uptime tracking method
- Better error handling and logging
2026-01-18 07:37:08 +07:00
RCD 3127555850 feat(updates): add rollback support with crash detection
New rollback module for version recovery:
- Version-aware backup metadata tracking
- Platform-specific restore (Windows batch, Unix swap)
- Crash loop detection via startup health monitoring
- Auto-rollback after 3 rapid failures in 30s window
- MarkHealthy() clears failure counter after stable run

Install module updated to save rollback info on update.
2026-01-18 07:34:57 +07:00
RCD 31ca3a2d93 feat(webui): add proactive update notification banner
New UpdateBanner component for dashboard:
- Auto-checks for updates on mount with 2s delay
- Shows dismissible banner when update available
- Session-based dismissal persistence
- Download progress bar during update
- Integrated into App.tsx main layout
2026-01-18 07:34:35 +07:00
RCD 4c3d538979 feat(updates): add background update poller
New poller module for periodic update checks:
- Configurable polling interval
- Channel support (stable/prerelease)
- Callback-based notification system
- Global singleton for tray integration
- Graceful start/stop with context cancellation
2026-01-18 07:34:09 +07:00
RCD 4d14eeb608 feat(config): add auto-update configuration settings
Add UpdatesConfig struct with configurable options:
- auto-check: enable/disable automatic update checks
- check-interval-hours: polling frequency (default 24h)
- auto-download/auto-install: for future automation
- notify-on-update: toast notifications
- channel: stable/prerelease support

Includes helper methods with sensible defaults.
2026-01-18 07:33:31 +07:00
Luis Pater 46433a25f8 fix(translator): add check for empty text to prevent invalid serialization in gemini and antigravity 2026-01-18 00:50:10 +08:00
Tubagusandgemini-code-assist[bot] c8843edb81 Update README_CN.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-17 11:33:29 +07:00
Tubagusandgemini-code-assist[bot] f89feb881c Update README.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-17 11:33:18 +07:00
Tubagus dbba71028e docs(readme): add ZeroLimit to projects based on CLIProxyAPI 2026-01-17 11:30:15 +07:00
Tubagus 8549a92e9a docs(readme): add ZeroLimit to projects based on CLIProxyAPI
Added ZeroLimit app to the list of projects in README.
2026-01-17 11:29:22 +07:00
hkfires 109cffc010 refactor(auth): simplify filename prefixes for qwen and iflow tokens 2026-01-17 12:20:58 +08:00
RCD 7fc975198d fix(translator): preserve multiple system prompts in Gemini requests
Cherry-pick from CLIProxyAPI v6.7.7 (f8f3ad8).

Fixes issue where only the last system/developer message was preserved
when multiple were provided. Added systemPartIndex counter to accumulate
parts across all system messages instead of overwriting at index 0.

Also fixed path inconsistency in gemini_openai_request.go where the
array branch incorrectly used request.systemInstruction instead of
system_instruction.

Fixes: router-for-me/CLIProxyAPI#1064
2026-01-17 08:10:59 +07:00
Luis Pater f8f3ad84fc Fixed: #1064
feat(translator): improve system message handling and content indexing across translators

- Updated logic for processing system messages in `claude`, `gemini`, `gemini-cli`, and `antigravity` translators.
- Introduced indexing for `systemInstruction.parts` to ensure proper ordering and handling of multi-part content.
- Added safeguards for accurate content transformation and serialization.
2026-01-17 05:40:56 +08:00
Luis Pater bc7167e9fe feat(runtime): add model alias support and enhance payload rule matching
- Introduced `payloadModelAliases` and `payloadModelCandidates` functions to support model aliases for improved flexibility.
- Updated rule matching logic to handle multiple model candidates.
- Refactored variable naming in executor to improve code clarity and consistency.
2026-01-17 05:05:24 +08:00
Luis Pater 384578a88c feat(cliproxy, gemini): improve ID matching logic and enrich normalized model output
- Enhanced ID matching in `cliproxy` by adding additional conditions to better handle ID equality cases.
- Updated `gemini` handlers to include `displayName` and `description` in normalized models for enriched metadata.
2026-01-17 04:44:09 +08:00
Luis Pater 65b4e1ec6c feat(codex): enable instruction toggling and update role terminology
- Added conditional logic for Codex instruction injection based on configuration.
- Updated role terminology from "user" to "developer" for better alignment with context.
2026-01-17 04:12:29 +08:00
Luis Pater 6600d58ba2 feat(codex): enhance input transformation and remove unused safety_identifier field
- Added logic to transform `inputResults` into structured JSON for improved processing.
- Removed redundant `safety_identifier` field in executor payload to streamline requests.
2026-01-16 19:59:01 +08:00
RCD 629bdad1c9 chore: remove installer-ui source and deprecated scripts
- Remove installer-ui/ React source (compiled assets already in cmd/installer/ui/)
- Remove start-tui-web.bat (deprecated)
- Update go.sum from mod tidy
2026-01-16 15:25:50 +07:00
RCD f2eabe57c5 fix(codex): ensure instructions field exists in request body
Add check to ensure 'instructions' field exists in Execute, ExecuteStream,
and CountTokens functions before sending request to Codex API.

Cherry-picked from:
- CLIProxyAPI v6.7.4 (902bea2)
2026-01-16 15:25:50 +07:00
RCD a2d701b205 fix(executor): update gemini-3-pro model name check to use internal name
Change conditional check from gemini-3-pro-preview (alias) to
gemini-3-pro-high (internal name) for system instruction injection.

Cherry-picked from:
- CLIProxyAPI v6.7.3 (c3ef46f)
2026-01-16 15:25:50 +07:00
RCD 7b22c4fd4d feat(auth): cherry-pick CLIProxyAPI v6.6.108-109 core updates
- Add ensureAntigravityProjectID to fetch project_id during token refresh
- Simplify filestore Save() to use os.O_TRUNC instead of temp file rename
- Auto-fetch project_id for antigravity provider in readAuthFile()
- Add metadataEqualIgnoringTimestamps to prevent refresh loops
- Use reflect.DeepEqual for cleaner metadata comparison

Cherry-picked from:
- CLIProxyAPI v6.6.108 (086eb3d)
- CLIProxyAPI v6.6.109-dev (7248f65)
2026-01-16 15:25:49 +07:00
Chén Mù 4dc7af5a5d Merge pull request #1054 from router-for-me/codex
fix(codex): ensure instructions field exists
2026-01-16 15:40:12 +08:00
hkfires 902bea24b4 fix(codex): ensure instructions field exists 2026-01-16 15:38:10 +08:00
hkfires c3ef46f409 feat(config): supplement missing default aliases during antigravity migration 2026-01-16 13:37:46 +08:00
Luis Pater aa0b63e214 refactor(config): clarify Codex instruction toggle documentation 2026-01-16 12:50:09 +08:00
Luis Pater ea3d22831e refactor(codex): update terminology to "official instructions" for clarity 2026-01-16 12:44:57 +08:00
Luis Pater 3b4d6d359b Merge pull request #1049 from router-for-me/codex
feat(codex): add config toggle for codex instructions injection
2026-01-16 12:38:35 +08:00
hkfires 48cba39a12 feat(codex): add config toggle for codex instructions injection 2026-01-16 12:30:12 +08:00
Luis Pater cec4e251bd feat(translator): preserve text field in serialized output during chat completions processing 2026-01-16 11:35:34 +08:00
Luis Pater 526dd866ba refactor(gemini): replace static model handling with dynamic model registry lookup 2026-01-16 10:39:16 +08:00
Luis Pater b31ddc7bf1 Merge branch 'dev' 2026-01-16 08:21:59 +08:00
Chén Mù 22e1ad3d8a Merge pull request #1018 from pikeman20/main
feat(docker): use environment variables for volume paths
2026-01-16 08:19:23 +08:00
Luis Pater f571b1deb0 feat(config): add support for raw JSON payload rules
- Introduced `default-raw` and `override-raw` rules to handle raw JSON values.
- Enhanced `PayloadConfig` to validate and sanitize raw JSON payload rules.
- Updated executor logic to apply `default-raw` and `override-raw` rules.
- Extended example YAML to include usage of raw JSON rules.
2026-01-16 08:15:28 +08:00
Luis Pater 67f8732683 Merge pull request #1033 from router-for-me/reasoning
Refactor thinking
2026-01-15 20:33:13 +08:00
hkfires 2b387e169b feat(iflow): add iflow-rome model definition 2026-01-15 20:23:55 +08:00
hkfires 199cf480b0 refactor(thinking): remove support for non-standard thinking configurations
This change removes the translation logic for several non-standard, proprietary extensions used to configure thinking/reasoning. Specifically, support for `extra_body.google.thinking_config` and the Anthropic-style `thinking` object has been dropped from the OpenAI request translators.

This simplification streamlines the translators, focusing them on the standard `reasoning_effort` parameter. It also removes the need to look up model information from the registry within these components.

BREAKING CHANGE: Support for non-standard thinking configurations via `extra_body.google.thinking_config` and the Anthropic-style `thinking` object has been removed. Clients should now use the standard `reasoning_effort` parameter to control reasoning.
2026-01-15 19:32:12 +08:00
hkfires 4ad6189487 refactor(thinking): extract antigravity logic into a dedicated provider 2026-01-15 19:08:22 +08:00
hkfires fe5b3c80cb refactor(config): rename oauth-model-mappings to oauth-model-alias 2026-01-15 18:03:26 +08:00
hkfires e0ffec885c fix(aistudio): remove levels from model definitions 2026-01-15 16:06:46 +08:00
hkfires ff4ff6bc2f feat(thinking): support zero as a valid thinking budget for capable models 2026-01-15 15:41:10 +08:00
Luis Pater 7248f65c36 feat(auth): prevent filestore writes on unchanged metadata
- Added `metadataEqualIgnoringTimestamps` to compare metadata while ignoring volatile fields.
- Prevented redundant writes caused by changes in timestamp-related fields.
- Improved efficiency in filestore operations by skipping unnecessary updates.
2026-01-15 14:05:23 +08:00
hkfires 5c40a2db21 refactor(thinking): simplify ModeNone and budget validation logic 2026-01-15 14:03:08 +08:00
Luis Pater 086eb3df7a refactor(auth): simplify file handling logic and remove redundant comparison functions
feat(auth): fetch and update Antigravity project ID from metadata during filestore operations

- Added support to retrieve and update `project_id` using the access token if missing in metadata.
- Integrated HTTP client to fetch project ID dynamically.
- Enhanced metadata persistence logic.
2026-01-15 13:29:14 +08:00
hkfires ee2976cca0 refactor(thinking): improve logging for user-defined models 2026-01-15 13:06:41 +08:00
hkfires 8bc6df329f fix(auth): apply API key model mapping to request model 2026-01-15 13:06:41 +08:00
hkfires bcd4d9595f fix(thinking): refine ModeNone handling based on provider capabilities 2026-01-15 13:06:41 +08:00
hkfires 5a77b7728e refactor(thinking): improve budget clamping and logging with provider/model context 2026-01-15 13:06:41 +08:00
hkfires 1fbbba6f59 feat(logging): order log fields for improved readability 2026-01-15 13:06:41 +08:00
hkfires 847be0e99d fix(auth): use base model name for auth matching by stripping suffix 2026-01-15 13:06:41 +08:00
hkfires f6a2d072e6 refactor(thinking): refine configuration logging 2026-01-15 13:06:41 +08:00
hkfires ed8b0f25ee fix(thinking): use LookupModelInfo for model data 2026-01-15 13:06:41 +08:00
hkfires 6e4a602c60 fix(thinking): map reasoning_effort to thinkingConfig 2026-01-15 13:06:40 +08:00
hkfires 2262479365 refactor(thinking): remove legacy utilities and simplify model mapping 2026-01-15 13:06:40 +08:00
hkfires 33d66959e9 test(thinking): remove legacy unit and integration tests 2026-01-15 13:06:40 +08:00
hkfires 7f1b2b3f6e fix(thinking): improve model lookup and validation 2026-01-15 13:06:40 +08:00
hkfires 40ee065eff fix(thinking): use static lookup to avoid alias issues 2026-01-15 13:06:40 +08:00
hkfires a75fb6af90 refactor(antigravity): remove hardcoded model aliases 2026-01-15 13:06:39 +08:00
hkfires 72f2125668 fix(executor): properly handle thinking application errors 2026-01-15 13:06:39 +08:00
hkfires e8f5888d8e fix(thinking): fix auth matching for thinking suffix and json field conflicts 2026-01-15 13:06:39 +08:00
hkfires 0b06d637e7 refactor: improve thinking logic 2026-01-15 13:06:39 +08:00
Luis Pater 5a7e5bd870 feat(auth): add Antigravity onboarding with tier selection
- Updated `ideType` to `ANTIGRAVITY` in request payload.
- Introduced tier-selection logic to determine default tier for onboarding.
- Added `antigravityOnboardUser` function for project ID retrieval via polling.
- Enhanced error handling and response decoding for onboarding flow.
2026-01-15 11:43:02 +08:00
Luis Pater 6f8a8f8136 feat(selector): add priority support for auth selection 2026-01-15 07:08:24 +08:00
pikeman20 5df195ea82 feat(docker): use environment variables for volume paths
This change introduces environment variable interpolation for volume paths, allowing users to customize where configuration, authentication, and log data are stored.

Why: Makes the project easier to deploy on various hosting environments that require decoupled data management without needing to modify the core docker-compose.yml..

Key points:

Defaults to existing paths (./config.yaml, ./auths, ./logs) to ensure zero breaking changes for current users.

Follows the existing naming convention used in the project.

Enhances portability for CI/CD and cloud-native deployments.
2026-01-15 05:42:51 +07:00
Luis Pater b163f8ed9e Fixed: #1004
feat(translator): add function name to response output item serialization

- Included `item.name` in the serialized response output to enhance output item handling.
2026-01-15 03:27:00 +08:00
Luis Pater a1da6ff5ac Fixed: #499 #985
feat(oauth): add support for customizable OAuth callback ports

- Introduced `oauth-callback-port` flag to override default callback ports.
- Updated SDK and login flows for `iflow`, `gemini`, `antigravity`, `codex`, `claude`, and `openai` to respect configurable callback ports.
- Refactored internal OAuth servers to dynamically assign ports based on the provided options.
- Revised tests and documentation to reflect the new flag and behavior.
2026-01-14 04:29:15 +08:00
adrenjcandClaude Opus 4.5 5977af96a0 fix(antigravity): prevent corrupted thought signature when switching models
When switching from Claude models (e.g., Opus 4.5) to Gemini models
(e.g., Flash) mid-conversation via Antigravity OAuth, the client-provided
thinking signatures from Claude would cause "Corrupted thought signature"
errors since they are incompatible with Gemini API.

Changes:
- Remove fallback to client-provided signatures in thinking block handling
- Only use cached signatures (from same-session Gemini responses)
- Skip thinking blocks without valid cached signatures
- tool_use blocks continue to use skip_thought_signature_validator when
  no valid signature is available

This ensures cross-model switching works correctly while preserving
signature validation for same-model conversations.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-13 18:24:05 +08:00
Luis Pater 43652d044c refactor(config): replace nonstream-keepalive with nonstream-keepalive-interval
- Updated `SDKConfig` to use `nonstream-keepalive-interval` (seconds) instead of the boolean `nonstream-keepalive`.
- Refactored handlers and logic to incorporate the new interval-based configuration.
- Updated config diff, tests, and example YAML to reflect the changes.
2026-01-13 03:14:38 +08:00
Luis Pater b1b379ea18 feat(api): add non-streaming keep-alive support for idle timeout prevention
- Introduced `StartNonStreamingKeepAlive` to emit periodic blank lines during non-streaming responses.
- Added `nonstream-keepalive` configuration option in `SDKConfig`.
- Updated handlers to utilize `StartNonStreamingKeepAlive` and ensure proper cleanup.
- Extended config diff and tests to include `nonstream-keepalive` changes.
2026-01-13 02:36:07 +08:00
hkfires 21ac161b21 fix(test): implement missing HttpRequest method in stream bootstrap mock 2026-01-12 16:33:43 +08:00
Luis Pater 94e979865e Fixed: #897
refactor(executor): remove `prompt_cache_retention` from request payloads
2026-01-12 10:46:47 +08:00
Luis Pater 6c324f2c8b Fixed: #936
feat(cliproxy): support multiple aliases for OAuth model mappings

- Updated mapping logic to allow multiple aliases per upstream model name.
- Adjusted `SanitizeOAuthModelMappings` to ensure aliases remain unique within channels.
- Added test cases to validate multi-alias scenarios.
- Updated example config to clarify multi-alias support.
2026-01-12 10:40:34 +08:00
Finessse e277e0f413 fix(installer): WiX v4 syntax fixes and add build-exe.bat 2026-01-12 08:21:04 +07:00
Finessse aab559c781 chore(npm): bump version to 0.2.9 2026-01-12 07:40:24 +07:00
Finessse c83da30d3d build(webui): rebuild embedded assets with rate limits component 2026-01-12 07:37:52 +07:00
Finessse 4d33b21446 chore(pricing): update model pricing table for Jan 2026
- Add Claude 4.5 model variants (opus, sonnet, haiku)
- Add Gemini 2.0/2.5 Flash and Pro pricing
- Add OpenAI o3/o4-mini pricing
- Update date reference from Dec 2024 to Jan 2026
2026-01-12 07:37:44 +07:00
Finessse e11daa1b39 feat(tray): single instance, settings menu, rate limits diagnostics
- Single-instance check prevents multiple tray apps
- Settings submenu with startup/auto-proxy toggles
- Copy Rate Limits diagnostic option
- Windows Defender exclusion option
2026-01-12 07:37:33 +07:00
Finessse d77af50d66 build(installer): add MSI installer and WinGet manifest
- WiX-based MSI installer (proxypilot.wxs)
- build-msi.ps1 script for packaging
- WinGet manifest files for package submission
2026-01-12 07:37:24 +07:00
Finessse 2d1c2070a9 feat(webui): add rate limits status dashboard component
- RateLimitsStatus component with visual gauge bar
- Shows available/cooling/disabled credential counts
- Reset cooldown button for stuck credentials
- Auto-refresh every 10 seconds
2026-01-12 07:37:14 +07:00
Finessse f415504d35 feat(api): add rate limits monitoring endpoints
- GET /v0/management/rate-limits - detailed per-credential status
- GET /v0/management/rate-limits/summary - availability overview
- Shows available, cooling_down, disabled counts and next recovery time
2026-01-12 07:37:03 +07:00
Finessse 522f0e5c89 feat(windows): add single-instance mutex and Windows service support
- winutil package with mutex-based single instance lock
- Toast notification helper for Windows
- Service stubs for future Windows service mode
2026-01-12 07:36:43 +07:00
Finessse d6dd24e2b7 feat(tui): add polished Flight Deck terminal dashboard
- Bubbletea-based TUI with 5 tabs: Status, Accounts, Rate Limits, Usage, Logs
- Industrial control room aesthetic with orange/green color scheme
- Double-line borders (╔═╗), active tab indicator 【】
- 3-column stat boxes on Status, 4-column on Usage
- Visual gauge bar for rate limit availability
- Config-optional mode allows TUI to run without config.yaml
- Full-width frame with properly aligned borders
2026-01-12 07:33:04 +07:00
Luis Pater 543dfd67e0 refactor(cache): remove max entries logic and extend signature TTL to 3 hours 2026-01-12 00:20:44 +08:00
Luis Pater 28bd1323a2 Merge pull request #971 from router-for-me/codex
feat(codex): add OpenCode instructions based on user agent
2026-01-11 16:01:13 +08:00
hkfires 220ca45f74 fix(codex): only override instructions when upstream provides them 2026-01-11 15:52:21 +08:00
hkfires 70a82d80ac fix(codex): only override instructions in responses for OpenCode UA 2026-01-11 15:19:37 +08:00
hkfires ac626111ac feat(codex): add OpenCode instructions based on user agent 2026-01-11 13:36:35 +08:00
extremk 5bb9c2a2bd Add candidate count parameter to OpenAI request 2026-01-10 18:50:13 +08:00
extremk 0b5bbe9234 Add candidate count handling in OpenAI request 2026-01-10 18:49:29 +08:00
extremk 14c74e5e84 Handle 'n' parameter for candidate count in requests
Added handling for the 'n' parameter to set candidate count in generationConfig.
2026-01-10 18:48:33 +08:00
extremk 6448d0ee7c Add candidate count handling in OpenAI request 2026-01-10 18:47:41 +08:00
extremk b0c17af2cf Enhance Gemini to OpenAI response conversion
Refactor response handling to support multiple candidates and improve parameter management.
2026-01-10 18:46:25 +08:00
Luis Pater 8cfe26f10c Merge branch 'sdk' into dev 2026-01-10 16:26:23 +08:00
Luis Pater 80db2dc254 Merge pull request #955 from router-for-me/api
feat(codex): add subscription date fields to ID token claims
2026-01-10 16:26:07 +08:00
Luis Pater e8e3bc8616 feat(executor): add HttpRequest support across executors for better http request handling 2026-01-10 16:25:25 +08:00
Luis Pater bc3195c8d8 refactor(logger): remove unnecessary request details limit logic 2026-01-10 14:46:59 +08:00
hkfires 6494330c6b feat(codex): add subscription date fields to ID token claims 2026-01-10 11:15:20 +08:00
Luis Pater 4d7f389b69 Fixed: #941
fix(translator): ensure fallback to valid originalRequestRawJSON in response handling
2026-01-10 01:01:09 +08:00
Luis Pater 95f87d5669 Merge pull request #947 from pykancha/fix-memory-leak
Resolve memory leaks causing OOM in k8s deployment
2026-01-10 00:40:47 +08:00
Luis Pater c83365a349 Merge pull request #938 from router-for-me/log
refactor(logging): clean up oauth logs and debugs
2026-01-10 00:02:45 +08:00
Luis Pater 6b3604cf2b Merge pull request #943 from ben-vargas/fix-tool-mappings
Fix Claude OAuth tool name mapping (proxy_)
2026-01-09 23:52:29 +08:00
Luis Pater af6bdca14f Fixed: #942
fix(executor): ignore non-SSE lines in OpenAI-compatible streams
2026-01-09 23:41:50 +08:00
hemanta212 1c773c428f fix: Remove investigation artifacts 2026-01-09 17:47:59 +05:45
Ben Vargas e785bfcd12 Use unprefixed Claude request for translation
Keep the upstream payload prefixed for OAuth while passing the unprefixed request body into response translators. This avoids proxy_ leaking into OpenAI Responses echoed tool metadata while preserving the Claude OAuth workaround.
2026-01-09 00:54:35 -07:00
hemanta212andAmp 47dacce6ea fix(server): resolve memory leaks causing OOM in k8s deployment
- usage/logger_plugin: cap modelStats.Details at 1000 entries per model
- cache/signature_cache: add background cleanup for expired sessions (10 min)
- management/handler: add background cleanup for stale IP rate-limit entries (1 hr)
- executor/cache_helpers: add mutex protection and TTL cleanup for codexCacheMap (15 min)
- executor/codex_executor: use thread-safe cache accessors

Add reproduction tests demonstrating leak behavior before/after fixes.

Amp-Thread-ID: https://ampcode.com/threads/T-019ba0fc-1d7b-7338-8e1d-ca0520412777
Co-authored-by: Amp <amp@ampcode.com>
2026-01-09 13:33:46 +05:45
Ben Vargas dcac3407ab Fix Claude OAuth tool name mapping
Prefix tool names with proxy_ for Claude OAuth requests and strip the prefix from streaming and non-streaming responses to restore client-facing names.

Updates the Claude executor to:
- add prefixing for tools, tool_choice, and tool_use messages when using OAuth tokens
- strip the prefix from tool_use events in SSE and non-streaming payloads
- add focused unit tests for prefix/strip helpers
2026-01-09 00:10:38 -07:00
hkfires 7004295e1d build(docker): move stats export execution after image build 2026-01-09 11:24:00 +08:00
hkfires ee62ef4745 refactor(logging): clean up oauth logs and debugs 2026-01-09 11:20:55 +08:00
Luis Pater ef6bafbf7e fix(executor): handle context cancellation and deadline errors explicitly 2026-01-09 10:48:29 +08:00
Luis Pater ed28b71e87 refactor(amp): remove duplicate comments in response rewriter 2026-01-09 08:21:13 +08:00
Luis Pater d47b7dc79a refactor(response): enhance parameter handling for Codex to Claude conversion 2026-01-09 05:20:19 +08:00
Luis Pater 49b9709ce5 Merge pull request #787 from sususu98/fix/antigravity-429-retry-delay-parsing
fix(antigravity): parse retry-after delay from 429 response body
2026-01-09 04:45:25 +08:00
Luis Pater a2eba2cdf5 Merge pull request #763 from mvelbaum/feature/improve-oauth-use-logging
feat(logging): disambiguate OAuth credential selection in debug logs
2026-01-09 04:43:21 +08:00
Luis Pater 3d01b3cfe8 Merge pull request #553 from XInTheDark/fix/builtin-tools-web-search
fix(translator): preserve built-in tools (web_search) to Responses API
2026-01-09 04:40:13 +08:00
Luis Pater af2efa6f7e Merge pull request #605 from soilSpoon/feature/amp-compat
feature: Improves Amp client compatibility
2026-01-09 04:28:17 +08:00
Luis Pater d73b61d367 Merge pull request #901 from uzhao/vscode-plugin
Vscode plugin
2026-01-08 22:22:27 +08:00
Luis Pater 59a448b645 feat(executor): centralize systemInstruction handling for Claude and Gemini-3-Pro models 2026-01-08 21:05:33 +08:00
Chén Mù 4adb9eed77 Merge pull request #921 from router-for-me/atgy
fix(executor): update gemini model identifier to gemini-3-pro-preview
2026-01-08 19:20:32 +08:00
hkfires b6a0f7a07f fix(executor): update gemini model identifier to gemini-3-pro-preview
Update the model name check in `buildRequest` to target "gemini-3-pro-preview" instead of "gemini-3-pro" when applying specific system instruction handling.
2026-01-08 19:14:52 +08:00
Luis Pater 1b2f907671 feat(executor): update system instruction handling for Claude and Gemini-3-Pro models 2026-01-08 12:42:26 +08:00
Luis Pater bda04eed8a feat(executor): add model-specific support for "gemini-3-pro" in execution and payload handling 2026-01-08 12:27:03 +08:00
Luis Pater 67985d8226 feat(executor): enhance Antigravity payload with user role and dynamic system instructions 2026-01-08 10:55:25 +08:00
Jianyang Zhaoandgemini-code-assist[bot] cbcb061812 Update README_CN.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-07 20:07:01 -05:00
Jianyang Zhaoandgemini-code-assist[bot] 9fc2e1b3c8 Update README.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-07 20:06:55 -05:00
Jianyang Zhao 3b484aea9e Add Claude Proxy VSCode to README_CN.md
Added information about Claude Proxy VSCode extension.
2026-01-07 20:03:07 -05:00
Jianyang Zhao 963a0950fa Add Claude Proxy VSCode extension to README
Added Claude Proxy VSCode extension to the README.
2026-01-07 20:02:50 -05:00
Luis Pater f4ba1ab910 fix(executor): remove unused tokenRefreshTimeout constant and pass zero timeout to HTTP client 2026-01-07 18:16:49 +08:00
Luis Pater 2662f91082 feat(management): add PostOAuthCallback handler to token requester interface 2026-01-07 10:47:32 +08:00
Luis Pater c1db2c7d7c Merge pull request #888 from router-for-me/api-call-TOKEN-fix
fix(management): refresh antigravity token for api-call $TOKEN$
2026-01-07 01:19:24 +08:00
LTbinglingfeng 5e5d8142f9 fix(auth): error when antigravity refresh token missing during refresh 2026-01-07 01:09:50 +08:00
LTbinglingfeng b01619b441 fix(management): refresh antigravity token for api-call $TOKEN$ 2026-01-07 00:14:02 +08:00
Luis Pater f861bd6a94 docs: add 9Router to community projects in README 2026-01-06 23:15:28 +08:00
Luis Pater 6dbfdd140d Merge pull request #871 from decolua/patch-1
Update README.md
2026-01-06 22:58:53 +08:00
zhiqing0205 aa8526edc0 fix(codex): use unicode title casing for plan 2026-01-06 10:24:02 +08:00
zhiqing0205 ac3ca0ad8e feat(codex): include plan type in auth filename 2026-01-06 02:25:56 +08:00
MohammadErfan JabbariandClaude fe6043aec7 fix(antigravity): preserve finish_reason tool_calls across streaming chunks
When streaming responses with tool calls, the finish_reason was being
overwritten. The upstream sends functionCall in chunk 1, then
finishReason: STOP in chunk 2. The old code would set finish_reason
from every chunk, causing "tool_calls" to be overwritten by "stop".

This broke clients like Claude Code that rely on finish_reason to
detect when tool calls are complete.

Changes:
- Add SawToolCall bool to track tool calls across entire stream
- Add UpstreamFinishReason to cache the finish reason
- Only emit finish_reason on final chunk (has both finishReason + usage)
- Priority: tool_calls > max_tokens > stop

Includes 5 unit tests covering:
- Tool calls not overwritten by subsequent STOP
- Normal text gets "stop"
- MAX_TOKENS without tool calls gets "max_tokens"
- Tool calls take priority over MAX_TOKENS
- Intermediate chunks have no finish_reason

Fixes streaming tool call detection for Claude Code + Gemini models.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-01-05 18:45:25 +01:00
decoluaandgemini-code-assist[bot] 386ccffed4 Update README.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-05 20:54:33 +07:00
FakerLandgemini-code-assist[bot] 08d21b76e2 Update sdk/auth/filestore.go
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-05 21:38:26 +08:00
decolua ffddd1c90a Update README.md 2026-01-05 20:29:26 +07:00
Zhi YangandClaude 33aa665555 fix(auth): persist access_token on refresh for providers that need it
Previously, metadataEqualIgnoringTimestamps() ignored access_token for all
providers, which prevented refreshed tokens from being persisted to disk/database.
This caused tokens to be lost on server restart for providers like iFlow.

This change makes the behavior provider-specific:
- Providers like gemini/gemini-cli that issue new tokens on every refresh and
  can re-fetch when needed will continue to ignore access_token (optimization)
- Other providers like iFlow will now persist access_token changes

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-01-05 13:25:46 +00:00
maoring24andClaude Opus 4.5 00280b6fe8 feat(claude): add native request cloaking for non-claude-code clients
integrate claude-cloak functionality to disguise api requests:
- add CloakConfig with mode (auto/always/never) and strict-mode options
- generate fake user_id in claude code format (user_[hex]_account__session_[uuid])
- inject claude code system prompt (configurable strict mode)
- obfuscate sensitive words with zero-width characters
- auto-detect claude code clients via user-agent

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-05 20:32:51 +08:00
Luis Pater 8f8dfd081b Merge pull request #850 from can1357/main
feat(translator): add developer role support for Gemini translators
2026-01-05 11:27:24 +08:00
Luis Pater 9f1b445c7c docs: add ProxyPilot to community projects in Chinese README 2026-01-05 11:23:48 +08:00
Luis Pater ae933dfe14 Merge pull request #858 from Finesssee/add-proxypilot
docs: add ProxyPilot to community projects
2026-01-05 11:20:52 +08:00
Luis Pater e124db723b Merge pull request #862 from router-for-me/gemini
fix(gemini): abort default injection on existing thinking keys
2026-01-05 10:41:07 +08:00
hkfires 05444cf32d fix(gemini): abort default injection on existing thinking keys 2026-01-05 10:24:30 +08:00
Luis Pater 8edbda57cf feat(translator): add thoughtSignature to node parts for Gemini and Antigravity requests
Enhanced node structure by including `thoughtSignature` for inline data parts in Gemini OpenAI, Gemini CLI, and Antigravity request handlers to improve traceability of thought processes.
2026-01-05 09:25:17 +08:00
CodeIgnitor 52760a4eaa fix(auth): use backend project ID for free tier Gemini CLI OAuth users
Fixes issue where free tier users cannot access Gemini 3 preview models
due to frontend/backend project ID mapping.

## Problem
Google's Gemini API uses a frontend/backend project mapping system for
free tier users:
- Frontend projects (e.g., gen-lang-client-*) are user-visible
- Backend projects (e.g., mystical-victor-*) host actual API access
- Only backend projects have access to preview models (gemini-3-*)

Previously, CLIProxyAPI ignored the backend project ID returned by
Google's onboarding API and kept using the frontend ID, preventing
access to preview models.

## Solution
### CLI (internal/cmd/login.go)
- Detect free tier users (gen-lang-client-* projects or FREE/LEGACY tier)
- Show interactive prompt allowing users to choose frontend or backend
- Default to backend (recommended for preview model access)
- Pro users: maintain original behavior (keep frontend ID)

### Web UI (internal/api/handlers/management/auth_files.go)
- Detect free tier users using same logic
- Automatically use backend project ID (recommended choice)
- Pro users: maintain original behavior (keep frontend ID)

### Deduplication (internal/cmd/login.go)
- Add deduplication when user selects ALL projects
- Prevents redundant API calls when multiple frontend projects map to
  same backend
- Skips duplicate project IDs in activation loop

## Impact
- Free tier users: Can now access gemini-3-pro-preview and
  gemini-3-flash-preview models
- Pro users: No change in behavior (backward compatible)
- Only affects Gemini CLI OAuth (not antigravity or API key auth)

## Testing
- Tested with free tier account selecting single project
- Tested with free tier account selecting ALL projects
- Verified deduplication prevents redundant onboarding calls
- Confirmed pro user behavior unchanged
2026-01-05 02:41:24 +05:00
Shun Kakinoki bc32096e9c fix: prevent race condition in objectstore auth sync
Remove os.RemoveAll() call in syncAuthFromBucket() that was causing
a race condition with the file watcher.

Problem:
1. syncAuthFromBucket() wipes local auth directory with RemoveAll
2. File watcher detects deletions and propagates them to remote store
3. syncAuthFromBucket() then pulls from remote, but files are now gone

Solution:
Use incremental sync instead of delete-then-pull. Just ensure the
directory exists and overwrite files as they're downloaded.
This prevents the watcher from seeing spurious delete events.
2026-01-05 00:10:59 +09:00
Finessse 821249a5ed docs: add ProxyPilot to community projects 2026-01-04 18:19:41 +07:00
Luis Pater ee33863b47 Merge pull request #857 from router-for-me/management-update
Management update
2026-01-04 18:07:13 +08:00
Supra4E8C cd22c849e2 feat(management): 更新OAuth模型映射的清理逻辑以增强数据安全性 2026-01-04 17:57:34 +08:00
Supra4E8C f0e73efda2 feat(management): add vertex api key and oauth model mappings endpoints 2026-01-04 17:32:00 +08:00
Supra4E8C 3156109c71 feat(management): 支持管理接口调整日志大小/强制前缀/路由策略 2026-01-04 12:21:49 +08:00
can1357 6762e081f3 feat(translator): add developer role support for Gemini translators
Treat OpenAI's "developer" role the same as "system" role in request
translation for gemini, gemini-cli, and antigravity backends.
2026-01-03 21:01:01 +01:00
Luis Pater 7815ee338d fix(translator): adjust message_delta emission boundary in Claude-to-OpenAI conversion
Fixed incorrect boundary logic for `message_delta` emission, ensuring proper handling of usage updates and `emitMessageStopIfNeeded` within the response loop.
2026-01-04 01:36:51 +08:00
Luis Pater 44b6c872e2 feat(config): add support for Fork in OAuth model mappings with alias handling
Implemented `Fork` flag in `ModelNameMapping` to allow aliases as additional models while preserving the original model ID. Updated the `applyOAuthModelMappings` logic, added tests for `Fork` behavior, and updated documentation and examples accordingly.
2026-01-04 01:18:29 +08:00
Luis Pater 7a77b23f2d feat(executor): add token refresh timeout and improve context handling during refresh
Introduced `tokenRefreshTimeout` constant for token refresh operations and enhanced context propagation for `refreshToken` by embedding roundtrip information if available. Adjusted `refreshAuth` to ensure default context initialization and handle cancellation errors appropriately.
2026-01-04 00:26:08 +08:00
Luis Pater 672e8549c0 docs: reorganize README to adjust CodMate placement
Moved CodMate entry under ProxyPal in both English and Chinese README files for consistency in structure and better readability.
2026-01-03 21:31:53 +08:00
Luis Pater 66f5269a23 Merge pull request #837 from loocor/main
docs: add CodMate to community projects
2026-01-03 21:30:15 +08:00
Luis Pater ebec293497 feat(api): integrate TokenStore for improved auth entry management
Replaced file-based auth entry counting with `TokenStore`-backed implementation, enhancing flexibility and context-aware token management. Updated related logic to reflect this change.
2026-01-03 04:53:47 +08:00
Luis Pater e02ceecd35 feat(registry): introduce ModelRegistryHook for monitoring model registrations and unregistrations
Added support for external hooks to observe model registry events using the `ModelRegistryHook` interface. Implemented thread-safe, non-blocking execution of hooks with panic recovery. Comprehensive tests added to verify hook behavior during registration, unregistration, blocking, and panic scenarios.
2026-01-02 23:18:40 +08:00
Luis Pater c8b33a8cc3 Merge pull request #824 from router-for-me/script
feat(script): add usage statistics preservation across container rebuilds
2026-01-02 20:42:25 +08:00
Loocor dca8d5ded8 Add CodMate app information to README
Added CodMate section to README with app details.
2026-01-02 17:15:38 +08:00
Loocor 2a7fd1e897 Add CodMate description to README_CN.md
添加 CodMate 应用的描述,提供 CLI AI 会话管理功能。
2026-01-02 17:15:09 +08:00
Luis Pater b9d1e70ac2 Merge pull request #830 from router-for-me/gemini
fix(util): disable default thinking for gemini-3 series
2026-01-02 10:59:24 +08:00
hkfires fdf5720217 fix(gemini): remove default thinking for gemini 3 models 2026-01-02 10:55:59 +08:00
hkfires f40bd0cd51 feat(script): add usage statistics preservation across container rebuilds 2026-01-02 10:01:20 +08:00
hkfires e33676bb87 fix(util): disable default thinking for gemini-3 series 2026-01-02 09:43:40 +08:00
Luis Pater 2a663d5cba feat(executor): enhance payload translation with original request context
Refactored `applyPayloadConfig` to `applyPayloadConfigWithRoot`, adding support for default rule validation against the original payload when available. Updated all executors to use `applyPayloadConfigWithRoot` and incorporate an optional original request payload for translations.
2026-01-02 00:03:26 +08:00
Luis Pater 750b930679 Merge pull request #823 from router-for-me/translator
feat(translator): enhance Claude-to-OpenAI conversion with thinking block and tool result handling
2026-01-01 20:16:10 +08:00
hkfires 3902fd7501 fix(iflow): remove thinking field from request body in thinking config handler 2026-01-01 19:40:28 +08:00
hkfires 4fc3d5e935 refactor(iflow): simplify thinking config handling for GLM and MiniMax models 2026-01-01 19:31:08 +08:00
hkfires 2d2f4572a7 fix(translator): remove unnecessary whitespace trimming in reasoning text collection 2026-01-01 12:39:09 +08:00
hkfires 8f4c46f38d fix(translator): emit tool_result messages before user content in Claude-to-OpenAI conversion 2026-01-01 11:11:43 +08:00
hkfires b6ba51bc2a feat(translator): add thinking block and tool result handling for Claude-to-OpenAI conversion 2026-01-01 09:41:25 +08:00
Luis Pater 6a66d32d37 Merge pull request #803 from HsnSaboor/fix-invalid-function-names-sanitization-v2
feat(translator): resolve invalid function name errors by sanitizing Claude tool names
2026-01-01 01:15:50 +08:00
Luis Pater 8d15723195 feat(registry): add GetAvailableModelsByProvider method for retrieving models by provider 2025-12-31 23:37:46 +08:00
Chén Mù 736e0aae86 Merge pull request #814 from router-for-me/aistudio
Fix model alias thinking suffix
2025-12-31 03:08:05 -08:00
hkfires 8bf3305b2b fix(thinking): fallback to upstream model for thinking support when alias not in registry 2025-12-31 18:07:13 +08:00
hkfires d00e3ea973 feat(thinking): add numeric budget to thinkingLevel conversion fallback 2025-12-31 17:14:47 +08:00
hkfires 89db4e9481 fix(thinking): use model alias for thinking config resolution in mapped models 2025-12-31 17:09:22 +08:00
hkfires e332419081 feat(registry): add thinking support for gemini-2.5-computer-use-preview model 2025-12-31 17:09:22 +08:00
Luis Pater e998b1229a feat(updater): add fallback URL and logic for missing management asset 2025-12-31 11:51:20 +08:00
Luis Pater bbed134bd1 feat(api): add GetAuthStatus method to ManagementTokenRequester interface 2025-12-31 09:40:48 +08:00
Saboor Hassanandfactory-droid[bot] 47b9503112 chore: revert changes to internal/translator to comply with path guard
This commit reverts all modifications within internal/translator. A separate issue
will be created for the maintenance team to integrate SanitizeFunctionName into
the translators.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 02:19:26 +05:00
Saboor Hassanandfactory-droid[bot] 3b9253c2be fix(translator): resolve invalid function name errors by sanitizing Claude tool names
This commit centralizes tool name sanitization in SanitizeFunctionName,
applying character compliance, starting character rules, and length limits.
It also fixes a regression in gemini_schema tests and preserves MCP-specific
shortening logic while ensuring compliance.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 02:14:46 +05:00
Saboor Hassanandfactory-droid[bot] d241359153 fix(translator): address PR feedback for tool name sanitization
- Pre-compile sanitization regex for better performance.
- Optimize SanitizeFunctionName for conciseness and correctness.
- Handle 64-char edge cases by truncating before prepending underscore.
- Fix bug in Antigravity translator (incorrect join index).
- Refactor Gemini translators to avoid redundant sanitization calls.
- Add comprehensive unit tests including 64-char edge cases.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 01:54:41 +05:00
Saboor Hassanandfactory-droid[bot] f4d4249ba5 feat(translator): sanitize tool/function names for upstream provider compatibility
Implemented SanitizeFunctionName utility to ensure Claude tool names meet
Gemini/Upstream strict naming conventions (alphanumeric, starts with letter/underscore, max 64 chars).
Applied sanitization to tool definitions and usage in all relevant translators.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 01:41:07 +05:00
Chén Mù cb56cb250e Merge pull request #800 from router-for-me/modelmappings
feat(watcher): add model mappings change detection
2025-12-30 06:50:42 -08:00
hkfires e0381a6ae0 refactor(watcher): extract model summary functions to dedicated file 2025-12-30 22:39:12 +08:00
hkfires 2c01b2ef64 feat(watcher): add Gemini models and OAuth model mappings change detection 2025-12-30 22:39:12 +08:00
Chén Mù e947266743 Merge pull request #795 from router-for-me/modelmappings
refactor(executor): resolve upstream model at conductor level before execution
2025-12-30 05:31:19 -08:00
Luis Pater c6b0e85b54 Fixed: #790
fix(gemini): include full text in response output events
2025-12-30 20:44:13 +08:00
hkfires 26efbed05c refactor(executor): remove redundant upstream model parameter from translateRequest 2025-12-30 20:20:42 +08:00
hkfires 96340bf136 refactor(executor): resolve upstream model at conductor level before execution 2025-12-30 19:31:54 +08:00
hkfires b055e00c1a fix(executor): use upstream model for thinking config and payload translation 2025-12-30 17:49:44 +08:00
sususu 414db44c00 fix(antigravity): parse retry-after delay from 429 response body
When receiving HTTP 429 (Too Many Requests) responses, parse the retry
delay from the response body using parseRetryDelay and populate the
statusErr.retryAfter field. This allows upstream callers to respect
the server's requested retry timing.

