- Add provider-specific auth header hook to Provider trait
- Use x-api-key + anthropic-version for Claude upstream requests
- Keep bearer auth for Codex/default provider path
- Strengthen active-Claude routing test to assert Anthropic headers
- Keep Rust suite green (53/53)
- Add claude config section and ClaudeProvider skeleton
- Register Claude in provider registry without changing default runtime provider
- Add manual Claude account CLI path and provider-generic manual account helper
- Add targeted Claude account/state tests
- Keep Rust suite green (52/52)
- Make Provider trait object-safe with boxed future refresh API
- Add ProviderRegistry and active provider resolution
- Refactor proxy runtime, health, upstream routing, and refresh paths
to use active provider instead of hardcoded Codex wiring
- Preserve Codex refresh metadata through generic refresh flow
- Keep full Rust suite green (49/49)
- Add ProvidersConfig with active provider field to AppConfig
- Add active_provider() and active_provider_label() config methods
- Update example TOML with providers section
- Fix all test AppConfig constructions with ..AppConfig::default()
- All 49 tests pass
ensureAmpSignature injects signature:"" into tool_use blocks so the
Amp TUI does not crash on P.signature.length. when Amp sends the
conversation back, Claude rejects the extra field with 400:
tool_use.signature: Extra inputs are not permitted
strip the proxy-injected signature from tool_use blocks in
SanitizeAmpRequestBody before forwarding to the upstream API.
Added comprehensive tests to ensure key order is maintained when modifying payloads in `normalizeCacheControlTTL` and `enforceCacheControlLimit` functions. Removed unused helper functions and refactored implementations for better readability and efficiency.
Added comprehensive support for resolving proxy URLs from configuration based on API key and provider attributes. Introduced new helper functions and extended the test suite to validate fallback mechanisms and compatibility cases.
Added Poixe AI sponsorship information, including referral bonuses and platform capabilities, to README files in English, Japanese, and Chinese. Updated assets to include Poixe AI logo.
Introduce `StartAntigravityVersionUpdater` to periodically refresh the cached Antigravity version using a non-blocking background process. Updated main server flow to initialize the updater.
Fetch the latest version from the antigravity auto-updater releases
endpoint and cache it for 6 hours. Falls back to 1.21.9 if the API
is unreachable or returns unexpected data.
The review asked for the builtin tool registry helper to live with the rest
of executor support utilities. This moves the registry code into the helps
package, exports the minimal surface executor needs, and keeps behavior tests
with the executor while leaving registry-focused checks with the helper.
Constraint: Requested layout keeps executor helper utilities centralized under internal/runtime/executor/helps
Rejected: Keep the files in executor and reply with rationale | conflicts with requested package organization
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep executor behavior tests near applyClaudeToolPrefix and keep pure registry tests in helps
Tested: go test ./internal/runtime/executor/helps ./internal/runtime/executor -run 'Claude|Builtin|Tool'; go test ./test/...; go test ./...
Not-tested: End-to-end Claude Code direct-connect/session runtime behavior
Follow-up review found two real framing hazards in the handler-layer
framer: it could flush a partial `data:` payload before the JSON was
complete, and it could inject an extra newline before chunks that
already began with `\n`/`\r\n`. This commit tightens the framer so it
only emits undelimited events when the buffered `data:` payload is
already valid JSON (or `[DONE]`), skips newline injection for chunks
that already start with a line break, and avoids the heavier
`bytes.Split` path while scanning SSE fields.
The regression suite now covers split `data:` payload chunks,
newline-prefixed chunks, and dropping incomplete trailing data on
flush, so the original Responses fix remains intact while the review
concerns are explicitly locked down.
Constraint: Keep the follow-up limited to handler-layer framing and tests
Rejected: Ignore the review and rely on current executor chunk shapes | leaves partial data payload corruption possible
Rejected: Build a fully generic SSE parser | wider change than needed for the identified risks
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Do not emit undelimited Responses SSE events unless buffered `data:` content is already complete and valid
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers/openai -count=1
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers -count=1
Tested: /tmp/go1.26.1/go/bin/go vet ./sdk/api/handlers/...
Not-tested: Full repository test suite outside sdk/api/handlers packages
Line-oriented upstream executors can emit `event:` and `data:` as
separate chunks, but the Responses handler had started terminating
each incoming chunk as a full SSE event. That split `response.created`
into an empty event plus a later data block, which broke downstream
clients like OpenClaw.
This keeps the fix in the handler layer: a small stateful framer now
buffers standalone `event:` lines until the matching `data:` arrives,
preserves already-framed events, and ignores delimiter-only leftovers.
The regression suite now covers split event/data framing, full-event
passthrough, terminal errors, and the bootstrap path that forwards
line-oriented openai-response streams from non-Codex executors too.
Constraint: Keep the fix localized to Responses handler framing instead of patching every executor
Rejected: Revert to v6.9.7 chunk writing | would reintroduce data-only framing regressions
Rejected: Patch each line-oriented executor separately | duplicates fragile SSE assembly logic
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Do not assume incoming Responses stream chunks are already complete SSE events; preserve handler-layer reassembly for split `event:`/`data:` inputs
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers/openai -count=1
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers -count=1
Tested: /tmp/go1.26.1/go test ./sdk/api/handlers/... -count=1
Tested: /tmp/go1.26.1/go/bin/go vet ./sdk/api/handlers/...
Tested: Temporary patched server on 127.0.0.1:18317 -> /v1/models 200, /v1/responses non-stream 200, /v1/responses stream emitted combined `event:` + `data:` frames
Not-tested: Full repository test suite outside sdk/api/handlers packages
This change stops short of broader Claude Code runtime alignment and instead
hardens two safe edges: builtin tool prefix handling and source-informed
sentinel coverage for future drift checks.
Constraint: Must preserve existing default behavior for current users
Rejected: Implement control-plane/session alignment now | too much runtime risk for a first slice
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Treat the new fixtures as compatibility sentinels, not a full Claude Code schema contract
Tested: go test ./test/...; go test ./sdk/translator/...; go test ./internal/runtime/executor -run 'Claude|Builtin|Tool'; go test ./...