Applied to all error paths in Execute, executeClaudeNonStream,
ExecuteStream, CountTokens, and refreshToken functions.
2025-12-30 16:07:32 +08:00
Chén Mù 857c880f99 Merge pull request #785 from router-for-me/gemini
feat(gemini): add per-key model alias support for Gemini provider
2025-12-29 23:32:40 -08:00
hkfires ce7474d953 feat(cliproxy): propagate thinking support metadata to aliased models 2025-12-30 15:16:54 +08:00
hkfires 70fdd70b84 refactor(cliproxy): extract generic buildConfigModels function for model info generation 2025-12-30 13:35:22 +08:00
hkfires 08ab6a7d77 feat(gemini): add per-key model alias support for Gemini provider 2025-12-30 13:27:57 +08:00
Luis Pater 9fa2a7e9df Merge pull request #782 from router-for-me/modelmappings
refactor(config): rename model-name-mappings to oauth-model-mappings
2025-12-30 11:40:12 +08:00
hkfires d443c86620 refactor(config): rename model mapping fields from from/to to name/alias 2025-12-30 11:07:59 +08:00
hkfires 7be3f1c36c refactor(config): rename model-name-mappings to oauth-model-mappings 2025-12-30 11:07:58 +08:00
Luis Pater f6ab6d97b9 fix(logging): add isDirWritable utility to enhance log dir validation in ConfigureLogOutput 2025-12-30 10:48:25 +08:00
Luis Pater bc866bac49 fix(logging): refactor ConfigureLogOutput to accept config object and adjust log directory handling 2025-12-30 10:28:25 +08:00
Luis Pater 50e6d845f4 feat(cliproxy): introduce global model name mappings for improved aliasing and routing 2025-12-30 08:13:06 +08:00
Luis Pater a8cb01819d Merge pull request #772 from soffchen/main
fix: Implement fallback log directory for file logging on read-only system
2025-12-30 02:24:49 +08:00
Luis Pater 530273906b Merge pull request #776 from router-for-me/fix-ag-claude
fix(antigravity): inject required placeholder when properties exist w…
2025-12-30 00:37:01 +08:00
Supra4E8C 06ddf575d9 fix(antigravity): inject required placeholder when properties exist without required 2025-12-29 23:55:59 +08:00
hkfires 3099114cbb refactor(api): simplify codex id token claims extraction 2025-12-29 19:48:02 +08:00
Soff 44b63f0767 fix: Return an error if the user home directory cannot be determined for the fallback log path. 2025-12-29 18:46:15 +08:00
Soff Chen 6705d20194 fix: Implement fallback log directory for file logging on read-only systems. 2025-12-29 18:35:48 +08:00
Chén Mù a38a9c0b0f Merge pull request #770 from router-for-me/api
feat(api): add id token claims extraction for codex auth entries
2025-12-29 00:44:41 -08:00
hkfires 8286caa366 feat(api): add id token claims extraction for codex auth entries 2025-12-29 16:34:16 +08:00
Chén Mù bd1ec8424d Merge pull request #767 from router-for-me/amp
feat(amp): add per-client upstream API key mapping support
2025-12-28 22:10:11 -08:00
hkfires 225e2c6797 feat(amp): add per-client upstream API key mapping support 2025-12-29 12:26:25 +08:00
Luis Pater d8fc485513 fix(translators): correct key path for system_instruction.parts in Claude request logic 2025-12-29 11:54:26 +08:00
hkfires f137eb0ac4 chore: add codex, agents, and opencode dirs to ignore files 2025-12-29 08:42:29 +08:00
Chén Mù f39a460487 Merge pull request #761 from router-for-me/log
fix(logging): improve request/response capture
2025-12-28 16:13:10 -08:00
Luis Pater ee171bc563 feat(api): add ManagementTokenRequester interface for management token request endpoints 2025-12-29 02:42:29 +08:00
hkfires a95428f204 fix(handlers): preserve upstream response logs before duplicate detection 2025-12-28 22:35:36 +08:00
Michael Velbaum cb3bdffb43 refactor(logging): streamline auth selection debug messages
Reduce duplicate Debugf calls by appending proxy info via an optional suffix and keep the debug-level guard inside the helper.
2025-12-28 16:10:11 +02:00
Michael Velbaum 48f19aab51 refactor(logging): pass request entry into auth selection log
Avoid re-creating the request-scoped log entry in the helper and use a switch for account type dispatch.
2025-12-28 15:51:11 +02:00
Michael Velbaum 48f6d7abdf refactor(logging): dedupe auth selection debug logs
Extract repeated debug logging for selected auth credentials into a helper so execute, count, and stream paths stay consistent.
2025-12-28 15:42:35 +02:00
Michael Velbaum 79fbcb3ec4 fix(logging): quote OAuth account field
Use strconv.Quote when embedding the OAuth account in debug logs so unexpected characters (e.g. quotes) can't break key=value parsing.
2025-12-28 15:32:54 +02:00
Michael Velbaum 0e4148b229 feat(logging): disambiguate OAuth credential selection in debug logs
When multiple OAuth providers share an account email, the existing "Use OAuth" debug lines are ambiguous and hard to correlate with management usage stats. Include provider, auth file, and auth index in the selection log, and only compute these fields when debug logging is enabled to avoid impacting normal request performance.

Before:
[debug] Use OAuth user@example.com for model gemini-3-flash-preview
[debug] Use OAuth user@example.com (project-1234) for model gemini-3-flash-preview

After:
[debug] Use OAuth provider=antigravity auth_file=antigravity-user_example_com.json auth_index=1a2b3c4d5e6f7788 account="user@example.com" for model gemini-3-flash-preview
[debug] Use OAuth provider=gemini-cli auth_file=gemini-user@example.com-project-1234.json auth_index=99aabbccddeeff00 account="user@example.com (project-1234)" for model gemini-3-flash-preview
2025-12-28 15:22:36 +02:00
hkfires 3ca5fb1046 fix(handlers): match raw error text before JSON body for duplicate detection 2025-12-28 19:35:36 +08:00
hkfires a091d12f4e fix(logging): improve request/response capture 2025-12-28 19:04:31 +08:00
Luis Pater 457924828a Merge pull request #757 from ben-vargas/fix-thinking-toolchoice-conflict
Fix: disable thinking when tool_choice forces tool use
2025-12-28 14:04:30 +08:00
Ben Vargas aca2ef6359 Fix: disable thinking when tool_choice forces tool use
Anthropic API does not allow extended thinking when tool_choice is set
to "any" or a specific tool. This was causing 400 errors when using
features like Amp's /handoff command which forces tool_choice.

Added disableThinkingIfToolChoiceForced() that removes thinking config
when incompatible tool_choice is detected, applied to both streaming
and non-streaming paths.

Fixes router-for-me/CLIProxyAPI#630
2025-12-27 16:31:37 -07:00
Luis Pater ade7194792 feat(management): add generic API call handler to management endpoints 2025-12-28 04:40:32 +08:00
Luis Pater 3a436e116a feat(cliproxy): implement model aliasing and hashing for Codex configurations, enhance request routing logic, and normalize Codex model entries 2025-12-28 03:06:51 +08:00
Luis Pater 336867853b Merge pull request #756 from leaph/check-ai-thinking-settings
feat(iflow): add model-specific thinking configs for GLM-4.7 and Mini…
2025-12-28 02:08:27 +08:00
leaph 6403ff4ec4 feat(iflow): add model-specific thinking configs for GLM-4.7 and MiniMax-M2.1
- GLM-4.7: Uses extra_body={"thinking": {"type": "enabled"}, "clear_thinking": false}
- MiniMax-M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
- Added preserveReasoningContentInMessages() to support re-injection of reasoning
  content in assistant message history for multi-turn conversations
- Added ThinkingSupport to MiniMax-M2.1 model definition
2025-12-27 18:39:15 +01:00
Luis Pater d222469b44 Update issue templates 2025-12-28 01:22:42 +08:00
Luis Pater 7646a2b877 Fixed: #749
fix(translators): ensure `gjson.String` content is non-empty before setting `parts` in OpenAI request logic
2025-12-28 00:54:26 +08:00
Luis Pater 62090f2568 Merge pull request #750 from router-for-me/config
fix(config): preserve original config structure and avoid default value pollution
2025-12-27 22:10:01 +08:00
Luis Pater c281f4cbaf Fixed: #747
fix(translators): rename and integrate `usageMetadata` as `cpaUsageMetadata` in Claude processing logic
2025-12-27 22:02:11 +08:00
hkfires 09455f9e85 fix(config): make streaming keepalive and retries ints 2025-12-27 20:56:47 +08:00
hkfires c8e72ba0dc fix(config): smart merge writes non-default new keys only 2025-12-27 20:28:54 +08:00
hkfires 375ef252ab docs(config): clarify merge mapping behavior 2025-12-27 19:30:21 +08:00
hkfires ee552f8720 chore(config): update ignore patterns 2025-12-27 19:13:14 +08:00
hkfires 2e88c4858e fix(config): avoid adding new keys when merging 2025-12-27 19:00:47 +08:00
Luis Pater 3f50da85c1 Merge pull request #745 from router-for-me/auth
fix(auth): make provider rotation atomic
2025-12-27 13:01:22 +08:00
hkfires 8be06255f7 fix(auth): make provider rotation atomic 2025-12-27 12:56:48 +08:00
Luis Pater 72274099aa Fixed: #738
fix(translators): refine prompt token calculation by incorporating cached tokens in Claude response handling
2025-12-27 03:56:11 +08:00
Luis Pater dcae098e23 Fixed: #736
fix(translators): handle gjson string types in Claude request processing to ensure consistent content parsing
2025-12-27 01:25:47 +08:00
Luis Pater 2eb05ec640 Merge pull request #727 from nguyenphutrong/main
docs: add Quotio to community projects
2025-12-26 11:53:09 +08:00
Luis Pater 3ce0d76aa4 feat(usage): add import/export functionality for usage statistics and enhance deduplication logic 2025-12-26 11:49:51 +08:00
Trong Nguyen a00b79d9be docs(readme): add Quotio to community projects section 2025-12-26 10:46:05 +07:00
Luis Pater 33e53a2a56 fix(translators): ensure correct handling and output of multimodal assistant content across request handlers 2025-12-26 05:08:04 +08:00
Luis Pater cd5b80785f Merge pull request #722 from hungthai1401/bugfix/remove-extra-args
Fixed incorrect function signature call to `NewBaseAPIHandlers`
2025-12-26 02:56:56 +08:00
Thai Nguyen Hung 54f71aa273 fix(test): remove extra argument from ExecuteStreamWithAuthManager call 2025-12-25 21:55:35 +07:00
Luis Pater 3f949b7f84 Merge pull request #704 from tinyc0der/add-index
fix(openai): add index field to image response for LiteLLM compatibility
2025-12-25 21:35:12 +08:00
TinyCoder a7fc2ee4cf refactor(image): avoid using json.Marshal 2025-12-25 14:21:01 +07:00
TinyCoder 671558a822 fix(openai): add index field to image response for LiteLLM compatibility
LiteLLM's Pydantic model requires an index field in each image object.
Without it, responses fail validation with "images.0.index Field required".
2025-12-24 17:43:31 +07:00
이대희 31bd90c748 feature: Improves Amp client compatibility
Ensures compatibility with the Amp client by suppressing
"thinking" blocks when "tool_use" blocks are also present in
the response.

The Amp client has issues rendering both types of blocks
simultaneously. This change filters out "thinking" blocks in
such cases, preventing rendering problems.
2025-12-19 08:18:27 +09:00
Muzhen Gaming 0b834fcb54 fix(translator): preserve built-in tools across openai<->responses
- Pass through non-function tool definitions like web_search

- Translate tool_choice for built-in tools and function tools

- Add regression tests for built-in tool passthrough
2025-12-15 21:18:54 +08:00
623 changed files with 82500 additions and 34655 deletions
+1
View File
@@ -31,6 +31,7 @@ bin/*
.agent/*
.agents/*
.opencode/*
.idea/*
.bmad/*
_bmad/*
_bmad-output/*
+4
View File
@@ -0,0 +1,4 @@
1071006060591-tmhssin2h21lcre235vtolojh4g403ep.apps.googleusercontent.com
681255809395-oo8ft2oprdrnp9e3aqf6av3hmdib135j.apps.googleusercontent.com
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
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
+22
View File
@@ -0,0 +1,22 @@
# Default owner for the entire repository
* @Finesssee
# Core proxy logic
/internal/runtime/executor/ @Finesssee
/internal/translator/ @Finesssee
/sdk/ @Finesssee
# Authentication providers
/internal/auth/ @Finesssee
# API and middleware
/internal/api/ @Finesssee
# WebUI dashboard
/webui/ @Finesssee
# CI/CD and infrastructure
/.github/ @Finesssee
/Dockerfile @Finesssee
/docker-compose.yml @Finesssee
/.goreleaser.yml @Finesssee
+21
View File
@@ -0,0 +1,21 @@
## Description
<!-- What does this PR do? Why is it needed? -->
## Changes
<!-- List the key changes made -->
-
## Testing
<!-- How was this tested? -->
- [ ] `go test ./...` passes
- [ ] `go vet ./...` passes
- [ ] Manually tested with relevant provider(s)
## Checklist
- [ ] Code follows existing patterns and conventions
- [ ] No secrets or credentials committed
- [ ] No changes under `internal/translator/` (restricted path)
+34 -18
View File
@@ -23,12 +23,15 @@ jobs:
with:
fetch-depth: 0
- name: Get current version
- name: Get tracked upstream version
id: current
run: |
# Extract current CLIProxyAPI version from go.mod or a version file
# For now, we'll check the latest commit from upstream
CURRENT_SHA=$(git ls-remote https://github.com/router-for-me/CLIProxyAPI.git HEAD | cut -f1)
CURRENT_TAG=$(tr -d '[:space:]' < UPSTREAM_VERSION 2>/dev/null || true)
CURRENT_SHA=""
if [ -n "$CURRENT_TAG" ]; then
CURRENT_SHA=$(git ls-remote https://github.com/router-for-me/CLIProxyAPI.git "refs/tags/$CURRENT_TAG" | cut -f1)
fi
echo "tag=$CURRENT_TAG" >> $GITHUB_OUTPUT
echo "sha=$CURRENT_SHA" >> $GITHUB_OUTPUT
- name: Get upstream release info
@@ -56,11 +59,17 @@ jobs:
- name: Check for updates
id: check
run: |
echo "Current tracked tag: ${{ steps.current.outputs.tag }}"
echo "Current SHA: ${{ steps.current.outputs.sha }}"
echo "Upstream SHA: ${{ steps.upstream.outputs.sha }}"
echo "Upstream Tag: ${{ steps.upstream.outputs.tag }}"
if [ "${{ steps.current.outputs.sha }}" != "${{ steps.upstream.outputs.sha }}" ]; then
if [ -z "${{ steps.upstream.outputs.tag }}" ]; then
echo "Unable to determine latest upstream release tag"
exit 1
fi
if [ "${{ steps.current.outputs.tag }}" != "${{ steps.upstream.outputs.tag }}" ]; then
echo "Update available!"
echo "has_update=true" >> $GITHUB_OUTPUT
else
@@ -73,42 +82,49 @@ jobs:
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
CURRENT_TAG="${{ steps.current.outputs.tag }}"
TAG="${{ steps.upstream.outputs.tag }}"
SHA="${{ steps.upstream.outputs.sha }}"
SHORT_SHA="${SHA:0:7}"
if [ -n "$TAG" ]; then
BRANCH_NAME="sync-upstream-$TAG"
PR_TITLE="feat: sync with CLIProxyAPI $TAG"
if [ -n "$CURRENT_TAG" ]; then
BRANCH_NAME="sync-upstream-$CURRENT_TAG-to-$TAG"
PR_TITLE="chore: sync CLIProxyAPI $CURRENT_TAG-$TAG"
PR_BODY="## Summary
This PR syncs ProxyPilot with upstream CLIProxyAPI release \`$TAG\`.
ProxyPilot is currently tracking upstream CLIProxyAPI release \`$CURRENT_TAG\` and a newer release \`$TAG\` is available.
**Upstream release:** https://github.com/router-for-me/CLIProxyAPI/releases/tag/$TAG
## Changes
## Tracking
- Updated to CLIProxyAPI $TAG ($SHORT_SHA)
- Current tracked upstream version: \`$CURRENT_TAG\`
- Latest upstream version: \`$TAG\`
- Latest upstream commit: \`$SHORT_SHA\`
## Checklist
- [ ] Merge upstream changes into ProxyPilot
- [ ] Review upstream changes
- [ ] Test locally before merging
- [ ] Update changelog if needed
- [ ] Update \`UPSTREAM_VERSION\`, docs, and release notes
- [ ] Cut a new ProxyPilot release tag
---
🤖 Generated by [check-upstream workflow](https://github.com/${{ github.repository }}/actions/workflows/check-upstream.yml)"
else
BRANCH_NAME="sync-upstream-$SHORT_SHA"
PR_TITLE="feat: sync with CLIProxyAPI ($SHORT_SHA)"
PR_TITLE="chore: sync CLIProxyAPI $TAG"
PR_BODY="## Summary
This PR syncs ProxyPilot with latest upstream CLIProxyAPI commit.
ProxyPilot does not have a tracked upstream version in \`UPSTREAM_VERSION\`, and upstream CLIProxyAPI release \`$TAG\` is available.
**Upstream commit:** https://github.com/router-for-me/CLIProxyAPI/commit/$SHA
**Upstream release:** https://github.com/router-for-me/CLIProxyAPI/releases/tag/$TAG
## Checklist
- [ ] Set the correct tracked upstream version
- [ ] Merge upstream changes into ProxyPilot
- [ ] Review upstream changes
- [ ] Test locally before merging
@@ -136,12 +152,12 @@ jobs:
# Create branch
git checkout -b "$BRANCH_NAME"
# Add a marker file to track the sync (optional, can be removed)
# Add marker files so the PR records which upstream release triggered it.
echo "$SHA" > .upstream-sync-sha
echo "$TAG" > .upstream-sync-tag 2>/dev/null || true
echo "$TAG" > .upstream-sync-tag
# Commit
git add -A
git add .upstream-sync-sha .upstream-sync-tag
git commit -m "$PR_TITLE" --allow-empty
# Push
+4 -3
View File
@@ -1,9 +1,7 @@
name: docker-image
on:
push:
tags:
- v*
workflow_dispatch:
env:
APP_NAME: ProxyPilot
@@ -28,6 +26,9 @@ jobs:
- name: Checkout
if: steps.check-secrets.outputs.skip != 'true'
uses: actions/checkout@v4
- name: Refresh models catalog
if: steps.check-secrets.outputs.skip != 'true'
run: curl -fsSL https://raw.githubusercontent.com/router-for-me/models/refs/heads/main/models.json -o internal/registry/models/models.json
- name: Set up QEMU
if: steps.check-secrets.outputs.skip != 'true'
uses: docker/setup-qemu-action@v3
+16
View File
@@ -12,6 +12,8 @@ jobs:
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Refresh models catalog
run: curl -fsSL https://raw.githubusercontent.com/router-for-me/models/refs/heads/main/models.json -o internal/registry/models/models.json
- name: Set up Go
uses: actions/setup-go@v5
with:
@@ -21,3 +23,17 @@ jobs:
run: |
go build -o test-output ./cmd/server
rm -f test-output
- name: Vet
run: go vet ./...
- name: Test with coverage
run: |
go test -coverprofile=coverage.out -covermode=atomic ./... 2>&1 | tee test-output.txt
# Extract total coverage percentage
COVERAGE=$(go tool cover -func=coverage.out | grep total | awk '{print $3}' | tr -d '%')
echo "Total coverage: ${COVERAGE}%"
# Fail if coverage drops below 30%
THRESHOLD=30
if [ "$(echo "$COVERAGE < $THRESHOLD" | bc -l)" -eq 1 ]; then
echo "ERROR: Coverage ${COVERAGE}% is below threshold ${THRESHOLD}%"
exit 1
fi
+1 -3
View File
@@ -1,9 +1,7 @@
name: ProxyPilot Release
on:
push:
tags:
- 'v*'
workflow_dispatch:
permissions:
contents: write
+3 -1
View File
@@ -16,10 +16,12 @@ jobs:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Refresh models catalog
run: curl -fsSL https://raw.githubusercontent.com/router-for-me/models/refs/heads/main/models.json -o internal/registry/models/models.json
- run: git fetch --force --tags
- uses: actions/setup-go@v4
with:
go-version: '>=1.24.0'
go-version: '>=1.26.0'
cache: true
- name: Generate Build Metadata
run: |
+6 -3
View File
@@ -27,7 +27,6 @@ static/*
!static/icon.png
!static/icon.ico
test/
refs/*
dist/*
.proxypilot/*
memory/*
@@ -56,13 +55,14 @@ GEMINI.md
# Tooling metadata
.vscode/*
.claude/*
.codex/*
.claude/*
.gemini/*
.serena/*
.agent/*
.agents/*
.opencode/*
.idea/*
.bmad/*
_bmad/*
_bmad-output/*
@@ -109,9 +109,12 @@ tray_click_log.txt
node_modules/
dist/
.turbo/
.env
build/
# Local files
PLAN-*.md
config-debug.yaml
.wix/
test_results.txt
test_results_full.txt
tmpclaude-*
+1
View File
@@ -0,0 +1 @@
76c064c7295f26b48cd5855b752a04a9ad4156e9
+1
View File
@@ -0,0 +1 @@
v6.9.2
+1 -1
View File
@@ -1,4 +1,4 @@
FROM golang:1.24-alpine AS builder
FROM golang:1.26-alpine AS builder
WORKDIR /app
+57 -2
View File
@@ -45,6 +45,8 @@
- 🤖 **Agentic Harness** - Guided workflow for coding agents (Anthropic research)
- 💾 **Session Memory** - Persistent storage across conversation turns
- 🎨 **System Tray** - Native Windows tray app for quick access
- 🔄 **Auto-Updates** - Background update checking with one-click install
- ⏪ **Rollback Support** - Automatic crash detection with version recovery
- 📡 **60+ Management APIs** - Full control via REST endpoints
---
@@ -93,7 +95,7 @@ go build -o proxypilot ./cmd/server
1. Copy config: `cp config.example.yaml config.yaml`
2. Run: `./proxypilot`
3. Server starts on `http://localhost:8317`
4. Open dashboard: `http://localhost:8317/proxypilot.html`
4. Open dashboard: `http://localhost:8317/management.html`
### Authentication
@@ -110,7 +112,6 @@ Run OAuth login for your provider:
./proxypilot --antigravity-login # Antigravity
# Import providers (from existing CLI tools)
./proxypilot --amazonq-import # Amazon Q CLI (run 'q login' first)
./proxypilot --kiro-import # Kiro IDE token
# API key providers (prompts for key)
@@ -249,6 +250,60 @@ prompt-cache:
---
## Auto-Updates
ProxyPilot includes a built-in auto-update system that checks for new releases and allows one-click installation.
### Configuration
**Config** (`config.yaml`):
```yaml
updates:
auto-check: true # Enable background update checking (default: true)
check-interval-hours: 24 # How often to check (default: 24)
notify-on-update: true # Show toast notification when update available (default: true)
channel: stable # Update channel: "stable" or "prerelease" (default: stable)
```
### Features
- **Background Polling** - Checks for updates at configurable intervals
- **Dashboard Banner** - Proactive notification when update is available
- **One-Click Install** - Download, verify, and install from the tray menu
- **Session Dismissal** - Dismissed banners won't reappear until next session
### Tray Menu
When an update is available:
- **Settings → Download & Install vX.X.X** - One-click update flow
- **Settings → Check for Updates** - Manual check
---
## Rollback Support
ProxyPilot automatically backs up the previous version during updates and can restore it if something goes wrong.
### Automatic Recovery
- **Crash Detection** - Tracks rapid restarts within a 30-second window
- **Auto-Rollback** - After 3 rapid failures, automatically restores previous version
- **Health Marking** - After 30 seconds of stable operation, clears the failure counter
### Manual Rollback
From the tray menu:
- **Settings → Rollback to Previous Version** - Restore the previous version
### How It Works
1. During update, current binary is saved as `.old` backup
2. Rollback metadata stored in `%APPDATA%/ProxyPilot/updates/`
3. On crash loop detection, previous version is automatically restored
4. After successful startup (30s), backup can be cleaned up
---
## CLI Tools
| Binary | Description |
+1
View File
@@ -0,0 +1 @@
v6.9.1
Binary file not shown.

After

Width:  |  Height:  |  Size: 45 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 51 KiB