Not-tested: End-to-end Claude Code direct-connect/session runtime behavior
- Introduced new logging functions for websocket requests, handshakes, errors, and responses in `logging_helpers.go`.
- Updated `CodexWebsocketsExecutor` to utilize the new logging functions for improved clarity and consistency in websocket operations.
- Modified the handling of websocket upgrade rejections to log relevant metadata.
- Changed the request body key to a timeline body key in `openai_responses_websocket.go` to better reflect its purpose.
- Enhanced tests to verify the correct logging of websocket events and responses, including disconnect events and error handling scenarios.
delegate schema sanitization to util.CleanJSONSchemaForGemini and drop the top-level eager_input_streaming key to prevent validation errors when sending claude tools to the gemini api
Add ProxyPal (https://github.com/buddingnewinsights/proxypal) to the
community projects list in all three README files (EN, CN, JA).
Placed after CCS, restoring its original position.
ProxyPal is a cross-platform desktop app (macOS, Windows, Linux) that
wraps CLIProxyAPI with a native GUI, supporting multiple AI providers,
usage analytics, request monitoring, and auto-configuration for popular
coding tools.
Closes#2420
- Narrow websocket transcript replacement detection to assistant outputs and function calls
- Preserve existing merge behavior for follow-up developer messages without previous_response_id
- Add a regression test covering mid-session developer message updates
- Add shouldReplaceWebsocketTranscript() to detect historical model output in input
- Add normalizeResponseTranscriptReplacement() for full transcript reset handling
- Prevent duplicate stale turn-state when clients replace local history post-compaction
- Avoid orphaned function_call items from incremental append on compact transcripts
- Add unit tests for transcript replacement detection and state reset behavior
Reverts the streaming thinking suppression introduced in b15453c.
rewriteStreamEvent should only inject signatures and rewrite model
names — suppressing thinking blocks in streaming mode breaks SSE
index alignment and causes the Amp TUI to render empty responses
on the second message onward (especially with model-mapped
non-Claude providers like GPT-5.4).
Non-streaming responses still suppress thinking when tool_use is
present via rewriteModelInResponse.
When a Claude assistant message contains [text, tool_use, text], the
Antigravity API internally splits the model message at functionCall
boundaries, creating an extra assistant turn between tool_use and the
following tool_result. Claude then rejects with:
tool_use ids were found without tool_result blocks immediately after
Fix: extend the existing 2-way part reordering (thinking-first) to a
3-way partition: thinking → regular → functionCall. This ensures
functionCall parts are always last, so Antigravity's split cannot
insert an extra assistant turn before the user's tool_result.
Fixes#989
- Call suppressAmpThinking in rewriteStreamEvent for streaming path
- Handle nil return from suppressAmpThinking to skip suppressed events
- Narrow looksLikeSSEChunk to line-prefix detection (HasPrefix vs Contains)
- Initialize suppressedContentBlock map in test
Emit signature only when non-empty in both streaming content_block_start
and non-streaming thinking blocks. Avoids turning 'missing signature'
into 'empty/invalid signature' which Claude clients may reject.
Drop the last affinity-related executor artifacts so the PR stays focused on the minimal Codex continuity fix set: stable prompt cache identity, stable session_id, and the executor-only behavior that was validated to restore cache reads.
Drop the chat-completions translator edits from this PR so the branch complies with the repository policy that forbids pull-request changes under internal/translator. The remaining PR stays focused on the executor-level Codex continuity fix that was validated to restore cache reuse.
Remove the experimental auth-affinity routing changes from this PR so it stays focused on the validated Codex continuity fix. This keeps the prompt-cache repair while avoiding unrelated routing-policy concerns such as provider/model affinity scope, lifecycle cleanup, and hard-pin fallback semantics.
Keep sticky auth affinity limited to matching providers and stop persisting execution-session IDs as long-lived affinity keys so provider switching and normal streaming traffic do not create incorrect pins or stale affinity state.
Stop using one-shot idempotency keys as long-lived auth-affinity identifiers and remove raw affinity-key values from debug logs so sticky routing keeps its continuity benefits without creating avoidable memory growth or credential exposure risks.
Restore Claude continuity after the continuity refactor, keep auth-affinity keys out of upstream Codex session identifiers, and only persist affinity after successful execution so retries can still rotate to healthy credentials when the first auth fails.
Align websocket continuity resolution with the HTTP Codex path, make auth-affinity principal keys use a stable string representation, and extract small helpers that remove duplicated continuity and affinity logic without changing the validated cache-hit behavior.
Prompt caching on Codex was not reliably reusable through the proxy because repeated chat-completions requests could reach the upstream without the same continuity envelope. In practice this showed up most clearly with OpenCode, where cache reads worked in the reference client but not through CLIProxyAPI, although the root cause is broader than OpenCode itself.
The proxy was breaking continuity in several ways: executor-layer Codex request preparation stripped prompt_cache_retention, chat-completions translation did not preserve that field, continuity headers used a different shape than the working client behavior, and OpenAI-style Codex requests could be sent without a stable prompt_cache_key. When that happened, session_id fell back to a fresh random value per request, so upstream Codex treated repeated requests as unrelated turns instead of as part of the same cacheable context.
This change fixes that by preserving caller-provided prompt_cache_retention on Codex execution paths, preserving prompt_cache_retention when translating OpenAI chat-completions requests to Codex, aligning Codex continuity headers to session_id, and introducing an explicit Codex continuity policy that derives a stable continuity key from the best available signal. The resolution order prefers an explicit prompt_cache_key, then execution session metadata, then an explicit idempotency key, then stable request-affinity metadata, then a stable client-principal hash, and finally a stable auth-ID hash when no better continuity signal exists.
The same continuity key is applied to both prompt_cache_key in the request body and session_id in the request headers so repeated requests reuse the same upstream cache/session identity. The auth manager also keeps auth selection sticky for repeated request sequences, preventing otherwise-equivalent Codex requests from drifting across different upstream auth contexts and accidentally breaking cache reuse.