+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "proxypilot",
"version": "0.2.8",
"version": "0.2.9",
"description": "ProxyPilot - Local API proxy for AI coding tools with CLI control",
"bin": {
"proxypilot": "bin/proxypilot"
+275
View File
@@ -0,0 +1,275 @@
// Command fetch_antigravity_models connects to the Antigravity API using the
// stored auth credentials and saves the dynamically fetched model list to a
// JSON file for inspection or offline use.
//
// Usage:
//
// go run ./cmd/fetch_antigravity_models [flags]
//
// Flags:
//
// --auths-dir <path> Directory containing auth JSON files (default: "auths")
// --output <path> Output JSON file path (default: "antigravity_models.json")
// --pretty Pretty-print the output JSON (default: true)
package main
import (
"context"
"encoding/json"
"flag"
"fmt"
"io"
"net/http"
"os"
"path/filepath"
"strings"
"time"
"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
sdkauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
"github.com/router-for-me/CLIProxyAPI/v6/sdk/proxyutil"
log "github.com/sirupsen/logrus"
"github.com/tidwall/gjson"
)
const (
antigravityBaseURLDaily = "https://daily-cloudcode-pa.googleapis.com"
antigravitySandboxBaseURLDaily = "https://daily-cloudcode-pa.sandbox.googleapis.com"
antigravityBaseURLProd = "https://cloudcode-pa.googleapis.com"
antigravityModelsPath = "/v1internal:fetchAvailableModels"
)
func init() {
logging.SetupBaseLogger()
log.SetLevel(log.InfoLevel)
}
// modelOutput wraps the fetched model list with fetch metadata.
type modelOutput struct {
Models []modelEntry `json:"models"`
}
// modelEntry contains only the fields we want to keep for static model definitions.
type modelEntry struct {
ID string `json:"id"`
Object string `json:"object"`
OwnedBy string `json:"owned_by"`
Type string `json:"type"`
DisplayName string `json:"display_name"`
Name string `json:"name"`
Description string `json:"description"`
ContextLength int `json:"context_length,omitempty"`
MaxCompletionTokens int `json:"max_completion_tokens,omitempty"`
}
func main() {
var authsDir string
var outputPath string
var pretty bool
flag.StringVar(&authsDir, "auths-dir", "auths", "Directory containing auth JSON files")
flag.StringVar(&outputPath, "output", "antigravity_models.json", "Output JSON file path")
flag.BoolVar(&pretty, "pretty", true, "Pretty-print the output JSON")
flag.Parse()
// Resolve relative paths against the working directory.
wd, err := os.Getwd()
if err != nil {
fmt.Fprintf(os.Stderr, "error: cannot get working directory: %v\n", err)
os.Exit(1)
}
if !filepath.IsAbs(authsDir) {
authsDir = filepath.Join(wd, authsDir)
}
if !filepath.IsAbs(outputPath) {
outputPath = filepath.Join(wd, outputPath)
}
fmt.Printf("Scanning auth files in: %s\n", authsDir)
// Load all auth records from the directory.
fileStore := sdkauth.NewFileTokenStore()
fileStore.SetBaseDir(authsDir)
ctx := context.Background()
auths, err := fileStore.List(ctx)
if err != nil {
fmt.Fprintf(os.Stderr, "error: failed to list auth files: %v\n", err)
os.Exit(1)
}
if len(auths) == 0 {
fmt.Fprintf(os.Stderr, "error: no auth files found in %s\n", authsDir)
os.Exit(1)
}
// Find the first enabled antigravity auth.
var chosen *coreauth.Auth
for _, a := range auths {
if a == nil || a.Disabled {
continue
}
if strings.EqualFold(strings.TrimSpace(a.Provider), "antigravity") {
chosen = a
break
}
}
if chosen == nil {
fmt.Fprintf(os.Stderr, "error: no enabled antigravity auth found in %s\n", authsDir)
os.Exit(1)
}
fmt.Printf("Using auth: id=%s label=%s\n", chosen.ID, chosen.Label)
// Fetch models from the upstream Antigravity API.
fmt.Println("Fetching Antigravity model list from upstream...")
fetchCtx, cancel := context.WithTimeout(ctx, 30*time.Second)
defer cancel()
models := fetchModels(fetchCtx, chosen)
if len(models) == 0 {
fmt.Fprintln(os.Stderr, "warning: no models returned (API may be unavailable or token expired)")
} else {
fmt.Printf("Fetched %d models.\n", len(models))
}
// Build the output payload.
out := modelOutput{
Models: models,
}
// Marshal to JSON.
var raw []byte
if pretty {
raw, err = json.MarshalIndent(out, "", " ")
} else {
raw, err = json.Marshal(out)
}
if err != nil {
fmt.Fprintf(os.Stderr, "error: failed to marshal JSON: %v\n", err)
os.Exit(1)
}
if err = os.WriteFile(outputPath, raw, 0o644); err != nil {
fmt.Fprintf(os.Stderr, "error: failed to write output file %s: %v\n", outputPath, err)
os.Exit(1)
}
fmt.Printf("Model list saved to: %s\n", outputPath)
}
func fetchModels(ctx context.Context, auth *coreauth.Auth) []modelEntry {
accessToken := metaStringValue(auth.Metadata, "access_token")
if accessToken == "" {
fmt.Fprintln(os.Stderr, "error: no access token found in auth")
return nil
}
baseURLs := []string{antigravityBaseURLProd, antigravityBaseURLDaily, antigravitySandboxBaseURLDaily}
for _, baseURL := range baseURLs {
modelsURL := baseURL + antigravityModelsPath
var payload []byte
if auth != nil && auth.Metadata != nil {
if pid, ok := auth.Metadata["project_id"].(string); ok && strings.TrimSpace(pid) != "" {
payload = []byte(fmt.Sprintf(`{"project": "%s"}`, strings.TrimSpace(pid)))
}
}
if len(payload) == 0 {
payload = []byte(`{}`)
}
httpReq, errReq := http.NewRequestWithContext(ctx, http.MethodPost, modelsURL, strings.NewReader(string(payload)))
if errReq != nil {
continue
}
httpReq.Close = true
httpReq.Header.Set("Content-Type", "application/json")
httpReq.Header.Set("Authorization", "Bearer "+accessToken)
httpReq.Header.Set("User-Agent", "antigravity/1.19.6 darwin/arm64")
httpClient := &http.Client{Timeout: 30 * time.Second}
if transport, _, errProxy := proxyutil.BuildHTTPTransport(auth.ProxyURL); errProxy == nil && transport != nil {
httpClient.Transport = transport
}
httpResp, errDo := httpClient.Do(httpReq)
if errDo != nil {
continue
}
bodyBytes, errRead := io.ReadAll(httpResp.Body)
httpResp.Body.Close()
if errRead != nil {
continue
}
if httpResp.StatusCode < http.StatusOK || httpResp.StatusCode >= http.StatusMultipleChoices {
continue
}
result := gjson.GetBytes(bodyBytes, "models")
if !result.Exists() {
continue
}
var models []modelEntry
for originalName, modelData := range result.Map() {
modelID := strings.TrimSpace(originalName)
if modelID == "" {
continue
}
// Skip internal/experimental models
switch modelID {
case "chat_20706", "chat_23310", "tab_flash_lite_preview", "tab_jump_flash_lite_preview", "gemini-2.5-flash-thinking", "gemini-2.5-pro":
continue
}
displayName := modelData.Get("displayName").String()
if displayName == "" {
displayName = modelID
}
entry := modelEntry{
ID: modelID,
Object: "model",
OwnedBy: "antigravity",
Type: "antigravity",
DisplayName: displayName,
Name: modelID,
Description: displayName,
}
if maxTok := modelData.Get("maxTokens").Int(); maxTok > 0 {
entry.ContextLength = int(maxTok)
}
if maxOut := modelData.Get("maxOutputTokens").Int(); maxOut > 0 {
entry.MaxCompletionTokens = int(maxOut)
}
models = append(models, entry)
}
return models
}
return nil
}
func metaStringValue(m map[string]interface{}, key string) string {
if m == nil {
return ""
}
v, ok := m[key]
if !ok {
return ""
}
switch val := v.(type) {
case string:
return val
default:
return ""
}
}
+9 -9
View File
@@ -11,9 +11,9 @@ import (
const (
// Registry key paths.
autostartKeyPath = `Software\Microsoft\Windows\CurrentVersion\Run`
uninstallKeyPath = `Software\Microsoft\Windows\CurrentVersion\Uninstall\` + appName
uninstallKeyBase = `Software\Microsoft\Windows\CurrentVersion\Uninstall`
autostartKeyPath = `Software\Microsoft\Windows\CurrentVersion\Run`
uninstallKeyPath = `Software\Microsoft\Windows\CurrentVersion\Uninstall\` + appName
uninstallKeyBase = `Software\Microsoft\Windows\CurrentVersion\Uninstall`
// Application metadata.
appPublisher = "ProxyPilot"
@@ -92,12 +92,12 @@ func RegisterUninstall(config *InstallConfig) error {
// Set the required values.
values := map[string]string{
"DisplayName": appName,
"DisplayVersion": appVersion,
"Publisher": appPublisher,
"InstallLocation": config.InstallDir,
"DisplayIcon": iconPath,
"UninstallString": `"` + exePath + `" --uninstall`,
"DisplayName": appName,
"DisplayVersion": appVersion,
"Publisher": appPublisher,
"InstallLocation": config.InstallDir,
"DisplayIcon": iconPath,
"UninstallString": `"` + exePath + `" --uninstall`,
"QuietUninstallString": `"` + exePath + `" --uninstall --quiet`,
}
+22 -22
View File
@@ -36,27 +36,27 @@ var (
// IShellLinkW virtual table.
type IShellLinkWVtbl struct {
QueryInterface uintptr
AddRef uintptr
Release uintptr
GetPath uintptr
GetIDList uintptr
SetIDList uintptr
GetDescription uintptr
SetDescription uintptr
QueryInterface uintptr
AddRef uintptr
Release uintptr
GetPath uintptr
GetIDList uintptr
SetIDList uintptr
GetDescription uintptr
SetDescription uintptr
GetWorkingDirectory uintptr
SetWorkingDirectory uintptr
GetArguments uintptr
SetArguments uintptr
GetHotkey uintptr
SetHotkey uintptr
GetShowCmd uintptr
SetShowCmd uintptr
GetIconLocation uintptr
SetIconLocation uintptr
SetRelativePath uintptr
Resolve uintptr
SetPath uintptr
GetArguments uintptr
SetArguments uintptr
GetHotkey uintptr
SetHotkey uintptr
GetShowCmd uintptr
SetShowCmd uintptr
GetIconLocation uintptr
SetIconLocation uintptr
SetRelativePath uintptr
Resolve uintptr
SetPath uintptr
}
type IShellLinkW struct {
@@ -81,10 +81,10 @@ type IPersistFile struct {
}
var (
ole32 = syscall.NewLazyDLL("ole32.dll")
coInitializeEx = ole32.NewProc("CoInitializeEx")
ole32 = syscall.NewLazyDLL("ole32.dll")
coInitializeEx = ole32.NewProc("CoInitializeEx")
coCreateInstance = ole32.NewProc("CoCreateInstance")
coUninitialize = ole32.NewProc("CoUninitialize")
coUninitialize = ole32.NewProc("CoUninitialize")
)
const (
+70 -6
View File
@@ -40,6 +40,12 @@ type EmbeddedEngine struct {
// wg waits for the service goroutine to complete.
wg sync.WaitGroup
// panicCount tracks the number of panics for monitoring.
panicCount int
// restartCount tracks the number of automatic restarts.
restartCount int
}
// NewEmbeddedEngine creates a new EmbeddedEngine instance.
@@ -90,10 +96,22 @@ func (e *EmbeddedEngine) Start(cfg *config.Config, configPath, password string)
log.Infof("starting embedded proxy engine on port %d", e.port)
// Run the service in a goroutine
// Run the service in a goroutine with panic recovery
e.wg.Add(1)
go func() {
defer e.wg.Done()
defer func() {
// Recover from panics to prevent crashing the tray app
if r := recover(); r != nil {
e.mu.Lock()
e.panicCount++
e.running = false
e.cancel = nil
e.lastError = fmt.Errorf("proxy service panicked: %v", r)
e.mu.Unlock()
log.Errorf("embedded proxy engine panic recovered: %v", r)
}
}()
defer func() {
e.mu.Lock()
e.running = false
@@ -114,8 +132,8 @@ func (e *EmbeddedEngine) Start(cfg *config.Config, configPath, password string)
return nil
}
// Stop cancels the running service and waits for it to shut down.
// It returns an error if the service is not running.
// Stop cancels the running service and waits for it to shut down gracefully.
// It returns an error if the service is not running or if shutdown times out.
func (e *EmbeddedEngine) Stop() error {
e.mu.Lock()
@@ -131,10 +149,27 @@ func (e *EmbeddedEngine) Stop() error {
e.mu.Unlock()
// Wait for the goroutine to complete
e.wg.Wait()
// Wait for the goroutine to complete with a timeout
done := make(chan struct{})
go func() {
e.wg.Wait()
close(done)
}()
return nil
select {
case <-done:
log.Info("embedded proxy engine stopped gracefully")
return nil
case <-time.After(10 * time.Second):
// Force mark as stopped to prevent deadlock
e.mu.Lock()
e.running = false
e.cancel = nil
e.lastError = errors.New("shutdown timed out after 10 seconds")
e.mu.Unlock()
log.Warn("embedded proxy engine shutdown timed out, forcing stop")
return errors.New("shutdown timed out")
}
}
// Restart stops the running service (if any) and starts it again with the new configuration.
@@ -146,6 +181,11 @@ func (e *EmbeddedEngine) Restart(cfg *config.Config, configPath, password string
}
}
// Increment restart counter
e.mu.Lock()
e.restartCount++
e.mu.Unlock()
// Start with new configuration
return e.Start(cfg, configPath, password)
}
@@ -195,3 +235,27 @@ func (e *EmbeddedEngine) Port() int {
defer e.mu.Unlock()
return e.port
}
// PanicCount returns the number of panics that have been recovered.
func (e *EmbeddedEngine) PanicCount() int {
e.mu.Lock()
defer e.mu.Unlock()
return e.panicCount
}
// RestartCount returns the number of times the engine has been restarted.
func (e *EmbeddedEngine) RestartCount() int {
e.mu.Lock()
defer e.mu.Unlock()
return e.restartCount
}
// Uptime returns the duration the engine has been running, or 0 if not running.
func (e *EmbeddedEngine) Uptime() time.Duration {
e.mu.Lock()
defer e.mu.Unlock()
if !e.running || e.startedAt.IsZero() {
return 0
}
return time.Since(e.startedAt)
}
+335 -11
View File
@@ -22,6 +22,7 @@ import (
"github.com/getlantern/systray"
"github.com/jchv/go-webview2"
configaccess "github.com/router-for-me/CLIProxyAPI/v6/internal/access/config_access"
"github.com/router-for-me/CLIProxyAPI/v6/internal/api/middleware"
"github.com/router-for-me/CLIProxyAPI/v6/internal/cmd"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
@@ -33,8 +34,9 @@ import (
"github.com/router-for-me/CLIProxyAPI/v6/internal/updates"
"github.com/router-for-me/CLIProxyAPI/v6/internal/usage"
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
configaccess "github.com/router-for-me/CLIProxyAPI/v6/sdk/access/config"
"github.com/router-for-me/CLIProxyAPI/v6/internal/winutil"
sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
log "github.com/sirupsen/logrus"
)
const autostartAppName = "ProxyPilot"
@@ -45,6 +47,19 @@ var dashboardMu sync.Mutex
var dashboardOpen bool
func main() {
// Single-instance check - prevent multiple tray apps
instance, err := winutil.AcquireSingleInstance("ProxyPilotTray")
if err != nil {
fmt.Fprintf(os.Stderr, "Failed to check for existing instance: %v\n", err)
os.Exit(1)
}
if instance == nil {
// Another instance is already running
_ = winutil.ShowToast("ProxyPilot", "Another instance is already running")
os.Exit(0)
}
defer instance.Release()
var repoRoot string
var configPath string
flag.StringVar(&repoRoot, "repo", "", "Repo root (used to locate logs/)")
@@ -59,10 +74,24 @@ func run(repoRoot, configPath string) {
// Initialize logging
logging.SetupBaseLogger()
// Check startup health - auto-rollback on crash loops
if health, err := updates.RecordStartup(); err == nil {
if health.ShouldRollback {
fmt.Fprintf(os.Stderr, "Detected crash loop (%d rapid restarts), triggering auto-rollback\n", health.StartupCount)
if result, err := updates.Rollback(); err == nil && result.Success {
_ = winutil.ShowToast("ProxyPilot", "Auto-rollback triggered due to startup failures. Restarting with previous version...")
// On Windows, execute the rollback script and exit
if result.NeedsRestart {
os.Exit(0) // Let the rollback script restart us
}
}
}
}
// Load config
cfg, err := config.LoadConfigOptional(configPath, false)
if err == nil && cfg != nil {
logging.ConfigureLogOutput(cfg.LoggingToFile, cfg.LogsMaxTotalSizeMB)
logging.ConfigureLogOutput(cfg)
util.SetLogLevel(cfg)
}
if cfg == nil {
@@ -73,7 +102,7 @@ func run(repoRoot, configPath string) {
sdkAuth.RegisterTokenStore(sdkAuth.NewFileTokenStore())
// Register access providers
configaccess.Register()
configaccess.Register(&cfg.SDKConfig)
// Create embedded engine (will be used instead of desktopctl)
engine := NewEmbeddedEngine()
@@ -129,12 +158,34 @@ func run(repoRoot, configPath string) {
diagMenu := systray.AddMenuItem("Diagnostics", "Diagnostic tools")
copyDiagItem := diagMenu.AddSubMenuItem("Copy Diagnostics", "Copy diagnostics to clipboard")
copyStatusItem := diagMenu.AddSubMenuItem("Copy Account Status", "Copy account health summary to clipboard")
copyRateLimitsItem := diagMenu.AddSubMenuItem("Copy Rate Limits", "Copy rate limit status to clipboard")
copyUsageItem := diagMenu.AddSubMenuItem("Copy Usage Stats", "Copy usage statistics to clipboard")
copyModelsItem := diagMenu.AddSubMenuItem("Copy Model List", "Copy available models to clipboard")
copyLogsItem := diagMenu.AddSubMenuItem("Copy Recent Logs", "Copy recent log entries to clipboard")
openLogsItem := diagMenu.AddSubMenuItem("Open Logs Folder", "Open logs folder in explorer")
openAuthItem := diagMenu.AddSubMenuItem("Open Auth Folder", "Open auth folder in explorer")
// Settings submenu
settingsMenu := systray.AddMenuItem("Settings", "Application settings")
startupItem := settingsMenu.AddSubMenuItem("Start with Windows", "Launch ProxyPilot on Windows startup")
autoProxyItem := settingsMenu.AddSubMenuItem("Auto-start Proxy", "Automatically start proxy when tray launches")
checkUpdateItem := settingsMenu.AddSubMenuItem("Check for Updates", "Check for new versions")
installUpdateItem := settingsMenu.AddSubMenuItem("Download & Install Update", "Download and install the latest version")
installUpdateItem.Hide() // Hidden until an update is available
rollbackItem := settingsMenu.AddSubMenuItem("Rollback to Previous Version", "Restore the previous version")
if !updates.CanRollback() {
rollbackItem.Disable()
}
defenderExclusionItem := settingsMenu.AddSubMenuItem("Add to Windows Defender Exclusions", "Prevent Defender from scanning ProxyPilot (requires admin)")
// Set initial checkbox states
if enabled, _, _ := desktopctl.IsWindowsRunAutostartEnabled(autostartAppName); enabled {
startupItem.Check()
}
if autoProxy, _ := desktopctl.GetAutoStartProxy(); autoProxy {
autoProxyItem.Check()
}
systray.AddSeparator()
quitItem := systray.AddMenuItem("Quit", "Quit ProxyPilot")
@@ -148,10 +199,39 @@ func run(repoRoot, configPath string) {
}()
}
// Check for updates on startup (silently, in background) with configurable polling
var latestUpdateInfo *updates.UpdateInfo
var updateMu sync.Mutex
if cfg.Updates.IsAutoCheckEnabled() {
updates.StartGlobalPoller(
cfg.Updates.GetCheckInterval(),
cfg.Updates.GetChannel(),
func(info *updates.UpdateInfo) {
if info != nil && info.Available {
updateMu.Lock()
latestUpdateInfo = info
updateMu.Unlock()
installUpdateItem.SetTitle(fmt.Sprintf("Download & Install v%s", info.Version))
installUpdateItem.Show()
if cfg.Updates.IsNotifyOnUpdateEnabled() {
_ = winutil.ShowToast("ProxyPilot Update", fmt.Sprintf("v%s is available! Click 'Check for Updates' to download.", info.Version))
}
}
},
)
}
// Mark as healthy after 30 seconds of successful operation
// This clears the startup failure counter
go func() {
time.Sleep(30 * time.Second)
_ = updates.MarkHealthy()
}()
// Update UI based on status
refresh := func() {
st := engine.Status()
// Get account count
accountCount := 0
if store := sdkAuth.GetTokenStore(); store != nil {
@@ -159,7 +239,7 @@ func run(repoRoot, configPath string) {
accountCount = len(auths)
}
}
if st.Running {
port := st.Port
if port <= 0 {
@@ -234,6 +314,12 @@ func run(repoRoot, configPath string) {
copyDiagnosticsToClipboard(engine)
case <-copyStatusItem.ClickedCh:
copyAccountStatusToClipboard(engine)
case <-copyRateLimitsItem.ClickedCh:
go func() {
if text := captureRateLimits(engine); text != "" {
copyToClipboard(text)
}
}()
case <-copyUsageItem.ClickedCh:
go func() {
if text := captureUsageStats(); text != "" {
@@ -272,13 +358,94 @@ func run(repoRoot, configPath string) {
if dir, err := desktopctl.AuthDirFor(configPath); err == nil {
desktopctl.OpenFolder(dir)
}
case <-startupItem.ClickedCh:
go func() {
if startupItem.Checked() {
// Disable startup
if err := desktopctl.DisableWindowsRunAutostart(autostartAppName); err == nil {
startupItem.Uncheck()
_ = winutil.ShowToast("ProxyPilot", "Removed from Windows startup")
}
} else {
// Enable startup
cmd, err := autostartCommand(repoRoot, configPath)
if err == nil {
if err := desktopctl.EnableWindowsRunAutostart(autostartAppName, cmd); err == nil {
startupItem.Check()
_ = winutil.ShowToast("ProxyPilot", "Added to Windows startup")
}
}
}
}()
case <-autoProxyItem.ClickedCh:
go func() {
if autoProxyItem.Checked() {
_ = desktopctl.SetAutoStartProxy(false)
autoProxyItem.Uncheck()
} else {
_ = desktopctl.SetAutoStartProxy(true)
autoProxyItem.Check()
}
}()
case <-checkUpdateItem.ClickedCh:
go checkForUpdatesWithToast()
case <-installUpdateItem.ClickedCh:
go func() {
updateMu.Lock()
info := latestUpdateInfo
updateMu.Unlock()
if info == nil || !info.Available {
_ = winutil.ShowToast("ProxyPilot", "No update available")
return
}
performOneClickUpdate(info)
}()
case <-rollbackItem.ClickedCh:
go func() {
if !updates.CanRollback() {
_ = winutil.ShowToast("ProxyPilot", "No previous version available for rollback")
return
}
result, err := updates.Rollback()
if err != nil {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Rollback failed: %v", err))
return
}
if result.Success {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Rolling back to v%s...", result.RestoredVersion))
if result.NeedsRestart {
// Execute the rollback script
systray.Quit()
}
}
}()
case <-defenderExclusionItem.ClickedCh:
go func() {
authDir, _ := desktopctl.AuthDirFor(configPath)
if err := winutil.PromptDefenderExclusion(authDir); err != nil {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Failed: %v", err))
} else {
_ = winutil.ShowToast("ProxyPilot", "Defender exclusion prompt shown (requires admin approval)")
}
}()
case <-quitItem.ClickedCh:
systray.Quit()
return
}
}
}()
}, func() {})
}, func() {
// onExit: Graceful cleanup when systray exits
log.Info("systray exiting, cleaning up...")
if engine.IsRunning() {
if err := engine.Stop(); err != nil {
log.Warnf("error stopping engine on exit: %v", err)
}
}
// Stop the update poller
updates.StopGlobalPoller()
log.Info("cleanup complete")
})
}
type closeFn func() error
@@ -811,6 +978,80 @@ func captureAccountList() string {
return runCLI("-list-accounts")
}
// captureRateLimits fetches rate limit status from the API
func captureRateLimits(engine *EmbeddedEngine) string {
st := engine.Status()
if !st.Running {
return "Rate Limits: Proxy not running"
}
port := st.Port
if port <= 0 {
port = 8318
}
url := fmt.Sprintf("http://127.0.0.1:%d/v0/management/rate-limits/summary", port)
resp, err := http.Get(url)
if err != nil {
return fmt.Sprintf("Failed to fetch rate limits: %v", err)
}
defer resp.Body.Close()
var summary struct {
Total int `json:"total"`
Available int `json:"available"`
CoolingDown int `json:"cooling_down"`
Disabled int `json:"disabled"`
NextRecoveryIn string `json:"next_recovery_in,omitempty"`
}
if err := json.NewDecoder(resp.Body).Decode(&summary); err != nil {
return fmt.Sprintf("Failed to parse rate limits: %v", err)
}
var sb strings.Builder
sb.WriteString("=== Rate Limit Status ===\n\n")
sb.WriteString(fmt.Sprintf("Total Credentials: %d\n", summary.Total))
sb.WriteString(fmt.Sprintf("Available: %d\n", summary.Available))
sb.WriteString(fmt.Sprintf("Cooling Down: %d\n", summary.CoolingDown))
sb.WriteString(fmt.Sprintf("Disabled: %d\n", summary.Disabled))
if summary.NextRecoveryIn != "" {
sb.WriteString(fmt.Sprintf("\nNext Recovery In: %s\n", summary.NextRecoveryIn))
}
// Also get detailed info
detailURL := fmt.Sprintf("http://127.0.0.1:%d/v0/management/rate-limits", port)
detailResp, err := http.Get(detailURL)
if err == nil {
defer detailResp.Body.Close()
var detail struct {
Credentials []struct {
AuthID string `json:"auth_id"`
Provider string `json:"provider"`
Email string `json:"email,omitempty"`
QuotaExceeded bool `json:"quota_exceeded"`
RecoverIn string `json:"recover_in,omitempty"`
} `json:"credentials"`
}
if err := json.NewDecoder(detailResp.Body).Decode(&detail); err == nil && len(detail.Credentials) > 0 {
sb.WriteString("\n=== Per-Credential Status ===\n")
for _, cred := range detail.Credentials {
status := "✓ OK"
if cred.QuotaExceeded {
status = fmt.Sprintf("⏳ Cooling (%s)", cred.RecoverIn)
}
name := cred.Email
if name == "" {
name = cred.AuthID[:8]
}
sb.WriteString(fmt.Sprintf("\n[%s] %s: %s", cred.Provider, name, status))
}
sb.WriteString("\n")
}
}
return sb.String()
}
// copyAccountStatusToClipboard copies account status summary to clipboard
func copyAccountStatusToClipboard(engine *EmbeddedEngine) error {
text := captureAccountStatus()
@@ -825,7 +1066,7 @@ func exportAccountsDialog() {
// Use a default filename in the user's home directory
home, _ := os.UserHomeDir()
defaultPath := filepath.Join(home, "proxypilot-accounts.json")
// Run export command
output := runCLI("-export-accounts", defaultPath)
if output != "" {
@@ -838,7 +1079,7 @@ func importAccountsDialog() {
// Check for default export location
home, _ := os.UserHomeDir()
defaultPath := filepath.Join(home, "proxypilot-accounts.json")
// Check if default file exists
if _, err := os.Stat(defaultPath); err == nil {
output := runCLI("-import-accounts", defaultPath, "-force")
@@ -856,14 +1097,14 @@ func runCLI(args ...string) string {
return ""
}
dir := filepath.Dir(exe)
// Try common CLI binary names
candidates := []string{
filepath.Join(dir, "ProxyPilot.exe"),
filepath.Join(dir, "proxypilot.exe"),
filepath.Join(dir, "server.exe"),
}
var cliPath string
for _, c := range candidates {
if _, err := os.Stat(c); err == nil {
@@ -874,7 +1115,7 @@ func runCLI(args ...string) string {
if cliPath == "" {
return ""
}
cmd := exec.Command(cliPath, args...)
cmd.Env = os.Environ()
// Hide console window on Windows
@@ -888,3 +1129,86 @@ func runCLI(args ...string) string {
}
return string(out)
}
// checkForUpdatesWithToast checks for updates and shows a toast notification
func checkForUpdatesWithToast() {
info, err := updates.CheckForUpdates()
if err != nil {
_ = winutil.ShowToast("ProxyPilot", "Failed to check for updates")
return
}
if info.Available {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Update available: v%s", info.Version))
// Open release page
_ = desktopctl.OpenBrowser(info.DownloadURL)
} else {
_ = winutil.ShowToast("ProxyPilot", "You're running the latest version")
}
}
// checkForUpdatesOnStartup silently checks for updates on startup
func checkForUpdatesOnStartup() {
time.Sleep(5 * time.Second) // Wait for tray to fully load
info, err := updates.CheckForUpdates()
if err != nil || !info.Available {
return
}
_ = winutil.ShowToast("ProxyPilot Update", fmt.Sprintf("v%s is available! Click 'Check for Updates' to download.", info.Version))
}
// performOneClickUpdate downloads, verifies, and installs the update
func performOneClickUpdate(info *updates.UpdateInfo) {
if info == nil || !info.Available {
_ = winutil.ShowToast("ProxyPilot", "No update available")
return
}
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Downloading v%s...", info.Version))
// Download with progress
result, err := updates.DownloadUpdate(info.Version, func(progress updates.DownloadProgress) {
// Could update a progress indicator here in the future
})
if err != nil {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Download failed: %v", err))
return
}
// Verify the download
verifyResult, err := updates.VerifyDownload(result)
if err != nil {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Verification failed: %v", err))
return
}
if !verifyResult.Valid {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Verification failed: %s", verifyResult.Message))
return
}
_ = winutil.ShowToast("ProxyPilot", "Preparing to install update...")
// Prepare the update (extract if needed)
executablePath, err := updates.PrepareInstall(result)
if err != nil {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Preparation failed: %v", err))
return
}
// Install
installResult, err := updates.InstallUpdate(executablePath)
if err != nil {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Installation failed: %v", err))
return
}
if installResult.Success {
if installResult.NeedsRestart {
_ = winutil.ShowToast("ProxyPilot", "Update installed! Restarting...")
// The install script will restart the app
} else {
_ = winutil.ShowToast("ProxyPilot", "Update installed successfully!")
}
} else {
_ = winutil.ShowToast("ProxyPilot", fmt.Sprintf("Installation failed: %s", installResult.Message))
}
}
Binary file not shown.
+6 -6
View File
@@ -2,14 +2,14 @@
"FixedFileInfo": {
"FileVersion": {
"Major": 0,
"Minor": 1,
"Patch": 6,
"Minor": 3,
"Patch": 0,
"Build": 0
},
"ProductVersion": {
"Major": 0,
"Minor": 1,
"Patch": 6,
"Minor": 3,
"Patch": 0,
"Build": 0
},
"FileFlagsMask": "3f",
@@ -22,12 +22,12 @@
"Comments": "Local AI Proxy with Embedded Engine",
"CompanyName": "ProxyPilot",
"FileDescription": "ProxyPilot - Single Binary Desktop App",
"FileVersion": "0.1.6",
"FileVersion": "0.3.0",
"InternalName": "ProxyPilot",
"LegalCopyright": "MIT License",
"OriginalFilename": "ProxyPilot.exe",
"ProductName": "ProxyPilot",
"ProductVersion": "0.1.6"
"ProductVersion": "0.3.0"
},
"VarFileInfo": {
"Translation": {
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+921 -785
View File
File diff suppressed because it is too large Load Diff
Binary file not shown.
+13
View File
@@ -0,0 +1,13 @@
//go:build !windows
package main
// Service stubs for non-Windows platforms
func runService(configPath string) error {
return nil
}
func handleServiceCommand(args []string) bool {
return false
}
+353
View File
@@ -0,0 +1,353 @@
//go:build windows
package main
import (
"context"
"fmt"
"os"
"path/filepath"
"strings"
"time"
"golang.org/x/sys/windows/svc"
"golang.org/x/sys/windows/svc/eventlog"
"golang.org/x/sys/windows/svc/mgr"
configaccess "github.com/router-for-me/CLIProxyAPI/v6/internal/access/config_access"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
"github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy"
)
const serviceName = "ProxyPilot"
const serviceDisplayName = "ProxyPilot API Proxy"
const serviceDescription = "Local API proxy for AI coding tools"
// proxyService implements svc.Handler
type proxyService struct {
configPath string
cancelFunc context.CancelFunc
}
func (s *proxyService) Execute(args []string, r <-chan svc.ChangeRequest, changes chan<- svc.Status) (ssec bool, errno uint32) {
const cmdsAccepted = svc.AcceptStop | svc.AcceptShutdown
changes <- svc.Status{State: svc.StartPending}
// Initialize logging
logging.SetupBaseLogger()
// Load config
cfg, err := config.LoadConfigOptional(s.configPath, false)
if err != nil {
elog, _ := eventlog.Open(serviceName)
if elog != nil {
elog.Error(1, fmt.Sprintf("Failed to load config: %v", err))
elog.Close()
}
return
}
if cfg == nil {
cfg = &config.Config{Port: 8318}
}
// Configure logging
logging.ConfigureLogOutput(cfg)
// Register token store
sdkAuth.RegisterTokenStore(sdkAuth.NewFileTokenStore())
// Register access providers
configaccess.Register(&cfg.SDKConfig)
// Build and start service using builder pattern
builder := cliproxy.NewBuilder().
WithConfig(cfg).
WithConfigPath(s.configPath)
service, err := builder.Build()
if err != nil {
elog, _ := eventlog.Open(serviceName)
if elog != nil {
elog.Error(1, fmt.Sprintf("Failed to build service: %v", err))
elog.Close()
}
return
}
// Create context for graceful shutdown
ctx, cancel := context.WithCancel(context.Background())
s.cancelFunc = cancel
// Start service in background
go func() {
if err := service.Run(ctx); err != nil && err != context.Canceled {
elog, _ := eventlog.Open(serviceName)
if elog != nil {
elog.Error(1, fmt.Sprintf("Service error: %v", err))
elog.Close()
}
}
}()
changes <- svc.Status{State: svc.Running, Accepts: cmdsAccepted}
// Wait for stop signal
for {
select {
case c := <-r:
switch c.Cmd {
case svc.Stop, svc.Shutdown:
changes <- svc.Status{State: svc.StopPending}
cancel()
return
case svc.Interrogate:
changes <- c.CurrentStatus
}
}
}
}
// runService starts the Windows service
func runService(configPath string) error {
elog, err := eventlog.Open(serviceName)
if err != nil {
return err
}
defer elog.Close()
elog.Info(1, fmt.Sprintf("Starting %s service", serviceName))
err = svc.Run(serviceName, &proxyService{configPath: configPath})
if err != nil {
elog.Error(1, fmt.Sprintf("Service failed: %v", err))
return err
}
elog.Info(1, fmt.Sprintf("%s service stopped", serviceName))
return nil
}
// installService installs ProxyPilot as a Windows service
func installService(configPath string) error {
exePath, err := os.Executable()
if err != nil {
return fmt.Errorf("failed to get executable path: %w", err)
}
exePath = filepath.Clean(exePath)
m, err := mgr.Connect()
if err != nil {
return fmt.Errorf("failed to connect to service manager: %w", err)
}
defer m.Disconnect()
// Check if service exists
s, err := m.OpenService(serviceName)
if err == nil {
s.Close()
return fmt.Errorf("service %s already exists", serviceName)
}
// Build service arguments
args := []string{"-service"}
if configPath != "" {
args = append(args, "-config", configPath)
}
s, err = m.CreateService(serviceName, exePath, mgr.Config{
DisplayName: serviceDisplayName,
Description: serviceDescription,
StartType: mgr.StartAutomatic,
ErrorControl: mgr.ErrorNormal,
}, args...)
if err != nil {
return fmt.Errorf("failed to create service: %w", err)
}
defer s.Close()
// Set recovery options (restart on failure)
err = s.SetRecoveryActions([]mgr.RecoveryAction{
{Type: mgr.ServiceRestart, Delay: 5 * time.Second},
{Type: mgr.ServiceRestart, Delay: 30 * time.Second},
{Type: mgr.ServiceRestart, Delay: 60 * time.Second},
}, 86400) // Reset failure count after 24 hours
if err != nil {
// Non-fatal
}
// Install event log source
err = eventlog.InstallAsEventCreate(serviceName, eventlog.Error|eventlog.Warning|eventlog.Info)
if err != nil {
// Non-fatal, may already exist
}
fmt.Printf("Service %s installed successfully\n", serviceName)
return nil
}
// uninstallService removes the Windows service
func uninstallService() error {
m, err := mgr.Connect()
if err != nil {
return fmt.Errorf("failed to connect to service manager: %w", err)
}
defer m.Disconnect()
s, err := m.OpenService(serviceName)
if err != nil {
return fmt.Errorf("service %s not found: %w", serviceName, err)
}
defer s.Close()
// Stop the service if running
status, err := s.Query()
if err == nil && status.State != svc.Stopped {
_, _ = s.Control(svc.Stop)
// Wait for stop
for i := 0; i < 10; i++ {
time.Sleep(500 * time.Millisecond)
status, err = s.Query()
if err != nil || status.State == svc.Stopped {
break
}
}
}
err = s.Delete()
if err != nil {
return fmt.Errorf("failed to delete service: %w", err)
}
// Remove event log source
_ = eventlog.Remove(serviceName)
fmt.Printf("Service %s uninstalled successfully\n", serviceName)
return nil
}
// startService starts the Windows service
func startService() error {
m, err := mgr.Connect()
if err != nil {
return err
}
defer m.Disconnect()
s, err := m.OpenService(serviceName)
if err != nil {
return fmt.Errorf("service %s not found: %w", serviceName, err)
}
defer s.Close()
return s.Start()
}
// stopService stops the Windows service
func stopService() error {
m, err := mgr.Connect()
if err != nil {
return err
}
defer m.Disconnect()
s, err := m.OpenService(serviceName)
if err != nil {
return fmt.Errorf("service %s not found: %w", serviceName, err)
}
defer s.Close()
_, err = s.Control(svc.Stop)
return err
}
// serviceStatus returns the current service status
func serviceStatus() string {
m, err := mgr.Connect()
if err != nil {
return "unknown"
}
defer m.Disconnect()
s, err := m.OpenService(serviceName)
if err != nil {
return "not installed"
}
defer s.Close()
status, err := s.Query()
if err != nil {
return "unknown"
}
switch status.State {
case svc.Stopped:
return "stopped"
case svc.StartPending:
return "starting"
case svc.StopPending:
return "stopping"
case svc.Running:
return "running"
case svc.ContinuePending:
return "resuming"
case svc.PausePending:
return "pausing"
case svc.Paused:
return "paused"
default:
return "unknown"
}
}
// handleServiceCommand handles service-related CLI commands
func handleServiceCommand(args []string) bool {
if len(args) == 0 {
return false
}
cmd := strings.ToLower(args[0])
switch cmd {
case "install":
configPath := ""
if len(args) > 1 {
configPath = args[1]
}
if err := installService(configPath); err != nil {
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
os.Exit(1)
}
return true
case "uninstall", "remove":
if err := uninstallService(); err != nil {
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
os.Exit(1)
}
return true
case "start":
if err := startService(); err != nil {
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
os.Exit(1)
}
fmt.Println("Service started")
return true
case "stop":
if err := stopService(); err != nil {
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
os.Exit(1)
}
fmt.Println("Service stopped")
return true
case "status":
fmt.Printf("Service status: %s\n", serviceStatus())
return true
default:
return false
}
}
+6 -6
View File
@@ -2,14 +2,14 @@
"FixedFileInfo": {
"FileVersion": {
"Major": 0,
"Minor": 1,
"Patch": 6,
"Minor": 3,
"Patch": 0,
"Build": 0
},
"ProductVersion": {
"Major": 0,
"Minor": 1,
"Patch": 6,
"Minor": 3,
"Patch": 0,
"Build": 0
},
"FileFlagsMask": "3f",
@@ -22,12 +22,12 @@
"Comments": "Local AI Proxy Engine",
"CompanyName": "ProxyPilot",
"FileDescription": "ProxyPilot Engine",
"FileVersion": "0.1.6",
"FileVersion": "0.3.0",
"InternalName": "proxypilot-engine",
"LegalCopyright": "MIT License",
"OriginalFilename": "proxypilot-engine.exe",
"ProductName": "ProxyPilot",
"ProductVersion": "0.1.6"
"ProductVersion": "0.3.0"
},
"VarFileInfo": {
"Translation": {
+202 -166
View File
@@ -1,23 +1,28 @@
# Server host/interface to bind to. Default is empty ("") to bind all interfaces (IPv4 + IPv6).
# Use "127.0.0.1" or "localhost" to restrict access to local machine only.
host: ""
# Server port
port: 8317
# TLS settings for HTTPS. When enabled, the server listens with the provided certificate and key.
tls:
enable: false
cert: ""
key: ""
# Management API settings
remote-management:
# Whether to allow remote (non-localhost) management access.
# When false, only localhost can access management endpoints (a key is still required).
# Whether to allow remote (non-localhost) management access.
# When false, only localhost can access management endpoints (a key is still required).
allow-remote: false
# Management key. If a plaintext value is provided here, it will be hashed on startup.
# All management requests (even from localhost) require this key.
# Leave empty to disable the Management API entirely (404 for all /v0/management routes).
secret-key: "$2a$10$iphjVa6f4T/FARz4e/edtOHvdoxTbE4tv/9mS0ebvDg/C8fEbPtgq"
# Disable the bundled management control panel asset download and HTTP route when true.
# Management key. If a plaintext value is provided here, it will be hashed on startup.
# All management requests (even from localhost) require this key.
# Leave empty to disable the Management API entirely (404 for all /v0/management routes).
secret-key: ""
# Disable the bundled management control panel asset download and HTTP route when true.
disable-control-panel: false
# GitHub repository for the management control panel. Accepts a repository URL or releases API URL.
@@ -25,44 +30,24 @@ remote-management:
# Authentication directory (supports ~ for home directory)
auth-dir: "~/.cli-proxy-api"
# Long-running agent harness files root directory (feature_list.json, claude-progress.txt).
# The harness guides AI agents through structured, incremental development workflows.
# - INITIALIZER mode: Creates feature list, progress log, and init.sh for new sessions
# - CODING mode: Forces one-feature-at-a-time workflow with verification
# Leave empty to use session-based memory storage (recommended).
# Set to a specific directory to share harness files across sessions.
# harness-root-dir: ""
#
# Environment variables:
# CLIPROXY_HARNESS_ENABLED=true/false # Enable/disable harness injection (default: true)
# API keys for authentication
api-keys:
- "local-dev-key"
- "your-api-key-1"
- "your-api-key-2"
- "your-api-key-3"
# Enable debug logging
debug: false
# Enable pprof HTTP debug server (host:port). Keep it bound to localhost for safety.
pprof:
enable: false
addr: "127.0.0.1:8316"
# When true, disable high-overhead HTTP middleware features to reduce per-request memory usage under high concurrency.
commercial-mode: false
# Lightweight profile (example)
# commercial-mode: true
# usage-statistics-enabled: false
# metrics-enabled: false
# request-history-enabled: false
# agentic-harness-enabled: false
# prompt-budget-enabled: false
# request-log: false
# response-cache:
# enabled: false
# prompt-cache:
# enabled: false
# Open OAuth URLs in incognito/private browser mode.
# Useful when you want to login with a different account without logging out from your current session.
# Default: false (but Kiro auth defaults to true for multi-account support)
incognito-browser: true
# When true, write application logs to rotating files instead of stdout
logging-to-file: false
@@ -70,30 +55,34 @@ logging-to-file: false
# files are deleted until within the limit. Set to 0 to disable.
logs-max-total-size-mb: 0
# Maximum number of error log files retained when request logging is disabled.
# When exceeded, the oldest error log files are deleted. Default is 10. Set to 0 to disable cleanup.
error-logs-max-files: 10
# When false, disable in-memory usage statistics aggregation
usage-statistics-enabled: false
# Usage sampling (0.0-1.0). Default: 1.0 (no sampling)
# usage-sample-rate: 1.0
# Prometheus metrics + /metrics endpoint (opt-in)
metrics-enabled: false
# Persistent request history (opt-in)
request-history-enabled: false
# Request history sampling (0.0-1.0). Default: 1.0 (no sampling)
# request-history-sample-rate: 1.0
# Agentic harness middleware (default: true)
agentic-harness-enabled: true
# Codex prompt budget middleware (default: true)
prompt-budget-enabled: true
# Proxy URL. Supports socks5/http/https protocols. Example: socks5://user:pass@192.168.1.1:1080/
# Per-entry proxy-url also supports "direct" or "none" to bypass both the global proxy-url and environment proxies explicitly.
proxy-url: ""
# When true, unprefixed model requests only use credentials without a prefix (except when prefix == model name).
force-model-prefix: false
# When true, forward filtered upstream response headers to downstream clients.
# Default is false (disabled).
passthrough-headers: false
# Number of times to retry a request. Retries will occur if the HTTP response code is 403, 408, 500, 502, 503, or 504.
request-retry: 3
# Maximum number of different credentials to try for one failed request.
# Set to 0 to keep legacy behavior (try all available credentials).
max-retry-credentials: 0
# Maximum wait time in seconds for a cooled-down credential before triggering a retry.
max-retry-interval: 30
# Quota exceeded behavior
quota-exceeded:
switch-project: true # Whether to automatically switch to another project when a quota is exceeded
@@ -101,98 +90,18 @@ quota-exceeded:
# Routing strategy for selecting credentials when multiple match.
routing:
strategy: "round-robin" # round-robin (default), fill-first, usage-aware
# Global model mappings - route friendly names to actual models across all providers.
# These mappings are checked before per-credential model mappings.
# global-model-mappings:
# - from: "smart" # Client requests "smart"
# to: "claude-opus-4-5-20251101" # Routes to Claude Opus
# - from: "rush"
# to: "claude-haiku-4-5-20251001" # Routes to Claude Haiku (fast)
# - from: "think"
# to: "claude-opus-4-5-thinking" # Routes to thinking model
# - from: "gemini-pro"
# to: "gemini-2.5-pro-preview"
# provider: "gemini" # Only applies to Gemini provider
# - from: "cheap"
# to: "gpt-4o-mini"
# provider: "codex"
# enabled: false # Disabled mapping (kept for reference)
strategy: "round-robin" # round-robin (default), fill-first
# When true, enable authentication for the WebSocket API (/v1/ws).
ws-auth: false
# Allow requests without API keys. Default: false (deny unauthenticated).
allow-unauthenticated: false
# When > 0, emit blank lines every N seconds for non-streaming responses to prevent idle timeouts.
nonstream-keepalive-interval: 0
# CORS settings. By default, non-management endpoints allow "*" and
# management endpoints send no CORS headers.
# cors:
# allow-origins:
# - "http://localhost:5173"
# management-allow-origins:
# - "http://localhost:5173"
# allow-methods:
# - "GET"
# - "POST"
# - "PUT"
# - "PATCH"
# - "DELETE"
# - "OPTIONS"
# allow-headers:
# - "Authorization"
# - "Content-Type"
# - "X-Management-Key"
# - "X-Local-Password"
# Streaming behavior (SSE keep-alives, bootstrap retries, chunk sizing).
# Streaming behavior (SSE keep-alives + safe bootstrap retries).
# streaming:
# keepalive-seconds: 15 # Default: 0 (disabled). <= 0 disables keep-alives.
# bootstrap-retries: 1 # Default: 0 (disabled). Retries before first byte is sent.
# max-chunk-size: 65536 # Default: 65536 (64KB). Max bytes per response chunk. 0 disables limiting.
# Context compression behavior (Factory.ai-style structured summarization).
# Uses LLM to generate intelligent summaries with structured sections when context
# exceeds the threshold. Summaries include: session intent, file modifications,
# decisions made, next steps, and technical details.
# compression:
# enabled: true # Default: true. Enable LLM-based structured summarization.
# threshold-percent: 0.75 # Default: 0.75. Trigger compression at 75% of context window.
# max-summary-tokens: 2000 # Default: 2000. Maximum tokens for generated summaries.
# summarization-timeout-seconds: 30 # Default: 30. Timeout for LLM summarization calls.
# fallback-to-regex: true # Default: true. Use regex-based summary when LLM fails.
# Response caching - cache identical API responses to reduce upstream calls.
# response-cache:
# enabled: true
# max-size: 1000 # Max cached responses
# max-bytes: 0 # Optional total cache size cap in bytes
# ttl-seconds: 300 # 5 minutes
# exclude-models: # Don't cache these models
# - "*-thinking"
# - "o1-*"
# Prompt caching - track system prompts for analytics.
# prompt-cache:
# enabled: true
# max-size: 500
# max-bytes: 0 # Optional total cache size cap in bytes
# ttl-seconds: 1800 # 30 minutes
# warm-from-file: "./prompts-to-cache.json" # Optional: pre-load prompts on startup
# Format: [{"prompt": "...", "provider": "claude"}, ...]
# Token refresh and usage tracking configuration.
# auto-refresh-buffer: 5m # Default: 5m. Refresh tokens this long before expiry.
# # Supports Go duration format: "5m", "10m", "1h", etc.
# daily-reset-hour: 0 # Default: 0 (midnight UTC). Hour (0-23, UTC) to reset daily usage stats.
# Token-aware compression (proactive trimming based on model context window).
# Prevents "prompt too long" errors by trimming before hitting model limits.
# Environment variables:
# CLIPROXY_TOKEN_AWARE_ENABLED=true # Default: true. Enable token-based compression.
# CLIPROXY_COMPRESSION_THRESHOLD=0.75 # Default: 0.75. Trim at 75% of context window.
# CLIPROXY_RESERVE_TOKENS=8192 # Default: 8192. Tokens reserved for model output.
# Gemini API keys
# gemini-api-key:
@@ -202,10 +111,14 @@ allow-unauthenticated: false
# headers:
# X-Custom-Header: "custom-value"
# proxy-url: "socks5://proxy.example.com:1080"
# # proxy-url: "direct" # optional: explicit direct connect for this credential
# models:
# - name: "gemini-2.5-flash" # upstream model name
# alias: "gemini-flash" # client alias mapped to the upstream model
# excluded-models:
# - "gemini-2.5-pro" # exclude specific models from this provider (exact match)
# - "gemini-2.5-*" # wildcard matching prefix (e.g. gemini-2.5-flash, gemini-2.5-pro)
# - "*-preview" # wildcard matching suffix (e.g. gemini-3-pro-preview, gemini-3-flash-preview)
# - "*-preview" # wildcard matching suffix (e.g. gemini-3-pro-preview)
# - "*flash*" # wildcard matching substring (e.g. gemini-2.5-flash-lite)
# - api-key: "AIzaSy...02"
@@ -217,11 +130,12 @@ allow-unauthenticated: false
# headers:
# X-Custom-Header: "custom-value"
# proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
# # proxy-url: "direct" # optional: explicit direct connect for this credential
# models:
# - name: "gpt-5-codex" # upstream model name
# - name: "gpt-5-codex" # upstream model name
# alias: "codex-latest" # client alias mapped to the upstream model
# excluded-models:
# - "gpt-5.2" # exclude specific models (exact match)
# - "gpt-5.1" # exclude specific models (exact match)
# - "gpt-5-*" # wildcard matching prefix (e.g. gpt-5-medium, gpt-5-codex)
# - "*-mini" # wildcard matching suffix (e.g. gpt-5-codex-mini)
# - "*codex*" # wildcard matching substring (e.g. gpt-5-codex-low)
@@ -235,33 +149,48 @@ allow-unauthenticated: false
# headers:
# X-Custom-Header: "custom-value"
# proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
# # proxy-url: "direct" # optional: explicit direct connect for this credential
# models:
# - name: "claude-sonnet-4-5-20250929" # upstream model name
# alias: "claude-sonnet-latest" # client alias mapped to the upstream model
# - name: "claude-3-5-sonnet-20241022" # upstream model name
# alias: "claude-sonnet-latest" # client alias mapped to the upstream model
# excluded-models:
# - "claude-opus-4-5-20251101" # exclude specific models (exact match)
# - "claude-4-*" # wildcard matching prefix (e.g. claude-sonnet-4-5-20250929)
# - "claude-3-*" # wildcard matching prefix (e.g. claude-3-7-sonnet-20250219)
# - "*-thinking" # wildcard matching suffix (e.g. claude-opus-4-5-thinking)
# - "*haiku*" # wildcard matching substring (e.g. claude-haiku-4-5-20251001)
# - "*haiku*" # wildcard matching substring (e.g. claude-3-5-haiku-20241022)
# cloak: # optional: request cloaking for non-Claude-Code clients
# mode: "auto" # "auto" (default): cloak only when client is not Claude Code
# # "always": always apply cloaking
# # "never": never apply cloaking
# strict-mode: false # false (default): prepend Claude Code prompt to user system messages
# # true: strip all user system messages, keep only Claude Code prompt
# sensitive-words: # optional: words to obfuscate with zero-width characters
# - "API"
# - "proxy"
# cache-user-id: true # optional: default is false; set true to reuse cached user_id per API key instead of generating a random one each request
# Kiro (AWS CodeWhisperer) configuration
# kiro-key:
# - token-file: "~/.aws/sso/cache/kiro-auth-token.json"
# region: "us-east-1"
# proxy-url: "socks5://proxy.example.com:1080"
# agent-task-type: "dev"
# excluded-models:
# - "kiro-claude-haiku"
# Default headers for Claude API requests. Update when Claude Code releases new versions.
# In legacy mode, user-agent/package-version/runtime-version/timeout are used as fallbacks
# when the client omits them, while OS/arch remain runtime-derived. When
# stabilize-device-profile is enabled, OS/arch stay pinned to the baseline values below,
# while user-agent/package-version/runtime-version seed a software fingerprint that can
# still upgrade to newer official Claude client versions.
# claude-header-defaults:
# user-agent: "claude-cli/2.1.44 (external, sdk-cli)"
# package-version: "0.74.0"
# runtime-version: "v24.3.0"
# os: "MacOS"
# arch: "arm64"
# timeout: "600"
# stabilize-device-profile: false # optional, default false; set true to enable per-auth/API-key fingerprint pinning
# Kiro (AWS CodeWhisperer) configuration
# Note: Kiro API currently only operates in us-east-1 region
#kiro:
# - token-file: "~/.aws/sso/cache/kiro-auth-token.json" # path to Kiro token file
# agent-task-type: "" # optional: "vibe" or empty (API default)
# - access-token: "aoaAAAAA..." # or provide tokens directly
# refresh-token: "aorAAAAA..."
# profile-arn: "arn:aws:codewhisperer:us-east-1:..."
# proxy-url: "socks5://proxy.example.com:1080" # optional: proxy override
# Default headers for Codex OAuth model requests.
# These are used only for file-backed/OAuth Codex requests when the client
# does not send the header. `user-agent` applies to HTTP and websocket requests;
# `beta-features` only applies to websocket requests. They do not apply to codex-api-key entries.
# codex-header-defaults:
# user-agent: "codex_cli_rs/0.114.0 (Mac OS 14.2.0; x86_64) vscode/1.111.0"
# beta-features: "multi_agent"
# OpenAI compatibility providers
# openai-compatibility:
@@ -273,35 +202,121 @@ allow-unauthenticated: false
# api-key-entries:
# - api-key: "sk-or-v1-...b780"
# proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
# # proxy-url: "direct" # optional: explicit direct connect for this credential
# - api-key: "sk-or-v1-...b781" # without proxy-url
# models: # The models supported by the provider.
# - name: "moonshotai/kimi-k2:free" # The actual model name.
# alias: "kimi-k2" # The alias used in the API.
# alias: "kimi-k2" # The alias used in the API.
# thinking: # optional: omit to default to levels ["low","medium","high"]
# levels: ["low", "medium", "high"]
# # You may repeat the same alias to build an internal model pool.
# # The client still sees only one alias in the model list.
# # Requests to that alias will round-robin across the upstream names below,
# # and if the chosen upstream fails before producing output, the request will
# # continue with the next upstream model in the same alias pool.
# - name: "qwen3.5-plus"
# alias: "claude-opus-4.66"
# - name: "glm-5"
# alias: "claude-opus-4.66"
# - name: "kimi-k2.5"
# alias: "claude-opus-4.66"
# Vertex API keys (Vertex-compatible endpoints, use API key + base URL)
# Vertex API keys (Vertex-compatible endpoints, base-url is optional)
# vertex-api-key:
# - api-key: "vk-123..." # x-goog-api-key header
# prefix: "test" # optional: require calls like "test/vertex-pro" to target this credential
# base-url: "https://example.com/api" # e.g. https://zenmux.ai/api
# base-url: "https://example.com/api" # optional, e.g. https://zenmux.ai/api; falls back to Google Vertex when omitted
# proxy-url: "socks5://proxy.example.com:1080" # optional per-key proxy override
# # proxy-url: "direct" # optional: explicit direct connect for this credential
# headers:
# X-Custom-Header: "custom-value"
# models: # optional: map aliases to upstream model names
# - name: "gemini-2.5-flash" # upstream model name
# alias: "vertex-flash" # client-visible alias
# - name: "gemini-1.5-pro"
# - name: "gemini-2.5-pro"
# alias: "vertex-pro"
# excluded-models: # optional: models to exclude from listing
# - "imagen-3.0-generate-002"
# - "imagen-*"
# Amp Integration
# ampcode:
# # Configure upstream URL for Amp CLI OAuth and management features
# upstream-url: "https://ampcode.com"
# # Optional: Override API key for Amp upstream (otherwise uses env or file)
# upstream-api-key: ""
# # Per-client upstream API key mapping
# # Maps client API keys (from top-level api-keys) to different Amp upstream API keys.
# # Useful when different clients need to use different Amp accounts/quotas.
# # If a client key isn't mapped, falls back to upstream-api-key (default behavior).
# upstream-api-keys:
# - upstream-api-key: "amp_key_for_team_a" # Upstream key to use for these clients
# api-keys: # Client keys that use this upstream key
# - "your-api-key-1"
# - "your-api-key-2"
# - upstream-api-key: "amp_key_for_team_b"
# api-keys:
# - "your-api-key-3"
# # Restrict Amp management routes (/api/auth, /api/user, etc.) to localhost only (default: false)
# restrict-management-to-localhost: false
# # Force model mappings to run before checking local API keys (default: false)
# force-model-mappings: false
# # Amp Model Mappings
# # Route unavailable Amp models to alternative models available in your local proxy.
# # Useful when Amp CLI requests models you don't have access to (e.g., Claude Opus 4.5)
# # but you have a similar model available (e.g., Claude Sonnet 4).
# model-mappings:
# - from: "claude-opus-4-5-20251101" # Model requested by Amp CLI
# to: "gemini-claude-opus-4-5-thinking" # Route to this available model instead
# - from: "claude-sonnet-4-5-20250929"
# to: "gemini-claude-sonnet-4-5-thinking"
# - from: "claude-haiku-4-5-20251001"
# to: "gemini-2.5-flash"
# Global OAuth model name aliases (per channel)
# These aliases rename model IDs for both model listing and request routing.
# Supported channels: gemini-cli, vertex, aistudio, antigravity, claude, codex, qwen, iflow, kimi.
# NOTE: Aliases do not apply to gemini-api-key, codex-api-key, claude-api-key, openai-compatibility, vertex-api-key, or ampcode.
# You can repeat the same name with different aliases to expose multiple client model names.
# oauth-model-alias:
# gemini-cli:
# - name: "gemini-2.5-pro" # original model name under this channel
# alias: "g2.5p" # client-visible alias
# fork: true # when true, keep original and also add the alias as an extra model (default: false)
# vertex:
# - name: "gemini-2.5-pro"
# alias: "g2.5p"
# aistudio:
# - name: "gemini-2.5-pro"
# alias: "g2.5p"
# antigravity:
# - name: "gemini-3-pro-high"
# alias: "gemini-3-pro-preview"
# claude:
# - name: "claude-sonnet-4-5-20250929"
# alias: "cs4.5"
# codex:
# - name: "gpt-5"
# alias: "g5"
# qwen:
# - name: "qwen3-coder-plus"
# alias: "qwen-plus"
# iflow:
# - name: "glm-4.7"
# alias: "glm-god"
# kimi:
# - name: "kimi-k2.5"
# alias: "k2.5"
# OAuth provider excluded models
# oauth-excluded-models:
# gemini-cli:
# - "gemini-2.5-pro" # exclude specific models (exact match)
# - "gemini-2.5-*" # wildcard matching prefix (e.g. gemini-2.5-flash, gemini-2.5-pro)
# - "*-preview" # wildcard matching suffix (e.g. gemini-3-pro-preview, gemini-3-flash-preview)
# - "*-preview" # wildcard matching suffix (e.g. gemini-3-pro-preview)
# - "*flash*" # wildcard matching substring (e.g. gemini-2.5-flash-lite)
# vertex:
# - "gemini-3-pro-preview"
# - "gemini-3-flash-preview"
# aistudio:
# - "gemini-3-pro-preview"
# antigravity:
@@ -312,20 +327,41 @@ allow-unauthenticated: false
# - "gpt-5-codex-mini"
# qwen:
# - "vision-model"
# kiro:
# - "kiro-claude-haiku"
# iflow:
# - "tstars2.0"
# kimi:
# - "kimi-k2-thinking"
# Optional payload configuration
# payload:
# default: # Default rules only set parameters when they are missing in the payload.
# - models:
# - name: "gemini-2.5-pro" # Supports wildcards (e.g., "gemini-*")
# protocol: "gemini" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex
# protocol: "gemini" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
# params: # JSON path (gjson/sjson syntax) -> value
# "generationConfig.thinkingConfig.thinkingBudget": 32768
# default-raw: # Default raw rules set parameters using raw JSON when missing (must be valid JSON).
# - models:
# - name: "gemini-2.5-pro" # Supports wildcards (e.g., "gemini-*")
# protocol: "gemini" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
# params: # JSON path (gjson/sjson syntax) -> raw JSON value (strings are used as-is, must be valid JSON)
# "generationConfig.responseJsonSchema": "{\"type\":\"object\",\"properties\":{\"answer\":{\"type\":\"string\"}}}"
# override: # Override rules always set parameters, overwriting any existing values.
# - models:
# - name: "gpt-*" # Supports wildcards (e.g., "gpt-*")
# protocol: "codex" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex
# protocol: "codex" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
# params: # JSON path (gjson/sjson syntax) -> value
# "reasoning.effort": "high"
# override-raw: # Override raw rules always set parameters using raw JSON (must be valid JSON).
# - models:
# - name: "gpt-*" # Supports wildcards (e.g., "gpt-*")
# protocol: "codex" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
# params: # JSON path (gjson/sjson syntax) -> raw JSON value (strings are used as-is, must be valid JSON)
# "response_format": "{\"type\":\"json_schema\",\"json_schema\":{\"name\":\"answer\",\"schema\":{\"type\":\"object\"}}}"
# filter: # Filter rules remove specified parameters from the payload.
# - models:
# - name: "gemini-2.5-pro" # Supports wildcards (e.g., "gemini-*")
# protocol: "gemini" # restricts the rule to a specific protocol, options: openai, gemini, claude, codex, antigravity
# params: # JSON paths (gjson/sjson syntax) to remove from the payload
# - "generationConfig.thinkingConfig.thinkingBudget"
# - "generationConfig.responseJsonSchema"
+3 -3
View File
@@ -22,7 +22,7 @@ services:
- "51121:51121"
- "11451:11451"
volumes:
- ./config.yaml:/ProxyPilot/config.yaml
- ./auths:/root/.cli-proxy-api
- ./logs:/ProxyPilot/logs
- ${CLI_PROXY_CONFIG_PATH:-./config.yaml}:/ProxyPilot/config.yaml
- ${CLI_PROXY_AUTH_PATH:-./auths}:/root/.cli-proxy-api
- ${CLI_PROXY_LOG_PATH:-./logs}:/ProxyPilot/logs
restart: unless-stopped
-1
View File
@@ -76,7 +76,6 @@ proxypilot --zhipu-login # Add Zhipu AI API key
```bash
proxypilot --vertex-import <file> # Import Vertex service account key JSON
proxypilot --kiro-import # Import Kiro token from Kiro IDE
proxypilot --amazonq-import # Import Amazon Q CLI token
```
## Agent Configuration
+53 -75
View File
@@ -7,80 +7,71 @@ The `github.com/router-for-me/CLIProxyAPI/v6/sdk/access` package centralizes inb
```go
import (
sdkaccess "github.com/router-for-me/CLIProxyAPI/v6/sdk/access"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
)
```
Add the module with `go get github.com/router-for-me/CLIProxyAPI/v6/sdk/access`.
## Provider Registry
Providers are registered globally and then attached to a `Manager` as a snapshot:
- `RegisterProvider(type, provider)` installs a pre-initialized provider instance.
- Registration order is preserved the first time each `type` is seen.
- `RegisteredProviders()` returns the providers in that order.
## Manager Lifecycle
```go
manager := sdkaccess.NewManager()
providers, err := sdkaccess.BuildProviders(cfg)
if err != nil {
return err
}
manager.SetProviders(providers)
manager.SetProviders(sdkaccess.RegisteredProviders())
```
* `NewManager` constructs an empty manager.
* `SetProviders` replaces the provider slice using a defensive copy.
* `Providers` retrieves a snapshot that can be iterated safely from other goroutines.
* `BuildProviders` translates `config.Config` access declarations into runnable providers. When the config omits explicit providers but defines inline API keys, the helper auto-installs the built-in `config-api-key` provider.
If the manager itself is `nil` or no providers are configured, the call returns `nil, nil`, allowing callers to treat access control as disabled.
## Authenticating Requests
```go
result, err := manager.Authenticate(ctx, req)
result, authErr := manager.Authenticate(ctx, req)
switch {
case err == nil:
case authErr == nil:
// Authentication succeeded; result describes the provider and principal.
case errors.Is(err, sdkaccess.ErrNoCredentials):
case sdkaccess.IsAuthErrorCode(authErr, sdkaccess.AuthErrorCodeNoCredentials):
// No recognizable credentials were supplied.
case errors.Is(err, sdkaccess.ErrInvalidCredential):
case sdkaccess.IsAuthErrorCode(authErr, sdkaccess.AuthErrorCodeInvalidCredential):
// Supplied credentials were present but rejected.
default:
// Transport-level failure was returned by a provider.
// Internal/transport failure was returned by a provider.
}
```
`Manager.Authenticate` walks the configured providers in order. It returns on the first success, skips providers that surface `ErrNotHandled`, and tracks whether any provider reported `ErrNoCredentials` or `ErrInvalidCredential` for downstream error reporting.
If the manager itself is `nil` or no providers are registered, the call returns `nil, nil`, allowing callers to treat access control as disabled without branching on errors.
`Manager.Authenticate` walks the configured providers in order. It returns on the first success, skips providers that return `AuthErrorCodeNotHandled`, and aggregates `AuthErrorCodeNoCredentials` / `AuthErrorCodeInvalidCredential` for a final result.
Each `Result` includes the provider identifier, the resolved principal, and optional metadata (for example, which header carried the credential).
## Configuration Layout
## Built-in `config-api-key` Provider
The manager expects access providers under the `auth.providers` key inside `config.yaml`:
The proxy includes one built-in access provider:
- `config-api-key`: Validates API keys declared under top-level `api-keys`.
- Credential sources: `Authorization: Bearer`, `X-Goog-Api-Key`, `X-Api-Key`, `?key=`, `?auth_token=`
- Metadata: `Result.Metadata["source"]` is set to the matched source label.
In the CLI server and `sdk/cliproxy`, this provider is registered automatically based on the loaded configuration.
```yaml
auth:
providers:
- name: inline-api
type: config-api-key
api-keys:
- sk-test-123
- sk-prod-456
api-keys:
- sk-test-123
- sk-prod-456
```
Fields map directly to `config.AccessProvider`: `name` labels the provider, `type` selects the registered factory, `sdk` can name an external module, `api-keys` seeds inline credentials, and `config` passes provider-specific options.
## Loading Providers from External Go Modules
### Loading providers from external SDK modules
To consume a provider shipped in another Go module, point the `sdk` field at the module path and import it for its registration side effect:
```yaml
auth:
providers:
- name: partner-auth
type: partner-token
sdk: github.com/acme/xplatform/sdk/access/providers/partner
config:
region: us-west-2
audience: cli-proxy
```
To consume a provider shipped in another Go module, import it for its registration side effect:
```go
import (
@@ -89,19 +80,11 @@ import (
)
```
The blank identifier import ensures `init` runs so `sdkaccess.RegisterProvider` executes before `BuildProviders` is called.
## Built-in Providers
The SDK ships with one provider out of the box:
- `config-api-key`: Validates API keys declared inline or under top-level `api-keys`. It accepts the key from `Authorization: Bearer`, `X-Goog-Api-Key`, `X-Api-Key`, or the `?key=` query string and reports `ErrInvalidCredential` when no match is found.
Additional providers can be delivered by third-party packages. When a provider package is imported, it registers itself with `sdkaccess.RegisterProvider`.
The blank identifier import ensures `init` runs so `sdkaccess.RegisterProvider` executes before you call `RegisteredProviders()` (or before `cliproxy.NewBuilder().Build()`).
### Metadata and auditing
`Result.Metadata` carries provider-specific context. The built-in `config-api-key` provider, for example, stores the credential source (`authorization`, `x-goog-api-key`, `x-api-key`, or `query-key`). Populate this map in custom providers to enrich logs and downstream auditing.
`Result.Metadata` carries provider-specific context. The built-in `config-api-key` provider, for example, stores the credential source (`authorization`, `x-goog-api-key`, `x-api-key`, `query-key`, `query-auth-token`). Populate this map in custom providers to enrich logs and downstream auditing.
## Writing Custom Providers
@@ -110,13 +93,13 @@ type customProvider struct{}
func (p *customProvider) Identifier() string { return "my-provider" }
func (p *customProvider) Authenticate(ctx context.Context, r *http.Request) (*sdkaccess.Result, error) {
func (p *customProvider) Authenticate(ctx context.Context, r *http.Request) (*sdkaccess.Result, *sdkaccess.AuthError) {
token := r.Header.Get("X-Custom")
if token == "" {
return nil, sdkaccess.ErrNoCredentials
return nil, sdkaccess.NewNotHandledError()
}
if token != "expected" {
return nil, sdkaccess.ErrInvalidCredential
return nil, sdkaccess.NewInvalidCredentialError()
}
return &sdkaccess.Result{
Provider: p.Identifier(),
@@ -126,51 +109,46 @@ func (p *customProvider) Authenticate(ctx context.Context, r *http.Request) (*sd
}
func init() {
sdkaccess.RegisterProvider("custom", func(cfg *config.AccessProvider, root *config.Config) (sdkaccess.Provider, error) {
return &customProvider{}, nil
})
sdkaccess.RegisterProvider("custom", &customProvider{})
}
```
A provider must implement `Identifier()` and `Authenticate()`. To expose it to configuration, call `RegisterProvider` inside `init`. Provider factories receive the specific `AccessProvider` block plus the full root configuration for contextual needs.
A provider must implement `Identifier()` and `Authenticate()`. To make it available to the access manager, call `RegisterProvider` inside `init` with an initialized provider instance.
## Error Semantics
- `ErrNoCredentials`: no credentials were present or recognized by any provider.
- `ErrInvalidCredential`: at least one provider processed the credentials but rejected them.
- `ErrNotHandled`: instructs the manager to fall through to the next provider without affecting aggregate error reporting.
- `NewNoCredentialsError()` (`AuthErrorCodeNoCredentials`): no credentials were present or recognized. (HTTP 401)
- `NewInvalidCredentialError()` (`AuthErrorCodeInvalidCredential`): credentials were present but rejected. (HTTP 401)
- `NewNotHandledError()` (`AuthErrorCodeNotHandled`): fall through to the next provider.
- `NewInternalAuthError(message, cause)` (`AuthErrorCodeInternal`): transport/system failure. (HTTP 500)
Return custom errors to surface transport failures; they propagate immediately to the caller instead of being masked.
Errors propagate immediately to the caller unless they are classified as `not_handled` / `no_credentials` / `invalid_credential` and can be aggregated by the manager.
## Integration with cliproxy Service
`sdk/cliproxy` wires `@sdk/access` automatically when you build a CLI service via `cliproxy.NewBuilder`. Supplying a preconfigured manager allows you to extend or override the default providers:
`sdk/cliproxy` wires `@sdk/access` automatically when you build a CLI service via `cliproxy.NewBuilder`. Supplying a manager lets you reuse the same instance in your host process:
```go
coreCfg, _ := config.LoadConfig("config.yaml")
providers, _ := sdkaccess.BuildProviders(coreCfg)
manager := sdkaccess.NewManager()
manager.SetProviders(providers)
accessManager := sdkaccess.NewManager()
svc, _ := cliproxy.NewBuilder().
WithConfig(coreCfg).
WithAccessManager(manager).
WithConfigPath("config.yaml").
WithRequestAccessManager(accessManager).
Build()
```
The service reuses the manager for every inbound request, ensuring consistent authentication across embedded deployments and the canonical CLI binary.
Register any custom providers (typically via blank imports) before calling `Build()` so they are present in the global registry snapshot.
### Hot reloading providers
### Hot reloading
When configuration changes, rebuild providers and swap them into the manager:
When configuration changes, refresh any config-backed providers and then reset the manager's provider chain:
```go
providers, err := sdkaccess.BuildProviders(newCfg)
if err != nil {
log.Errorf("reload auth providers failed: %v", err)
return
}
accessManager.SetProviders(providers)
// configaccess is github.com/router-for-me/CLIProxyAPI/v6/internal/access/config_access
configaccess.Register(&newCfg.SDKConfig)
accessManager.SetProviders(sdkaccess.RegisteredProviders())
```
This mirrors the behaviour in `cliproxy.Service.refreshAccessProviders` and `api.Server.applyAccessConfig`, enabling runtime updates without restarting the process.
This mirrors the behaviour in `internal/access.ApplyAccessProviders`, enabling runtime updates without restarting the process.
+51 -73
View File
@@ -7,80 +7,71 @@
```go
import (
sdkaccess "github.com/router-for-me/CLIProxyAPI/v6/sdk/access"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
)
```
通过 `go get github.com/router-for-me/CLIProxyAPI/v6/sdk/access` 添加依赖。
## Provider Registry
访问提供者是全局注册,然后以快照形式挂到 `Manager` 上:
- `RegisterProvider(type, provider)` 注册一个已经初始化好的 provider 实例。
- 每个 `type` 第一次出现时会记录其注册顺序。
- `RegisteredProviders()` 会按该顺序返回 provider 列表。
## 管理器生命周期
```go
manager := sdkaccess.NewManager()
providers, err := sdkaccess.BuildProviders(cfg)
if err != nil {
return err
}
manager.SetProviders(providers)
manager.SetProviders(sdkaccess.RegisteredProviders())
```
- `NewManager` 创建空管理器。
- `SetProviders` 替换提供者切片并做防御性拷贝。
- `Providers` 返回适合并发读取的快照。
- `BuildProviders` 将 `config.Config` 中的访问配置转换成可运行的提供者。当配置没有显式声明但包含顶层 `api-keys` 时,会自动挂载内建的 `config-api-key` 提供者。
如果管理器本身为 `nil` 或未配置任何 provider,调用会返回 `nil, nil`,可视为关闭访问控制。
## 认证请求
```go
result, err := manager.Authenticate(ctx, req)
result, authErr := manager.Authenticate(ctx, req)
switch {
case err == nil:
case authErr == nil:
// Authentication succeeded; result carries provider and principal.
case errors.Is(err, sdkaccess.ErrNoCredentials):
case sdkaccess.IsAuthErrorCode(authErr, sdkaccess.AuthErrorCodeNoCredentials):
// No recognizable credentials were supplied.
case errors.Is(err, sdkaccess.ErrInvalidCredential):
case sdkaccess.IsAuthErrorCode(authErr, sdkaccess.AuthErrorCodeInvalidCredential):
// Credentials were present but rejected.
default:
// Provider surfaced a transport-level failure.
}
```
`Manager.Authenticate` 按配置顺序遍历提供者。遇到成功立即返回,`ErrNotHandled` 会继续尝试下一个;若发现 `ErrNoCredentials` 或 `ErrInvalidCredential`,会在遍历结束后汇总给调用方。
若管理器本身为 `nil` 或尚未注册提供者,调用会返回 `nil, nil`,让调用方无需针对错误做额外分支即可关闭访问控制。
`Manager.Authenticate` 会按顺序遍历 provider:遇到成功立即返回,`AuthErrorCodeNotHandled` 会继续尝试下一个;`AuthErrorCodeNoCredentials` / `AuthErrorCodeInvalidCredential` 会在遍历结束后汇总给调用方。
`Result` 提供认证提供者标识、解析出的主体以及可选元数据(例如凭证来源)。
## 配置结构
## 内建 `config-api-key` Provider
在 `config.yaml` 的 `auth.providers` 下定义访问提供者:
代理内置一个访问提供者:
- `config-api-key`:校验 `config.yaml` 顶层的 `api-keys`。
- 凭证来源:`Authorization: Bearer`、`X-Goog-Api-Key`、`X-Api-Key`、`?key=`、`?auth_token=`
- 元数据:`Result.Metadata["source"]` 会写入匹配到的来源标识
在 CLI 服务端与 `sdk/cliproxy` 中,该 provider 会根据加载到的配置自动注册。
```yaml
auth:
providers:
- name: inline-api
type: config-api-key
api-keys:
- sk-test-123
- sk-prod-456
api-keys:
- sk-test-123
- sk-prod-456
```
条目映射到 `config.AccessProvider`:`name` 指定实例名,`type` 选择注册的工厂,`sdk` 可引用第三方模块,`api-keys` 提供内联凭证,`config` 用于传递特定选项。
## 引入外部 Go 模块提供者
### 引入外部 SDK 提供者
若要消费其它 Go 模块输出的访问提供者,可在配置里填写 `sdk` 字段并在代码中引入该包,利用其 `init` 注册过程:
```yaml
auth:
providers:
- name: partner-auth
type: partner-token
sdk: github.com/acme/xplatform/sdk/access/providers/partner
config:
region: us-west-2
audience: cli-proxy
```
若要消费其它 Go 模块输出的访问提供者,直接用空白标识符导入以触发其 `init` 注册即可:
```go
import (
@@ -89,19 +80,11 @@ import (
)
```
通过空白标识符导入即可确保 `init` 调用,先于 `BuildProviders` 完成 `sdkaccess.RegisterProvider`。
## 内建提供者
当前 SDK 默认内置:
- `config-api-key`:校验配置中的 API Key。它从 `Authorization: Bearer`、`X-Goog-Api-Key`、`X-Api-Key` 以及查询参数 `?key=` 提取凭证,不匹配时抛出 `ErrInvalidCredential`。
导入第三方包即可通过 `sdkaccess.RegisterProvider` 注册更多类型。
空白导入可确保 `init` 先执行,从而在你调用 `RegisteredProviders()`(或 `cliproxy.NewBuilder().Build()`)之前完成 `sdkaccess.RegisterProvider`。
### 元数据与审计
`Result.Metadata` 用于携带提供者特定的上下文信息。内建的 `config-api-key` 会记录凭证来源(`authorization`、`x-goog-api-key`、`x-api-key` 或 `query-key`)。自定义提供者同样可以填充该 Map,以便丰富日志与审计场景。
`Result.Metadata` 用于携带提供者特定的上下文信息。内建的 `config-api-key` 会记录凭证来源(`authorization`、`x-goog-api-key`、`x-api-key`、`query-key`、`query-auth-token`)。自定义提供者同样可以填充该 Map,以便丰富日志与审计场景。
## 编写自定义提供者
@@ -110,13 +93,13 @@ type customProvider struct{}
func (p *customProvider) Identifier() string { return "my-provider" }
func (p *customProvider) Authenticate(ctx context.Context, r *http.Request) (*sdkaccess.Result, error) {
func (p *customProvider) Authenticate(ctx context.Context, r *http.Request) (*sdkaccess.Result, *sdkaccess.AuthError) {
token := r.Header.Get("X-Custom")
if token == "" {
return nil, sdkaccess.ErrNoCredentials
return nil, sdkaccess.NewNotHandledError()
}
if token != "expected" {
return nil, sdkaccess.ErrInvalidCredential
return nil, sdkaccess.NewInvalidCredentialError()
}
return &sdkaccess.Result{
Provider: p.Identifier(),
@@ -126,51 +109,46 @@ func (p *customProvider) Authenticate(ctx context.Context, r *http.Request) (*sd
}
func init() {
sdkaccess.RegisterProvider("custom", func(cfg *config.AccessProvider, root *config.Config) (sdkaccess.Provider, error) {
return &customProvider{}, nil
})
sdkaccess.RegisterProvider("custom", &customProvider{})
}
```
自定义提供者需要实现 `Identifier()` 与 `Authenticate()`。在 `init` 中调用 `RegisterProvider` 暴露给配置层,工厂函数既能读取当前条目,也能访问完整根配置。
自定义提供者需要实现 `Identifier()` 与 `Authenticate()`。在 `init` 中用已初始化实例调用 `RegisterProvider` 注册到全局 registry。
## 错误语义
- `ErrNoCredentials`:任何提供者都未识别到凭证。
- `ErrInvalidCredential`:至少一个提供者处理了凭证但判定无效。
- `ErrNotHandled`:告诉管理器跳到下一个提供者,不影响最终错误统计。
- `NewNoCredentialsError()`(`AuthErrorCodeNoCredentials`):未提供或未识别到凭证。(HTTP 401)
- `NewInvalidCredentialError()`(`AuthErrorCodeInvalidCredential`):凭证存在但校验失败。(HTTP 401)
- `NewNotHandledError()`(`AuthErrorCodeNotHandled`):告诉管理器跳到下一个 provider。
- `NewInternalAuthError(message, cause)`(`AuthErrorCodeInternal`):网络/系统错误。(HTTP 500)
自定义错误(例如网络异常)会马上冒泡返回。
除可汇总的 `not_handled` / `no_credentials` / `invalid_credential` 外,其它错误会立即冒泡返回。
## 与 cliproxy 集成
使用 `sdk/cliproxy` 构建服务时会自动接入 `@sdk/access`。如果需要扩展内置行为,可传入自定义管理器:
使用 `sdk/cliproxy` 构建服务时会自动接入 `@sdk/access`。如果希望在宿主进程里复用同一个 `Manager` 实例,可传入自定义管理器:
```go
coreCfg, _ := config.LoadConfig("config.yaml")
providers, _ := sdkaccess.BuildProviders(coreCfg)
manager := sdkaccess.NewManager()
manager.SetProviders(providers)
accessManager := sdkaccess.NewManager()
svc, _ := cliproxy.NewBuilder().
WithConfig(coreCfg).
WithAccessManager(manager).
WithConfigPath("config.yaml").
WithRequestAccessManager(accessManager).
Build()
```
服务会复用该管理器处理每一个入站请求,实现与 CLI 二进制一致的访问控制体验。
请在调用 `Build()` 之前完成自定义 provider 的注册(通常通过空白导入触发 `init`),以确保它们被包含在全局 registry 的快照中。
### 动态热更新提供者
当配置发生变化时,可以重新构建提供者并替换当前列表:
当配置发生变化时,刷新依赖配置的 provider,然后重置 manager 的 provider 链:
```go
providers, err := sdkaccess.BuildProviders(newCfg)
if err != nil {
log.Errorf("reload auth providers failed: %v", err)
return
}
accessManager.SetProviders(providers)
// configaccess is github.com/router-for-me/CLIProxyAPI/v6/internal/access/config_access
configaccess.Register(&newCfg.SDKConfig)
accessManager.SetProviders(sdkaccess.RegisteredProviders())
```
这一流程与 `cliproxy.Service.refreshAccessProviders` 和 `api.Server.applyAccessConfig` 保持一致,避免为更新访问策略而重启进程。
这一流程与 `internal/access.ApplyAccessProviders` 保持一致,避免为更新访问策略而重启进程。
+29
View File
@@ -0,0 +1,29 @@
# Session Progress - 2026-03-07
## Summary
Merged upstream CLIProxyAPI releases `v6.8.40` through `v6.8.46` into ProxyPilot on branch `sync-upstream-v6.8.40-to-v6.8.46` and prepared the next dev release tag `v0.3.0-dev-0.40`.
## Upstream Releases Included
- `v6.8.40` - adaptive thinking updates across Claude, Codex, OpenAI, and Antigravity flows
- `v6.8.41` - auth file handling follow-ups, Antigravity effort mapping, watcher synth changes
- `v6.8.42` - excluded Vertex models support, `defer_loading` stripping, Gemini schema cleanup
- `v6.8.43` - Claude SSE decompression fixes, watcher debounce fixes, codex response cleanup
- `v6.8.44` - watcher timer fix and initial GPT-5.4 registry entry
- `v6.8.45` - GPT-5.4 description cleanup and conditional `service_tier` handling
- `v6.8.46` - Gemini 3.1 Flash Lite Preview registry support and Codex websocket `response.create` cleanup
## Conflict Resolution Notes
- Kept ProxyPilot branding in `README.md` during the `v6.8.41` merge.
- Preserved deletion of `README_CN.md` when upstream tried to reintroduce it.
- Accepted upstream behavior in translator, watcher, executor, and registry paths unless the fork already had a stronger ProxyPilot-specific customization.
## Verification
- Clean `origin/main` baseline still fails `go test ./sdk/cliproxy/auth` in `TestFileStore_Delete_RemovesFile`; treated as a pre-existing failure.
- Targeted subsystem checks passed after each upstream merge for thinking, translators, watcher, registry, executor, and OpenAI websocket paths.
- Final full-suite verification should still record the pre-existing `sdk/cliproxy/auth` failure explicitly if it remains on the final release commit.
## Release Notes
- Next dev tag: `v0.3.0-dev-0.40`
- Upstream marker files updated:
- `UPSTREAM_VERSION` -> `v6.8.46`
- `features.json.upstream` -> `CLIProxyAPI v6.8.46`
+36
View File
@@ -0,0 +1,36 @@
# Session Progress - 2026-03-09
## Summary
Merged upstream CLIProxyAPI releases `v6.8.47` through `v6.8.49` into ProxyPilot on branch `sync-upstream-v6.8.47-to-v6.8.49`, fixed fork-specific release lookup drift, and prepared the next dev release tag `v0.3.0-dev-0.41`.
## Upstream Releases Included
- `v6.8.47` - watcher incremental auth-file changes, websocket follow-ups, and OpenAI-to-Claude request coverage
- `v6.8.48` - auth scheduler implementation, registry safety fixes, adaptive thinking pass-through, and Gemini/Vertex/model updates
- `v6.8.49` - scheduler refresh regression fix and OpenAI-to-Gemini `systemInstruction` camelCase correction
## Conflict Resolution Notes
- Kept ProxyPilot branding and structure in `README.md` during the `v6.8.49` merge.
- Preserved deletion of `README_CN.md` when upstream tried to reintroduce it.
- Accepted upstream behavior in watcher, registry, auth scheduler, translator, and executor paths unless the fork already had a stronger ProxyPilot-specific customization.
## Fork-Specific Follow-Ups
- Updated `UPSTREAM_VERSION` to `v6.8.49`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.8.49`.
- Fixed `.github/workflows/check-upstream.yml` so it compares the tracked `UPSTREAM_VERSION` tag against the latest upstream release tag instead of comparing upstream HEAD to itself.
- Switched fork-facing release lookups in `internal/api/handlers/management/config_basic.go` and `internal/proxypilotupdate/github.go` to `Finesssee/ProxyPilot` releases.
## Verification
- `go build ./cmd/server ./cmd/proxypilot-tray ./cmd/proxypilotpack` - PASS
- `go vet ./...` - PASS
- `go test ./...` - FAIL, but only on the pre-existing baseline failure in `sdk/cliproxy/auth`:
- `TestFileStore_Delete_RemovesFile/deletes_file_in_subdirectory`
- Spot-checked changed packages through the full test sweep:
- `internal/api/handlers/management` - PASS
- `internal/proxypilotupdate` - no test files
- `internal/registry` - PASS
- `internal/runtime/executor` - PASS
- `internal/watcher` - PASS
## Release Notes
- Next dev tag: `v0.3.0-dev-0.41`
- Latest upstream target at merge time: `CLIProxyAPI v6.8.49`
+84
View File
@@ -0,0 +1,84 @@
# Session Progress - 2026-03-12
## Summary
Merged upstream CLIProxyAPI releases `v6.8.50` and `v6.8.51` directly into ProxyPilot `main`, resolved fork-specific conflicts in startup and Docker publishing paths, prepared the next dev release tag `v0.3.0-dev-0.42`, then switched release publishing to a local/manual flow and uploaded the release assets outside GitHub Actions.
## Upstream Releases Included
- `v6.8.50` - preserve string-form system prompts, cap websocket body log growth, and extend scheduler / executor coverage
- `v6.8.51` - refresh model catalog from network on startup, register Codex models by plan tier, and refresh release / workflow paths
## Conflict Resolution Notes
- Kept ProxyPilot Docker publishing identity in `.github/workflows/docker-image.yml` and added the upstream models catalog refresh step before image builds.
- Kept ProxyPilot's management-password startup flow in `cmd/server/main.go` and added `registry.StartModelsUpdater(...)` before service startup.
- Accepted the upstream move from generated static registry data to embedded `internal/registry/models/models.json`, including deletion of `internal/registry/model_definitions_static_data.go`.
## Fork-Specific Follow-Ups
- Updated `internal/cmd/list_models.go` to use the new Codex plan-tier model getters instead of the removed `registry.GetOpenAIModels`.
- Fixed `sdk/auth/filestore.go` delete-path resolution so nested relative auth IDs delete under the configured base dir, absolute paths still work for the management API, and traversal outside the base dir is rejected.
- Updated `UPSTREAM_VERSION` to `v6.8.51`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.8.51`.
- Changed `.github/workflows/proxypilot-release.yml` and `.github/workflows/docker-image.yml` from tag-triggered runs to manual dispatch so releases can be built locally and uploaded manually instead of consuming GitHub Actions minutes.
- Built the `v0.3.0-dev-0.42` release assets locally from the tag snapshot and uploaded:
- `proxypilot-darwin-amd64`
- `proxypilot-darwin-arm64`
- `proxypilot-linux-amd64`
- `proxypilot-linux-arm64`
- `proxypilot-windows-amd64.exe`
- `checksums.txt`
## Verification
- `go build ./cmd/server ./cmd/proxypilot-tray ./cmd/proxypilotpack` - PASS
- `go vet ./...` - PASS
- `go test ./internal/runtime/executor/...` - PASS
- `go test ./internal/registry/...` - PASS
- `go test ./sdk/api/handlers/openai/...` - PASS
- `go test ./sdk/cliproxy/auth -run 'TestFileStore_Delete_(RemovesFile|NotFound|AbsolutePath|RejectsTraversalOutsideBaseDir)' -v` - PASS
- `go test ./sdk/cliproxy/auth` - PASS
- `go test ./sdk/cliproxy/...` - PASS
- `go test ./...` - PASS
## Release Notes
- Next dev tag: `v0.3.0-dev-0.42`
- Latest upstream target at merge time: `CLIProxyAPI v6.8.51`
## Maintenance Review
- Completed parallel findings-first review of `internal/auth/*`, `internal/translator/*`, and `internal/api/handlers/*` on 2026-03-12 12:01:40 +07.
- Auth review findings:
- `internal/auth/kiro/token_repository.go` only queues `auth_method` values `idc` and `builder-id` for background refresh even though `internal/auth/kiro/oauth.go` persists social logins as `auth_method: "social"` and the refresher has a default OAuth refresh path for non-SSO methods. Result: Google/GitHub Kiro tokens are skipped by auto-refresh.
- `internal/auth/kiro/token_repository.go` walks nested token files but rewrites refreshed tokens back to `filepath.Join(baseDir, token.ID)` after truncating IDs to `filepath.Base(path)`. Result: nested Kiro token files would be rewritten into the auth root instead of their original directory.
- Translator review findings:
- `internal/translator/kiro/openai` can emit streamed tool-call argument deltas with the wrong OpenAI tool index.
- `internal/translator/kiro/openai` does not actually enforce `tool_choice`; it still forwards tools when callers request `none` or pin a specific function.
- `internal/translator/openai/openai/responses` downgrades `developer` messages to `user`.
- `internal/translator/gemini/openai/chat-completions` reads/mapping finish reasons incorrectly for some response shapes.
- `internal/translator/gemini/openai/responses` can send `functionResponse.name = "unknown"` on follow-up tool-output requests.
- API handler review findings:
- `internal/api/handlers/management/memory.go` uses raw `session` query values to build filesystem paths for delete/export/import instead of the memory store's sanitized session path helper, allowing traversal outside the memory store root.
- `internal/api/handlers/management/generic_import.go` derives auth filenames from the first characters of imported API keys, exposing secret prefixes in filenames and management responses.
- `internal/api/handlers/management/auth_files.go` writes uploaded auth files to disk before validation and leaves invalid files behind on registration failure.
- `internal/api/handlers/management/config_basic.go` returns a zero-value config from `GetConfig` because it serializes `new(*h.cfg)` instead of the current config.
- `internal/api/handlers/management/auth_priority.go` and `internal/api/handlers/management/auth_files.go` update priority in places the runtime selector does not read, so management-set auth priority does not affect routing and does not persist reliably for file-backed auths.
- Config mutation helpers in `internal/api/handlers/management/handler.go` mutate `h.cfg` before persistence succeeds, so failed writes can leave runtime config diverged from disk until restart.
- Review validation:
- `go test ./internal/auth/... ./internal/translator/... ./internal/api/handlers/...` - PASS
## Maintenance Fixes
- Hardened management memory delete/export/import so session names are validated before resolving filesystem paths, blocking traversal attempts outside the memory store root.
- Changed bulk API-key import filenames to opaque `provider-import-...` names so credential prefixes are no longer exposed in filenames or management responses.
- Changed auth upload handling to validate uploaded JSON before committing it to disk and to roll back failed registrations instead of leaving broken auth files behind.
- Fixed `GetConfig` to return the live in-memory config and changed the simple config mutation helpers to persist cloned config state instead of mutating runtime config before the file write succeeds.
- Fixed file-backed auth persistence so `priority`, `prefix`, and `proxy_url` survive saves, reloads, and management edits, and so runtime selection prefers `Auth.Priority` with a legacy attribute fallback.
- Changed token writers across codex, claude, gemini, kimi, qwen, iflow, copilot, and vertex to use atomic `0600` JSON writes.
- Fixed Kiro background refresh so blank refresh responses do not erase the existing refresh token, nested token paths refresh in place, and social auth token files participate in the refresh scan.
- Fixed Kiro OAuth callback servers so shutdown waits on a dedicated completion signal instead of racing the login flow for the only callback result.
- Fixed Kiro/OpenAI tool streaming to keep a stable mapping from content-block indexes to OpenAI tool ordinals.
- Fixed Kiro/OpenAI request translation so `tool_choice=none|required|function` is enforced instead of treated as a prompt-only hint.
- Fixed OpenAI Responses to Chat Completions conversion to preserve `developer` role messages.
- Fixed Gemini/OpenAI finish-reason mapping so OpenAI receives valid enums while the original Gemini reason is preserved in `native_finish_reason`.
- Added a bounded Gemini function-call name cache so `previous_response_id` follow-up tool outputs resolve the original function name and fail closed when they cannot.
## Maintenance Fix Verification
- `go test ./internal/auth/... ./sdk/auth ./sdk/cliproxy/auth ./internal/translator/... ./internal/api/handlers/...` - PASS
- `go test ./internal/api/handlers/management` - PASS
- `go test ./...` - PASS
- `go build ./cmd/server ./cmd/proxypilot-tray ./cmd/proxypilotpack` - PASS
+28
View File
@@ -0,0 +1,28 @@
# Session Progress - 2026-03-17
## Summary
Merged upstream CLIProxyAPI release `v6.8.55` into ProxyPilot `main`, carrying forward the fork's workflow and branding decisions while absorbing upstream changes from `v6.8.52` through `v6.8.55`.
Built the release assets locally and published `v0.3.0-dev-0.43` on GitHub as the latest ProxyPilot release.
## Upstream Releases Included
- `v6.8.52` - Codex websocket header defaults and related compatibility updates
- `v6.8.53` - Antigravity model refresh and proxy helper improvements
- `v6.8.54` - auth file metadata exposure and management API test coverage
- `v6.8.55` - auth list priority/note support, Gemini responses tool-output fixes, and proxy utility additions
## Conflict Resolution Notes
- Kept the fork versions of `.github/workflows/docker-image.yml`, `.github/workflows/release.yaml`, `.github/workflows/pr-test-build.yml`, and `.goreleaser.yml` so this sync does not alter CI or release automation.
- Kept ProxyPilot README branding and deleted the upstream `README_CN.md` revival because this fork intentionally does not ship that file.
- Merged `internal/api/handlers/management/auth_files.go` semantically so ProxyPilot keeps its `Auth.Priority` persistence while also adding upstream `note` support and priority/note exposure in the auth-file API.
- Kept the stricter Gemini Responses JSON validation in `internal/translator/gemini/openai/responses/gemini_openai-responses_request.go` so partial JSON strings are not embedded as structured results.
## Repo State Updates
- Updated `UPSTREAM_VERSION` to `v6.8.55`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.8.55`.
- Published dev release: `v0.3.0-dev-0.43`.
## Verification
- `mise exec go@1.26.0 -- go build ./cmd/server ./cmd/proxypilot-tray ./cmd/proxypilotpack` - PASS
- `mise exec go@1.26.0 -- go vet ./...` - PASS
- `mise exec go@1.26.0 -- go test ./...` - PASS
- `gh release list -R Finesssee/ProxyPilot --limit 5` - PASS (`v0.3.0-dev-0.43` is `Latest`)
+11 -240
View File
@@ -21,7 +21,6 @@ import (
"os"
"path/filepath"
"strings"
"sync"
"time"
"github.com/gin-gonic/gin"
@@ -33,8 +32,6 @@ import (
"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
"github.com/router-for-me/CLIProxyAPI/v6/sdk/logging"
sdktr "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
"github.com/tidwall/gjson"
"github.com/tiktoken-go/tokenizer"
)
const (
@@ -55,195 +52,16 @@ func init() {
sdktr.Register(fOpenAI, fMyProv,
func(model string, raw []byte, stream bool) []byte { return raw },
sdktr.ResponseTransform{
Stream: func(ctx context.Context, model string, originalReq, translatedReq, raw []byte, param *any) []string {
return []string{string(raw)}
Stream: func(ctx context.Context, model string, originalReq, translatedReq, raw []byte, param *any) [][]byte {
return [][]byte{raw}
},
NonStream: func(ctx context.Context, model string, originalReq, translatedReq, raw []byte, param *any) string {
return string(raw)
NonStream: func(ctx context.Context, model string, originalReq, translatedReq, raw []byte, param *any) []byte {
return raw
},
},
)
}
// ============================================================================
// Token Counting Utilities
// ============================================================================
//
// This section demonstrates how to implement token counting for a custom provider.
// Token counting is important for:
// - Quota management and billing estimation
// - Ensuring requests don't exceed model context limits
// - Client-side optimization and request batching
//
// There are several approaches you can use:
//
// 1. SIMPLE ESTIMATION (shown in estimateTokens):
// - Fast and requires no external dependencies beyond string operations
// - Uses character count / 4 as a rough approximation
// - Good for quick estimates, less accurate for complex text
//
// 2. TIKTOKEN (shown in countWithTiktoken):
// - Uses OpenAI's tiktoken library for accurate BPE token counting
// - Best for OpenAI-compatible models (GPT-4, GPT-3.5, etc.)
// - Very accurate but requires the tiktoken-go package
//
// 3. UPSTREAM API (not shown):
// - Call your provider's token counting API endpoint
// - Most accurate but adds latency and API costs
// - Implement this if your provider offers a /count_tokens endpoint
//
// Choose the approach that best fits your accuracy needs and performance requirements.
var (
// tokenizerCache stores tokenizer instances to avoid repeated initialization.
// The sync.Map is safe for concurrent access.
tokenizerCache sync.Map
)
// getOrCreateTokenizer returns a cached tokenizer codec for the given model.
// This improves performance by avoiding repeated tokenizer initialization.
//
// Customize this function to map your provider's model names to appropriate
// tokenizer encodings. The tiktoken-go library provides encodings for:
// - O200kBase: GPT-4o, GPT-5, and newer models (default fallback)
// - Cl100kBase: GPT-4, GPT-3.5-turbo
// - P50kBase: text-davinci-003, Codex models
func getOrCreateTokenizer(model string) (tokenizer.Codec, error) {
// Check cache first
if cached, ok := tokenizerCache.Load(model); ok {
return cached.(tokenizer.Codec), nil
}
// Select encoding based on model prefix
// Customize this mapping for your provider's model naming convention
var enc tokenizer.Codec
var err error
sanitized := strings.ToLower(strings.TrimSpace(model))
switch {
// Example: Map your custom models to appropriate encodings
case strings.HasPrefix(sanitized, "myprov-gpt4"):
enc, err = tokenizer.ForModel(tokenizer.GPT4)
case strings.HasPrefix(sanitized, "myprov-gpt3"):
enc, err = tokenizer.ForModel(tokenizer.GPT35Turbo)
case strings.HasPrefix(sanitized, "gpt-4o"), strings.HasPrefix(sanitized, "gpt-4.1"):
enc, err = tokenizer.ForModel(tokenizer.GPT4o)
case strings.HasPrefix(sanitized, "gpt-4"):
enc, err = tokenizer.ForModel(tokenizer.GPT4)
case strings.HasPrefix(sanitized, "gpt-3.5"):
enc, err = tokenizer.ForModel(tokenizer.GPT35Turbo)
default:
// Default to O200kBase - the most recent encoding for modern models
enc, err = tokenizer.Get(tokenizer.O200kBase)
}
if err != nil {
return nil, err
}
// Store in cache (use LoadOrStore to handle race conditions)
actual, _ := tokenizerCache.LoadOrStore(model, enc)
return actual.(tokenizer.Codec), nil
}
// estimateTokens provides a simple token count estimation without external libraries.
// This is useful as a fallback when tiktoken is unavailable or for quick approximations.
//
// The algorithm uses character count / 4, which is based on the observation that
// English text averages about 4 characters per token. This is less accurate for:
// - Code (typically more tokens per character)
// - Non-English text (varies by language)
// - Text with many special characters or numbers
//
// For production use, consider tiktoken for better accuracy.
func estimateTokens(text string) int {
if len(text) == 0 {
return 0
}
// Simple estimation: ~4 characters per token on average
// This is a reasonable approximation for English text
tokens := len(text) / 4
if tokens == 0 && len(text) > 0 {
tokens = 1 // At least 1 token for non-empty text
}
return tokens
}
// countWithTiktoken counts tokens using the tiktoken BPE tokenizer.
// This provides accurate token counts for OpenAI-compatible models.
//
// For custom providers with different tokenization schemes, you may need to:
// - Apply an adjustment factor (e.g., multiply by 1.1 for Claude models)
// - Use a custom tokenizer that matches your provider's implementation
// - Call your provider's native token counting API instead
func countWithTiktoken(enc tokenizer.Codec, text string) (int, error) {
if enc == nil {
return 0, fmt.Errorf("tokenizer is nil")
}
_, tokens, err := enc.Encode(text)
if err != nil {
return 0, err
}
return len(tokens), nil
}
// extractMessagesText extracts all text content from an OpenAI-format chat request.
// This handles the standard messages array structure with role/content fields.
//
// Customize this function if your provider uses a different request format.
func extractMessagesText(payload []byte) string {
if len(payload) == 0 {
return ""
}
root := gjson.ParseBytes(payload)
var segments []string
// Extract from messages array (OpenAI chat format)
messages := root.Get("messages")
if messages.Exists() && messages.IsArray() {
messages.ForEach(func(_, msg gjson.Result) bool {
// Extract role for context (adds ~1 token overhead per message)
if role := msg.Get("role").String(); role != "" {
segments = append(segments, role)
}
// Extract text content
content := msg.Get("content")
if content.IsArray() {
// Handle array content (e.g., with images)
content.ForEach(func(_, part gjson.Result) bool {
if part.Get("type").String() == "text" {
if text := part.Get("text").String(); text != "" {
segments = append(segments, text)
}
}
return true
})
} else if text := content.String(); text != "" {
segments = append(segments, text)
}
return true
})
}
// Extract from prompt field (completion format)
if prompt := root.Get("prompt").String(); prompt != "" {
segments = append(segments, prompt)
}
// Extract from input field (some APIs use this)
if input := root.Get("input").String(); input != "" {
segments = append(segments, input)
}
// Extract system prompt if present at top level
if system := root.Get("system").String(); system != "" {
segments = append(segments, system)
}
return strings.Join(segments, "\n")
}
// MyExecutor is a minimal provider implementation for demonstration purposes.
// It implements the Executor interface to handle requests to a custom AI provider.
type MyExecutor struct{}
@@ -322,57 +140,6 @@ func (MyExecutor) Execute(ctx context.Context, a *coreauth.Auth, req clipexec.Re
return clipexec.Response{Payload: body}, nil
}
// CountTokens counts tokens in the request payload.
// This implementation demonstrates a layered approach:
// 1. Try tiktoken for accurate BPE-based counting
// 2. Fall back to simple character-based estimation if tiktoken fails
//
// The response format follows the Anthropic API convention: {"count": <number>}
// Adjust the response format to match your provider's expected format.
//
// For production use, consider:
// - Caching token counts for identical payloads
// - Using your provider's native token counting API if available
// - Applying model-specific adjustment factors
func (MyExecutor) CountTokens(_ context.Context, _ *coreauth.Auth, req clipexec.Request, _ clipexec.Options) (clipexec.Response, error) {
var tokenCount int
// Extract text content from the request payload
text := extractMessagesText(req.Payload)
// If no text was extracted from structured fields, use raw payload
if text == "" && len(req.Payload) > 0 {
text = string(req.Payload)
}
// Try tiktoken first for accurate counting
enc, err := getOrCreateTokenizer(req.Model)
if err == nil {
// Successfully got a tokenizer, use it for accurate counting
count, countErr := countWithTiktoken(enc, text)
if countErr == nil {
tokenCount = count
} else {
// Tiktoken encoding failed, fall back to estimation
tokenCount = estimateTokens(text)
}
} else {
// Could not get tokenizer, fall back to simple estimation
tokenCount = estimateTokens(text)
}
// Return response in the expected format
// The format follows Anthropic's count_tokens response: {"count": <number>}
// Adjust this format to match your provider's API specification
response := fmt.Sprintf(`{"count":%d}`, tokenCount)
return clipexec.Response{Payload: []byte(response)}, nil
}
func (MyExecutor) Embed(context.Context, *coreauth.Auth, clipexec.Request, clipexec.Options) (clipexec.Response, error) {
return clipexec.Response{}, errors.New("embeddings not implemented")
}
func (MyExecutor) HttpRequest(ctx context.Context, a *coreauth.Auth, req *http.Request) (*http.Response, error) {
if req == nil {
return nil, fmt.Errorf("myprov executor: request is nil")
@@ -388,13 +155,17 @@ func (MyExecutor) HttpRequest(ctx context.Context, a *coreauth.Auth, req *http.R
return client.Do(httpReq)
}
func (MyExecutor) ExecuteStream(ctx context.Context, a *coreauth.Auth, req clipexec.Request, opts clipexec.Options) (<-chan clipexec.StreamChunk, error) {
func (MyExecutor) CountTokens(context.Context, *coreauth.Auth, clipexec.Request, clipexec.Options) (clipexec.Response, error) {
return clipexec.Response{}, errors.New("count tokens not implemented")
}
func (MyExecutor) ExecuteStream(ctx context.Context, a *coreauth.Auth, req clipexec.Request, opts clipexec.Options) (*clipexec.StreamResult, error) {
ch := make(chan clipexec.StreamChunk, 1)
go func() {
defer close(ch)
ch <- clipexec.StreamChunk{Payload: []byte("data: {\"ok\":true}\n\n")}
}()
return ch, nil
return &clipexec.StreamResult{Chunks: ch}, nil
}
func (MyExecutor) Refresh(ctx context.Context, a *coreauth.Auth) (*coreauth.Auth, error) {
@@ -434,7 +205,7 @@ func main() {
// Optional: add a simple middleware + custom request logger
api.WithMiddleware(func(c *gin.Context) { c.Header("X-Example", "custom-provider"); c.Next() }),
api.WithRequestLoggerFactory(func(cfg *config.Config, cfgPath string) logging.RequestLogger {
return logging.NewFileRequestLogger(true, "logs", filepath.Dir(cfgPath))
return logging.NewFileRequestLoggerWithOptions(true, "logs", filepath.Dir(cfgPath), cfg.ErrorLogsMaxFiles)
}),
).
WithHooks(hooks).
+1 -5
View File
@@ -58,7 +58,7 @@ func (EchoExecutor) Execute(context.Context, *coreauth.Auth, clipexec.Request, c
return clipexec.Response{}, errors.New("echo executor: Execute not implemented")
}
func (EchoExecutor) ExecuteStream(context.Context, *coreauth.Auth, clipexec.Request, clipexec.Options) (<-chan clipexec.StreamChunk, error) {
func (EchoExecutor) ExecuteStream(context.Context, *coreauth.Auth, clipexec.Request, clipexec.Options) (*clipexec.StreamResult, error) {
return nil, errors.New("echo executor: ExecuteStream not implemented")
}
@@ -70,10 +70,6 @@ func (EchoExecutor) CountTokens(context.Context, *coreauth.Auth, clipexec.Reques
return clipexec.Response{}, errors.New("echo executor: CountTokens not implemented")
}
func (EchoExecutor) Embed(context.Context, *coreauth.Auth, clipexec.Request, clipexec.Options) (clipexec.Response, error) {
return clipexec.Response{}, errors.New("echo executor: Embed not implemented")
}
func main() {
log.SetLevel(log.InfoLevel)
+126
View File
@@ -0,0 +1,126 @@
{
"project": "ProxyPilot",
"version": "0.3.0",
"upstream": "CLIProxyAPI v6.9.1",
"features": [
{
"id": 1,
"name": "Version sync",
"description": "Version strings synced to 0.3.0 in versioninfo.json files",
"passes": true
},
{
"id": 2,
"name": "Dead code removal",
"description": "Deprecated RouteModule V1 interface removed",
"passes": true
},
{
"id": 3,
"name": "conductor.go split",
"description": "Split 2,280-line conductor.go into 3 focused modules",
"passes": true
},
{
"id": 4,
"name": "kiro_executor.go split",
"description": "Split 3,891-line kiro_executor.go into 4 focused modules",
"passes": true
},
{
"id": 5,
"name": "codex_prompt_budget.go split",
"description": "Split 2,762-line codex_prompt_budget.go into 3 focused modules",
"passes": true
},
{
"id": 6,
"name": "Auth package tests",
"description": "Unit tests for claude, codex, gemini auth packages",
"passes": true
},
{
"id": 7,
"name": "Trimming loop fix",
"description": "Fixed prompt budget trimming loop that never executed",
"passes": true
},
{
"id": 8,
"name": "Token analysis recompute",
"description": "Token analysis recomputed after scaffold injection",
"passes": true
},
{
"id": 9,
"name": "Body read error handling",
"description": "Return 400 on body read error instead of empty body",
"passes": true
},
{
"id": 10,
"name": "Header leak fix",
"description": "Strip internal header regardless of memory store state",
"passes": true
},
{
"id": 11,
"name": "TokenKey panic fix",
"description": "Safe truncation of tokenKey for logging",
"passes": true
},
{
"id": 12,
"name": "EventStreamError order fix",
"description": "Check EventStreamError before string patterns in isRetryableError",
"passes": true
},
{
"id": 13,
"name": "isTokenExpired logic fix",
"description": "Return true on parse failure per function contract",
"passes": true
},
{
"id": 14,
"name": "StartAutoRefresh interval fix",
"description": "Respect caller-provided interval parameter",
"passes": true
},
{
"id": 15,
"name": "refreshCancel race fix",
"description": "Protect refreshCancel with mutex",
"passes": true
},
{
"id": 16,
"name": "executorKeyFromAuth fix",
"description": "Use correct key lookup for compat auths in refreshAuth",
"passes": true
},
{
"id": 17,
"name": "Auth packages code review",
"description": "Codex review of internal/auth/* packages",
"passes": true
},
{
"id": 18,
"name": "Translator packages code review",
"description": "Codex review of internal/translator/* packages",
"passes": true
},
{
"id": 19,
"name": "API handlers code review",
"description": "Codex review of internal/api/handlers/* packages",
"passes": true
}
],
"summary": {
"total": 19,
"passing": 19,
"failing": 0
}
}
+3 -8
View File
@@ -1,6 +1,6 @@
module github.com/router-for-me/CLIProxyAPI/v6
go 1.24.0
go 1.26.0
require (
github.com/ProtonMail/go-crypto v1.3.0
@@ -22,6 +22,7 @@ require (
github.com/pelletier/go-toml/v2 v2.2.2
github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c
github.com/prometheus/client_golang v1.23.2
github.com/refraction-networking/utls v1.8.2
github.com/sirupsen/logrus v1.9.3
github.com/stretchr/testify v1.11.1
github.com/tidwall/gjson v1.18.0
@@ -30,11 +31,11 @@ require (
golang.org/x/crypto v0.45.0
golang.org/x/net v0.47.0
golang.org/x/oauth2 v0.30.0
golang.org/x/sync v0.18.0
golang.org/x/sys v0.38.0
golang.org/x/term v0.37.0
gopkg.in/natefinch/lumberjack.v2 v2.2.1
gopkg.in/yaml.v3 v3.0.1
modernc.org/sqlite v1.42.2
)
require (
@@ -94,14 +95,12 @@ require (
github.com/muesli/cancelreader v0.2.2 // indirect
github.com/muesli/termenv v0.16.0 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
github.com/ncruces/go-strftime v0.1.9 // indirect
github.com/oxtoacart/bpool v0.0.0-20190530202638-03653db5a59c // indirect
github.com/pjbgf/sha1cd v0.5.0 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
github.com/prometheus/client_model v0.6.2 // indirect
github.com/prometheus/common v0.66.1 // indirect
github.com/prometheus/procfs v0.16.1 // indirect
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
github.com/rivo/uniseg v0.4.7 // indirect
github.com/rs/xid v1.5.0 // indirect
github.com/sergi/go-diff v1.4.0 // indirect
@@ -113,11 +112,7 @@ require (
go.yaml.in/yaml/v2 v2.4.2 // indirect
golang.org/x/arch v0.8.0 // indirect
golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
golang.org/x/sync v0.18.0 // indirect
golang.org/x/text v0.31.0 // indirect
google.golang.org/protobuf v1.36.8 // indirect
gopkg.in/ini.v1 v1.67.0 // indirect
modernc.org/libc v1.66.10 // indirect
modernc.org/mathutil v1.7.1 // indirect
modernc.org/memory v1.11.0 // indirect
)
+6 -36
View File
@@ -12,6 +12,8 @@ github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPd
github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5/go.mod h1:wHh0iHkYZB8zMSxRWpUBQtwG5a7fFgvEO+odwuTv2gs=
github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiErDT4WkJ2k=
github.com/aymanbagabas/go-osc52/v2 v2.0.1/go.mod h1:uYgXzlJ7ZpABp8OJ+exZzJJhRNQ2ASbcXHWsFqH8hp8=
github.com/aymanbagabas/go-udiff v0.2.0 h1:TK0fH4MteXUDspT88n8CKzvK0X9O2xu9yQjWpi6yML8=
github.com/aymanbagabas/go-udiff v0.2.0/go.mod h1:RE4Ex0qsGkTAJoQdQQCA0uG+nAzJO/pI/QwceO5fgrA=
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0=
@@ -32,6 +34,8 @@ github.com/charmbracelet/x/ansi v0.10.1 h1:rL3Koar5XvX0pHGfovN03f5cxLbCF2YvLeyz7
github.com/charmbracelet/x/ansi v0.10.1/go.mod h1:3RQDQ6lDnROptfpWuUVIUG64bD2g2BgntdxH0Ya5TeE=
github.com/charmbracelet/x/cellbuf v0.0.13-0.20250311204145-2c3ea96c31dd h1:vy0GVL4jeHEwG5YOXDmi86oYw2yuYUGqz6a8sLwg0X8=
github.com/charmbracelet/x/cellbuf v0.0.13-0.20250311204145-2c3ea96c31dd/go.mod h1:xe0nKWGd3eJgtqZRaN9RjMtK7xUYchjzPr7q6kcvCCs=
github.com/charmbracelet/x/exp/golden v0.0.0-20241011142426-46044092ad91 h1:payRxjMjKgx2PaCWLZ4p3ro9y97+TVLZNaRZgJwSVDQ=
github.com/charmbracelet/x/exp/golden v0.0.0-20241011142426-46044092ad91/go.mod h1:wDlXFlCrmJ8J+swcL/MnGUuYnqgQdW9rhSD61oNMb6U=
github.com/charmbracelet/x/term v0.2.1 h1:AQeHeLZ1OqSXhrAWpYUtZyX1T3zVxfpZuEQMIQaGIAQ=
github.com/charmbracelet/x/term v0.2.1/go.mod h1:oQ4enTYFV7QN4m0i9mzHrViD7TQKvNEEkHUMCmsxdUg=
github.com/cloudflare/circl v1.6.1 h1:zqIqSPIndyBh1bjLVVDHMPpVKqp8Su/V+6MeDzzQBQ0=
@@ -104,8 +108,6 @@ github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8/go.mod h1:wcDNUv
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=
github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e/go.mod h1:boTsfXsheKC2y+lKOCMpSfarhxDeIzfZG1jqGcPl3cA=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
@@ -174,8 +176,6 @@ github.com/muesli/termenv v0.16.0 h1:S5AlUN9dENB57rsbnkPyfdGuWIlkmzJjbFf0Tf5FWUc
github.com/muesli/termenv v0.16.0/go.mod h1:ZRfOIKPFDYQoDFF4Olj7/QJbW60Ol/kL1pU3VfY/Cnk=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
github.com/ncruces/go-strftime v0.1.9 h1:bY0MQC28UADQmHmaF5dgpLmImcShSi2kHU9XLdhx/f4=
github.com/ncruces/go-strftime v0.1.9/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
github.com/oxtoacart/bpool v0.0.0-20190530202638-03653db5a59c h1:rp5dCmg/yLR3mgFuSOe4oEnDDmGLROTvMragMUXpTQw=
github.com/oxtoacart/bpool v0.0.0-20190530202638-03653db5a59c/go.mod h1:X07ZCGwUbLaax7L0S3Tw4hpejzu63ZrrQiUe6W0hcy0=
github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6Wq+LM=
@@ -194,8 +194,8 @@ github.com/prometheus/common v0.66.1 h1:h5E0h5/Y8niHc5DlaLlWLArTQI7tMrsfQjHV+d9Z
github.com/prometheus/common v0.66.1/go.mod h1:gcaUsgf3KfRSwHY4dIMXLPV0K/Wg1oZ8+SbZk/HH/dA=
github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
github.com/refraction-networking/utls v1.8.2 h1:j4Q1gJj0xngdeH+Ox/qND11aEfhpgoEvV+S9iJ2IdQo=
github.com/refraction-networking/utls v1.8.2/go.mod h1:jkSOEkLqn+S/jtpEHPOsVv/4V4EVnelwbMQl4vCWXAM=
github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
@@ -250,8 +250,6 @@ golang.org/x/crypto v0.45.0 h1:jMBrvKuj23MTlT0bQEOBcAE0mjg8mK9RXFhRH6nyF3Q=
golang.org/x/crypto v0.45.0/go.mod h1:XTGrrkGJve7CYK7J8PEww4aY7gM3qMCElcJQ8n8JdX4=
golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=
golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
golang.org/x/mod v0.29.0 h1:HV8lRxZC4l2cr3Zq1LvtOsi/ThTgWnUk/y64QSs8GwA=
golang.org/x/mod v0.29.0/go.mod h1:NyhrlYXJ2H4eJiRy/WDBO6HMqZQ6q9nk4JzS3NuCK+w=
golang.org/x/net v0.47.0 h1:Mx+4dIFzqraBXUugkia1OOvlD6LemFo1ALMHjrXDOhY=
golang.org/x/net v0.47.0/go.mod h1:/jNxtkgq5yWUGYkaZGqo27cfGZ1c5Nen03aYrrKpVRU=
golang.org/x/oauth2 v0.30.0 h1:dnDm7JmhM45NNpd8FDDeLhK6FwqbOf4MLCM9zb1BOHI=
@@ -271,8 +269,6 @@ golang.org/x/term v0.37.0 h1:8EGAD0qCmHYZg6J17DvsMy9/wJ7/D/4pV/wfnld5lTU=
golang.org/x/term v0.37.0/go.mod h1:5pB4lxRNYYVZuTLmy8oR2BH8dflOR+IbTYFD8fi3254=
golang.org/x/text v0.31.0 h1:aC8ghyu4JhP8VojJ2lEHBnochRno1sgL6nEi9WGFGMM=
golang.org/x/text v0.31.0/go.mod h1:tKRAlv61yKIjGGHX/4tP1LTbc13YSec1pxVEWXzfoeM=
golang.org/x/tools v0.38.0 h1:Hx2Xv8hISq8Lm16jvBZ2VQf+RLmbd7wVUsALibYI/IQ=
golang.org/x/tools v0.38.0/go.mod h1:yEsQ/d/YK8cjh0L6rZlY8tgtlKiBNTL14pGDJPJpYQs=
google.golang.org/protobuf v1.36.8 h1:xHScyCOEuuwZEc6UtSOvPbAT4zRh0xcNRYekJwfqyMc=
google.golang.org/protobuf v1.36.8/go.mod h1:fuxRtAxBytpl4zzqUh6/eyUujkJdNiuEkXntxiD/uRU=
gopkg.in/Knetic/govaluate.v3 v3.0.0/go.mod h1:csKLBORsPbafmSCGTEh3U7Ozmsuq8ZSIlKk1bcqph0E=
@@ -289,31 +285,5 @@ gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
modernc.org/cc/v4 v4.26.5 h1:xM3bX7Mve6G8K8b+T11ReenJOT+BmVqQj0FY5T4+5Y4=
modernc.org/cc/v4 v4.26.5/go.mod h1:uVtb5OGqUKpoLWhqwNQo/8LwvoiEBLvZXIQ/SmO6mL0=
modernc.org/ccgo/v4 v4.28.1 h1:wPKYn5EC/mYTqBO373jKjvX2n+3+aK7+sICCv4Fjy1A=
modernc.org/ccgo/v4 v4.28.1/go.mod h1:uD+4RnfrVgE6ec9NGguUNdhqzNIeeomeXf6CL0GTE5Q=
modernc.org/fileutil v1.3.40 h1:ZGMswMNc9JOCrcrakF1HrvmergNLAmxOPjizirpfqBA=
modernc.org/fileutil v1.3.40/go.mod h1:HxmghZSZVAz/LXcMNwZPA/DRrQZEVP9VX0V4LQGQFOc=
modernc.org/gc/v2 v2.6.5 h1:nyqdV8q46KvTpZlsw66kWqwXRHdjIlJOhG6kxiV/9xI=
modernc.org/gc/v2 v2.6.5/go.mod h1:YgIahr1ypgfe7chRuJi2gD7DBQiKSLMPgBQe9oIiito=
modernc.org/goabi0 v0.2.0 h1:HvEowk7LxcPd0eq6mVOAEMai46V+i7Jrj13t4AzuNks=
modernc.org/goabi0 v0.2.0/go.mod h1:CEFRnnJhKvWT1c1JTI3Avm+tgOWbkOu5oPA8eH8LnMI=
modernc.org/libc v1.66.10 h1:yZkb3YeLx4oynyR+iUsXsybsX4Ubx7MQlSYEw4yj59A=
modernc.org/libc v1.66.10/go.mod h1:8vGSEwvoUoltr4dlywvHqjtAqHBaw0j1jI7iFBTAr2I=
modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=
modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=
modernc.org/memory v1.11.0 h1:o4QC8aMQzmcwCK3t3Ux/ZHmwFPzE6hf2Y5LbkRs+hbI=
modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw=
modernc.org/opt v0.1.4 h1:2kNGMRiUjrp4LcaPuLY2PzUfqM/w9N23quVwhKt5Qm8=
modernc.org/opt v0.1.4/go.mod h1:03fq9lsNfvkYSfxrfUhZCWPk1lm4cq4N+Bh//bEtgns=
modernc.org/sortutil v1.2.1 h1:+xyoGf15mM3NMlPDnFqrteY07klSFxLElE2PVuWIJ7w=
modernc.org/sortutil v1.2.1/go.mod h1:7ZI3a3REbai7gzCLcotuw9AC4VZVpYMjDzETGsSMqJE=
modernc.org/sqlite v1.42.2 h1:7hkZUNJvJFN2PgfUdjni9Kbvd4ef4mNLOu0B9FGxM74=
modernc.org/sqlite v1.42.2/go.mod h1:+VkC6v3pLOAE0A0uVucQEcbVW0I5nHCeDaBf+DpsQT8=
modernc.org/strutil v1.2.1 h1:UneZBkQA+DX2Rp35KcM69cSsNES9ly8mQWD71HKlOA0=
modernc.org/strutil v1.2.1/go.mod h1:EHkiggD70koQxjVdSBM3JKM7k6L0FbGE5eymy9i3B9A=
modernc.org/token v1.1.0 h1:Xl7Ap9dKaEs5kLoOQeQmPWevfnk/DM5qcLcYlA8ys6Y=
modernc.org/token v1.1.0/go.mod h1:UGzOrNV1mAFSEB63lOFHIpNRUVMvYTc6yu1SMY/XTDM=
nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=
-34
View File
@@ -1,34 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta http-equiv="X-UA-Compatible" content="IE=edge" />
<title>ProxyPilot Installer</title>
<link rel="preconnect" href="https://fonts.googleapis.com" />
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600&display=swap" rel="stylesheet" />
<style>
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
html, body, #root {
height: 100%;
width: 100%;
overflow: hidden;
}
body {
font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
-webkit-font-smoothing: antialiased;
-moz-osx-font-smoothing: grayscale;
background: #0a0a0b;
}
</style>
</head>
<body>
<div id="root"></div>
<script type="module" src="/src/main.tsx"></script>
</body>
</html>
-1926
View File
File diff suppressed because it is too large Load Diff
-24
View File
@@ -1,24 +0,0 @@
{
"name": "proxypilot-installer-ui",
"private": true,
"version": "0.1.0",
"type": "module",
"scripts": {
"dev": "vite",
"build": "tsc -b && vite build",
"preview": "vite preview"
},
"dependencies": {
"react": "^18.3.1",
"react-dom": "^18.3.1",
"framer-motion": "^11.15.0"
},
"devDependencies": {
"@types/react": "^18.3.17",
"@types/react-dom": "^18.3.5",
"@vitejs/plugin-react": "^4.3.4",
"terser": "^5.37.0",
"typescript": "~5.6.2",
"vite": "^6.0.0"
}
}
Binary file not shown.