To keep the implementation maintainable, the continuity resolution and diagnostics are centralized in a dedicated Codex continuity helper instead of being scattered across executor flow code. Regression coverage now verifies retention preservation, continuity-key precedence, stable auth-ID fallback, websocket parity, translator preservation, and auth-affinity behavior. Manual validation confirmed prompt cache reads now occur through CLIProxyAPI when using Codex via OpenCode, and the fix should also benefit other clients that rely on stable repeated Codex request continuity.
The Codex/OpenAI Responses API does not support the stream_options
parameter. When clients (e.g. Amp CLI) include stream_options in their
requests, CLIProxyAPI forwards it as-is, causing a 400 error:
{"detail":"Unsupported parameter: stream_options"}
Strip stream_options alongside the other unsupported parameters
(previous_response_id, prompt_cache_retention, safety_identifier)
in Execute, ExecuteStream, and CountTokens.
- Read maxAssetDownloadSize+1 bytes and error if exceeded, preventing
silent truncation that could write a broken management.html to disk
- Log explicit warning when fallback URL is used without digest
verification, so users are aware of the reduced security guarantee
- Abort update when SHA256 digest mismatch is detected instead of
logging a warning and proceeding (prevents MITM asset replacement)
- Cap asset download size to 10 MB via io.LimitReader (defense-in-depth
against OOM from oversized responses)
- Add `auto-update-panel` config option (default: false) to make the
periodic background updater opt-in; the panel is still downloaded
on first access when missing, but no longer silently auto-updated
every 3 hours unless explicitly enabled
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).
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.
- 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.
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.
- 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
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.
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.
Address two blocking issues from PR review:
- Auth file now named vertex-{prefix}-{project}.json so importing the
same project with different prefixes no longer overwrites credentials
- Prefix containing "/" is rejected at import time instead of being
silently ignored at runtime
- Add prefix to in-memory metadata map for consistency
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
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.
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>
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>
- 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>
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.
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.
When an auth file is deleted and re-created with the same path/ID, the
new auth could inherit stale ModelStates (cooldown/backoff) from the
previously disabled entry, preventing it from being routed.
Gate runtime state inheritance (ModelStates, LastRefreshedAt,
NextRefreshAfter) on both existing and incoming auth being non-disabled
in Manager.Update and Service.applyCoreAuthAddOrUpdate.
Closes#2061
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>
Add Manager.ReconcileRegistryModelStates to clear stale per-model runtime failures for models currently registered in the global model registry. The method finds models supported for an auth, resets non-clean ModelState entries, updates aggregated availability, persists changes, and pushes a snapshot to the scheduler. Introduce modelStateIsClean helper to determine when a model state needs resetting. Call ReconcileRegistryModelStates from Service paths that register/refresh models (applyCoreAuthAddOrUpdate and refreshModelRegistrationForAuth) to keep the scheduler and global registry aligned after model re-registration.
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.
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
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.
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.
When adjustedBudget < minBudget, the previous fix blindly set
max_tokens = budgetTokens+1 which could exceed MaxCompletionTokens.
Now: cap max_tokens at MaxCompletionTokens, recalculate budget, and
disable thinking entirely if constraints are unsatisfiable.
Add unit tests covering raise, clamp, disable, and no-op scenarios.
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.
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.
- 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.
1. Always include interleaved-thinking-2025-05-14 beta header so that
thinking blocks are returned correctly for all Claude models.
2. Remove status-code guard in AMP reverse proxy ModifyResponse so that
error responses (4xx/5xx) with hidden gzip encoding are decoded
properly — prevents garbled error messages reaching the client.
3. In normalizeClaudeBudget, when the adjusted budget falls below the
model minimum, set max_tokens = budgetTokens+1 instead of leaving
the request unchanged (which causes a 400 from the API).
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.
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.
- 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.
- 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>
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.
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.
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
- 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.
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.
Closesrouter-for-me/CLIProxyAPI#1868
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.
- 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
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.
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
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.
## 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>
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>
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.
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.
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.
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.
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.
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.
- 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
- 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
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.
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
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>
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.
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.
- 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.
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.
- 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.
- 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.
- 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.
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.
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.
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
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
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.
- 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.
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.
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>
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)
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.
- 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.
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.)
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).
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>
- 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`.
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.
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>
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
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.
- 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`.
- 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.
- Added support to extract and include `cachedContentTokenCount` in `usage.prompt_tokens_details`.
- Logged warnings for failures to set cached token count for better debugging.
- 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.
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
- 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>
- Replaced all instances of `bytes.Clone` with direct references to enhance efficiency.
- Simplified payload handling across executors and translators by eliminating unnecessary data duplication.
- 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.
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
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
- 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.
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
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
- 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.
- 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
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.
- 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.
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>
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>
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>
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>
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>
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>
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>
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>
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>
Cherry-picked from upstream 7ff3936e
Adds multi-turn cache control tests.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
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>
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>
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>
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`.
- 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.
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.
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>
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>
- 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>
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>
- 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>
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>
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>
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>
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>
- 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>
- 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.
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>
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>
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>
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.
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>
Introduce `TestExecuteStreamWithAuthManager_DoesNotRetryAfterFirstByte` to validate that stream executions do not retry after receiving partial responses. Implement `payloadThenErrorStreamExecutor` for test coverage of this behavior.
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.
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.
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.
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.
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.
- 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
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.
- 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
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.
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.
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
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
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.
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
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)
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.
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
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
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.
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.
- 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.
- 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.
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
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.
Rename include_thoughts to includeThoughts across all translator files
for consistency with the Gemini API field naming convention.
Cherry-picked key change from d5ef4a6d.
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
- 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.
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.
- 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.
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.
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
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.
- 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
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)
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.
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
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
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
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.
- 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.
- 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.
- Added conditional logic for Codex instruction injection based on configuration.
- Updated role terminology from "user" to "developer" for better alignment with context.
- Added logic to transform `inputResults` into structured JSON for improved processing.
- Removed redundant `safety_identifier` field in executor payload to streamline requests.
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)
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)
- 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.
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.
- 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.
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.
- 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.
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.
feat(translator): add function name to response output item serialization
- Included `item.name` in the serialized response output to enhance output item handling.
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.
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>
- 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.
- 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.
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.
- 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
- 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
- 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
New Accounts submenu:
- Copy Account List (-list-accounts)
- Cleanup Expired (-cleanup-expired)
- Export Accounts... (-export-accounts)
- Import Accounts... (-import-accounts)
All menu items harness CLI binary for single source of truth.
Add menu items to copy CLI output to clipboard:
- Copy Account Status (account health summary)
- Copy Usage Stats (token usage by provider)
- Copy Model List (available models)
- Copy Recent Logs (last 100 log entries)
Uses stdout capture to get formatted CLI output.
- Add -usage flag (token usage stats per provider)
- Add -logs flag (view recent logs, -n for line count)
- Add -refresh flag (force token refresh)
- Add -list-models flag (show available models)
- Add -export-accounts/-import-accounts (backup/restore)
- Add --include-tokens and --force flags for export/import
- install.ts: read version from package.json (auto-sync)
- release.yml: manual dispatch only (no auto-trigger on tags)
- proxypilot-release.yml: add checksums.txt generation
- Add 26 tests for SetLogLevel() in logging package
- Add 6 tests for AppError in errors package
- Add 10 tests for SDKConfig in config package
- Add 3 tests for EmailRequiredError in sdk/auth
- Remove dead code: GeminiCLIToken type alias, LoadGeminiCLIToken,
LoadGeminiCLITokenFromPath (no callers found)
- Add tests for gemini auth (CredentialFileName, SaveTokenToFile)
Cherry-picked from e8e3bc86. Adds HttpRequest method to ProviderExecutor
interface for injecting credentials into arbitrary HTTP requests.
- Added HttpRequest to conductor.go interface
- Added HttpRequest stubs to kiro, minimax, zhipu executors
- Added http-request example
- Updated mock executors in tests
Also kept our Embed method and CountTokens implementations.
- feat(executor): enhance Antigravity payload with user role and dynamic system instructions
- feat(executor): add model-specific support for "gemini-3-pro" in execution
- feat(executor): update system instruction handling for Claude and Gemini-3-Pro models
- fix(executor): update gemini model identifier to gemini-3-pro-preview
- feat(executor): centralize systemInstruction handling
Cherry-picked: 67985d82, bda04eed, 1b2f9076, b6a0f7a0, 59a448b6
- fix(logging): improve request/response capture
- fix(handlers): match raw error text before JSON body for duplicate detection
- feat(logging): disambiguate OAuth credential selection in debug logs
- Various logging refinements for auth selection
Cherry-picked from upstream: a091d12f, 3ca5fb10, 0e4148b2, 79fbcb3e, 48f6d7ab, 48f19aab, cb3bdffb, a95428f2
- Add internal/auth/antigravity package with token loading from ~/.gemini/oauth_creds.json
- Add ImportFromGeminiCLI method to AntigravityAuthenticator
- Add DoAntigravityImport CLI command
- Add --antigravity-import flag to server binary
Usage: proxypilot --antigravity-import
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.
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
Update the model name check in `buildRequest` to target "gemini-3-pro-preview" instead of "gemini-3-pro" when applying specific system instruction handling.
Routes requests to the account with lowest daily output tokens.
Spreads load across accounts to avoid hitting quota limits.
Config: routing.strategy = "usage-aware" or "least-used"
Initialize response/prompt caches in Service.Run from config.
Add cache lookup to executor payload helpers.
Document cache config and management API in README.
ProviderLogins table now shows:
- Priority column with up/down reorder buttons
- Expires column with color-coded status (green/yellow/red)
API exposes token_expires_at for WebUI consumption.
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>
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>
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>
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.
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
- Add Priority field to Auth for per-provider account ordering
- Add UsageStats struct tracking total/daily tokens and requests
- Track usage in MarkResult with daily reset logic
- Add TokenExpiresAt for proactive refresh (5min buffer)
- Sort available auths by priority in selector
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.
Fixed incorrect boundary logic for `message_delta` emission, ensuring proper handling of usage updates and `emitMessageStopIfNeeded` within the response loop.
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.
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.
Replaced file-based auth entry counting with `TokenStore`-backed implementation, enhancing flexibility and context-aware token management. Updated related logic to reflect this change.
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.
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.
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>
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>
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>
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.
COMPLETED:
- Added ViewWithSize(width, height) pattern to all submodels
- login.go: responsive provider rows with adaptive widths
- switch.go: responsive agent rows without card borders
- mappings.go: responsive table columns with calculateColumnWidths()
- usage.go: responsive stat cards (2x2 grid layout)
- logs.go: responsive log entries with message truncation
- Fixed main View() layout calculation in tui.go
- Properly accounts for border (2) + padding (2) = 4 chars per panel
- sidebarWidth now represents content width (20/14 for normal/narrow)
- contentWidth = m.width - sidebarWidth - 9 (accounts for both panels)
- Added new screen files:
- integrations.go: setup/integration screen
- logs.go: real-time log viewer with filtering
- mappings.go: model alias mappings table
- usage.go: usage statistics with charts
PENDING TEST:
- Verify sidebar displays correctly alongside content (was overflowing)
- Test all screens at various terminal widths (60, 80, 100+ cols)
KNOWN ISSUE BEING FIXED:
- Sidebar was showing only "[8] Setup" at top due to width overflow
- Content panel was too wide, causing horizontal wrap
Cherry-picked fixes:
- fix(antigravity): inject required placeholder when properties exist without required
- fix(translators): correct key path for system_instruction.parts in Claude request logic
- Add package.json with bun postinstall script
- Add install.ts for binary download
- Add bin wrapper script
- Add README with usage instructions
- Version 0.1.0
Add 'Shell' button per agent that opens modal displaying environment
variables and shell profile configuration snippets. Includes copy-to-
clipboard functionality for easy shell integration.
Add live/history toggle, date range filtering, model/provider/status
filters, pagination, export/import/clear buttons, and statistics display.
Fetches from persistent /request-history endpoint.
Add standalone ppswitch binary for fast agent configuration switching
without server logging overhead. Usage:
- ppswitch Show all agent statuses
- ppswitch <agent> Show specific agent status
- ppswitch <agent> <mode> Switch agent to proxy/native mode
Add --switch and --mode flags plus subcommand-style 'proxypilot switch'
syntax for quick agent configuration switching. Supports both flag style
(--switch claude --mode proxy) and subcommand style (proxypilot switch
claude proxy).