Before

Width:  |  Height:  |  Size: 194 KiB

-122
View File
@@ -1,122 +0,0 @@
import { useState, useEffect, useCallback } from 'react'
import { motion, AnimatePresence } from 'framer-motion'
import { WelcomeStep } from './components/WelcomeStep'
import { InstallingStep } from './components/InstallingStep'
import { CompleteStep } from './components/CompleteStep'
import { setProgressCallback } from './main'
type InstallStep = 'welcome' | 'installing' | 'complete'
function App() {
const [step, setStep] = useState<InstallStep>('welcome')
const [progress, setProgress] = useState(0)
const [status, setStatus] = useState('Preparing installation...')
const handleProgress = useCallback((percent: number, statusText: string) => {
setProgress(percent)
setStatus(statusText)
if (percent >= 100) {
setTimeout(() => setStep('complete'), 800)
}
}, [])
useEffect(() => {
setProgressCallback(handleProgress)
}, [handleProgress])
const handleInstall = () => {
setStep('installing')
setProgress(0)
setStatus('Preparing installation...')
window.installer.startInstall()
}
const handleLaunch = () => {
window.installer.launch()
}
const pageVariants = {
initial: {
opacity: 0,
y: 20
},
animate: {
opacity: 1,
y: 0,
transition: {
duration: 0.4,
ease: [0.25, 0.1, 0.25, 1]
}
},
exit: {
opacity: 0,
y: -20,
transition: {
duration: 0.3,
ease: [0.25, 0.1, 0.25, 1]
}
}
}
return (
<div className="app-container">
<main className="main-content">
<AnimatePresence mode="wait">
{step === 'welcome' && (
<motion.div
key="welcome"
variants={pageVariants}
initial="initial"
animate="animate"
exit="exit"
className="step-container"
>
<WelcomeStep onInstall={handleInstall} />
</motion.div>
)}
{step === 'installing' && (
<motion.div
key="installing"
variants={pageVariants}
initial="initial"
animate="animate"
exit="exit"
className="step-container"
>
<InstallingStep progress={progress} status={status} />
</motion.div>
)}
{step === 'complete' && (
<motion.div
key="complete"
variants={pageVariants}
initial="initial"
animate="animate"
exit="exit"
className="step-container"
>
<CompleteStep onLaunch={handleLaunch} />
</motion.div>
)}
</AnimatePresence>
</main>
{/* Window Controls */}
<div className="window-controls">
<button
className="window-btn"
onClick={() => window.installer.close()}
aria-label="Close"
>
<svg viewBox="0 0 10 10" fill="none">
<path d="M1 1L9 9M9 1L1 9" stroke="currentColor" strokeWidth="1.5" strokeLinecap="round"/>
</svg>
</button>
</div>
</div>
)
}
export default App
@@ -1,85 +0,0 @@
import { motion } from 'framer-motion'
interface CompleteStepProps {
onLaunch: () => void
}
export function CompleteStep({ onLaunch }: CompleteStepProps) {
return (
<div className="complete-step">
{/* Success Icon */}
<motion.div
className="success-icon-container"
initial={{ scale: 0 }}
animate={{ scale: 1 }}
transition={{
type: 'spring',
stiffness: 200,
damping: 15,
delay: 0.1
}}
>
<div className="success-icon">
<svg viewBox="0 0 24 24" fill="none">
<motion.path
d="M5 13l4 4L19 7"
stroke="currentColor"
strokeWidth="3"
strokeLinecap="round"
strokeLinejoin="round"
initial={{ pathLength: 0 }}
animate={{ pathLength: 1 }}
transition={{ duration: 0.4, delay: 0.3 }}
/>
</svg>
</div>
</motion.div>
{/* Success Content */}
<motion.div
className="success-content"
initial={{ opacity: 0, y: 10 }}
animate={{ opacity: 1, y: 0 }}
transition={{ delay: 0.4, duration: 0.4 }}
>
<h2 className="success-title">Installation Complete</h2>
<p className="success-message">
ProxyPilot has been installed successfully and is ready to use.
</p>
</motion.div>
{/* Launch Button */}
<motion.button
className="launch-btn"
onClick={onLaunch}
initial={{ opacity: 0, y: 10 }}
animate={{ opacity: 1, y: 0 }}
transition={{ delay: 0.5, duration: 0.4 }}
whileHover={{ scale: 1.02 }}
whileTap={{ scale: 0.98 }}
>
<svg viewBox="0 0 20 20" fill="none">
<path d="M4 10h12m0 0l-4-4m4 4l-4 4" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round"/>
</svg>
Launch ProxyPilot
</motion.button>
{/* Post Install Info */}
<motion.div
className="post-install-info"
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
transition={{ delay: 0.6, duration: 0.4 }}
>
<div className="info-icon">
<svg viewBox="0 0 16 16" fill="none">
<circle cx="8" cy="8" r="7" stroke="currentColor" strokeWidth="1.5"/>
<path d="M8 5v3" stroke="currentColor" strokeWidth="1.5" strokeLinecap="round"/>
<circle cx="8" cy="11" r="0.75" fill="currentColor"/>
</svg>
</div>
<p>ProxyPilot will start automatically and run in the system tray.</p>
</motion.div>
</div>
)
}
@@ -1,78 +0,0 @@
import { motion } from 'framer-motion'
interface InstallingStepProps {
progress: number
status: string
}
export function InstallingStep({ progress, status }: InstallingStepProps) {
const radius = 52
const circumference = 2 * Math.PI * radius
const strokeDashoffset = circumference - (circumference * progress) / 100
return (
<div className="installing-step">
{/* Progress Circle */}
<motion.div
className="progress-circle-container"
initial={{ scale: 0.8, opacity: 0 }}
animate={{ scale: 1, opacity: 1 }}
transition={{ duration: 0.5 }}
>
<svg className="progress-circle" viewBox="0 0 120 120">
<circle
className="progress-circle-bg"
cx="60"
cy="60"
r={radius}
/>
<motion.circle
className="progress-circle-fill"
cx="60"
cy="60"
r={radius}
strokeDasharray={circumference}
strokeDashoffset={strokeDashoffset}
initial={{ strokeDashoffset: circumference }}
animate={{ strokeDashoffset }}
transition={{ duration: 0.3, ease: 'easeOut' }}
/>
</svg>
<div className="progress-percent">
{Math.round(progress)}<span>%</span>
</div>
</motion.div>
{/* Progress Info */}
<motion.div
className="progress-info"
initial={{ opacity: 0, y: 10 }}
animate={{ opacity: 1, y: 0 }}
transition={{ delay: 0.2, duration: 0.4 }}
>
<h2 className="installing-title">Installing ProxyPilot</h2>
{/* Progress Bar */}
<div className="progress-bar-container">
<motion.div
className="progress-bar-fill"
initial={{ width: 0 }}
animate={{ width: `${progress}%` }}
transition={{ duration: 0.3, ease: 'easeOut' }}
/>
</div>
{/* Status */}
<motion.p
className="status-text"
key={status}
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
transition={{ duration: 0.2 }}
>
{status}
</motion.p>
</motion.div>
</div>
)
}
-104
View File
@@ -1,104 +0,0 @@
import { motion } from 'framer-motion'
interface WelcomeStepProps {
onInstall: () => void
}
export function WelcomeStep({ onInstall }: WelcomeStepProps) {
const features = [
{ icon: 'route', text: 'Route AI requests seamlessly' },
{ icon: 'config', text: 'One config, all providers' },
{ icon: 'shield', text: 'Privacy-first local processing' }
]
return (
<div className="welcome-step">
{/* Logo */}
<motion.div
className="logo-container"
initial={{ scale: 0.8, opacity: 0 }}
animate={{ scale: 1, opacity: 1 }}
transition={{ duration: 0.5, ease: [0.25, 0.1, 0.25, 1] }}
>
<img src="/logo.png" alt="ProxyPilot" />
</motion.div>
{/* Text Content */}
<motion.div
className="text-content"
initial={{ opacity: 0, y: 10 }}
animate={{ opacity: 1, y: 0 }}
transition={{ delay: 0.1, duration: 0.4 }}
>
<h1 className="app-name">ProxyPilot</h1>
<p className="app-tagline">Navigate AI with precision</p>
</motion.div>
{/* Features Card */}
<motion.div
className="features-card"
initial={{ opacity: 0, y: 10 }}
animate={{ opacity: 1, y: 0 }}
transition={{ delay: 0.2, duration: 0.4 }}
>
<div className="features">
{features.map((feature, i) => (
<motion.div
key={feature.icon}
className="feature"
initial={{ opacity: 0, x: -10 }}
animate={{ opacity: 1, x: 0 }}
transition={{ delay: 0.3 + i * 0.1, duration: 0.3 }}
>
<span className="feature-icon">
{feature.icon === 'route' && (
<svg viewBox="0 0 20 20" fill="currentColor">
<path fillRule="evenodd" d="M5.05 3.636a1 1 0 010 1.414 7 7 0 000 9.9 1 1 0 11-1.414 1.414 9 9 0 010-12.728 1 1 0 011.414 0zm9.9 0a1 1 0 011.414 0 9 9 0 010 12.728 1 1 0 11-1.414-1.414 7 7 0 000-9.9 1 1 0 010-1.414zM7.879 6.464a1 1 0 010 1.414 3 3 0 000 4.243 1 1 0 11-1.415 1.414 5 5 0 010-7.07 1 1 0 011.415 0zm4.242 0a1 1 0 011.415 0 5 5 0 010 7.072 1 1 0 01-1.415-1.415 3 3 0 000-4.242 1 1 0 010-1.415zM10 9a1 1 0 011 1v.01a1 1 0 11-2 0V10a1 1 0 011-1z" clipRule="evenodd"/>
</svg>
)}
{feature.icon === 'config' && (
<svg viewBox="0 0 20 20" fill="currentColor">
<path fillRule="evenodd" d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z" clipRule="evenodd"/>
</svg>
)}
{feature.icon === 'shield' && (
<svg viewBox="0 0 20 20" fill="currentColor">
<path fillRule="evenodd" d="M2.166 4.999A11.954 11.954 0 0010 1.944 11.954 11.954 0 0017.834 5c.11.65.166 1.32.166 2.001 0 5.225-3.34 9.67-8 11.317C5.34 16.67 2 12.225 2 7c0-.682.057-1.35.166-2.001zm11.541 3.708a1 1 0 00-1.414-1.414L9 10.586 7.707 9.293a1 1 0 00-1.414 1.414l2 2a1 1 0 001.414 0l4-4z" clipRule="evenodd"/>
</svg>
)}
</span>
<span>{feature.text}</span>
</motion.div>
))}
</div>
</motion.div>
{/* Install Button */}
<motion.button
className="install-btn"
onClick={onInstall}
initial={{ opacity: 0, y: 10 }}
animate={{ opacity: 1, y: 0 }}
transition={{ delay: 0.4, duration: 0.4 }}
whileHover={{ scale: 1.02 }}
whileTap={{ scale: 0.98 }}
>
<svg viewBox="0 0 20 20" fill="none">
<path d="M10 3v10m0 0l-4-4m4 4l4-4" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round"/>
<path d="M3 15v1a2 2 0 002 2h10a2 2 0 002-2v-1" stroke="currentColor" strokeWidth="2" strokeLinecap="round"/>
</svg>
Install ProxyPilot
</motion.button>
{/* Version */}
<motion.p
className="version-info"
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
transition={{ delay: 0.5, duration: 0.4 }}
>
v0.1.6
</motion.p>
</div>
)
}
-526
View File
@@ -1,526 +0,0 @@
/* ============================================
ProxyPilot Installer - Clean Professional Theme
Inspired by Perplexity Comet's minimal aesthetic
============================================ */
:root {
/* Dark theme colors */
--bg-primary: #0a0a0b;
--bg-secondary: #111113;
--bg-elevated: #18181b;
--bg-hover: #1f1f23;
/* Text colors */
--text-primary: #fafafa;
--text-secondary: #a1a1aa;
--text-muted: #71717a;
/* Accent - ProxyPilot blue */
--accent: #3b82f6;
--accent-hover: #2563eb;
--accent-glow: rgba(59, 130, 246, 0.15);
/* Success green */
--success: #22c55e;
--success-glow: rgba(34, 197, 94, 0.15);
/* Borders */
--border: rgba(255, 255, 255, 0.08);
--border-hover: rgba(255, 255, 255, 0.12);
/* Spacing */
--space-xs: 8px;
--space-sm: 12px;
--space-md: 16px;
--space-lg: 24px;
--space-xl: 32px;
--space-2xl: 48px;
/* Typography */
--font-sans: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
--font-mono: 'SF Mono', 'Fira Code', monospace;
/* Transitions */
--transition-fast: 150ms ease;
--transition-base: 200ms ease;
--transition-slow: 300ms ease;
}
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
html, body, #root {
height: 100%;
width: 100%;
overflow: hidden;
}
body {
font-family: var(--font-sans);
font-size: 14px;
line-height: 1.5;
color: var(--text-primary);
background: var(--bg-primary);
-webkit-font-smoothing: antialiased;
-moz-osx-font-smoothing: grayscale;
}
/* ============================================
App Container
============================================ */
.app-container {
height: 100%;
width: 100%;
display: flex;
flex-direction: column;
background: var(--bg-primary);
position: relative;
}
/* Subtle gradient background */
.app-container::before {
content: '';
position: absolute;
inset: 0;
background: radial-gradient(
ellipse 80% 50% at 50% -20%,
var(--accent-glow) 0%,
transparent 70%
);
pointer-events: none;
}
/* ============================================
Window Controls
============================================ */
.window-controls {
position: absolute;
top: var(--space-md);
right: var(--space-md);
z-index: 100;
-webkit-app-region: no-drag;
}
.window-btn {
width: 32px;
height: 32px;
border-radius: 8px;
border: none;
background: transparent;
color: var(--text-muted);
cursor: pointer;
display: flex;
align-items: center;
justify-content: center;
transition: all var(--transition-fast);
}
.window-btn:hover {
background: var(--bg-hover);
color: var(--text-primary);
}
.window-btn svg {
width: 12px;
height: 12px;
}
/* ============================================
Main Content
============================================ */
.main-content {
flex: 1;
display: flex;
align-items: center;
justify-content: center;
padding: var(--space-xl);
-webkit-app-region: drag;
}
.step-container {
width: 100%;
max-width: 400px;
-webkit-app-region: no-drag;
}
/* ============================================
Welcome Step
============================================ */
.welcome-step {
display: flex;
flex-direction: column;
align-items: center;
gap: var(--space-lg);
text-align: center;
}
/* Logo */
.logo-container {
width: 96px;
height: 96px;
border-radius: 24px;
overflow: hidden;
box-shadow:
0 0 0 1px var(--border),
0 8px 32px rgba(0, 0, 0, 0.4),
0 0 60px var(--accent-glow);
}
.logo-container img {
width: 100%;
height: 100%;
object-fit: cover;
}
/* Text content */
.text-content {
display: flex;
flex-direction: column;
gap: var(--space-xs);
}
.app-name {
font-size: 28px;
font-weight: 600;
color: var(--text-primary);
letter-spacing: -0.02em;
}
.app-tagline {
font-size: 15px;
color: var(--text-secondary);
}
/* Features */
.features-card {
width: 100%;
padding: var(--space-lg);
background: var(--bg-secondary);
border: 1px solid var(--border);
border-radius: 16px;
}
.features {
display: flex;
flex-direction: column;
gap: var(--space-sm);
}
.feature {
display: flex;
align-items: center;
gap: var(--space-sm);
font-size: 14px;
color: var(--text-secondary);
}
.feature-icon {
width: 20px;
height: 20px;
color: var(--accent);
flex-shrink: 0;
}
.feature-icon svg {
width: 100%;
height: 100%;
}
/* Install Button */
.install-btn {
width: 100%;
height: 48px;
border: none;
border-radius: 12px;
background: var(--accent);
color: white;
font-family: var(--font-sans);
font-size: 15px;
font-weight: 500;
cursor: pointer;
display: flex;
align-items: center;
justify-content: center;
gap: var(--space-xs);
transition: all var(--transition-fast);
}
.install-btn:hover {
background: var(--accent-hover);
transform: translateY(-1px);
}
.install-btn:active {
transform: translateY(0);
}
.install-btn svg {
width: 18px;
height: 18px;
}
/* Version */
.version-info {
font-size: 12px;
color: var(--text-muted);
font-family: var(--font-mono);
}
/* ============================================
Installing Step
============================================ */
.installing-step {
display: flex;
flex-direction: column;
align-items: center;
gap: var(--space-xl);
text-align: center;
}
/* Progress Circle */
.progress-circle-container {
position: relative;
width: 120px;
height: 120px;
}
.progress-circle {
width: 100%;
height: 100%;
transform: rotate(-90deg);
}
.progress-circle-bg {
fill: none;
stroke: var(--bg-elevated);
stroke-width: 8;
}
.progress-circle-fill {
fill: none;
stroke: var(--accent);
stroke-width: 8;
stroke-linecap: round;
transition: stroke-dashoffset var(--transition-slow);
}
.progress-percent {
position: absolute;
inset: 0;
display: flex;
align-items: center;
justify-content: center;
font-size: 28px;
font-weight: 600;
color: var(--text-primary);
}
.progress-percent span {
font-size: 16px;
color: var(--text-muted);
margin-left: 2px;
}
/* Progress Info */
.progress-info {
display: flex;
flex-direction: column;
gap: var(--space-md);
width: 100%;
}
.installing-title {
font-size: 20px;
font-weight: 600;
color: var(--text-primary);
}
/* Progress Bar */
.progress-bar-container {
width: 100%;
height: 6px;
background: var(--bg-elevated);
border-radius: 3px;
overflow: hidden;
}
.progress-bar-fill {
height: 100%;
background: var(--accent);
border-radius: 3px;
transition: width var(--transition-slow);
}
/* Status */
.status-text {
font-size: 14px;
color: var(--text-secondary);
min-height: 21px;
}
/* ============================================
Complete Step
============================================ */
.complete-step {
display: flex;
flex-direction: column;
align-items: center;
gap: var(--space-lg);
text-align: center;
}
/* Success Icon */
.success-icon-container {
width: 80px;
height: 80px;
border-radius: 50%;
background: var(--success-glow);
display: flex;
align-items: center;
justify-content: center;
}
.success-icon {
width: 48px;
height: 48px;
color: var(--success);
}
.success-icon svg {
width: 100%;
height: 100%;
}
/* Success Content */
.success-content {
display: flex;
flex-direction: column;
gap: var(--space-xs);
}
.success-title {
font-size: 24px;
font-weight: 600;
color: var(--text-primary);
}
.success-message {
font-size: 14px;
color: var(--text-secondary);
line-height: 1.6;
}
/* Launch Button */
.launch-btn {
width: 100%;
height: 48px;
border: none;
border-radius: 12px;
background: var(--success);
color: white;
font-family: var(--font-sans);
font-size: 15px;
font-weight: 500;
cursor: pointer;
display: flex;
align-items: center;
justify-content: center;
gap: var(--space-xs);
transition: all var(--transition-fast);
}
.launch-btn:hover {
filter: brightness(1.1);
transform: translateY(-1px);
}
.launch-btn:active {
transform: translateY(0);
}
.launch-btn svg {
width: 18px;
height: 18px;
}
/* Post Install Info */
.post-install-info {
display: flex;
align-items: center;
gap: var(--space-sm);
padding: var(--space-md);
background: var(--bg-secondary);
border: 1px solid var(--border);
border-radius: 12px;
width: 100%;
}
.info-icon {
width: 16px;
height: 16px;
color: var(--text-muted);
flex-shrink: 0;
}
.info-icon svg {
width: 100%;
height: 100%;
}
.post-install-info p {
font-size: 13px;
color: var(--text-muted);
text-align: left;
}
/* ============================================
Accessibility
============================================ */
@media (prefers-reduced-motion: reduce) {
* {
animation-duration: 0.01ms !important;
transition-duration: 0.01ms !important;
}
}
button:focus-visible {
outline: 2px solid var(--accent);
outline-offset: 2px;
}
/* ============================================
Responsive
============================================ */
@media (max-height: 400px) {
.main-content {
padding: var(--space-md);
}
.logo-container {
width: 72px;
height: 72px;
border-radius: 18px;
}
.welcome-step,
.installing-step,
.complete-step {
gap: var(--space-md);
}
.progress-circle-container {
width: 100px;
height: 100px;
}
}
-68
View File
@@ -1,68 +0,0 @@
import React from 'react'
import ReactDOM from 'react-dom/client'
import App from './App'
import './index.css'
// Type declarations for Go/WebView2 bridge
declare global {
interface Window {
installer: {
startInstall: (options?: { installPath?: string }) => void
launch: () => void
close: () => void
}
setProgress: (percent: number, status: string) => void
}
}
// Store progress callback for Go to call
let progressCallback: ((percent: number, status: string) => void) | null = null
export function setProgressCallback(callback: (percent: number, status: string) => void) {
progressCallback = callback
}
// Expose to Go backend
window.setProgress = (percent: number, status: string) => {
if (progressCallback) {
progressCallback(percent, status)
}
}
// Mock installer for development (will be replaced by WebView2 in production)
if (!window.installer) {
window.installer = {
startInstall: () => {
console.log('Mock: Starting installation...')
let progress = 0
const steps = [
'Preparing installation...',
'Extracting files...',
'Installing components...',
'Configuring ProxyPilot...',
'Finishing up...'
]
const interval = setInterval(() => {
progress += Math.random() * 15 + 5
if (progress >= 100) {
progress = 100
clearInterval(interval)
}
const stepIndex = Math.min(Math.floor(progress / 20), steps.length - 1)
window.setProgress(Math.round(progress), steps[stepIndex])
}, 500)
},
launch: () => {
console.log('Mock: Launching ProxyPilot...')
},
close: () => {
console.log('Mock: Closing installer...')
}
}
}
ReactDOM.createRoot(document.getElementById('root')!).render(
<React.StrictMode>
<App />
</React.StrictMode>
)
-24
View File
@@ -1,24 +0,0 @@
{
"compilerOptions": {
"target": "ES2020",
"useDefineForClassFields": true,
"lib": ["ES2020", "DOM", "DOM.Iterable"],
"module": "ESNext",
"skipLibCheck": true,
"moduleResolution": "bundler",
"allowImportingTsExtensions": true,
"resolveJsonModule": true,
"isolatedModules": true,
"noEmit": true,
"jsx": "react-jsx",
"strict": true,
"noUnusedLocals": true,
"noUnusedParameters": true,
"noFallthroughCasesInSwitch": true,
"forceConsistentCasingInFileNames": true
},
"include": ["src"],
"references": [{ "path": "./tsconfig.node.json" }]
}
-11
View File
@@ -1,11 +0,0 @@
{
"compilerOptions": {
"composite": true,
"skipLibCheck": true,
"module": "ESNext",
"moduleResolution": "bundler",
"allowSyntheticDefaultImports": true,
"strict": true
},
"include": ["vite.config.ts"]
}
File diff suppressed because one or more lines are too long
-1
View File
@@ -1 +0,0 @@
{"root":["./src/app.tsx","./src/main.tsx","./src/components/completestep.tsx","./src/components/installingstep.tsx","./src/components/welcomestep.tsx"],"version":"5.6.3"}
-2
View File
@@ -1,2 +0,0 @@
declare const _default: import("vite").UserConfig;
export default _default;
-28
View File
@@ -1,28 +0,0 @@
import { defineConfig } from 'vite';
import react from '@vitejs/plugin-react';
export default defineConfig({
plugins: [react()],
base: './',
build: {
outDir: 'dist',
assetsDir: 'assets',
emptyOutDir: true,
minify: 'terser',
terserOptions: {
compress: {
drop_console: true,
drop_debugger: true
}
},
rollupOptions: {
output: {
manualChunks: undefined,
inlineDynamicImports: true
}
}
},
server: {
port: 3000,
strictPort: true
}
});
-29
View File
@@ -1,29 +0,0 @@
import { defineConfig } from 'vite'
import react from '@vitejs/plugin-react'
export default defineConfig({
plugins: [react()],
base: './',
build: {
outDir: 'dist',
assetsDir: 'assets',
emptyOutDir: true,
minify: 'terser',
terserOptions: {
compress: {
drop_console: true,
drop_debugger: true
}
},
rollupOptions: {
output: {
manualChunks: undefined,
inlineDynamicImports: true
}
}
},
server: {
port: 3000,
strictPort: true
}
})
+2
View File
@@ -0,0 +1,2 @@
@echo off
"%LOCALAPPDATA%\Programs\Inno Setup 6\ISCC.exe" /DAppVersion=0.2.9 "%~dp0proxypilot.iss"
+54
View File
@@ -0,0 +1,54 @@
# Build ProxyPilot MSI installer using WiX v4
# Requires: dotnet tool install --global wix
param(
[string]$Version = "0.2.9",
[string]$SourceDir = "..\dist",
[string]$OutDir = "..\dist"
)
$ErrorActionPreference = "Stop"
# Resolve paths
$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
$SourceDir = Resolve-Path (Join-Path $ScriptDir $SourceDir)
$OutDir = Join-Path $ScriptDir $OutDir
# Ensure output directory exists
if (-not (Test-Path $OutDir)) {
New-Item -ItemType Directory -Path $OutDir -Force | Out-Null
}
$WxsFile = Join-Path $ScriptDir "proxypilot.wxs"
$MsiFile = Join-Path $OutDir "ProxyPilot-$Version.msi"
Write-Host "Building ProxyPilot MSI installer v$Version" -ForegroundColor Cyan
Write-Host "Source: $SourceDir"
Write-Host "Output: $MsiFile"
# Check WiX is installed
$wix = Get-Command wix -ErrorAction SilentlyContinue
if (-not $wix) {
Write-Host "WiX not found. Installing via dotnet..." -ForegroundColor Yellow
dotnet tool install --global wix
$env:PATH += ";$env:USERPROFILE\.dotnet\tools"
}
# Build the MSI
wix build `
-d SourceDir="$SourceDir" `
-d Version="$Version" `
-ext WixToolset.UI.wixext `
-o "$MsiFile" `
"$WxsFile"
if ($LASTEXITCODE -eq 0) {
Write-Host "`nMSI built successfully: $MsiFile" -ForegroundColor Green
# Show file size
$size = (Get-Item $MsiFile).Length / 1MB
Write-Host "Size: $([math]::Round($size, 2)) MB"
} else {
Write-Host "MSI build failed with exit code $LASTEXITCODE" -ForegroundColor Red
exit 1
}
+121
View File
@@ -0,0 +1,121 @@
<?xml version="1.0" encoding="utf-8"?>
<!--
ProxyPilot MSI Installer (WiX v4)
Build: wix build -o ProxyPilot.msi proxypilot.wxs
-->
<Wix xmlns="http://wixtoolset.org/schemas/v4/wxs"
xmlns:ui="http://wixtoolset.org/schemas/v4/wxs/ui">
<Package
Name="ProxyPilot"
Manufacturer="ProxyPilot"
Version="!(bind.FileVersion.ProxyPilot.exe)"
UpgradeCode="3D9053A0-3F6A-47D7-9D91-8BB1D1CC2A4F"
Scope="perUser">
<SummaryInformation
Description="ProxyPilot - Local API proxy for AI coding tools"
Manufacturer="ProxyPilot" />
<!-- Upgrade handling -->
<MajorUpgrade
DowngradeErrorMessage="A newer version of ProxyPilot is already installed."
Schedule="afterInstallInitialize" />
<!-- Media -->
<MediaTemplate EmbedCab="yes" CompressionLevel="high" />
<!-- Custom icon for Add/Remove Programs -->
<Icon Id="icon.ico" SourceFile="$(var.SourceDir)\icon.ico" />
<Property Id="ARPPRODUCTICON" Value="icon.ico" />
<Property Id="ARPHELPLINK" Value="https://github.com/Finesssee/ProxyPilot" />
<Property Id="ARPURLINFOABOUT" Value="https://github.com/Finesssee/ProxyPilot" />
<!-- Features -->
<Feature Id="MainFeature" Title="ProxyPilot" Level="1">
<ComponentGroupRef Id="ProductComponents" />
<ComponentGroupRef Id="StartMenuShortcuts" />
</Feature>
<Feature Id="AutoStart" Title="Start with Windows" Level="1">
<ComponentRef Id="AutoStartRegistry" />
</Feature>
<!-- Standard directories -->
<StandardDirectory Id="LocalAppDataFolder">
<Directory Id="INSTALLFOLDER" Name="ProxyPilot" />
</StandardDirectory>
<StandardDirectory Id="ProgramMenuFolder">
<Directory Id="ApplicationProgramsFolder" Name="ProxyPilot" />
</StandardDirectory>
<!-- Product components -->
<ComponentGroup Id="ProductComponents" Directory="INSTALLFOLDER">
<Component Id="ProxyPilot.exe" Guid="*">
<File Id="ProxyPilot.exe" Source="$(var.SourceDir)\ProxyPilot.exe" KeyPath="yes" />
</Component>
<Component Id="ProxyPilotTray.exe" Guid="*">
<File Id="ProxyPilotTray.exe" Source="$(var.SourceDir)\proxypilot-tray.exe" KeyPath="yes" />
</Component>
<Component Id="icon.ico" Guid="*">
<File Id="icon.ico" Source="$(var.SourceDir)\icon.ico" KeyPath="yes" />
</Component>
<Component Id="config.example.yaml" Guid="*">
<File Id="config.example.yaml" Source="$(var.SourceDir)\config.example.yaml" KeyPath="yes" />
</Component>
</ComponentGroup>
<!-- Start Menu shortcuts -->
<ComponentGroup Id="StartMenuShortcuts" Directory="ApplicationProgramsFolder">
<Component Id="AppShortcut" Guid="*">
<Shortcut Id="AppShortcut"
Name="ProxyPilot"
Description="ProxyPilot - Local API Proxy"
Target="[INSTALLFOLDER]proxypilot-tray.exe"
WorkingDirectory="INSTALLFOLDER"
Icon="icon.ico" />
<Shortcut Id="UninstallShortcut"
Name="Uninstall ProxyPilot"
Description="Uninstall ProxyPilot"
Target="[SystemFolder]msiexec.exe"
Arguments="/x [ProductCode]" />
<RemoveFolder Id="CleanUpShortCut" Directory="ApplicationProgramsFolder" On="uninstall" />
<RegistryValue Root="HKCU" Key="Software\ProxyPilot" Name="installed" Type="integer" Value="1" KeyPath="yes" />
</Component>
</ComponentGroup>
<!-- Auto-start registry -->
<Component Id="AutoStartRegistry" Directory="INSTALLFOLDER" Guid="*">
<RegistryValue
Root="HKCU"
Key="Software\Microsoft\Windows\CurrentVersion\Run"
Name="ProxyPilot"
Type="string"
Value="&quot;[INSTALLFOLDER]proxypilot-tray.exe&quot;"
KeyPath="yes" />
</Component>
<!-- Custom actions -->
<CustomAction Id="KillTray" Directory="SystemFolder" Execute="deferred" Impersonate="no" Return="ignore"
ExeCommand="taskkill.exe /F /IM proxypilot-tray.exe" />
<InstallExecuteSequence>
<Custom Action="KillTray" Before="RemoveFiles" Condition="Installed" />
</InstallExecuteSequence>
<!-- Launch after install -->
<CustomAction Id="LaunchApp"
FileRef="ProxyPilotTray.exe"
ExeCommand=""
Impersonate="yes"
Return="asyncNoWait" />
<ui:WixUI Id="WixUI_Minimal" />
</Package>
</Wix>
@@ -0,0 +1,24 @@
# Created using wingetcreate 1.6.0.0
# yaml-language-server: $schema=https://aka.ms/winget-manifest.installer.1.6.0.schema.json
PackageIdentifier: ProxyPilot.ProxyPilot
PackageVersion: 0.2.9
InstallerLocale: en-US
InstallerType: inno
Scope: user
InstallModes:
- interactive
- silent
- silentWithProgress
UpgradeBehavior: install
Commands:
- proxypilot
Installers:
- Architecture: x64
InstallerUrl: https://github.com/Finesssee/ProxyPilot/releases/download/v0.2.9/ProxyPilot-0.2.9-Setup.exe
InstallerSha256: # TODO: Add SHA256 hash after building
InstallerSwitches:
Silent: /VERYSILENT /SUPPRESSMSGBOXES /NORESTART
SilentWithProgress: /SILENT /SUPPRESSMSGBOXES /NORESTART
ManifestType: installer
ManifestVersion: 1.6.0
@@ -0,0 +1,41 @@
# Created using wingetcreate 1.6.0.0
# yaml-language-server: $schema=https://aka.ms/winget-manifest.locale.1.6.0.schema.json
PackageIdentifier: ProxyPilot.ProxyPilot
PackageVersion: 0.2.9
PackageLocale: en-US
Publisher: ProxyPilot
PublisherUrl: https://github.com/Finesssee/ProxyPilot
PublisherSupportUrl: https://github.com/Finesssee/ProxyPilot/issues
Author: Finessse
PackageName: ProxyPilot
PackageUrl: https://github.com/Finesssee/ProxyPilot
License: MIT
LicenseUrl: https://github.com/Finesssee/ProxyPilot/blob/main/LICENSE
Copyright: Copyright (c) 2024-2026 ProxyPilot Contributors
ShortDescription: Local API proxy for AI coding tools with OAuth, token refresh, and format translation.
Description: |
ProxyPilot is a powerful local API proxy that lets you use your existing Claude Code,
Codex, Gemini, Kiro, and Qwen subscriptions with any AI coding tool – no separate API keys required.
Features:
- 10 Auth Providers: Claude, Codex (OpenAI), Gemini, Kiro (AWS), Qwen, and more
- Universal API Translation: Auto-converts between OpenAI, Anthropic, and Gemini formats
- OAuth Integration: Browser-based login with automatic token refresh
- Multi-Account Support: Round-robin distribution with automatic failover
- System Tray: Native Windows tray app for quick access
- 60+ Management APIs: Full control via REST endpoints
Moniker: proxypilot
Tags:
- ai
- api
- claude
- codex
- developer
- gemini
- openai
- proxy
- cli
ReleaseNotesUrl: https://github.com/Finesssee/ProxyPilot/releases
ManifestType: defaultLocale
ManifestVersion: 1.6.0
@@ -0,0 +1,8 @@
# Created using wingetcreate 1.6.0.0
# yaml-language-server: $schema=https://aka.ms/winget-manifest.version.1.6.0.schema.json
PackageIdentifier: ProxyPilot.ProxyPilot
PackageVersion: 0.2.9
DefaultLocale: en-US
ManifestType: version
ManifestVersion: 1.6.0
@@ -1,22 +1,31 @@
package config
package configaccess
import (
"context"
"net/http"
"strings"
"sync"
sdkaccess "github.com/router-for-me/CLIProxyAPI/v6/sdk/access"
sdkconfig "github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
)
var registerOnce sync.Once
// Register ensures the config-access provider is available to the access manager.
func Register() {
registerOnce.Do(func() {
sdkaccess.RegisterProvider(sdkconfig.AccessProviderTypeConfigAPIKey, newProvider)
})
func Register(cfg *sdkconfig.SDKConfig) {
if cfg == nil {
sdkaccess.UnregisterProvider(sdkaccess.AccessProviderTypeConfigAPIKey)
return
}
keys := normalizeKeys(cfg.APIKeys)
if len(keys) == 0 {
sdkaccess.UnregisterProvider(sdkaccess.AccessProviderTypeConfigAPIKey)
return
}
sdkaccess.RegisterProvider(
sdkaccess.AccessProviderTypeConfigAPIKey,
newProvider(sdkaccess.DefaultAccessProviderName, keys),
)
}
type provider struct {
@@ -24,34 +33,31 @@ type provider struct {
keys map[string]struct{}
}
func newProvider(cfg *sdkconfig.AccessProvider, _ *sdkconfig.SDKConfig) (sdkaccess.Provider, error) {
name := cfg.Name
if name == "" {
name = sdkconfig.DefaultAccessProviderName
func newProvider(name string, keys []string) *provider {
providerName := strings.TrimSpace(name)
if providerName == "" {
providerName = sdkaccess.DefaultAccessProviderName
}
keys := make(map[string]struct{}, len(cfg.APIKeys))
for _, key := range cfg.APIKeys {
if key == "" {
continue
}
keys[key] = struct{}{}
keySet := make(map[string]struct{}, len(keys))
for _, key := range keys {
keySet[key] = struct{}{}
}
return &provider{name: name, keys: keys}, nil
return &provider{name: providerName, keys: keySet}
}
func (p *provider) Identifier() string {
if p == nil || p.name == "" {
return sdkconfig.DefaultAccessProviderName
return sdkaccess.DefaultAccessProviderName
}
return p.name
}
func (p *provider) Authenticate(_ context.Context, r *http.Request) (*sdkaccess.Result, error) {
func (p *provider) Authenticate(_ context.Context, r *http.Request) (*sdkaccess.Result, *sdkaccess.AuthError) {
if p == nil {
return nil, sdkaccess.ErrNotHandled
return nil, sdkaccess.NewNotHandledError()
}
if len(p.keys) == 0 {
return nil, sdkaccess.ErrNotHandled
return nil, sdkaccess.NewNotHandledError()
}
authHeader := r.Header.Get("Authorization")
authHeaderGoogle := r.Header.Get("X-Goog-Api-Key")
@@ -63,7 +69,7 @@ func (p *provider) Authenticate(_ context.Context, r *http.Request) (*sdkaccess.
queryAuthToken = r.URL.Query().Get("auth_token")
}
if authHeader == "" && authHeaderGoogle == "" && authHeaderAnthropic == "" && queryKey == "" && queryAuthToken == "" {
return nil, sdkaccess.ErrNoCredentials
return nil, sdkaccess.NewNoCredentialsError()
}
apiKey := extractBearerToken(authHeader)
@@ -94,7 +100,7 @@ func (p *provider) Authenticate(_ context.Context, r *http.Request) (*sdkaccess.
}
}
return nil, sdkaccess.ErrInvalidCredential
return nil, sdkaccess.NewInvalidCredentialError()
}
func extractBearerToken(header string) string {
@@ -110,3 +116,26 @@ func extractBearerToken(header string) string {
}
return strings.TrimSpace(parts[1])
}
func normalizeKeys(keys []string) []string {
if len(keys) == 0 {
return nil
}
normalized := make([]string, 0, len(keys))
seen := make(map[string]struct{}, len(keys))
for _, key := range keys {
trimmedKey := strings.TrimSpace(key)
if trimmedKey == "" {
continue
}
if _, exists := seen[trimmedKey]; exists {
continue
}
seen[trimmedKey] = struct{}{}
normalized = append(normalized, trimmedKey)
}
if len(normalized) == 0 {
return nil
}
return normalized
}
+127
View File
@@ -0,0 +1,127 @@
package access
import (
"fmt"
"reflect"
"sort"
"strings"
configaccess "github.com/router-for-me/CLIProxyAPI/v6/internal/access/config_access"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
sdkaccess "github.com/router-for-me/CLIProxyAPI/v6/sdk/access"
log "github.com/sirupsen/logrus"
)
// ReconcileProviders builds the desired provider list by reusing existing providers when possible
// and creating or removing providers only when their configuration changed. It returns the final
// ordered provider slice along with the identifiers of providers that were added, updated, or
// removed compared to the previous configuration.
func ReconcileProviders(oldCfg, newCfg *config.Config, existing []sdkaccess.Provider) (result []sdkaccess.Provider, added, updated, removed []string, err error) {
_ = oldCfg
if newCfg == nil {
return nil, nil, nil, nil, nil
}
result = sdkaccess.RegisteredProviders()
existingMap := make(map[string]sdkaccess.Provider, len(existing))
for _, provider := range existing {
providerID := identifierFromProvider(provider)
if providerID == "" {
continue
}
existingMap[providerID] = provider
}
finalIDs := make(map[string]struct{}, len(result))
isInlineProvider := func(id string) bool {
return strings.EqualFold(id, sdkaccess.DefaultAccessProviderName)
}
appendChange := func(list *[]string, id string) {
if isInlineProvider(id) {
return
}
*list = append(*list, id)
}
for _, provider := range result {
providerID := identifierFromProvider(provider)
if providerID == "" {
continue
}
finalIDs[providerID] = struct{}{}
existingProvider, exists := existingMap[providerID]
if !exists {
appendChange(&added, providerID)
continue
}
if !providerInstanceEqual(existingProvider, provider) {
appendChange(&updated, providerID)
}
}
for providerID := range existingMap {
if _, exists := finalIDs[providerID]; exists {
continue
}
appendChange(&removed, providerID)
}
sort.Strings(added)
sort.Strings(updated)
sort.Strings(removed)
return result, added, updated, removed, nil
}
// ApplyAccessProviders reconciles the configured access providers against the
// currently registered providers and updates the manager. It logs a concise
// summary of the detected changes and returns whether any provider changed.
func ApplyAccessProviders(manager *sdkaccess.Manager, oldCfg, newCfg *config.Config) (bool, error) {
if manager == nil || newCfg == nil {
return false, nil
}
existing := manager.Providers()
configaccess.Register(&newCfg.SDKConfig)
providers, added, updated, removed, err := ReconcileProviders(oldCfg, newCfg, existing)
if err != nil {
log.Errorf("failed to reconcile request auth providers: %v", err)
return false, fmt.Errorf("reconciling access providers: %w", err)
}
manager.SetProviders(providers)
if len(added)+len(updated)+len(removed) > 0 {
log.Debugf("auth providers reconciled (added=%d updated=%d removed=%d)", len(added), len(updated), len(removed))
log.Debugf("auth providers changes details - added=%v updated=%v removed=%v", added, updated, removed)
return true, nil
}
log.Debug("auth providers unchanged after config update")
return false, nil
}
func identifierFromProvider(provider sdkaccess.Provider) string {
if provider == nil {
return ""
}
return strings.TrimSpace(provider.Identifier())
}
func providerInstanceEqual(a, b sdkaccess.Provider) bool {
if a == nil || b == nil {
return a == nil && b == nil
}
if reflect.TypeOf(a) != reflect.TypeOf(b) {
return false
}
valueA := reflect.ValueOf(a)
valueB := reflect.ValueOf(b)
if valueA.Kind() == reflect.Pointer && valueB.Kind() == reflect.Pointer {
return valueA.Pointer() == valueB.Pointer()
}
return reflect.DeepEqual(a, b)
}
+80 -83
View File
@@ -1,83 +1,80 @@
package agentdebug
import (
"encoding/json"
"os"
"runtime"
"sync/atomic"
"time"
)
const defaultWindowsLogPath = `d:\code\ProxyPilot\.cursor\debug.log`
var seq uint64
type entry struct {
ID string `json:"id,omitempty"`
Timestamp int64 `json:"timestamp"`
Location string `json:"location"`
Message string `json:"message"`
Data map[string]any `json:"data,omitempty"`
SessionID string `json:"sessionId"`
RunID string `json:"runId"`
HypothesisID string `json:"hypothesisId"`
}
func Log(hypothesisID, location, message string, data map[string]any) {
logPath := os.Getenv("PROXYPILOT_AGENT_DEBUG_LOG_PATH")
if logPath == "" {
if runtime.GOOS != "windows" {
// Debug session is Windows-scoped; avoid hard-failing on other OS.
return
}
logPath = defaultWindowsLogPath
}
runID := os.Getenv("PROXYPILOT_AGENT_DEBUG_RUN_ID")
if runID == "" {
runID = "pre-fix"
}
now := time.Now()
id := atomic.AddUint64(&seq, 1)
b, err := json.Marshal(entry{
ID: "log_" + now.Format("20060102T150405.000") + "_" + fmtUint(id),
Timestamp: now.UnixMilli(),
Location: location,
Message: message,
Data: data,
SessionID: "debug-session",
RunID: runID,
HypothesisID: hypothesisID,
})
if err != nil {
return
}
f, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
if err != nil {
return
}
_, _ = f.Write(append(b, '\n'))
_ = f.Close()
}
func fmtUint(v uint64) string {
// tiny, allocation-light formatting; no need for strconv import in hot paths.
const digits = "0123456789"
if v == 0 {
return "0"
}
var buf [20]byte
i := len(buf)
for v > 0 {
i--
buf[i] = digits[v%10]
v /= 10
}
return string(buf[i:])
}
package agentdebug
import (
"encoding/json"
"os"
"runtime"
"sync/atomic"
"time"
)
const defaultWindowsLogPath = `d:\code\ProxyPilot\.cursor\debug.log`
var seq uint64
type entry struct {
ID string `json:"id,omitempty"`
Timestamp int64 `json:"timestamp"`
Location string `json:"location"`
Message string `json:"message"`
Data map[string]any `json:"data,omitempty"`
SessionID string `json:"sessionId"`
RunID string `json:"runId"`
HypothesisID string `json:"hypothesisId"`
}
func Log(hypothesisID, location, message string, data map[string]any) {
logPath := os.Getenv("PROXYPILOT_AGENT_DEBUG_LOG_PATH")
if logPath == "" {
if runtime.GOOS != "windows" {
// Debug session is Windows-scoped; avoid hard-failing on other OS.
return
}
logPath = defaultWindowsLogPath
}
runID := os.Getenv("PROXYPILOT_AGENT_DEBUG_RUN_ID")
if runID == "" {
runID = "pre-fix"
}
now := time.Now()
id := atomic.AddUint64(&seq, 1)
b, err := json.Marshal(entry{
ID: "log_" + now.Format("20060102T150405.000") + "_" + fmtUint(id),
Timestamp: now.UnixMilli(),
Location: location,
Message: message,
Data: data,
SessionID: "debug-session",
RunID: runID,
HypothesisID: hypothesisID,
})
if err != nil {
return
}
f, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
if err != nil {
return
}
_, _ = f.Write(append(b, '\n'))
_ = f.Close()
}
func fmtUint(v uint64) string {
// tiny, allocation-light formatting; no need for strconv import in hot paths.
const digits = "0123456789"
if v == 0 {
return "0"
}
var buf [20]byte
i := len(buf)
for v > 0 {
i--
buf[i] = digits[v%10]
v /= 10
}
return string(buf[i:])
}
-276
View File
@@ -1,276 +0,0 @@
package agents
import (
"fmt"
"os"
"os/exec"
"path/filepath"
"runtime"
"strings"
)
// AmazonQCLIHandler handles Amazon Q CLI detection and configuration.
// Amazon Q CLI is only available on Linux/macOS or via WSL on Windows.
// It stores tokens in a SQLite database at ~/.local/share/amazon-q/data.sqlite3
type AmazonQCLIHandler struct {
// wslDistro is the WSL distribution name (Windows only)
wslDistro string
// wslUser is the WSL username (Windows only)
wslUser string
}
// NewAmazonQCLIHandler creates a new Amazon Q CLI handler
func NewAmazonQCLIHandler() *AmazonQCLIHandler {
return &AmazonQCLIHandler{}
}
func (h *AmazonQCLIHandler) ID() string {
return "amazonq-cli"
}
func (h *AmazonQCLIHandler) Name() string {
return "Amazon Q CLI"
}
func (h *AmazonQCLIHandler) CanAutoConfigure() bool {
// Amazon Q CLI uses its own auth, no configuration needed from our side
return false
}
func (h *AmazonQCLIHandler) GetConfigPath() string {
if runtime.GOOS == "windows" {
// Return WSL path for display purposes
return "\\\\wsl$\\<distro>\\home\\<user>\\.local\\share\\amazon-q\\data.sqlite3"
}
homeDir, _ := os.UserHomeDir()
return filepath.Join(homeDir, ".local", "share", "amazon-q", "data.sqlite3")
}
// Detect checks if Amazon Q CLI is installed
func (h *AmazonQCLIHandler) Detect() (bool, error) {
if runtime.GOOS == "windows" {
return h.detectInWSL()
}
return h.detectNative()
}
// detectNative checks for q CLI on Linux/macOS
func (h *AmazonQCLIHandler) detectNative() (bool, error) {
// Check for 'q' binary in PATH
if _, err := exec.LookPath("q"); err == nil {
return true, nil
}
// Check common installation locations
homeDir, _ := os.UserHomeDir()
locations := []string{
filepath.Join(homeDir, ".local", "bin", "q"),
"/usr/local/bin/q",
}
for _, loc := range locations {
if _, err := os.Stat(loc); err == nil {
return true, nil
}
}
// Check for data directory (indicates Q CLI was installed and used)
dataDir := filepath.Join(homeDir, ".local", "share", "amazon-q")
if _, err := os.Stat(dataDir); err == nil {
return true, nil
}
return false, nil
}
// detectInWSL checks for q CLI within WSL
func (h *AmazonQCLIHandler) detectInWSL() (bool, error) {
// Check if WSL is available
if _, err := exec.LookPath("wsl"); err != nil {
return false, nil
}
// Get default WSL distro
distro, err := h.getDefaultWSLDistro()
if err != nil || distro == "" {
return false, nil
}
h.wslDistro = distro
// Get WSL username
user, err := h.getWSLUsername(distro)
if err != nil || user == "" {
return false, nil
}
h.wslUser = user
// Check for q CLI in WSL
cmd := exec.Command("wsl", "-d", distro, "--", "which", "q")
if err := cmd.Run(); err == nil {
return true, nil
}
// Check for common install locations in WSL
checkCmd := exec.Command("wsl", "-d", distro, "--", "test", "-f", fmt.Sprintf("/home/%s/.local/bin/q", user))
if err := checkCmd.Run(); err == nil {
return true, nil
}
// Check for data directory in WSL
dataCmd := exec.Command("wsl", "-d", distro, "--", "test", "-d", fmt.Sprintf("/home/%s/.local/share/amazon-q", user))
if err := dataCmd.Run(); err == nil {
return true, nil
}
return false, nil
}
// getDefaultWSLDistro returns the default WSL distribution name
func (h *AmazonQCLIHandler) getDefaultWSLDistro() (string, error) {
// First try to get default distro
cmd := exec.Command("wsl", "-l", "-q")
output, err := cmd.Output()
if err != nil {
return "", err
}
// Parse output - first line is usually the default distro
lines := strings.Split(strings.TrimSpace(string(output)), "\n")
for _, line := range lines {
// Clean up the line (remove null bytes from UTF-16 encoding on Windows)
line = strings.TrimSpace(line)
line = strings.ReplaceAll(line, "\x00", "")
if line != "" && line != "docker-desktop" && line != "docker-desktop-data" {
return line, nil
}
}
return "", fmt.Errorf("no WSL distribution found")
}
// getWSLUsername returns the default username in the WSL distribution
func (h *AmazonQCLIHandler) getWSLUsername(distro string) (string, error) {
cmd := exec.Command("wsl", "-d", distro, "--", "whoami")
output, err := cmd.Output()