Add DoSwitch() and DoSwitchStatusAll() for switching agent configs
between proxy mode (routed through ProxyPilot) and native mode (direct
API access). Supports claude, gemini, codex, opencode, droid, cursor,
kilo, and roocode agents with backup/restore functionality.
Add GET/PUT /thinking-budget endpoint for configuring extended
thinking token budgets. Supports preset levels (Low 2048, Medium 8192,
High 32768) and custom values with enable/disable toggle.
Add management endpoints for request history:
- GET /request-history - list entries with pagination
- GET /request-history/stats - aggregate statistics
- DELETE /request-history - clear all entries
- POST /request-history/export - export to JSON
- POST /request-history/import - import from JSON
- POST /request-history/save - force save to disk
Integrate RequestHistoryManager with request logging middleware.
Add RequestHistoryManager with file-based persistence at
~/.cli-proxy-api/request-history.json. Features:
- Max 500 entries with automatic pruning
- Auto-save every 30 seconds
- Thread-safe with mutex protection
- In-memory ring buffer for performance
Add GetShellConfig() to AgentHandler interface returning ShellConfigInfo
with environment variables and shell profile snippets. Implement for all
agents: Claude Code, Codex, Gemini CLI, Cursor, OpenCode, Factory Droid,
and Amazon Q CLI.
Major overhaul of agent integration system:
- Add support for additional agent types
- Improve configuration detection and management
- Better error handling and validation
- Add --minimax-login, --zhipu-login for API key providers
- Add --amazonq-import for Amazon Q CLI token import
- Add --kiro-import for Kiro IDE token import
- Add --kiro-aws-login for AWS Builder ID flow
- Improve agent detection logic for multiple CLI tools
- Add support for detecting Amazon Q CLI, OpenCode
- Better path resolution and state management
Add React-based UI for the custom installer:
- Clean modern installation wizard interface
- Progress tracking and status display
- TypeScript + Vite build
Document the migration from iFlow to MiniMax and Zhipu AI providers.
Includes:
- Summary of changes
- Files deleted/created/modified
- New model definitions
- API details for new providers
- Auth file format examples
- Migration notes for existing users
Remove the iFlow OAuth and cookie-based authentication implementation.
This provider is being replaced with simpler API key-based providers.
Deleted files:
- internal/auth/iflow/cookie_helpers.go
- internal/auth/iflow/iflow_auth.go
- internal/auth/iflow/iflow_token.go
- internal/auth/iflow/oauth_server.go
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
Includes:
- Vision base64 parsing fix for OpenAI-to-Claude translation
- Memory API localhost authentication with API keys
- Global model mapping SDK hook for cross-provider aliases
- Comprehensive unit tests for auth, config, memory, and runtime
Adds GlobalModelMapperFunc type and hook to SDKConfig, allowing
SDK-level handlers to access Config-level global model mappings.
This enables cross-provider model aliasing (e.g., gpt-4o → claude-sonnet).
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.
Fixesrouter-for-me/CLIProxyAPI#630
This release removes the need for a separate proxypilot-engine.exe binary.
The ProxyPilot.exe tray app now runs the proxy service in-process using
the cliproxy SDK builder pattern.
Changes:
- Add internal/embedded package for in-process server management
- Update desktopctl to support embedded mode alongside subprocess mode
- Clean up vestigial -exe flag and engine binary references
- Update package scripts to build only single binary
- Bump version to 0.1.2
The embedded engine in cmd/cliproxytray was already implemented; this
commit cleans up the remaining references to the old two-binary architecture.
Prepare release v0.1.1 with new features:
- Model-specific pricing for cost estimation
- Auto-update with download, verify, and install flow
- Cost savings display in Analytics
- Logo branding assets
Update Header with logo display, improve AgentSetup and ProviderLogins
components. Update App.tsx and index.html for better structure.
Adjust Vite config for development.
Add complete update workflow with stages: checking, available, downloading,
ready, installing. Show download progress bar, version info, and release
notes. Add Install & Restart button for applying updates.
Add Cost Savings hero card showing proxy cost vs direct API cost with
visual comparison bars. Add Cost column to Model Breakdown table.
Display savings percentage and total amount saved.
Add handlers for update status, download, verify, and install operations.
Register new routes: GET /updates/status, POST /updates/download,
POST /updates/verify, POST /updates/install. Track download progress
with background goroutine and mutex-protected state.
Add install.go with archive extraction (zip, tar.gz) and binary replacement
logic. Windows uses batch script for safe replacement of running executable.
Unix directly replaces binary with backup. Includes cleanup for old versions.
Add DownloadUpdate function to download platform-specific binaries from
GitHub releases with progress tracking. Add verify.go with SHA256 checksum
verification for downloaded files. Fix GitHub repo URL and add 404 handling
for repositories without releases.
Add comprehensive pricing table for Claude, GPT, Gemini, Qwen, and DeepSeek
models with per-million-token rates. Update cost calculation to use actual
model pricing instead of hardcoded estimates. Add new cost fields to
UsageStats for tracking actual cost, direct API cost, and savings.
- 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
- Add agent detection and configuration bindings
- Add update check and download bindings
- Add usage and request monitoring bindings
- Update useProxyContext with new desktop API hooks
- Refactor EngineControl with new status indicators
- Update Integrations with provider cards
- Enhance LogsViewer with better filtering and display
- Improve MemoryManager with modern UI patterns
- Update ModelMappings with collapsible sections
- Refactor ProviderLogins with OAuth flow improvements
- Update SemanticMemory styling
- Add versioninfo.json for goversioninfo in tray and server
- Generate resource.syso files with embedded icon
- Update ico.go to embed actual icon.ico for tray
- All exes now show ProxyPilot logo in File Explorer
- Embed React dashboard assets in tray binary
- Open dashboard in WebView2 window from tray
- Remove need for separate proxypilotui.exe
- Simplifies distribution to just ProxyPilot.exe + proxypilot-engine.exe
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove logo and test files from tracking
- Keep files locally but exclude from repo
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Credits Factory.ai and Anthropic for their research on context
compression and building effective agents.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Cleaner centered branding with star badge
- Bold tagline with concise value prop
- GitHub tip callout for latest models
- Emoji bullet feature list
- Simplified sections
- Setup guide links
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removed dead code (commented-out ErrTokenExpired error constant) from
both claude/errors.go and codex/errors.go.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removed redundant `_ "embed"` import as `embed` is already imported
and used for embed.FS.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove desktop-ui-spec.md and windows-ui-spec.md which reference
deleted cliproxyctl CLI that no longer exists.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Type was defined but never used anywhere in codebase.
Keep EmailRequiredError which is actively used.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Document Factory.ai context compression and Anthropic agentic harness
implementations with architecture diagrams and configuration reference.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Test context compression adapter and harness middleware work together
without conflicts.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removed feature not present in original Factory.ai or Anthropic sources.
Keep implementation pure to research references.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enable Anthropic-style INITIALIZER/CODING mode prompts for long-running
agentic clients.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add coreManagerWrapper to adapt auth manager types and initialize
LLM-based summarization after server creation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enables Factory.ai-style LLM summarization by wiring the summarizer
executor to the core auth manager.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Bridge type differences between coreauth.Manager and memory.AuthExecutor
to enable LLM-based context compression through the auth pipeline.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Centered logo and badges
- Catchy tagline "Stop juggling API keys"
- Emoji-styled feature list
- Latest models callout section
- Cleaner installation/usage sections
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add downloadBlob helper to reduce duplication
- Refactor export functions to use helper
- Fix model mapping edit to use controlled React state
instead of DOM getElementById manipulation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Delete input.tsx, progress.tsx, tabs.tsx - none were imported
or used anywhere in the codebase.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Complete rewrite with:
- ProxyPilot branding and badges
- Feature list and architecture overview
- Quick start and configuration guide
- API endpoints documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove internal/letta/ package (unused memory bridge)
- Remove Letta references from run.go and start-cliproxy.ps1
- Move docker-build scripts to scripts/
- Move TROUBLESHOOTING_ANTIGRAVITY.md and WARP.md to docs/
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update droid.go to use ~/.factory/settings.json (runtime config)
- Add /healthz endpoint for Droid health checks
- Add root-level API routes (/responses, /messages, etc.)
- Fix detection in proxypilotui to check settings.json
- Use thinking models with provider: "openai" for Responses API
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add WebView2 JavaScript bindings:
- pp_detect_agents: List installed CLI agents
- pp_configure_agent: Configure agent for ProxyPilot
- pp_get_model_mappings: Get global mappings
- pp_save_model_mappings: Save global mappings
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove bloated React bundle (~500KB) in favor of
simple embedded HTML (~15KB). Update embed.go to
only include index.html and vite.svg.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Generate config files to point CLI agents at ProxyPilot:
- Claude Code: ~/.claude/settings.json
- Codex CLI: ~/.codex/config.toml
- Factory Droid: ~/.factory/config.json
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Detect installed CLI agents (Claude Code, Codex, Droid, Gemini)
by checking binaries and config files.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add global-model-mappings section to config.example.yaml
showing smart/rush/think aliases.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add API handler for managing global model mappings
stored in ~/.proxypilot/model-mappings.json.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add GlobalModelMapping struct and LookupGlobalModelMapping()
for routing friendly model names to actual models.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add CRUD operations for harness files:
- GET /v0/management/harness/files - list files
- GET /v0/management/harness/file - read file
- PUT /v0/management/harness/file - write file
- GET /v0/management/harness/export - export all
- POST /v0/management/harness/import - import files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Improve INITIALIZER and CODING prompts based on Anthropic guidance:
- Structured feature_list.json format
- GET BEARINGS workflow for coding mode
- Puppeteer MCP detection for browser testing
- Session-aware state detection
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add utilities for estimating token counts using tiktoken
to support token-aware compression decisions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement proactive compression based on token count rather than bytes:
- Uses tiktoken for accurate token estimation
- Compresses at 75% threshold before hitting limits
- Reserves tokens for output generation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update file_store.go with BuildAnchoredSummaryWithLLM() for
generating context-aware summaries during compression.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add structured summary generation for context compression:
- structured_summary.go: Types and parsing for summaries
- summarizer.go: LLM summarization logic
- summarizer_executor.go: Routes to LLM pipeline
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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.
- 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
883 changed files with 158990 additions and 33925 deletions
**What does not belong here:** service command definitions (use `.factory/services.yaml`).
---
## Validation Surface
### HTTP runtime surface
- Endpoints:
-`GET /healthz`
-`GET /v0/runtime/stats`
- supported local Codex proxy routes touched by runtime tracking
- Primary tools:
-`curl`
- Rust mocked endpoint tests
- Validation focus:
- local health identity
- runtime stats schema and semantics
- request counters
- proactive refresh
- 401 retry refresh
- refresh failure tracking
### TUI surface
- Command:
-`cargo run -p proxypilot-rs -- tui --config <path>`
- Primary tools:
-`tuistory`
- manual local smoke when needed
- Validation focus:
- runtime/auth visibility
- truthful footer/help text
- local account visibility when runtime is down
- reload, clear feedback, selected refresh, active refresh-now
- readable empty/error states
### CLI/account surface
- Commands:
-`init`
-`account add-codex`
-`account list`
-`account activate`
-`account remove`
-`account refresh-codex`
- Primary tools:
- shell
- Validation focus:
- config creation semantics
- disk-backed account lifecycle semantics
- refreshable vs static-account behavior
## Validation Concurrency
- Automated Rust validation activities: max `2` concurrent
- rationale: machine has ample memory/CPU, but Rust tests plus local mocked listener flows should stay conservative
- Manual TUI validation: max `1` at a time
- rationale: interactive terminal verification is not realistically parallel and should not overlap with another heavy manual runtime smoke
## Setup Notes
- Baseline automated validation does not require live external credentials.
- Prefer mocked local upstream and refresh fixtures for HTTP/runtime tests.
- TUI validation requires a local config file and usually a running local Rust proxy for runtime-visible scenarios.
- Proxy-down scenarios are also required: validators should verify local disk-backed account visibility when runtime is unreachable.