if err != nil {
return "", err
}
return strings.TrimSpace(string(output)), nil
}
// IsConfigured checks if Amazon Q CLI is authenticated
func (h *AmazonQCLIHandler) IsConfigured(proxyURL string) (bool, error) {
// Check if the SQLite database exists with auth tokens
dbPath, err := h.GetDatabasePath()
if err != nil {
return false, nil
}
// Check if file exists
if _, err := os.Stat(dbPath); os.IsNotExist(err) {
return false, nil
}
// Database exists, assume configured (actual token validation happens in auth layer)
return true, nil
}
// GetDatabasePath returns the path to the Amazon Q SQLite database
func (h *AmazonQCLIHandler) GetDatabasePath() (string, error) {
if runtime.GOOS == "windows" {
if h.wslDistro == "" || h.wslUser == "" {
// Try to detect
distro, err := h.getDefaultWSLDistro()
if err != nil {
return "", fmt.Errorf("no WSL distribution found: %w", err)
}
h.wslDistro = distro
user, err := h.getWSLUsername(distro)
if err != nil {
return "", fmt.Errorf("failed to get WSL user: %w", err)
}
h.wslUser = user
}
// Windows UNC path to WSL filesystem
return fmt.Sprintf(`\\wsl$\%s\home\%s\.local\share\amazon-q\data.sqlite3`, h.wslDistro, h.wslUser), nil
}
homeDir, err := os.UserHomeDir()
if err != nil {
return "", err
}
return filepath.Join(homeDir, ".local", "share", "amazon-q", "data.sqlite3"), nil
}
// Enable is not supported for Amazon Q CLI (uses its own auth)
func (h *AmazonQCLIHandler) Enable(proxyURL string) ([]Change, error) {
return nil, fmt.Errorf("Amazon Q CLI uses its own authentication. Run 'q login' to authenticate")
}
// Disable is not supported for Amazon Q CLI
func (h *AmazonQCLIHandler) Disable(changes []Change) error {
// Nothing to disable - Q CLI manages its own auth
return nil
}
// GetInstructions returns instructions for Amazon Q CLI setup
func (h *AmazonQCLIHandler) GetInstructions(proxyURL string) string {
if runtime.GOOS == "windows" {
return `Amazon Q CLI is available via WSL on Windows.
To install and authenticate:
1. Open WSL (Ubuntu recommended)
2. Install Amazon Q CLI:
curl -sS https://desktop-release.q.us-east-1.amazonaws.com/latest/q-x86_64-linux.zip -o q.zip
unzip q.zip
./q/install.sh --no-confirm
3. Authenticate with AWS Builder ID:
q login
4. ProxyPilot will automatically detect and use your Amazon Q CLI tokens.
Note: Amazon Q CLI has separate usage quota from Kiro IDE.
`
}
return `To install and authenticate Amazon Q CLI:
1. Install Amazon Q CLI:
curl -sS https://desktop-release.q.us-east-1.amazonaws.com/latest/q-x86_64-linux.zip -o q.zip
unzip q.zip
./q/install.sh --no-confirm
2. Authenticate with AWS Builder ID:
q login
3. ProxyPilot will automatically detect and use your Amazon Q CLI tokens.
Note: Amazon Q CLI has separate usage quota from Kiro IDE.
`
}
// GetShellConfig returns shell profile configuration for Amazon Q CLI
func (h *AmazonQCLIHandler) GetShellConfig(proxyURL string) string {
return fmt.Sprintf(`# ProxyPilot - Amazon Q CLI Configuration
# Amazon Q CLI uses its own authentication via 'q login'.
# ProxyPilot automatically imports the tokens after you authenticate.
# To authenticate:
# q login
# ProxyPilot will detect and use the tokens automatically.
# No additional environment variables needed.
# Optional: For other OpenAI-compatible tools
export OPENAI_BASE_URL="%s/v1"
export OPENAI_API_KEY="proxypilot-local"
`, proxyURL)
}
// GetWSLInfo returns WSL distro and user information (for external use)
func (h *AmazonQCLIHandler) GetWSLInfo() (distro, user string) {
return h.wslDistro, h.wslUser
}
+1 -6
View File
@@ -254,18 +254,13 @@ func buildDroidModels(proxyURL string) []map[string]any {
// OpenAI latest
{"GPT 5.2", "gpt-5.2", "openai"},
{"GPT 5.2 Codex", "gpt-5.2-codex", "openai"},
{"GPT 5.1 Codex Max", "gpt-5.1-codex-max", "openai"},
{"GPT 5.3 Codex", "gpt-5.3-codex", "openai"},
// Kiro (AWS)
{"Kiro Claude Opus 4.5", "kiro-claude-opus-4-5", "kiro"},
{"Kiro Claude Sonnet 4.5", "kiro-claude-sonnet-4-5", "kiro"},
{"Kiro Claude Haiku 4.5", "kiro-claude-haiku-4-5", "kiro"},
// Amazon Q
{"Amazon Q Auto", "amazonq-auto", "amazonq"},
{"Amazon Q Claude Opus 4.5", "amazonq-claude-opus-4.5", "amazonq"},
{"Amazon Q Claude Sonnet 4.5", "amazonq-claude-sonnet-4.5", "amazonq"},
// GitHub Copilot
{"Copilot GPT 5.2", "gpt-5.2", "github-copilot"},
{"Copilot Claude Opus 4.5", "claude-opus-4.5", "github-copilot"},
-1
View File
@@ -101,7 +101,6 @@ func (m *Manager) registerDefaultHandlers() {
NewCursorHandler(),
NewOpenCodeHandler(),
NewFactoryDroidHandler(),
NewAmazonQCLIHandler(),
}
for _, h := range handlers {
+5 -5
View File
@@ -32,11 +32,11 @@ type AgentState struct {
// Change represents a single configuration change made to an agent
type Change struct {
Path string `json:"path"` // JSON path or config key (e.g., "env.ANTHROPIC_BASE_URL")
Original any `json:"original"` // Original value (nil if key didn't exist)
Applied any `json:"applied"` // Value applied by ProxyPilot
Type string `json:"type,omitempty"` // Type of change: "json", "toml", "env", "shell"
File string `json:"file,omitempty"` // Specific file if different from ConfigPath
Path string `json:"path"` // JSON path or config key (e.g., "env.ANTHROPIC_BASE_URL")
Original any `json:"original"` // Original value (nil if key didn't exist)
Applied any `json:"applied"` // Value applied by ProxyPilot
Type string `json:"type,omitempty"` // Type of change: "json", "toml", "env", "shell"
File string `json:"file,omitempty"` // Specific file if different from ConfigPath
}
// StateManager handles loading, saving, and manipulating ProxyPilot state
+5 -41
View File
@@ -5,7 +5,6 @@ import (
"encoding/json"
"fmt"
"io"
"net"
"net/http"
"net/url"
"strings"
@@ -14,8 +13,8 @@ import (
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/runtime/geminicli"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
"github.com/router-for-me/CLIProxyAPI/v6/sdk/proxyutil"
log "github.com/sirupsen/logrus"
"golang.org/x/net/proxy"
"golang.org/x/oauth2"
"golang.org/x/oauth2/google"
)
@@ -660,45 +659,10 @@ func (h *Handler) apiCallTransport(auth *coreauth.Auth) http.RoundTripper {
}
func buildProxyTransport(proxyStr string) *http.Transport {
proxyStr = strings.TrimSpace(proxyStr)
if proxyStr == "" {
transport, _, errBuild := proxyutil.BuildHTTPTransport(proxyStr)
if errBuild != nil {
log.WithError(errBuild).Debug("build proxy transport failed")
return nil
}
proxyURL, errParse := url.Parse(proxyStr)
if errParse != nil {
log.WithError(errParse).Debug("parse proxy URL failed")
return nil
}
if proxyURL.Scheme == "" || proxyURL.Host == "" {
log.Debug("proxy URL missing scheme/host")
return nil
}
if proxyURL.Scheme == "socks5" {
var proxyAuth *proxy.Auth
if proxyURL.User != nil {
username := proxyURL.User.Username()
password, _ := proxyURL.User.Password()
proxyAuth = &proxy.Auth{User: username, Password: password}
}
dialer, errSOCKS5 := proxy.SOCKS5("tcp", proxyURL.Host, proxyAuth, proxy.Direct)
if errSOCKS5 != nil {
log.WithError(errSOCKS5).Debug("create SOCKS5 dialer failed")
return nil
}
return &http.Transport{
Proxy: nil,
DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
return dialer.Dial(network, addr)
},
}
}
if proxyURL.Scheme == "http" || proxyURL.Scheme == "https" {
return &http.Transport{Proxy: http.ProxyURL(proxyURL)}
}
log.Debugf("unsupported proxy scheme: %s", proxyURL.Scheme)
return nil
return transport
}
@@ -2,172 +2,112 @@ package management
import (
"context"
"encoding/json"
"io"
"net/http"
"net/http/httptest"
"net/url"
"strings"
"sync"
"testing"
"time"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
sdkconfig "github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
)
type memoryAuthStore struct {
mu sync.Mutex
items map[string]*coreauth.Auth
}
func TestAPICallTransportDirectBypassesGlobalProxy(t *testing.T) {
t.Parallel()
func (s *memoryAuthStore) List(ctx context.Context) ([]*coreauth.Auth, error) {
_ = ctx
s.mu.Lock()
defer s.mu.Unlock()
out := make([]*coreauth.Auth, 0, len(s.items))
for _, a := range s.items {
out = append(out, a.Clone())
}
return out, nil
}
func (s *memoryAuthStore) Save(ctx context.Context, auth *coreauth.Auth) (string, error) {
_ = ctx
if auth == nil {
return "", nil
}
s.mu.Lock()
if s.items == nil {
s.items = make(map[string]*coreauth.Auth)
}
s.items[auth.ID] = auth.Clone()
s.mu.Unlock()
return auth.ID, nil
}
func (s *memoryAuthStore) Delete(ctx context.Context, id string) error {
_ = ctx
s.mu.Lock()
delete(s.items, id)
s.mu.Unlock()
return nil
}
func TestResolveTokenForAuth_Antigravity_RefreshesExpiredToken(t *testing.T) {
var callCount int
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
callCount++
if r.Method != http.MethodPost {
t.Fatalf("expected POST, got %s", r.Method)
}
if ct := r.Header.Get("Content-Type"); !strings.HasPrefix(ct, "application/x-www-form-urlencoded") {
t.Fatalf("unexpected content-type: %s", ct)
}
bodyBytes, _ := io.ReadAll(r.Body)
_ = r.Body.Close()
values, err := url.ParseQuery(string(bodyBytes))
if err != nil {
t.Fatalf("parse form: %v", err)
}
if values.Get("grant_type") != "refresh_token" {
t.Fatalf("unexpected grant_type: %s", values.Get("grant_type"))
}
if values.Get("refresh_token") != "rt" {
t.Fatalf("unexpected refresh_token: %s", values.Get("refresh_token"))
}
if values.Get("client_id") != antigravityOAuthClientID {
t.Fatalf("unexpected client_id: %s", values.Get("client_id"))
}
if values.Get("client_secret") != antigravityOAuthClientSecret {
t.Fatalf("unexpected client_secret")
}
w.Header().Set("Content-Type", "application/json")
_ = json.NewEncoder(w).Encode(map[string]any{
"access_token": "new-token",
"refresh_token": "rt2",
"expires_in": int64(3600),
"token_type": "Bearer",
})
}))
t.Cleanup(srv.Close)
originalURL := antigravityOAuthTokenURL
antigravityOAuthTokenURL = srv.URL
t.Cleanup(func() { antigravityOAuthTokenURL = originalURL })
store := &memoryAuthStore{}
manager := coreauth.NewManager(store, nil, nil)
auth := &coreauth.Auth{
ID: "antigravity-test.json",
FileName: "antigravity-test.json",
Provider: "antigravity",
Metadata: map[string]any{
"type": "antigravity",
"access_token": "old-token",
"refresh_token": "rt",
"expires_in": int64(3600),
"timestamp": time.Now().Add(-2 * time.Hour).UnixMilli(),
"expired": time.Now().Add(-1 * time.Hour).Format(time.RFC3339),
h := &Handler{
cfg: &config.Config{
SDKConfig: sdkconfig.SDKConfig{ProxyURL: "http://global-proxy.example.com:8080"},
},
}
if _, err := manager.Register(context.Background(), auth); err != nil {
t.Fatalf("register auth: %v", err)
transport := h.apiCallTransport(&coreauth.Auth{ProxyURL: "direct"})
httpTransport, ok := transport.(*http.Transport)
if !ok {
t.Fatalf("transport type = %T, want *http.Transport", transport)
}
if httpTransport.Proxy != nil {
t.Fatal("expected direct transport to disable proxy function")
}
}
func TestAPICallTransportInvalidAuthFallsBackToGlobalProxy(t *testing.T) {
t.Parallel()
h := &Handler{
cfg: &config.Config{
SDKConfig: sdkconfig.SDKConfig{ProxyURL: "http://global-proxy.example.com:8080"},
},
}
transport := h.apiCallTransport(&coreauth.Auth{ProxyURL: "bad-value"})
httpTransport, ok := transport.(*http.Transport)
if !ok {
t.Fatalf("transport type = %T, want *http.Transport", transport)
}
req, errRequest := http.NewRequest(http.MethodGet, "https://example.com", nil)
if errRequest != nil {
t.Fatalf("http.NewRequest returned error: %v", errRequest)
}
proxyURL, errProxy := httpTransport.Proxy(req)
if errProxy != nil {
t.Fatalf("httpTransport.Proxy returned error: %v", errProxy)
}
if proxyURL == nil || proxyURL.String() != "http://global-proxy.example.com:8080" {
t.Fatalf("proxy URL = %v, want http://global-proxy.example.com:8080", proxyURL)
}
}
func TestAuthByIndexDistinguishesSharedAPIKeysAcrossProviders(t *testing.T) {
t.Parallel()
manager := coreauth.NewManager(nil, nil, nil)
geminiAuth := &coreauth.Auth{
ID: "gemini:apikey:123",
Provider: "gemini",
Attributes: map[string]string{
"api_key": "shared-key",
},
}
compatAuth := &coreauth.Auth{
ID: "openai-compatibility:bohe:456",
Provider: "bohe",
Label: "bohe",
Attributes: map[string]string{
"api_key": "shared-key",
"compat_name": "bohe",
"provider_key": "bohe",
},
}
if _, errRegister := manager.Register(context.Background(), geminiAuth); errRegister != nil {
t.Fatalf("register gemini auth: %v", errRegister)
}
if _, errRegister := manager.Register(context.Background(), compatAuth); errRegister != nil {
t.Fatalf("register compat auth: %v", errRegister)
}
geminiIndex := geminiAuth.EnsureIndex()
compatIndex := compatAuth.EnsureIndex()
if geminiIndex == compatIndex {
t.Fatalf("shared api key produced duplicate auth_index %q", geminiIndex)
}
h := &Handler{authManager: manager}
token, err := h.resolveTokenForAuth(context.Background(), auth)
if err != nil {
t.Fatalf("resolveTokenForAuth: %v", err)
gotGemini := h.authByIndex(geminiIndex)
if gotGemini == nil {
t.Fatal("expected gemini auth by index")
}
if token != "new-token" {
t.Fatalf("expected refreshed token, got %q", token)
}
if callCount != 1 {
t.Fatalf("expected 1 refresh call, got %d", callCount)
if gotGemini.ID != geminiAuth.ID {
t.Fatalf("authByIndex(gemini) returned %q, want %q", gotGemini.ID, geminiAuth.ID)
}
updated, ok := manager.GetByID(auth.ID)
if !ok || updated == nil {
t.Fatalf("expected auth in manager after update")
gotCompat := h.authByIndex(compatIndex)
if gotCompat == nil {
t.Fatal("expected compat auth by index")
}
if got := tokenValueFromMetadata(updated.Metadata); got != "new-token" {
t.Fatalf("expected manager metadata updated, got %q", got)
}
}
func TestResolveTokenForAuth_Antigravity_SkipsRefreshWhenTokenValid(t *testing.T) {
var callCount int
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
callCount++
w.WriteHeader(http.StatusInternalServerError)
}))
t.Cleanup(srv.Close)
originalURL := antigravityOAuthTokenURL
antigravityOAuthTokenURL = srv.URL
t.Cleanup(func() { antigravityOAuthTokenURL = originalURL })
auth := &coreauth.Auth{
ID: "antigravity-valid.json",
FileName: "antigravity-valid.json",
Provider: "antigravity",
Metadata: map[string]any{
"type": "antigravity",
"access_token": "ok-token",
"expired": time.Now().Add(30 * time.Minute).Format(time.RFC3339),
},
}
h := &Handler{}
token, err := h.resolveTokenForAuth(context.Background(), auth)
if err != nil {
t.Fatalf("resolveTokenForAuth: %v", err)
}
if token != "ok-token" {
t.Fatalf("expected existing token, got %q", token)
}
if callCount != 0 {
t.Fatalf("expected no refresh calls, got %d", callCount)
if gotCompat.ID != compatAuth.ID {
t.Fatalf("authByIndex(compat) returned %q, want %q", gotCompat.ID, compatAuth.ID)
}
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,197 @@
package management
import (
"bytes"
"encoding/json"
"mime/multipart"
"net/http"
"net/http/httptest"
"net/url"
"os"
"path/filepath"
"testing"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
)
func TestUploadAuthFile_BatchMultipart(t *testing.T) {
t.Setenv("MANAGEMENT_PASSWORD", "")
gin.SetMode(gin.TestMode)
authDir := t.TempDir()
manager := coreauth.NewManager(nil, nil, nil)
h := NewHandlerWithoutConfigFilePath(&config.Config{AuthDir: authDir}, manager)
files := []struct {
name string
content string
}{
{name: "alpha.json", content: `{"type":"codex","email":"alpha@example.com"}`},
{name: "beta.json", content: `{"type":"claude","email":"beta@example.com"}`},
}
var body bytes.Buffer
writer := multipart.NewWriter(&body)
for _, file := range files {
part, err := writer.CreateFormFile("file", file.name)
if err != nil {
t.Fatalf("failed to create multipart file: %v", err)
}
if _, err = part.Write([]byte(file.content)); err != nil {
t.Fatalf("failed to write multipart content: %v", err)
}
}
if err := writer.Close(); err != nil {
t.Fatalf("failed to close multipart writer: %v", err)
}
rec := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(rec)
req := httptest.NewRequest(http.MethodPost, "/v0/management/auth-files", &body)
req.Header.Set("Content-Type", writer.FormDataContentType())
ctx.Request = req
h.UploadAuthFile(ctx)
if rec.Code != http.StatusOK {
t.Fatalf("expected upload status %d, got %d with body %s", http.StatusOK, rec.Code, rec.Body.String())
}
var payload map[string]any
if err := json.Unmarshal(rec.Body.Bytes(), &payload); err != nil {
t.Fatalf("failed to decode response: %v", err)
}
if got, ok := payload["uploaded"].(float64); !ok || int(got) != len(files) {
t.Fatalf("expected uploaded=%d, got %#v", len(files), payload["uploaded"])
}
for _, file := range files {
fullPath := filepath.Join(authDir, file.name)
data, err := os.ReadFile(fullPath)
if err != nil {
t.Fatalf("expected uploaded file %s to exist: %v", file.name, err)
}
if string(data) != file.content {
t.Fatalf("expected file %s content %q, got %q", file.name, file.content, string(data))
}
}
auths := manager.List()
if len(auths) != len(files) {
t.Fatalf("expected %d auth entries, got %d", len(files), len(auths))
}
}
func TestUploadAuthFile_BatchMultipart_InvalidJSONDoesNotOverwriteExistingFile(t *testing.T) {
t.Setenv("MANAGEMENT_PASSWORD", "")
gin.SetMode(gin.TestMode)
authDir := t.TempDir()
manager := coreauth.NewManager(nil, nil, nil)
h := NewHandlerWithoutConfigFilePath(&config.Config{AuthDir: authDir}, manager)
existingName := "alpha.json"
existingContent := `{"type":"codex","email":"alpha@example.com"}`
if err := os.WriteFile(filepath.Join(authDir, existingName), []byte(existingContent), 0o600); err != nil {
t.Fatalf("failed to seed existing auth file: %v", err)
}
files := []struct {
name string
content string
}{
{name: existingName, content: `{"type":"codex"`},
{name: "beta.json", content: `{"type":"claude","email":"beta@example.com"}`},
}
var body bytes.Buffer
writer := multipart.NewWriter(&body)
for _, file := range files {
part, err := writer.CreateFormFile("file", file.name)
if err != nil {
t.Fatalf("failed to create multipart file: %v", err)
}
if _, err = part.Write([]byte(file.content)); err != nil {
t.Fatalf("failed to write multipart content: %v", err)
}
}
if err := writer.Close(); err != nil {
t.Fatalf("failed to close multipart writer: %v", err)
}
rec := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(rec)
req := httptest.NewRequest(http.MethodPost, "/v0/management/auth-files", &body)
req.Header.Set("Content-Type", writer.FormDataContentType())
ctx.Request = req
h.UploadAuthFile(ctx)
if rec.Code != http.StatusMultiStatus {
t.Fatalf("expected upload status %d, got %d with body %s", http.StatusMultiStatus, rec.Code, rec.Body.String())
}
data, err := os.ReadFile(filepath.Join(authDir, existingName))
if err != nil {
t.Fatalf("expected existing auth file to remain readable: %v", err)
}
if string(data) != existingContent {
t.Fatalf("expected existing auth file to remain %q, got %q", existingContent, string(data))
}
betaData, err := os.ReadFile(filepath.Join(authDir, "beta.json"))
if err != nil {
t.Fatalf("expected valid auth file to be created: %v", err)
}
if string(betaData) != files[1].content {
t.Fatalf("expected beta auth file content %q, got %q", files[1].content, string(betaData))
}
}
func TestDeleteAuthFile_BatchQuery(t *testing.T) {
t.Setenv("MANAGEMENT_PASSWORD", "")
gin.SetMode(gin.TestMode)
authDir := t.TempDir()
files := []string{"alpha.json", "beta.json"}
for _, name := range files {
if err := os.WriteFile(filepath.Join(authDir, name), []byte(`{"type":"codex"}`), 0o600); err != nil {
t.Fatalf("failed to write auth file %s: %v", name, err)
}
}
manager := coreauth.NewManager(nil, nil, nil)
h := NewHandlerWithoutConfigFilePath(&config.Config{AuthDir: authDir}, manager)
h.tokenStore = &memoryAuthStore{}
rec := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(rec)
req := httptest.NewRequest(
http.MethodDelete,
"/v0/management/auth-files?name="+url.QueryEscape(files[0])+"&name="+url.QueryEscape(files[1]),
nil,
)
ctx.Request = req
h.DeleteAuthFile(ctx)
if rec.Code != http.StatusOK {
t.Fatalf("expected delete status %d, got %d with body %s", http.StatusOK, rec.Code, rec.Body.String())
}
var payload map[string]any
if err := json.Unmarshal(rec.Body.Bytes(), &payload); err != nil {
t.Fatalf("failed to decode response: %v", err)
}
if got, ok := payload["deleted"].(float64); !ok || int(got) != len(files) {
t.Fatalf("expected deleted=%d, got %#v", len(files), payload["deleted"])
}
for _, name := range files {
if _, err := os.Stat(filepath.Join(authDir, name)); !os.IsNotExist(err) {
t.Fatalf("expected auth file %s to be removed, stat err: %v", name, err)
}
}
}
@@ -0,0 +1,129 @@
package management
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"net/url"
"os"
"path/filepath"
"testing"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
)
func TestDeleteAuthFile_UsesAuthPathFromManager(t *testing.T) {
t.Setenv("MANAGEMENT_PASSWORD", "")
gin.SetMode(gin.TestMode)
tempDir := t.TempDir()
authDir := filepath.Join(tempDir, "auth")
externalDir := filepath.Join(tempDir, "external")
if errMkdirAuth := os.MkdirAll(authDir, 0o700); errMkdirAuth != nil {
t.Fatalf("failed to create auth dir: %v", errMkdirAuth)
}
if errMkdirExternal := os.MkdirAll(externalDir, 0o700); errMkdirExternal != nil {
t.Fatalf("failed to create external dir: %v", errMkdirExternal)
}
fileName := "codex-user@example.com-plus.json"
shadowPath := filepath.Join(authDir, fileName)
realPath := filepath.Join(externalDir, fileName)
if errWriteShadow := os.WriteFile(shadowPath, []byte(`{"type":"codex","email":"shadow@example.com"}`), 0o600); errWriteShadow != nil {
t.Fatalf("failed to write shadow file: %v", errWriteShadow)
}
if errWriteReal := os.WriteFile(realPath, []byte(`{"type":"codex","email":"real@example.com"}`), 0o600); errWriteReal != nil {
t.Fatalf("failed to write real file: %v", errWriteReal)
}
manager := coreauth.NewManager(nil, nil, nil)
record := &coreauth.Auth{
ID: "legacy/" + fileName,
FileName: fileName,
Provider: "codex",
Status: coreauth.StatusError,
Unavailable: true,
Attributes: map[string]string{
"path": realPath,
},
Metadata: map[string]any{
"type": "codex",
"email": "real@example.com",
},
}
if _, errRegister := manager.Register(context.Background(), record); errRegister != nil {
t.Fatalf("failed to register auth record: %v", errRegister)
}
h := NewHandlerWithoutConfigFilePath(&config.Config{AuthDir: authDir}, manager)
h.tokenStore = &memoryAuthStore{}
deleteRec := httptest.NewRecorder()
deleteCtx, _ := gin.CreateTestContext(deleteRec)
deleteReq := httptest.NewRequest(http.MethodDelete, "/v0/management/auth-files?name="+url.QueryEscape(fileName), nil)
deleteCtx.Request = deleteReq
h.DeleteAuthFile(deleteCtx)
if deleteRec.Code != http.StatusOK {
t.Fatalf("expected delete status %d, got %d with body %s", http.StatusOK, deleteRec.Code, deleteRec.Body.String())
}
if _, errStatReal := os.Stat(realPath); !os.IsNotExist(errStatReal) {
t.Fatalf("expected managed auth file to be removed, stat err: %v", errStatReal)
}
if _, errStatShadow := os.Stat(shadowPath); errStatShadow != nil {
t.Fatalf("expected shadow auth file to remain, stat err: %v", errStatShadow)
}
listRec := httptest.NewRecorder()
listCtx, _ := gin.CreateTestContext(listRec)
listReq := httptest.NewRequest(http.MethodGet, "/v0/management/auth-files", nil)
listCtx.Request = listReq
h.ListAuthFiles(listCtx)
if listRec.Code != http.StatusOK {
t.Fatalf("expected list status %d, got %d with body %s", http.StatusOK, listRec.Code, listRec.Body.String())
}
var listPayload map[string]any
if errUnmarshal := json.Unmarshal(listRec.Body.Bytes(), &listPayload); errUnmarshal != nil {
t.Fatalf("failed to decode list payload: %v", errUnmarshal)
}
filesRaw, ok := listPayload["files"].([]any)
if !ok {
t.Fatalf("expected files array, payload: %#v", listPayload)
}
if len(filesRaw) != 0 {
t.Fatalf("expected removed auth to be hidden from list, got %d entries", len(filesRaw))
}
}
func TestDeleteAuthFile_FallbackToAuthDirPath(t *testing.T) {
t.Setenv("MANAGEMENT_PASSWORD", "")
gin.SetMode(gin.TestMode)
authDir := t.TempDir()
fileName := "fallback-user.json"
filePath := filepath.Join(authDir, fileName)
if errWrite := os.WriteFile(filePath, []byte(`{"type":"codex"}`), 0o600); errWrite != nil {
t.Fatalf("failed to write auth file: %v", errWrite)
}
manager := coreauth.NewManager(nil, nil, nil)
h := NewHandlerWithoutConfigFilePath(&config.Config{AuthDir: authDir}, manager)
h.tokenStore = &memoryAuthStore{}
deleteRec := httptest.NewRecorder()
deleteCtx, _ := gin.CreateTestContext(deleteRec)
deleteReq := httptest.NewRequest(http.MethodDelete, "/v0/management/auth-files?name="+url.QueryEscape(fileName), nil)
deleteCtx.Request = deleteReq
h.DeleteAuthFile(deleteCtx)
if deleteRec.Code != http.StatusOK {
t.Fatalf("expected delete status %d, got %d with body %s", http.StatusOK, deleteRec.Code, deleteRec.Body.String())
}
if _, errStat := os.Stat(filePath); !os.IsNotExist(errStat) {
t.Fatalf("expected auth file to be removed from auth dir, stat err: %v", errStat)
}
}
@@ -2,6 +2,7 @@ package management
import (
"net/http"
"strconv"
"strings"
"time"
@@ -38,6 +39,19 @@ func (h *Handler) SetAuthPriority(c *gin.Context) {
}
auth.Priority = *req.Priority
if auth.Metadata == nil {
auth.Metadata = make(map[string]any)
}
if auth.Attributes == nil {
auth.Attributes = make(map[string]string)
}
if *req.Priority == 0 {
delete(auth.Metadata, "priority")
delete(auth.Attributes, "priority")
} else {
auth.Metadata["priority"] = *req.Priority
auth.Attributes["priority"] = strconv.Itoa(*req.Priority)
}
auth.UpdatedAt = time.Now()
updated, err := h.authManager.Update(c.Request.Context(), auth)
@@ -90,4 +90,3 @@ func (h *Handler) ResetAuthCooldown(c *gin.Context) {
}
c.JSON(http.StatusOK, gin.H{"updated": updated})
}
+109 -118
View File
@@ -12,17 +12,15 @@ import (
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
"github.com/router-for-me/CLIProxyAPI/v6/internal/routingdebug"
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
sdkconfig "github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
log "github.com/sirupsen/logrus"
"github.com/tidwall/gjson"
"gopkg.in/yaml.v3"
)
const (
latestReleaseURL = "https://api.github.com/repos/router-for-me/CLIProxyAPIPlus/releases/latest"
latestReleaseUserAgent = "CLIProxyAPIPlus"
latestReleaseURL = "https://api.github.com/repos/Finesssee/ProxyPilot/releases/latest"
latestReleaseUserAgent = "ProxyPilot"
)
func (h *Handler) GetConfig(c *gin.Context) {
@@ -30,90 +28,7 @@ func (h *Handler) GetConfig(c *gin.Context) {
c.JSON(200, gin.H{})
return
}
cfgCopy := *h.cfg
c.JSON(200, &cfgCopy)
}
// GetRoutingPreview returns a JSON description of how a given model would be normalised and routed.
//
// Query parameters:
// - model: required model identifier (may be alias, auto, or provider://model)
func (h *Handler) GetRoutingPreview(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(http.StatusServiceUnavailable, gin.H{"error": "unavailable", "message": "configuration not loaded"})
return
}
model := strings.TrimSpace(c.Query("model"))
if model == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing_model", "message": "provide model via ?model="})
return
}
preview, err := h.computeRoutingPreview(model)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "routing_error", "message": err.Error()})
return
}
c.JSON(http.StatusOK, preview)
}
// GetRoutingRecent returns a small ring buffer of recently routed requests using the runtime selection trace.
func (h *Handler) GetRoutingRecent(c *gin.Context) {
// Even if h or cfg are nil, routingdebug.Snapshot() is safe; this endpoint is purely diagnostic.
entries := routingdebug.Snapshot()
if len(entries) == 0 {
c.JSON(http.StatusOK, gin.H{"entries": []routingdebug.Entry{}})
return
}
c.JSON(http.StatusOK, gin.H{"entries": entries})
}
// PostRoutingPreview accepts a full request JSON (OpenAI/OpenAIResponses-compatible) and
// extracts the model name for routing preview.
func (h *Handler) PostRoutingPreview(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(http.StatusServiceUnavailable, gin.H{"error": "unavailable", "message": "configuration not loaded"})
return
}
body, err := io.ReadAll(io.LimitReader(c.Request.Body, 1<<20)) // 1 MiB safety cap
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid_body", "message": "cannot read request body"})
return
}
if !gjson.ValidBytes(body) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid_json", "message": "body is not valid JSON"})
return
}
// Try a few common shapes to extract the model name.
paths := []string{
"model", // standard OpenAI
"request.model", // some wrapper shapes
"response.model", // responses-style wrappers
}
var model string
for _, path := range paths {
v := gjson.GetBytes(body, path)
if v.Exists() && strings.TrimSpace(v.String()) != "" {
model = strings.TrimSpace(v.String())
break
}
}
if model == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing_model", "message": "could not find model field in JSON body"})
return
}
preview, err := h.computeRoutingPreview(model)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "routing_error", "message": err.Error(), "model": model})
return
}
c.JSON(http.StatusOK, gin.H{
"model": model,
"preview": preview,
})
c.JSON(200, h.cfg)
}
type releaseInfo struct {
@@ -226,24 +141,11 @@ func (h *Handler) PutConfigYAML(c *gin.Context) {
defer func() {
_ = os.Remove(tempFile)
}()
validatedCfg, err := config.LoadConfigOptional(tempFile, false)
_, err = config.LoadConfigOptional(tempFile, false)
if err != nil {
c.JSON(http.StatusUnprocessableEntity, gin.H{"error": "invalid_config", "message": err.Error()})
return
}
if validatedCfg == nil {
c.JSON(http.StatusUnprocessableEntity, gin.H{"error": "invalid_config", "message": "configuration is empty"})
return
}
if warnings, errValidate := config.ValidateConfig(validatedCfg); errValidate != nil {
c.JSON(http.StatusUnprocessableEntity, gin.H{"error": "invalid_config", "message": errValidate.Error()})
return
} else if len(warnings) > 0 {
// Surface warnings in logs; the response body will include them after successful persist.
for _, w := range warnings {
log.Warnf("config warning (management update): %s", w)
}
}
h.mu.Lock()
defer h.mu.Unlock()
if WriteConfig(h.configFilePath, body) != nil {
@@ -256,12 +158,9 @@ func (h *Handler) PutConfigYAML(c *gin.Context) {
c.JSON(http.StatusInternalServerError, gin.H{"error": "reload_failed", "message": err.Error()})
return
}
h.cfg = newCfg
resp := gin.H{"ok": true, "changed": []string{"config"}}
if warnings, errValidate := config.ValidateConfig(newCfg); errValidate == nil && len(warnings) > 0 {
resp["warnings"] = warnings
}
c.JSON(http.StatusOK, resp)
h.cfg = cloneConfig(newCfg)
h.committedCfg = cloneConfig(h.cfg)
c.JSON(http.StatusOK, gin.H{"ok": true, "changed": []string{"config"}})
}
// GetConfigYAML returns the raw config.yaml file bytes without re-encoding.
@@ -285,14 +184,16 @@ func (h *Handler) GetConfigYAML(c *gin.Context) {
// Debug
func (h *Handler) GetDebug(c *gin.Context) { c.JSON(200, gin.H{"debug": h.cfg.Debug}) }
func (h *Handler) PutDebug(c *gin.Context) { h.updateBoolField(c, func(v bool) { h.cfg.Debug = v }) }
func (h *Handler) PutDebug(c *gin.Context) {
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.Debug = v })
}
// UsageStatisticsEnabled
func (h *Handler) GetUsageStatisticsEnabled(c *gin.Context) {
c.JSON(200, gin.H{"usage-statistics-enabled": h.cfg.UsageStatisticsEnabled})
}
func (h *Handler) PutUsageStatisticsEnabled(c *gin.Context) {
h.updateBoolField(c, func(v bool) { h.cfg.UsageStatisticsEnabled = v })
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.UsageStatisticsEnabled = v })
}
// UsageStatisticsEnabled
@@ -300,13 +201,55 @@ func (h *Handler) GetLoggingToFile(c *gin.Context) {
c.JSON(200, gin.H{"logging-to-file": h.cfg.LoggingToFile})
}
func (h *Handler) PutLoggingToFile(c *gin.Context) {
h.updateBoolField(c, func(v bool) { h.cfg.LoggingToFile = v })
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.LoggingToFile = v })
}
// LogsMaxTotalSizeMB
func (h *Handler) GetLogsMaxTotalSizeMB(c *gin.Context) {
c.JSON(200, gin.H{"logs-max-total-size-mb": h.cfg.LogsMaxTotalSizeMB})
}
func (h *Handler) PutLogsMaxTotalSizeMB(c *gin.Context) {
var body struct {
Value *int `json:"value"`
}
if errBindJSON := c.ShouldBindJSON(&body); errBindJSON != nil || body.Value == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
return
}
value := *body.Value
if value < 0 {
value = 0
}
h.mutateConfig(c, func(cfg *config.Config) {
cfg.LogsMaxTotalSizeMB = value
})
}
// ErrorLogsMaxFiles
func (h *Handler) GetErrorLogsMaxFiles(c *gin.Context) {
c.JSON(200, gin.H{"error-logs-max-files": h.cfg.ErrorLogsMaxFiles})
}
func (h *Handler) PutErrorLogsMaxFiles(c *gin.Context) {
var body struct {
Value *int `json:"value"`
}
if errBindJSON := c.ShouldBindJSON(&body); errBindJSON != nil || body.Value == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
return
}
value := *body.Value
if value < 0 {
value = 10
}
h.mutateConfig(c, func(cfg *config.Config) {
cfg.ErrorLogsMaxFiles = value
})
}
// Request log
func (h *Handler) GetRequestLog(c *gin.Context) { c.JSON(200, gin.H{"request-log": h.cfg.RequestLog}) }
func (h *Handler) PutRequestLog(c *gin.Context) {
h.updateBoolField(c, func(v bool) { h.cfg.RequestLog = v })
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.RequestLog = v })
}
// Websocket auth
@@ -314,7 +257,7 @@ func (h *Handler) GetWebsocketAuth(c *gin.Context) {
c.JSON(200, gin.H{"ws-auth": h.cfg.WebsocketAuth})
}
func (h *Handler) PutWebsocketAuth(c *gin.Context) {
h.updateBoolField(c, func(v bool) { h.cfg.WebsocketAuth = v })
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.WebsocketAuth = v })
}
// Request retry
@@ -322,7 +265,7 @@ func (h *Handler) GetRequestRetry(c *gin.Context) {
c.JSON(200, gin.H{"request-retry": h.cfg.RequestRetry})
}
func (h *Handler) PutRequestRetry(c *gin.Context) {
h.updateIntField(c, func(v int) { h.cfg.RequestRetry = v })
h.updateIntField(c, func(cfg *config.Config, v int) { cfg.RequestRetry = v })
}
// Max retry interval
@@ -330,15 +273,63 @@ func (h *Handler) GetMaxRetryInterval(c *gin.Context) {
c.JSON(200, gin.H{"max-retry-interval": h.cfg.MaxRetryInterval})
}
func (h *Handler) PutMaxRetryInterval(c *gin.Context) {
h.updateIntField(c, func(v int) { h.cfg.MaxRetryInterval = v })
h.updateIntField(c, func(cfg *config.Config, v int) { cfg.MaxRetryInterval = v })
}
// ForceModelPrefix
func (h *Handler) GetForceModelPrefix(c *gin.Context) {
c.JSON(200, gin.H{"force-model-prefix": h.cfg.ForceModelPrefix})
}
func (h *Handler) PutForceModelPrefix(c *gin.Context) {
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.ForceModelPrefix = v })
}
func normalizeRoutingStrategy(strategy string) (string, bool) {
normalized := strings.ToLower(strings.TrimSpace(strategy))
switch normalized {
case "", "round-robin", "roundrobin", "rr":
return "round-robin", true
case "fill-first", "fillfirst", "ff":
return "fill-first", true
default:
return "", false
}
}
// RoutingStrategy
func (h *Handler) GetRoutingStrategy(c *gin.Context) {
strategy, ok := normalizeRoutingStrategy(h.cfg.Routing.Strategy)
if !ok {
c.JSON(200, gin.H{"strategy": strings.TrimSpace(h.cfg.Routing.Strategy)})
return
}
c.JSON(200, gin.H{"strategy": strategy})
}
func (h *Handler) PutRoutingStrategy(c *gin.Context) {
var body struct {
Value *string `json:"value"`
}
if errBindJSON := c.ShouldBindJSON(&body); errBindJSON != nil || body.Value == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
return
}
normalized, ok := normalizeRoutingStrategy(*body.Value)
if !ok {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid strategy"})
return
}
h.mutateConfig(c, func(cfg *config.Config) {
cfg.Routing.Strategy = normalized
})
}
// Proxy URL
func (h *Handler) GetProxyURL(c *gin.Context) { c.JSON(200, gin.H{"proxy-url": h.cfg.ProxyURL}) }
func (h *Handler) PutProxyURL(c *gin.Context) {
h.updateStringField(c, func(v string) { h.cfg.ProxyURL = v })
h.updateStringField(c, func(cfg *config.Config, v string) { cfg.ProxyURL = v })
}
func (h *Handler) DeleteProxyURL(c *gin.Context) {
h.cfg.ProxyURL = ""
h.persist(c)
h.mutateConfig(c, func(cfg *config.Config) {
cfg.ProxyURL = ""
})
}
@@ -109,14 +109,13 @@ func (h *Handler) GetAPIKeys(c *gin.Context) { c.JSON(200, gin.H{"api-keys": h.c
func (h *Handler) PutAPIKeys(c *gin.Context) {
h.putStringList(c, func(v []string) {
h.cfg.APIKeys = append([]string(nil), v...)
h.cfg.Access.Providers = nil
}, nil)
}
func (h *Handler) PatchAPIKeys(c *gin.Context) {
h.patchStringList(c, &h.cfg.APIKeys, func() { h.cfg.Access.Providers = nil })
h.patchStringList(c, &h.cfg.APIKeys, func() {})
}
func (h *Handler) DeleteAPIKeys(c *gin.Context) {
h.deleteFromStringList(c, &h.cfg.APIKeys, func() { h.cfg.Access.Providers = nil })
h.deleteFromStringList(c, &h.cfg.APIKeys, func() {})
}
// gemini-api-key: []GeminiKey
@@ -487,6 +486,145 @@ func (h *Handler) DeleteOpenAICompat(c *gin.Context) {
c.JSON(400, gin.H{"error": "missing name or index"})
}
// vertex-api-key: []VertexCompatKey
func (h *Handler) GetVertexCompatKeys(c *gin.Context) {
c.JSON(200, gin.H{"vertex-api-key": h.cfg.VertexCompatAPIKey})
}
func (h *Handler) PutVertexCompatKeys(c *gin.Context) {
data, err := c.GetRawData()
if err != nil {
c.JSON(400, gin.H{"error": "failed to read body"})
return
}
var arr []config.VertexCompatKey
if err = json.Unmarshal(data, &arr); err != nil {
var obj struct {
Items []config.VertexCompatKey `json:"items"`
}
if err2 := json.Unmarshal(data, &obj); err2 != nil || len(obj.Items) == 0 {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
arr = obj.Items
}
for i := range arr {
normalizeVertexCompatKey(&arr[i])
if arr[i].APIKey == "" {
c.JSON(400, gin.H{"error": fmt.Sprintf("vertex-api-key[%d].api-key is required", i)})
return
}
}
h.cfg.VertexCompatAPIKey = append([]config.VertexCompatKey(nil), arr...)
h.cfg.SanitizeVertexCompatKeys()
h.persist(c)
}
func (h *Handler) PatchVertexCompatKey(c *gin.Context) {
type vertexCompatPatch struct {
APIKey *string `json:"api-key"`
Prefix *string `json:"prefix"`
BaseURL *string `json:"base-url"`
ProxyURL *string `json:"proxy-url"`
Headers *map[string]string `json:"headers"`
Models *[]config.VertexCompatModel `json:"models"`
ExcludedModels *[]string `json:"excluded-models"`
}
var body struct {
Index *int `json:"index"`
Match *string `json:"match"`
Value *vertexCompatPatch `json:"value"`
}
if errBindJSON := c.ShouldBindJSON(&body); errBindJSON != nil || body.Value == nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
targetIndex := -1
if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.VertexCompatAPIKey) {
targetIndex = *body.Index
}
if targetIndex == -1 && body.Match != nil {
match := strings.TrimSpace(*body.Match)
if match != "" {
for i := range h.cfg.VertexCompatAPIKey {
if h.cfg.VertexCompatAPIKey[i].APIKey == match {
targetIndex = i
break
}
}
}
}
if targetIndex == -1 {
c.JSON(404, gin.H{"error": "item not found"})
return
}
entry := h.cfg.VertexCompatAPIKey[targetIndex]
if body.Value.APIKey != nil {
trimmed := strings.TrimSpace(*body.Value.APIKey)
if trimmed == "" {
h.cfg.VertexCompatAPIKey = append(h.cfg.VertexCompatAPIKey[:targetIndex], h.cfg.VertexCompatAPIKey[targetIndex+1:]...)
h.cfg.SanitizeVertexCompatKeys()
h.persist(c)
return
}
entry.APIKey = trimmed
}
if body.Value.Prefix != nil {
entry.Prefix = strings.TrimSpace(*body.Value.Prefix)
}
if body.Value.BaseURL != nil {
trimmed := strings.TrimSpace(*body.Value.BaseURL)
if trimmed == "" {
h.cfg.VertexCompatAPIKey = append(h.cfg.VertexCompatAPIKey[:targetIndex], h.cfg.VertexCompatAPIKey[targetIndex+1:]...)
h.cfg.SanitizeVertexCompatKeys()
h.persist(c)
return
}
entry.BaseURL = trimmed
}
if body.Value.ProxyURL != nil {
entry.ProxyURL = strings.TrimSpace(*body.Value.ProxyURL)
}
if body.Value.Headers != nil {
entry.Headers = config.NormalizeHeaders(*body.Value.Headers)
}
if body.Value.Models != nil {
entry.Models = append([]config.VertexCompatModel(nil), (*body.Value.Models)...)
}
if body.Value.ExcludedModels != nil {
entry.ExcludedModels = config.NormalizeExcludedModels(*body.Value.ExcludedModels)
}
normalizeVertexCompatKey(&entry)
h.cfg.VertexCompatAPIKey[targetIndex] = entry
h.cfg.SanitizeVertexCompatKeys()
h.persist(c)
}
func (h *Handler) DeleteVertexCompatKey(c *gin.Context) {
if val := strings.TrimSpace(c.Query("api-key")); val != "" {
out := make([]config.VertexCompatKey, 0, len(h.cfg.VertexCompatAPIKey))
for _, v := range h.cfg.VertexCompatAPIKey {
if v.APIKey != val {
out = append(out, v)
}
}
h.cfg.VertexCompatAPIKey = out
h.cfg.SanitizeVertexCompatKeys()
h.persist(c)
return
}
if idxStr := c.Query("index"); idxStr != "" {
var idx int
_, errScan := fmt.Sscanf(idxStr, "%d", &idx)
if errScan == nil && idx >= 0 && idx < len(h.cfg.VertexCompatAPIKey) {
h.cfg.VertexCompatAPIKey = append(h.cfg.VertexCompatAPIKey[:idx], h.cfg.VertexCompatAPIKey[idx+1:]...)
h.cfg.SanitizeVertexCompatKeys()
h.persist(c)
return
}
}
c.JSON(400, gin.H{"error": "missing api-key or index"})
}
// oauth-excluded-models: map[string][]string
func (h *Handler) GetOAuthExcludedModels(c *gin.Context) {
c.JSON(200, gin.H{"oauth-excluded-models": config.NormalizeOAuthExcludedModels(h.cfg.OAuthExcludedModels)})
@@ -572,6 +710,103 @@ func (h *Handler) DeleteOAuthExcludedModels(c *gin.Context) {
h.persist(c)
}
// oauth-model-alias: map[string][]OAuthModelAlias
func (h *Handler) GetOAuthModelAlias(c *gin.Context) {
c.JSON(200, gin.H{"oauth-model-alias": sanitizedOAuthModelAlias(h.cfg.OAuthModelAlias)})
}
func (h *Handler) PutOAuthModelAlias(c *gin.Context) {
data, err := c.GetRawData()
if err != nil {
c.JSON(400, gin.H{"error": "failed to read body"})
return
}
var entries map[string][]config.OAuthModelAlias
if err = json.Unmarshal(data, &entries); err != nil {
var wrapper struct {
Items map[string][]config.OAuthModelAlias `json:"items"`
}
if err2 := json.Unmarshal(data, &wrapper); err2 != nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
entries = wrapper.Items
}
h.cfg.OAuthModelAlias = sanitizedOAuthModelAlias(entries)
h.persist(c)
}
func (h *Handler) PatchOAuthModelAlias(c *gin.Context) {
var body struct {
Provider *string `json:"provider"`
Channel *string `json:"channel"`
Aliases []config.OAuthModelAlias `json:"aliases"`
}
if errBindJSON := c.ShouldBindJSON(&body); errBindJSON != nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
channelRaw := ""
if body.Channel != nil {
channelRaw = *body.Channel
} else if body.Provider != nil {
channelRaw = *body.Provider
}
channel := strings.ToLower(strings.TrimSpace(channelRaw))
if channel == "" {
c.JSON(400, gin.H{"error": "invalid channel"})
return
}
normalizedMap := sanitizedOAuthModelAlias(map[string][]config.OAuthModelAlias{channel: body.Aliases})
normalized := normalizedMap[channel]
if len(normalized) == 0 {
if h.cfg.OAuthModelAlias == nil {
c.JSON(404, gin.H{"error": "channel not found"})
return
}
if _, ok := h.cfg.OAuthModelAlias[channel]; !ok {
c.JSON(404, gin.H{"error": "channel not found"})
return
}
delete(h.cfg.OAuthModelAlias, channel)
if len(h.cfg.OAuthModelAlias) == 0 {
h.cfg.OAuthModelAlias = nil
}
h.persist(c)
return
}
if h.cfg.OAuthModelAlias == nil {
h.cfg.OAuthModelAlias = make(map[string][]config.OAuthModelAlias)
}
h.cfg.OAuthModelAlias[channel] = normalized
h.persist(c)
}
func (h *Handler) DeleteOAuthModelAlias(c *gin.Context) {
channel := strings.ToLower(strings.TrimSpace(c.Query("channel")))
if channel == "" {
channel = strings.ToLower(strings.TrimSpace(c.Query("provider")))
}
if channel == "" {
c.JSON(400, gin.H{"error": "missing channel"})
return
}
if h.cfg.OAuthModelAlias == nil {
c.JSON(404, gin.H{"error": "channel not found"})
return
}
if _, ok := h.cfg.OAuthModelAlias[channel]; !ok {
c.JSON(404, gin.H{"error": "channel not found"})
return
}
delete(h.cfg.OAuthModelAlias, channel)
if len(h.cfg.OAuthModelAlias) == 0 {
h.cfg.OAuthModelAlias = nil
}
h.persist(c)
}
// codex-api-key: []CodexKey
func (h *Handler) GetCodexKeys(c *gin.Context) {
c.JSON(200, gin.H{"codex-api-key": h.cfg.CodexKey})
@@ -788,3 +1023,351 @@ func normalizeCodexKey(entry *config.CodexKey) {
}
entry.Models = normalized
}
func normalizeVertexCompatKey(entry *config.VertexCompatKey) {
if entry == nil {
return
}
entry.APIKey = strings.TrimSpace(entry.APIKey)
entry.Prefix = strings.TrimSpace(entry.Prefix)
entry.BaseURL = strings.TrimSpace(entry.BaseURL)
entry.ProxyURL = strings.TrimSpace(entry.ProxyURL)
entry.Headers = config.NormalizeHeaders(entry.Headers)
entry.ExcludedModels = config.NormalizeExcludedModels(entry.ExcludedModels)
if len(entry.Models) == 0 {
return
}
normalized := make([]config.VertexCompatModel, 0, len(entry.Models))
for i := range entry.Models {
model := entry.Models[i]
model.Name = strings.TrimSpace(model.Name)