## Flow Validator Guidance: shell
- Use only `.factory/validation/terminal-operator-console/user-testing/fixtures/cli-shell/` plus `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/evidence/terminal-operator-console/cli-shell/`.
- Use temporary config/state files inside that fixture directory; do not modify repo-root default configs.
- Stay on CLI/account flows only; do not start long-lived proxy services from this fixture.
- Do not use live device-login. Prefer `init`, `account add-codex`, `account list`, `account activate`, `account remove`, and negative-path `account refresh-codex` checks against local fixture state.
- If refresh-success validation cannot be isolated without live OpenAI OAuth, record it as blocked with concrete evidence rather than using private credentials.
## Flow Validator Guidance: curl
- Use only `.factory/validation/terminal-operator-console/user-testing/fixtures/http-runtime/` plus `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/evidence/terminal-operator-console/http-runtime/`.
- Own ports `18318-18339` for this validator only. Keep the proxy on `127.0.0.1:18318` unless a collision forces another port in that range.
- Mock the Codex upstream locally; never send `/v1/*` validation traffic to the real OpenAI upstream.
- Auth-refresh success paths may be blocked if the running binary cannot be pointed at a local OAuth token stub. Failure-path validation with intentionally invalid refresh tokens is allowed if it stays within the assigned fixture.
- Capture before/after `curl` output for stats-changing requests so counter deltas are explicit.
## Flow Validator Guidance: tuistory
- Use only `.factory/validation/terminal-operator-console/user-testing/fixtures/tui-console/` plus `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/evidence/terminal-operator-console/tui-console/`.
- Run only one TUI session at a time.
- Own ports `18418-18439` for proxy/mock services used by this validator. Keep runtime-down scenarios fully local by stopping those fixture services instead of touching shared ports.
- Keep disk-backed state isolated to the assigned fixture config/state files so reload, activate, delete, and refresh actions are attributable to this validator alone.
- Capture snapshots before and after each key flow (`r`, `a`, `d`, `f`, `R`, `c`) and note whether feedback came from local disk state or live runtime stats.
## Discovered Validation Quirks
- CLI `account refresh-codex` and runtime-triggered refresh paths now honor `codex.refresh_token_url` when set, so validators can redirect refresh success to a local stub from the real user surface while still relying on the built-in OpenAI OAuth endpoint when the override is unset.
-`tuistory` sessions should be closed explicitly after the TUI exits with `q`; the PTY can remain allocated even after the binary terminates.
- In runtime-down TUI scenarios, selected-account refresh (`f`) still attempts the hardwired OAuth refresh exchange for refreshable saved accounts and surfaces that remote failure text. Treat that as truthful runtime-dependent behavior, not as loss of local disk state.
description:Implement Rust terminal-operator-console features for proxypilot-rs with test-first discipline and truthful runtime/TUI verification.
---
# Rust Operator Worker
NOTE: Startup and cleanup are handled by `worker-base`. This skill defines the WORK PROCEDURE.
## When to Use This Skill
Use for features in the Rust replatform slice that touch `proxypilot-rs` runtime/auth logic, local HTTP observability, CLI/account coherence, or the terminal operator console.
## Required Skills
-`tdd` — invoke before implementation to drive failing tests first for new runtime/auth/TUI helper behavior.
-`tuistory` — invoke when manually validating terminal operator-console behavior.
-`verification-before-completion` — invoke before claiming the feature is complete so evidence matches the actual commands and outputs.
## Work Procedure
1. Read `mission.md`, `validation-contract.md`, mission `AGENTS.md`, and `.factory/library/*.md` relevant to the feature before editing.
2. Confirm which validation assertions the feature fulfills and restate them in your notes.
3. Write or update failing Rust tests first (red) for the feature's intended behavior before changing implementation.
4. Implement the smallest Rust changes needed to make those tests pass while preserving the mission boundaries:
- keep the work inside the Rust replatform slice unless docs are explicitly part of the feature
- prefer shared auth/runtime helpers over duplicating logic
- keep runtime-memory state distinct from disk-backed saved state
5. Run focused checks during iteration, then the required final validators:
6. If the feature affects the TUI or runtime observability surface, perform manual verification with `tuistory` or equivalent local smoke and capture what changed on screen or via local HTTP output.
7. Review the changed files for truthfulness of operator-visible wording, especially where runtime state and disk state can diverge.
8. Produce a handoff that cites exact commands, tests added, interactive checks, and any discovered gaps.
## Example Handoff
```json
{
"salientSummary":"Added a shared auth-health/runtime model plus `/v0/runtime/stats`, then wired the TUI runtime panel to the new stats surface. Ran fmt/tests successfully and manually verified runtime counters plus active-account refresh feedback in the terminal UI.",
"whatWasImplemented":"Created a shared runtime/auth module for auth-health classification and refresh status, extended proxy state with in-memory counters and last refresh metadata, added GET /v0/runtime/stats with stable fields, and updated the TUI to render runtime stats while keeping disk-backed account controls separate.",
"observation":"Formatting completed without changes needed after final pass."
},
{
"command":"cargo test --manifest-path rust/Cargo.toml",
"exitCode":0,
"observation":"Workspace tests passed, including new runtime stats and auth-health cases."
}
],
"interactiveChecks":[
{
"action":"Launched proxypilot-rs TUI against a local fixture config, pressed `r`, `R`, and `c`, and inspected the runtime/auth panel.",
"observed":"Runtime counters and last refresh outcome became visible, active-account refresh targeted the active account even when another row was selected, and clear-feedback only cleared the transient status line."
}
]
},
"tests":{
"added":[
{
"file":"rust/proxypilot-rs/src/proxy.rs",
"cases":[
{
"name":"runtime_stats_reset_after_restart",
"verifies":"In-memory runtime stats start empty on fresh process start and do not persist across restarts."
"verifies":"A single client request that triggers 401 and retry increments upstream 401 and refresh counters without double-counting total proxied requests."
}
]
}
]
},
"discoveredIssues":[]
}
```
## When to Return to Orchestrator
- The feature requires changing mission boundaries or touching non-Rust product surfaces outside the approved scope.