model.Alias = strings.TrimSpace(model.Alias)
if model.Name == "" || model.Alias == "" {
continue
}
normalized = append(normalized, model)
}
entry.Models = normalized
}
func sanitizedOAuthModelAlias(entries map[string][]config.OAuthModelAlias) map[string][]config.OAuthModelAlias {
if len(entries) == 0 {
return nil
}
copied := make(map[string][]config.OAuthModelAlias, len(entries))
for channel, aliases := range entries {
if len(aliases) == 0 {
continue
}
copied[channel] = append([]config.OAuthModelAlias(nil), aliases...)
}
if len(copied) == 0 {
return nil
}
cfg := config.Config{OAuthModelAlias: copied}
cfg.SanitizeOAuthModelAlias()
if len(cfg.OAuthModelAlias) == 0 {
return nil
}
return cfg.OAuthModelAlias
}
// GetAmpCode returns the complete ampcode configuration.
func (h *Handler) GetAmpCode(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(200, gin.H{"ampcode": config.AmpCode{}})
return
}
c.JSON(200, gin.H{"ampcode": h.cfg.AmpCode})
}
// GetAmpUpstreamURL returns the ampcode upstream URL.
func (h *Handler) GetAmpUpstreamURL(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(200, gin.H{"upstream-url": ""})
return
}
c.JSON(200, gin.H{"upstream-url": h.cfg.AmpCode.UpstreamURL})
}
// PutAmpUpstreamURL updates the ampcode upstream URL.
func (h *Handler) PutAmpUpstreamURL(c *gin.Context) {
h.updateStringField(c, func(cfg *config.Config, v string) { cfg.AmpCode.UpstreamURL = strings.TrimSpace(v) })
}
// DeleteAmpUpstreamURL clears the ampcode upstream URL.
func (h *Handler) DeleteAmpUpstreamURL(c *gin.Context) {
h.cfg.AmpCode.UpstreamURL = ""
h.persist(c)
}
// GetAmpUpstreamAPIKey returns the ampcode upstream API key.
func (h *Handler) GetAmpUpstreamAPIKey(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(200, gin.H{"upstream-api-key": ""})
return
}
c.JSON(200, gin.H{"upstream-api-key": h.cfg.AmpCode.UpstreamAPIKey})
}
// PutAmpUpstreamAPIKey updates the ampcode upstream API key.
func (h *Handler) PutAmpUpstreamAPIKey(c *gin.Context) {
h.updateStringField(c, func(cfg *config.Config, v string) { cfg.AmpCode.UpstreamAPIKey = strings.TrimSpace(v) })
}
// DeleteAmpUpstreamAPIKey clears the ampcode upstream API key.
func (h *Handler) DeleteAmpUpstreamAPIKey(c *gin.Context) {
h.cfg.AmpCode.UpstreamAPIKey = ""
h.persist(c)
}
// GetAmpRestrictManagementToLocalhost returns the localhost restriction setting.
func (h *Handler) GetAmpRestrictManagementToLocalhost(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(200, gin.H{"restrict-management-to-localhost": true})
return
}
c.JSON(200, gin.H{"restrict-management-to-localhost": h.cfg.AmpCode.RestrictManagementToLocalhost})
}
// PutAmpRestrictManagementToLocalhost updates the localhost restriction setting.
func (h *Handler) PutAmpRestrictManagementToLocalhost(c *gin.Context) {
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.AmpCode.RestrictManagementToLocalhost = v })
}
// GetAmpModelMappings returns the ampcode model mappings.
func (h *Handler) GetAmpModelMappings(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(200, gin.H{"model-mappings": []config.AmpModelMapping{}})
return
}
c.JSON(200, gin.H{"model-mappings": h.cfg.AmpCode.ModelMappings})
}
// PutAmpModelMappings replaces all ampcode model mappings.
func (h *Handler) PutAmpModelMappings(c *gin.Context) {
var body struct {
Value []config.AmpModelMapping `json:"value"`
}
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
h.cfg.AmpCode.ModelMappings = body.Value
h.persist(c)
}
// PatchAmpModelMappings adds or updates model mappings.
func (h *Handler) PatchAmpModelMappings(c *gin.Context) {
var body struct {
Value []config.AmpModelMapping `json:"value"`
}
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
existing := make(map[string]int)
for i, m := range h.cfg.AmpCode.ModelMappings {
existing[strings.TrimSpace(m.From)] = i
}
for _, newMapping := range body.Value {
from := strings.TrimSpace(newMapping.From)
if idx, ok := existing[from]; ok {
h.cfg.AmpCode.ModelMappings[idx] = newMapping
} else {
h.cfg.AmpCode.ModelMappings = append(h.cfg.AmpCode.ModelMappings, newMapping)
existing[from] = len(h.cfg.AmpCode.ModelMappings) - 1
}
}
h.persist(c)
}
// DeleteAmpModelMappings removes specified model mappings by "from" field.
func (h *Handler) DeleteAmpModelMappings(c *gin.Context) {
var body struct {
Value []string `json:"value"`
}
if err := c.ShouldBindJSON(&body); err != nil || len(body.Value) == 0 {
h.cfg.AmpCode.ModelMappings = nil
h.persist(c)
return
}
toRemove := make(map[string]bool)
for _, from := range body.Value {
toRemove[strings.TrimSpace(from)] = true
}
newMappings := make([]config.AmpModelMapping, 0, len(h.cfg.AmpCode.ModelMappings))
for _, m := range h.cfg.AmpCode.ModelMappings {
if !toRemove[strings.TrimSpace(m.From)] {
newMappings = append(newMappings, m)
}
}
h.cfg.AmpCode.ModelMappings = newMappings
h.persist(c)
}
// GetAmpForceModelMappings returns whether model mappings are forced.
func (h *Handler) GetAmpForceModelMappings(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(200, gin.H{"force-model-mappings": false})
return
}
c.JSON(200, gin.H{"force-model-mappings": h.cfg.AmpCode.ForceModelMappings})
}
// PutAmpForceModelMappings updates the force model mappings setting.
func (h *Handler) PutAmpForceModelMappings(c *gin.Context) {
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.AmpCode.ForceModelMappings = v })
}
// GetAmpUpstreamAPIKeys returns the ampcode upstream API keys mapping.
func (h *Handler) GetAmpUpstreamAPIKeys(c *gin.Context) {
if h == nil || h.cfg == nil {
c.JSON(200, gin.H{"upstream-api-keys": []config.AmpUpstreamAPIKeyEntry{}})
return
}
c.JSON(200, gin.H{"upstream-api-keys": h.cfg.AmpCode.UpstreamAPIKeys})
}
// PutAmpUpstreamAPIKeys replaces all ampcode upstream API keys mappings.
func (h *Handler) PutAmpUpstreamAPIKeys(c *gin.Context) {
var body struct {
Value []config.AmpUpstreamAPIKeyEntry `json:"value"`
}
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
// Normalize entries: trim whitespace, filter empty
normalized := normalizeAmpUpstreamAPIKeyEntries(body.Value)
h.cfg.AmpCode.UpstreamAPIKeys = normalized
h.persist(c)
}
// PatchAmpUpstreamAPIKeys adds or updates upstream API keys entries.
// Matching is done by upstream-api-key value.
func (h *Handler) PatchAmpUpstreamAPIKeys(c *gin.Context) {
var body struct {
Value []config.AmpUpstreamAPIKeyEntry `json:"value"`
}
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
existing := make(map[string]int)
for i, entry := range h.cfg.AmpCode.UpstreamAPIKeys {
existing[strings.TrimSpace(entry.UpstreamAPIKey)] = i
}
for _, newEntry := range body.Value {
upstreamKey := strings.TrimSpace(newEntry.UpstreamAPIKey)
if upstreamKey == "" {
continue
}
normalizedEntry := config.AmpUpstreamAPIKeyEntry{
UpstreamAPIKey: upstreamKey,
APIKeys: normalizeAPIKeysList(newEntry.APIKeys),
}
if idx, ok := existing[upstreamKey]; ok {
h.cfg.AmpCode.UpstreamAPIKeys[idx] = normalizedEntry
} else {
h.cfg.AmpCode.UpstreamAPIKeys = append(h.cfg.AmpCode.UpstreamAPIKeys, normalizedEntry)
existing[upstreamKey] = len(h.cfg.AmpCode.UpstreamAPIKeys) - 1
}
}
h.persist(c)
}
// DeleteAmpUpstreamAPIKeys removes specified upstream API keys entries.
// Body must be JSON: {"value": ["<upstream-api-key>", ...]}.
// If "value" is an empty array, clears all entries.
// If JSON is invalid or "value" is missing/null, returns 400 and does not persist any change.
func (h *Handler) DeleteAmpUpstreamAPIKeys(c *gin.Context) {
var body struct {
Value []string `json:"value"`
}
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(400, gin.H{"error": "invalid body"})
return
}
if body.Value == nil {
c.JSON(400, gin.H{"error": "missing value"})
return
}
// Empty array means clear all
if len(body.Value) == 0 {
h.cfg.AmpCode.UpstreamAPIKeys = nil
h.persist(c)
return
}
toRemove := make(map[string]bool)
for _, key := range body.Value {
trimmed := strings.TrimSpace(key)
if trimmed == "" {
continue
}
toRemove[trimmed] = true
}
if len(toRemove) == 0 {
c.JSON(400, gin.H{"error": "empty value"})
return
}
newEntries := make([]config.AmpUpstreamAPIKeyEntry, 0, len(h.cfg.AmpCode.UpstreamAPIKeys))
for _, entry := range h.cfg.AmpCode.UpstreamAPIKeys {
if !toRemove[strings.TrimSpace(entry.UpstreamAPIKey)] {
newEntries = append(newEntries, entry)
}
}
h.cfg.AmpCode.UpstreamAPIKeys = newEntries
h.persist(c)
}
// normalizeAmpUpstreamAPIKeyEntries normalizes a list of upstream API key entries.
func normalizeAmpUpstreamAPIKeyEntries(entries []config.AmpUpstreamAPIKeyEntry) []config.AmpUpstreamAPIKeyEntry {
if len(entries) == 0 {
return nil
}
out := make([]config.AmpUpstreamAPIKeyEntry, 0, len(entries))
for _, entry := range entries {
upstreamKey := strings.TrimSpace(entry.UpstreamAPIKey)
if upstreamKey == "" {
continue
}
apiKeys := normalizeAPIKeysList(entry.APIKeys)
out = append(out, config.AmpUpstreamAPIKeyEntry{
UpstreamAPIKey: upstreamKey,
APIKeys: apiKeys,
})
}
if len(out) == 0 {
return nil
}
return out
}
// normalizeAPIKeysList trims and filters empty strings from a list of API keys.
func normalizeAPIKeysList(keys []string) []string {
if len(keys) == 0 {
return nil
}
out := make([]string, 0, len(keys))
for _, k := range keys {
trimmed := strings.TrimSpace(k)
if trimmed != "" {
out = append(out, trimmed)
}
}
if len(out) == 0 {
return nil
}
return out
}
@@ -3,6 +3,8 @@ package management
import (
"bufio"
"context"
"crypto/rand"
"encoding/hex"
"fmt"
"io"
"net/http"
@@ -117,9 +119,7 @@ func (h *Handler) processAPIKey(ctx context.Context, provider, key string, lineN
// Basic duplicate check could be added here if needed
timestamp := time.Now().Unix()
// Use a shortened key hash or prefix for filename to avoid leaking credentials in filenames
safeName := fmt.Sprintf("%s-%s", provider, key[:min(8, len(key))])
fileName := fmt.Sprintf("%s-%d.json", safeName, timestamp)
fileName := newImportedCredentialFileName(provider, timestamp)
record := &coreauth.Auth{
ID: fileName,
@@ -161,9 +161,10 @@ func parseLines(r io.Reader) ([]string, error) {
return lines, nil
}
func min(a, b int) int {
if a < b {
return a
func newImportedCredentialFileName(provider string, timestamp int64) string {
suffix := make([]byte, 6)
if _, err := rand.Read(suffix); err != nil {
return fmt.Sprintf("%s-import-%d.json", provider, timestamp)
}
return b
return fmt.Sprintf("%s-import-%d-%s.json", provider, timestamp, hex.EncodeToString(suffix))
}
+109 -166
View File
@@ -17,10 +17,10 @@ import (
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
"github.com/router-for-me/CLIProxyAPI/v6/internal/integrations"
"github.com/router-for-me/CLIProxyAPI/v6/internal/usage"
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
"golang.org/x/crypto/bcrypt"
"gopkg.in/yaml.v3"
)
type attemptInfo struct {
@@ -38,6 +38,7 @@ const attemptMaxIdleTime = 2 * time.Hour
// Handler aggregates config reference, persistence path and helpers.
type Handler struct {
cfg *config.Config
committedCfg *config.Config
configFilePath string
mu sync.Mutex
attemptsMu sync.Mutex
@@ -50,31 +51,18 @@ type Handler struct {
envSecret string
logDir string
integrationManager *integrations.Manager
}
// openAICompatProviderNames returns the configured OpenAI-compat provider names from the current config.
func (h *Handler) openAICompatProviderNames() []string {
cfg := h.cfg
if cfg == nil {
return nil
}
out := make([]string, 0, len(cfg.OpenAICompatibility))
for _, c := range cfg.OpenAICompatibility {
name := strings.TrimSpace(c.Name)
if name != "" {
out = append(out, name)
}
}
return out
postAuthHook coreauth.PostAuthHook
}
// NewHandler creates a new management handler instance.
func NewHandler(cfg *config.Config, configFilePath string, manager *coreauth.Manager) *Handler {
envSecret, _ := os.LookupEnv("MANAGEMENT_PASSWORD")
envSecret = strings.TrimSpace(envSecret)
clonedCfg := cloneConfig(cfg)
h := &Handler{
cfg: cfg,
cfg: clonedCfg,
committedCfg: cloneConfig(clonedCfg),
configFilePath: configFilePath,
failedAttempts: make(map[string]*attemptInfo),
authManager: manager,
@@ -83,28 +71,6 @@ func NewHandler(cfg *config.Config, configFilePath string, manager *coreauth.Man
allowRemoteOverride: envSecret != "",
envSecret: envSecret,
}
// Initialize Integration Manager
// We need the proxy URL. If not in config, assume localhost default.
proxyURL := cfg.ProxyURL
if proxyURL == "" {
host := cfg.Host
if host == "" {
host = "http://127.0.0.1"
} else {
if !strings.HasPrefix(host, "http") {
host = "http://" + host
}
}
proxyURL = fmt.Sprintf("%s:%d", host, cfg.Port)
}
h.integrationManager = integrations.NewManager(proxyURL)
h.integrationManager.Register(&integrations.CodexIntegration{})
h.integrationManager.Register(&integrations.ClaudeIntegration{})
h.integrationManager.Register(&integrations.DroidIntegration{})
h.integrationManager.Register(&integrations.GeminiIntegration{})
h.startAttemptCleanup()
return h
}
@@ -145,116 +111,17 @@ func NewHandlerWithoutConfigFilePath(cfg *config.Config, manager *coreauth.Manag
}
// SetConfig updates the in-memory config reference when the server hot-reloads.
func (h *Handler) SetConfig(cfg *config.Config) { h.cfg = cfg }
func (h *Handler) SetConfig(cfg *config.Config) {
clonedCfg := cloneConfig(cfg)
h.mu.Lock()
h.cfg = clonedCfg
h.committedCfg = cloneConfig(clonedCfg)
h.mu.Unlock()
}
// SetAuthManager updates the auth manager reference used by management endpoints.
func (h *Handler) SetAuthManager(manager *coreauth.Manager) { h.authManager = manager }
// routingPreview describes how a model would be normalised and routed according to current config.
type routingPreview struct {
RequestedModel string `json:"requested_model"`
ResolvedModel string `json:"resolved_model"`
NormalizedModel string `json:"normalized_model"`
ProviderCandidates []string `json:"provider_candidates"`
PreferredProvider string `json:"preferred_provider"`
Dynamic map[string]any `json:"dynamic"`
Metadata map[string]any `json:"metadata"`
}
// computeRoutingPreview replicates BaseAPIHandler.getRequestDetails for management/debug purposes.
func (h *Handler) computeRoutingPreview(modelName string) (*routingPreview, error) {
if strings.TrimSpace(modelName) == "" {
return nil, fmt.Errorf("model name is empty")
}
requested := strings.TrimSpace(modelName)
// Droid CLI sometimes sends a "custom:*" model id; normalize it before routing.
modelName = util.NormalizeDroidCustomModel(modelName)
// Resolve "auto" model to an actual available model first
resolvedModelName := util.ResolveAutoModel(modelName)
providerName, extractedModelName, isDynamic := parseDynamicModelWithConfig(resolvedModelName, h.openAICompatProviderNames())
targetModelName := resolvedModelName
if isDynamic {
targetModelName = extractedModelName
}
// Normalize the model name to handle dynamic thinking suffixes before determining the provider.
normalizedModel, metadata := util.NormalizeThinkingModel(targetModelName)
var providers []string
if isDynamic {
providers = []string{providerName}
} else {
// For non-dynamic models, use the normalizedModel to get the provider name.
providers = util.GetProviderName(normalizedModel)
if len(providers) == 0 && metadata != nil {
if originalRaw, ok := metadata[util.ThinkingOriginalModelMetadataKey]; ok {
if originalModel, okStr := originalRaw.(string); okStr {
originalModel = strings.TrimSpace(originalModel)
if originalModel != "" && !strings.EqualFold(originalModel, normalizedModel) {
if altProviders := util.GetProviderName(originalModel); len(altProviders) > 0 {
providers = altProviders
normalizedModel = originalModel
}
}
}
}
}
}
if len(providers) == 0 {
return nil, fmt.Errorf("unknown provider for model %s", requested)
}
preferred := ""
if len(providers) > 0 {
preferred = providers[0]
}
preview := &routingPreview{
RequestedModel: requested,
ResolvedModel: resolvedModelName,
NormalizedModel: normalizedModel,
ProviderCandidates: providers,
PreferredProvider: preferred,
Dynamic: map[string]any{
"is_dynamic": isDynamic,
"dynamic_provider": providerName,
"dynamic_model": extractedModelName,
},
Metadata: metadata,
}
return preview, nil
}
// parseDynamicModelWithConfig mirrors BaseAPIHandler.parseDynamicModel but uses the config provider list.
func parseDynamicModelWithConfig(modelName string, openAICompatProviders []string) (providerName, model string, isDynamic bool) {
var providerPart, modelPart string
for _, sep := range []string{"://"} {
if parts := strings.SplitN(modelName, sep, 2); len(parts) == 2 {
providerPart = parts[0]
modelPart = parts[1]
break
}
}
if providerPart == "" {
return "", modelName, false
}
for _, pName := range openAICompatProviders {
if pName == providerPart {
return providerPart, modelPart, true
}
}
return "", modelName, false
}
// SetUsageStatistics allows replacing the usage statistics reference.
func (h *Handler) SetUsageStatistics(stats *usage.RequestStatistics) { h.usageStats = stats }
@@ -274,6 +141,11 @@ func (h *Handler) SetLogDirectory(dir string) {
h.logDir = dir
}
// SetPostAuthHook registers a hook to be called after auth record creation but before persistence.
func (h *Handler) SetPostAuthHook(hook coreauth.PostAuthHook) {
h.postAuthHook = hook
}
// Middleware enforces access control for management endpoints.
// All requests (local and remote) require a valid management key.
// Additionally, remote access requires allow-remote-management=true.
@@ -376,15 +248,6 @@ func (h *Handler) Middleware() gin.HandlerFunc {
return
}
}
// For localhost, also accept configured API keys (same keys that work for main API)
if cfg != nil {
for _, apiKey := range cfg.APIKeys {
if apiKey != "" && subtle.ConstantTimeCompare([]byte(provided), []byte(apiKey)) == 1 {
c.Next()
return
}
}
}
}
if envSecret != "" && subtle.ConstantTimeCompare([]byte(provided), []byte(envSecret)) == 1 {
@@ -423,19 +286,45 @@ func (h *Handler) Middleware() gin.HandlerFunc {
// persist saves the current in-memory config to disk.
func (h *Handler) persist(c *gin.Context) bool {
h.mu.Lock()
current := cloneConfig(h.cfg)
h.mu.Unlock()
return h.persistConfig(c, current)
}
func (h *Handler) persistConfig(c *gin.Context, next *config.Config) bool {
if next == nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "config unavailable"})
return false
}
next = cloneConfig(next)
h.mu.Lock()
defer h.mu.Unlock()
// Preserve comments when writing
if err := config.SaveConfigPreserveComments(h.configFilePath, h.cfg); err != nil {
if err := saveConfigAtomically(h.configFilePath, next); err != nil {
h.cfg = cloneConfig(h.committedCfg)
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to save config: %v", err)})
return false
}
h.cfg = next
h.committedCfg = cloneConfig(next)
c.JSON(http.StatusOK, gin.H{"status": "ok"})
return true
}
func (h *Handler) mutateConfig(c *gin.Context, mutate func(*config.Config)) bool {
h.mu.Lock()
next := cloneConfig(h.cfg)
h.mu.Unlock()
if next == nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "config unavailable"})
return false
}
mutate(next)
return h.persistConfig(c, next)
}
// Helper methods for simple types
func (h *Handler) updateBoolField(c *gin.Context, set func(bool)) {
func (h *Handler) updateBoolField(c *gin.Context, set func(*config.Config, bool)) {
var body struct {
Value *bool `json:"value"`
}
@@ -443,11 +332,12 @@ func (h *Handler) updateBoolField(c *gin.Context, set func(bool)) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
return
}
set(*body.Value)
h.persist(c)
h.mutateConfig(c, func(cfg *config.Config) {
set(cfg, *body.Value)
})
}
func (h *Handler) updateIntField(c *gin.Context, set func(int)) {
func (h *Handler) updateIntField(c *gin.Context, set func(*config.Config, int)) {
var body struct {
Value *int `json:"value"`
}
@@ -455,11 +345,12 @@ func (h *Handler) updateIntField(c *gin.Context, set func(int)) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
return
}
set(*body.Value)
h.persist(c)
h.mutateConfig(c, func(cfg *config.Config) {
set(cfg, *body.Value)
})
}
func (h *Handler) updateStringField(c *gin.Context, set func(string)) {
func (h *Handler) updateStringField(c *gin.Context, set func(*config.Config, string)) {
var body struct {
Value *string `json:"value"`
}
@@ -467,6 +358,58 @@ func (h *Handler) updateStringField(c *gin.Context, set func(string)) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
return
}
set(*body.Value)
h.persist(c)
h.mutateConfig(c, func(cfg *config.Config) {
set(cfg, *body.Value)
})
}
func cloneConfig(cfg *config.Config) *config.Config {
if cfg == nil {
return nil
}
raw, err := yaml.Marshal(cfg)
if err != nil {
cloned := *cfg
return &cloned
}
var cloned config.Config
if err = yaml.Unmarshal(raw, &cloned); err != nil {
fallback := *cfg
return &fallback
}
return &cloned
}
func saveConfigAtomically(path string, cfg *config.Config) error {
path = strings.TrimSpace(path)
if path == "" {
return fmt.Errorf("config file path not configured")
}
info, err := os.Stat(path)
if err != nil {
return err
}
original, err := os.ReadFile(path)
if err != nil {
return err
}
tmpFile, err := os.CreateTemp(filepath.Dir(path), ".config-save-*.yaml")
if err != nil {
return err
}
tmpPath := tmpFile.Name()
if errClose := tmpFile.Close(); errClose != nil {
_ = os.Remove(tmpPath)
return errClose
}
defer func() {
_ = os.Remove(tmpPath)
}()
if err = os.WriteFile(tmpPath, original, info.Mode().Perm()); err != nil {
return err
}
if err = config.SaveConfigPreserveComments(tmpPath, cfg); err != nil {
return err
}
return os.Rename(tmpPath, path)
}
+2 -11
View File
@@ -13,7 +13,7 @@ import (
"time"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
)
const (
@@ -360,16 +360,7 @@ func (h *Handler) logDirectory() string {
if h.logDir != "" {
return h.logDir
}
if base := util.WritablePath(); base != "" {
return filepath.Join(base, "logs")
}
if h.configFilePath != "" {
dir := filepath.Dir(h.configFilePath)
if dir != "" && dir != "." {
return filepath.Join(dir, "logs")
}
}
return "logs"
return logging.ResolveLogDirectory(h.cfg)
}
func (h *Handler) collectLogFiles(dir string) ([]string, error) {
@@ -0,0 +1,111 @@
package management
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"net/url"
"os"
"path/filepath"
"strings"
"testing"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
)
func TestDeleteMemorySession_RejectsTraversal(t *testing.T) {
t.Setenv("CLIPROXY_MEMORY_DIR", t.TempDir())
gin.SetMode(gin.TestMode)
outsidePath := filepath.Join(t.TempDir(), "outside")
if err := os.WriteFile(outsidePath, []byte("keep"), 0o600); err != nil {
t.Fatalf("WriteFile() error = %v", err)
}
recorder := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(recorder)
ctx.Request = httptest.NewRequest(http.MethodDelete, "/v0/management/memory/session?session="+url.QueryEscape("../outside"), nil)
h := &Handler{}
h.DeleteMemorySession(ctx)
if recorder.Code != http.StatusBadRequest {
t.Fatalf("status = %d, want %d body=%s", recorder.Code, http.StatusBadRequest, recorder.Body.String())
}
if _, err := os.Stat(outsidePath); err != nil {
t.Fatalf("outside path should remain untouched: %v", err)
}
}
func TestProcessAPIKey_DoesNotLeakSecretPrefixInSavedPath(t *testing.T) {
gin.SetMode(gin.TestMode)
authDir := t.TempDir()
h := NewHandlerWithoutConfigFilePath(&config.Config{AuthDir: authDir}, nil)
key := "sk-secret-prefix-1234567890"
result := h.processAPIKey(context.Background(), "openai", key, 1)
if !result.Success {
t.Fatalf("processAPIKey() failed: %+v", result)
}
if strings.Contains(result.SavedPath, "sk-secret") {
t.Fatalf("saved path leaked key prefix: %q", result.SavedPath)
}
if !strings.HasPrefix(filepath.Base(result.SavedPath), "openai-import-") {
t.Fatalf("saved path = %q, want generated import prefix", result.SavedPath)
}
}
func TestCommitUploadedAuthFile_InvalidDataDoesNotWriteFile(t *testing.T) {
gin.SetMode(gin.TestMode)
authDir := t.TempDir()
path := filepath.Join(authDir, "broken.json")
h := NewHandlerWithoutConfigFilePath(&config.Config{AuthDir: authDir}, nil)
err := h.commitUploadedAuthFile(context.Background(), path, []byte(`{"type":`))
if err == nil {
t.Fatal("commitUploadedAuthFile() unexpectedly succeeded")
}
if _, statErr := os.Stat(path); !os.IsNotExist(statErr) {
t.Fatalf("invalid upload should not leave a file behind, stat err=%v", statErr)
}
}
func TestGetConfig_ReturnsLiveConfig(t *testing.T) {
gin.SetMode(gin.TestMode)
h := NewHandlerWithoutConfigFilePath(&config.Config{
SDKConfig: config.SDKConfig{
ProxyURL: "http://127.0.0.1:8080",
},
Debug: true,
UsageStatisticsEnabled: true,
}, nil)
recorder := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(recorder)
ctx.Request = httptest.NewRequest(http.MethodGet, "/v0/management/config", nil)
h.GetConfig(ctx)
if recorder.Code != http.StatusOK {
t.Fatalf("status = %d, want %d body=%s", recorder.Code, http.StatusOK, recorder.Body.String())
}
var got config.Config
if err := json.Unmarshal(recorder.Body.Bytes(), &got); err != nil {
t.Fatalf("Unmarshal() error = %v body=%s", err, recorder.Body.String())
}
if !got.Debug {
t.Fatalf("Debug = %v, want true", got.Debug)
}
if got.ProxyURL != "http://127.0.0.1:8080" {
t.Fatalf("ProxyURL = %q", got.ProxyURL)
}
if !got.UsageStatisticsEnabled {
t.Fatalf("UsageStatisticsEnabled = %v, want true", got.UsageStatisticsEnabled)
}
}
+27 -12
View File
@@ -210,12 +210,11 @@ func (h *Handler) DeleteMemorySession(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{"status": "ok"})
return
}
session := strings.TrimSpace(c.Query("session"))
if session == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing session"})
store := memory.NewFileStore(base)
_, path, ok := resolveManagedMemorySession(c, store, c.Query("session"))
if !ok {
return
}
path := filepath.Join(base, "sessions", session)
if err := os.RemoveAll(path); err != nil && !os.IsNotExist(err) {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
@@ -289,12 +288,11 @@ func (h *Handler) ExportMemorySession(c *gin.Context) {
c.JSON(http.StatusBadRequest, gin.H{"error": "memory not configured"})
return
}
session := strings.TrimSpace(c.Query("session"))
if session == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing session"})
store := memory.NewFileStore(base)
session, dir, ok := resolveManagedMemorySession(c, store, c.Query("session"))
if !ok {
return
}
dir := filepath.Join(base, "sessions", session)
if _, err := os.Stat(dir); err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "session not found"})
return
@@ -357,9 +355,9 @@ func (h *Handler) ImportMemorySession(c *gin.Context) {
c.JSON(http.StatusBadRequest, gin.H{"error": "multipart form required"})
return
}
session := strings.TrimSpace(c.Query("session"))
if session == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing session"})
store := memory.NewFileStore(base)
_, dest, ok := resolveManagedMemorySession(c, store, c.Query("session"))
if !ok {
return
}
replace := strings.EqualFold(strings.TrimSpace(c.Query("replace")), "true")
@@ -388,7 +386,6 @@ func (h *Handler) ImportMemorySession(c *gin.Context) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid zip"})
return
}
dest := filepath.Join(base, "sessions", session)
if replace {
_ = os.RemoveAll(dest)
}
@@ -460,3 +457,21 @@ func anchorAppendOnlyEnabled() bool {
}
return true
}
func resolveManagedMemorySession(c *gin.Context, store *memory.FileStore, rawSession string) (string, string, bool) {
session := strings.TrimSpace(rawSession)
if session == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing session"})
return "", "", false
}
if strings.Contains(session, "..") || strings.ContainsAny(session, `/\`) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid session"})
return "", "", false
}
dir := store.SessionDir(session)
if dir == "" {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to resolve session path"})
return "", "", false
}
return filepath.Base(dir), dir, true
}
@@ -0,0 +1,33 @@
package management
import (
"net/http"
"strings"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
)
// GetStaticModelDefinitions returns static model metadata for a given channel.
// Channel is provided via path param (:channel) or query param (?channel=...).
func (h *Handler) GetStaticModelDefinitions(c *gin.Context) {
channel := strings.TrimSpace(c.Param("channel"))
if channel == "" {
channel = strings.TrimSpace(c.Query("channel"))
}
if channel == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "channel is required"})
return
}
models := registry.GetStaticModelDefinitionsByChannel(channel)
if models == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "unknown channel", "channel": channel})
return
}
c.JSON(http.StatusOK, gin.H{
"channel": strings.ToLower(strings.TrimSpace(channel)),
"models": models,
})
}
@@ -158,12 +158,7 @@ func (s *oauthSessionStore) IsPending(state, provider string) bool {
return false
}
if session.Status != "" {
if !strings.EqualFold(session.Provider, "kiro") {
return false
}
if !strings.HasPrefix(session.Status, "device_code|") && !strings.HasPrefix(session.Status, "auth_url|") {
return false
}
return false
}
if provider == "" {
return true
@@ -230,12 +225,12 @@ func NormalizeOAuthProvider(provider string) (string, error) {
return "codex", nil
case "gemini", "google":
return "gemini", nil
case "iflow", "i-flow":
return "iflow", nil
case "antigravity", "anti-gravity":
return "antigravity", nil
case "qwen":
return "qwen", nil
case "kiro":
return "kiro", nil
default:
return "", errUnsupportedOAuthFlow
}
+6 -3
View File
@@ -1,18 +1,21 @@
package management
import "github.com/gin-gonic/gin"
import (
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
)
// Quota exceeded toggles
func (h *Handler) GetSwitchProject(c *gin.Context) {
c.JSON(200, gin.H{"switch-project": h.cfg.QuotaExceeded.SwitchProject})
}
func (h *Handler) PutSwitchProject(c *gin.Context) {
h.updateBoolField(c, func(v bool) { h.cfg.QuotaExceeded.SwitchProject = v })
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.QuotaExceeded.SwitchProject = v })
}
func (h *Handler) GetSwitchPreviewModel(c *gin.Context) {
c.JSON(200, gin.H{"switch-preview-model": h.cfg.QuotaExceeded.SwitchPreviewModel})
}
func (h *Handler) PutSwitchPreviewModel(c *gin.Context) {
h.updateBoolField(c, func(v bool) { h.cfg.QuotaExceeded.SwitchPreviewModel = v })
h.updateBoolField(c, func(cfg *config.Config, v bool) { cfg.QuotaExceeded.SwitchPreviewModel = v })
}
@@ -0,0 +1,168 @@
package management
import (
"net/http"
"time"
"github.com/gin-gonic/gin"
)
// RateLimitEntry represents the rate limit status for a single credential.
type RateLimitEntry struct {
AuthID string `json:"auth_id"`
Provider string `json:"provider"`
Label string `json:"label,omitempty"`
Email string `json:"email,omitempty"`
QuotaExceeded bool `json:"quota_exceeded"`
QuotaReason string `json:"quota_reason,omitempty"`
RecoverAt time.Time `json:"recover_at,omitempty"`
RecoverIn string `json:"recover_in,omitempty"`
BackoffLevel int `json:"backoff_level,omitempty"`
ModelLimits []ModelRateLimitEntry `json:"model_limits,omitempty"`
}
// ModelRateLimitEntry represents the rate limit status for a specific model.
type ModelRateLimitEntry struct {
Model string `json:"model"`
QuotaExceeded bool `json:"quota_exceeded"`
QuotaReason string `json:"quota_reason,omitempty"`
RecoverAt time.Time `json:"recover_at,omitempty"`
RecoverIn string `json:"recover_in,omitempty"`
BackoffLevel int `json:"backoff_level,omitempty"`
}
// RateLimitsResponse contains overall rate limit status.
type RateLimitsResponse struct {
TotalCredentials int `json:"total_credentials"`
CoolingDown int `json:"cooling_down"`
Available int `json:"available"`
Credentials []RateLimitEntry `json:"credentials"`
}
// GetRateLimits returns the rate limit status for all credentials.
// GET /v0/management/rate-limits
func (h *Handler) GetRateLimits(c *gin.Context) {
if h.authManager == nil {
c.JSON(http.StatusOK, RateLimitsResponse{})
return
}
auths := h.authManager.List()
now := time.Now()
resp := RateLimitsResponse{
TotalCredentials: len(auths),
Credentials: make([]RateLimitEntry, 0, len(auths)),
}
for _, auth := range auths {
entry := RateLimitEntry{
AuthID: auth.ID,
Provider: auth.Provider,
Label: auth.Label,
QuotaExceeded: auth.Quota.Exceeded,
QuotaReason: auth.Quota.Reason,
BackoffLevel: auth.Quota.BackoffLevel,
}
// Extract email from metadata
if auth.Metadata != nil {
if email, ok := auth.Metadata["email"].(string); ok {
entry.Email = email
}
}
// Calculate recover time
if !auth.Quota.NextRecoverAt.IsZero() {
entry.RecoverAt = auth.Quota.NextRecoverAt
if auth.Quota.NextRecoverAt.After(now) {
entry.RecoverIn = auth.Quota.NextRecoverAt.Sub(now).Round(time.Second).String()
}
}
// Per-model rate limits
if len(auth.ModelStates) > 0 {
entry.ModelLimits = make([]ModelRateLimitEntry, 0, len(auth.ModelStates))
for model, state := range auth.ModelStates {
if state.Quota.Exceeded || !state.Quota.NextRecoverAt.IsZero() {
modelEntry := ModelRateLimitEntry{
Model: model,
QuotaExceeded: state.Quota.Exceeded,
QuotaReason: state.Quota.Reason,
BackoffLevel: state.Quota.BackoffLevel,
}
if !state.Quota.NextRecoverAt.IsZero() {
modelEntry.RecoverAt = state.Quota.NextRecoverAt
if state.Quota.NextRecoverAt.After(now) {
modelEntry.RecoverIn = state.Quota.NextRecoverAt.Sub(now).Round(time.Second).String()
}
}
entry.ModelLimits = append(entry.ModelLimits, modelEntry)
}
}
}
// Count cooling down vs available
isCooling := auth.Quota.Exceeded || (auth.Quota.NextRecoverAt.After(now))
if isCooling {
resp.CoolingDown++
} else if !auth.Disabled && !auth.Unavailable {
resp.Available++
}
resp.Credentials = append(resp.Credentials, entry)
}
c.JSON(http.StatusOK, resp)
}
// GetRateLimitsSummary returns a brief summary of rate limit status.
// GET /v0/management/rate-limits/summary
func (h *Handler) GetRateLimitsSummary(c *gin.Context) {
if h.authManager == nil {
c.JSON(http.StatusOK, gin.H{
"total": 0,
"available": 0,
"cooling_down": 0,
"disabled": 0,
})
return
}
auths := h.authManager.List()
now := time.Now()
var available, coolingDown, disabled int
var nextRecovery time.Time
for _, auth := range auths {
if auth.Disabled {
disabled++
continue
}
isCooling := auth.Quota.Exceeded || (auth.Quota.NextRecoverAt.After(now))
if isCooling {
coolingDown++
if nextRecovery.IsZero() || auth.Quota.NextRecoverAt.Before(nextRecovery) {
nextRecovery = auth.Quota.NextRecoverAt
}
} else if !auth.Unavailable {
available++
}
}
resp := gin.H{
"total": len(auths),
"available": available,
"cooling_down": coolingDown,
"disabled": disabled,
}
if !nextRecovery.IsZero() && nextRecovery.After(now) {
resp["next_recovery_at"] = nextRecovery
resp["next_recovery_in"] = nextRecovery.Sub(now).Round(time.Second).String()
}
c.JSON(http.StatusOK, resp)
}
+16 -16
View File
@@ -1,16 +1,16 @@
package management
import (
"net/http"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/api/middleware"
)
// GetRequests returns the list of recent requests from the in-memory ring buffer.
func (h *Handler) GetRequests(c *gin.Context) {
requests := middleware.GetRequestMonitor()
c.JSON(http.StatusOK, gin.H{
"requests": requests,
})
}
package management
import (
"net/http"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/api/middleware"
)
// GetRequests returns the list of recent requests from the in-memory ring buffer.
func (h *Handler) GetRequests(c *gin.Context) {
requests := middleware.GetRequestMonitor()
c.JSON(http.StatusOK, gin.H{
"requests": requests,
})
}
@@ -0,0 +1,49 @@
package management
import (
"context"
"sync"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
)
type memoryAuthStore struct {
mu sync.Mutex
items map[string]*coreauth.Auth
}
func (s *memoryAuthStore) List(_ context.Context) ([]*coreauth.Auth, error) {
s.mu.Lock()
defer s.mu.Unlock()
out := make([]*coreauth.Auth, 0, len(s.items))
for _, item := range s.items {
out = append(out, item)
}
return out, nil
}
func (s *memoryAuthStore) Save(_ context.Context, auth *coreauth.Auth) (string, error) {
if auth == nil {
return "", nil
}
s.mu.Lock()
defer s.mu.Unlock()
if s.items == nil {
s.items = make(map[string]*coreauth.Auth)
}
s.items[auth.ID] = auth
return auth.ID, nil
}
func (s *memoryAuthStore) Delete(_ context.Context, id string) error {
s.mu.Lock()
defer s.mu.Unlock()
delete(s.items, id)
return nil
}
func (s *memoryAuthStore) SetBaseDir(string) {}
+145 -145
View File
@@ -1,145 +1,145 @@
package management
import (
"net/http"
"sync"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/updates"
)
// updateState tracks the current update operation state.
type updateState struct {
mu sync.RWMutex
downloading bool
progress updates.DownloadProgress
downloadResult *updates.DownloadResult
lastError string
}
var currentUpdate = &updateState{}
func (h *Handler) GetUpdateInfo(c *gin.Context) {
info, err := updates.CheckForUpdates()
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
c.JSON(http.StatusOK, info)
}
// GetUpdateStatus returns the current update download status.
func (h *Handler) GetUpdateStatus(c *gin.Context) {
currentUpdate.mu.RLock()
defer currentUpdate.mu.RUnlock()
c.JSON(http.StatusOK, gin.H{
"downloading": currentUpdate.downloading,
"progress": currentUpdate.progress,
"ready": currentUpdate.downloadResult != nil,
"error": currentUpdate.lastError,
})
}
// DownloadUpdate starts downloading an update.
func (h *Handler) DownloadUpdate(c *gin.Context) {
var req struct {
Version string `json:"version"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "version is required"})
return
}
currentUpdate.mu.Lock()
if currentUpdate.downloading {
currentUpdate.mu.Unlock()
c.JSON(http.StatusConflict, gin.H{"error": "download already in progress"})
return
}
currentUpdate.downloading = true
currentUpdate.progress = updates.DownloadProgress{}
currentUpdate.downloadResult = nil
currentUpdate.lastError = ""
currentUpdate.mu.Unlock()
// Start download in background
go func() {
result, err := updates.DownloadUpdate(req.Version, func(progress updates.DownloadProgress) {
currentUpdate.mu.Lock()
currentUpdate.progress = progress
currentUpdate.mu.Unlock()
})
currentUpdate.mu.Lock()
currentUpdate.downloading = false
if err != nil {
currentUpdate.lastError = err.Error()
} else {
currentUpdate.downloadResult = result
}
currentUpdate.mu.Unlock()
}()
c.JSON(http.StatusAccepted, gin.H{"message": "download started"})
}
// VerifyUpdate verifies the downloaded update.
func (h *Handler) VerifyUpdate(c *gin.Context) {
currentUpdate.mu.RLock()
result := currentUpdate.downloadResult
currentUpdate.mu.RUnlock()
if result == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "no download available to verify"})
return
}
verifyResult, err := updates.VerifyDownload(result)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
c.JSON(http.StatusOK, verifyResult)
}
// InstallUpdate installs the downloaded update.
func (h *Handler) InstallUpdate(c *gin.Context) {
currentUpdate.mu.RLock()
downloadResult := currentUpdate.downloadResult
currentUpdate.mu.RUnlock()
if downloadResult == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "no download available to install"})
return
}
// Verify before install
verifyResult, err := updates.VerifyDownload(downloadResult)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
if !verifyResult.Valid {
c.JSON(http.StatusBadRequest, gin.H{"error": "verification failed: " + verifyResult.Message})
return
}
// Prepare the update (extract if needed)
executablePath, err := updates.PrepareInstall(downloadResult)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
// Install
installResult, err := updates.InstallUpdate(executablePath)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
c.JSON(http.StatusOK, installResult)
}
package management
import (
"net/http"
"sync"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/updates"
)
// updateState tracks the current update operation state.
type updateState struct {
mu sync.RWMutex
downloading bool
progress updates.DownloadProgress
downloadResult *updates.DownloadResult
lastError string
}
var currentUpdate = &updateState{}
func (h *Handler) GetUpdateInfo(c *gin.Context) {
info, err := updates.CheckForUpdates()
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
c.JSON(http.StatusOK, info)
}
// GetUpdateStatus returns the current update download status.
func (h *Handler) GetUpdateStatus(c *gin.Context) {
currentUpdate.mu.RLock()
defer currentUpdate.mu.RUnlock()
c.JSON(http.StatusOK, gin.H{
"downloading": currentUpdate.downloading,
"progress": currentUpdate.progress,
"ready": currentUpdate.downloadResult != nil,
"error": currentUpdate.lastError,
})
}
// DownloadUpdate starts downloading an update.
func (h *Handler) DownloadUpdate(c *gin.Context) {
var req struct {
Version string `json:"version"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "version is required"})
return
}
currentUpdate.mu.Lock()
if currentUpdate.downloading {
currentUpdate.mu.Unlock()
c.JSON(http.StatusConflict, gin.H{"error": "download already in progress"})
return
}
currentUpdate.downloading = true
currentUpdate.progress = updates.DownloadProgress{}
currentUpdate.downloadResult = nil
currentUpdate.lastError = ""
currentUpdate.mu.Unlock()
// Start download in background
go func() {
result, err := updates.DownloadUpdate(req.Version, func(progress updates.DownloadProgress) {
currentUpdate.mu.Lock()
currentUpdate.progress = progress
currentUpdate.mu.Unlock()
})
currentUpdate.mu.Lock()
currentUpdate.downloading = false
if err != nil {
currentUpdate.lastError = err.Error()
} else {
currentUpdate.downloadResult = result
}
currentUpdate.mu.Unlock()
}()
c.JSON(http.StatusAccepted, gin.H{"message": "download started"})
}
// VerifyUpdate verifies the downloaded update.
func (h *Handler) VerifyUpdate(c *gin.Context) {
currentUpdate.mu.RLock()
result := currentUpdate.downloadResult
currentUpdate.mu.RUnlock()
if result == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "no download available to verify"})
return
}
verifyResult, err := updates.VerifyDownload(result)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
c.JSON(http.StatusOK, verifyResult)
}
// InstallUpdate installs the downloaded update.
func (h *Handler) InstallUpdate(c *gin.Context) {
currentUpdate.mu.RLock()
downloadResult := currentUpdate.downloadResult
currentUpdate.mu.RUnlock()
if downloadResult == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "no download available to install"})
return
}
// Verify before install
verifyResult, err := updates.VerifyDownload(downloadResult)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
if !verifyResult.Valid {
c.JSON(http.StatusBadRequest, gin.H{"error": "verification failed: " + verifyResult.Message})
return
}
// Prepare the update (extract if needed)
executablePath, err := updates.PrepareInstall(downloadResult)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
// Install
installResult, err := updates.InstallUpdate(executablePath)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
c.JSON(http.StatusOK, installResult)
}
+1 -5
View File
@@ -26,12 +26,8 @@ func (h *Handler) GetUsageStatistics(c *gin.Context) {
if h != nil && h.usageStats != nil {
snapshot = h.usageStats.Snapshot()
}
usageStats := usage.ComputeUsageStats(snapshot)
c.JSON(http.StatusOK, gin.H{
"usage": usageStats,
"raw_snapshot": snapshot,
"usage": snapshot,
"failed_requests": snapshot.FailureCount,
})
}
+8 -8
View File
@@ -18,9 +18,9 @@ func NewTranslatorHandler() *TranslatorHandler {
// TranslationsMatrixResponse represents the response for the translations matrix endpoint.
type TranslationsMatrixResponse struct {
Matrix map[string][]string `json:"matrix"`
Formats []string `json:"formats"`
Total int `json:"total_translations"`
Matrix map[string][]string `json:"matrix"`
Formats []string `json:"formats"`
Total int `json:"total_translations"`
Details []translator.TranslationInfo `json:"details,omitempty"`
}
@@ -61,12 +61,12 @@ func (h *TranslatorHandler) GetTranslationsMatrix(c *gin.Context) {
// CheckTranslationResponse represents the response for checking a specific translation.
type CheckTranslationResponse struct {
Supported bool `json:"supported"`
Fallback bool `json:"fallback"`
From string `json:"from"`
To string `json:"to"`
Supported bool `json:"supported"`
Fallback bool `json:"fallback"`
From string `json:"from"`
To string `json:"to"`
Info *translator.TranslationInfo `json:"info,omitempty"`
Alternatives []string `json:"alternatives,omitempty"`
Alternatives []string `json:"alternatives,omitempty"`
}
// CheckTranslation checks if a specific translation path is supported.
@@ -214,4 +214,3 @@ func TestAgenticHarnessMiddleware_SessionStorage(t *testing.T) {
t.Error("Expected harness mode header to be set")
}
}

Some files were not shown because too many files have changed in this diff Show More