- The intended behavior cannot be implemented truthfully without clarifying runtime-vs-disk ownership semantics.
- A required local validation path cannot be exercised because config/fixtures/runtime setup is missing or broken.
- The feature reveals a larger refactor is needed than fits a single worker session.
"summary":"Reviewed feature commit 1c2396bb together with the directly relevant follow-up fixes f4ae033c and cea7a0f4. CLI wording, docs alignment, static-account refresh errors, and runtime-vs-disk refresh targeting are much clearer after those changes, but the TUI footer layout still prevents the new explanatory copy from being visible.",
"issues":[
{
"file":"rust/proxypilot-rs/src/tui.rs",
"line":389,
"severity":"blocking",
"description":"The footer block is still allocated `Constraint::Length(3)` even though it now renders four content lines (feedback, selected-account hint, runtime status hint, and key help) inside a bordered paragraph at lines 523-534. In ratatui that height leaves room for only a single inner text row, so the newly added runtime/disk guidance and keybinding help are clipped off-screen. That means the feature does not actually make the cross-surface behavior explicit to operators, and docs/tests now describe footer copy that users cannot see."
}
]
},
"sharedStateObservations":[
{
"area":"skills",
"observation":"TUI copy changes in this mission need a visibility check, not just string-helper tests. The current worker skill and tests verified footer text helpers, but they did not verify that the fixed-height footer block can actually render the added lines.",
"evidence":"rust/proxypilot-rs/src/tui.rs:389 keeps the footer at `Constraint::Length(3)` while rust/proxypilot-rs/src/tui.rs:523-534 renders four lines; the added tests at rust/proxypilot-rs/src/tui.rs:770-842 assert string content only and do not exercise visible layout fit."
}
],
"addressesFailureFrom":null,
"summary":"Fail: the reviewed feature and its direct follow-up fixes improved CLI/runtime truthfulness, but the TUI footer's fixed height still clips the newly added selected-account/runtime hints and key help, so an operator cannot see the copy intended to explain runtime-vs-disk divergence."
"summary":"Reviewed the original runtime-stats feature (`1b3542d7`), the prior scrutiny finding, and the fix commit (`91fe6562`). The fix resolves the remaining non-blocking truthfulness issue: `/v0/runtime/stats.account_count` now counts only runtime-usable Codex accounts, mixed-provider and blank-key entries no longer inflate that value, and the TUI wording matches the runtime semantics.",
"issues":[]
},
"sharedStateObservations":[
{
"area":"skills",
"observation":"The worker skipped the rust-operator-worker skill's required manual `tuistory` verification even though the feature touched TUI-visible runtime wording. For this fix the unit-level wording assertion was likely sufficient, but the skill currently leaves that lightweight label-only case undocumented.",
"evidence":"Skill procedure step 6 requires manual verification with `tuistory` when the feature affects the TUI or runtime observability surface (`/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/skills/rust-operator-worker/SKILL.md`). The handoff for session `38bb865f-5bfd-4b20-8a75-281170e69c06` records `followedProcedure: false` and says manual TUI verification was skipped in favor of unit tests because the change was only label alignment."
"summary":"Reviewed commit `f4ae033c97c0912c03c0a0eaa9b14a2aeb696f8f` against the feature requirements and worker handoff. The implementation now rejects impossible RFC3339 calendar dates in `auth_runtime::parse_rfc3339_z`, classifies malformed impossible expiry metadata as `unknown`, and recomputes `/v0/runtime/stats` auth health from the live in-memory account state after proactive and 401-triggered refresh mutations. The targeted regressions in `auth_runtime.rs` and `proxy.rs` cover invalid leap-day/month-end inputs plus successful and failed refresh paths, and I found no remaining high-confidence correctness issues in scope.",
"issues":[]
},
"sharedStateObservations":[],
"addressesFailureFrom":null,
"summary":"Pass. The reviewed fix closes the two reported blockers: impossible RFC3339 calendar dates no longer parse as valid expiries, and proxy runtime stats now report refreshed auth health truthfully after runtime credential mutations."
"summary":"Reviewed the fix commit together with both prior failed reviews (`terminal-tui-operator-console` and `cli-state-runtime-truthfulness-and-docs`). The passive-polling blocker is resolved: idle polling now stays on `/healthz` + `/v0/runtime/stats`, and the new regression test proves it no longer calls `/v1/models`. However, the footer visibility blocker is only partially fixed: the panel now fits the four nominal footer lines, but realistic long feedback still wraps and pushes the help text back out of view.",
"issues":[
{
"file":"rust/proxypilot-rs/src/tui.rs",
"line":396,
"severity":"blocking",
"description":"The footer still has a fixed height of `Constraint::Length(6)`, which leaves only four inner text rows once the bordered `Keys` block is rendered (`tui.rs:530-543`). That is enough only when the feedback line stays on a single row. But routine operator messages in this same file are much longer\u2014for example the `runtime_refresh_target` failure text at `tui.rs:701-708` is 131 characters before account-name variation, so in the worker's own 120-column verification geometry it wraps to two rows. When that happens, one of the status/help lines is clipped again, so the feature does not fully satisfy the prior blocker of keeping all footer/help guidance visible. The added snapshot test (`tui.rs:943-975`) only exercises a short `Feedback line`, so it misses this realistic wrapped-feedback path."
}
]
},
"sharedStateObservations":[
{
"area":"skills",
"observation":"The shared Rust operator-worker guidance still does not tell workers to exercise long, wrapped operator feedback when validating fixed-height TUI regions. That omission helped this fix reintroduce a footer-visibility edge case even though the worker followed the documented procedure and added a snapshot test.",
"evidence":"`rust-operator-worker` step 6/7 asks for manual TUI verification and truthful operator-visible wording review, but it does not call out wrap/line-budget checks for fixed-height panels (`/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/skills/rust-operator-worker/SKILL.md`). In this fix, the new regression test in `rust/proxypilot-rs/src/tui.rs:943-975` only uses a one-line `Feedback line`, while the production footer can render much longer routine messages such as `runtime_refresh_target` at `tui.rs:701-708`."
"summary":"Fail. The fix successfully stops passive idle polling from contaminating runtime telemetry, but the footer/help blocker is not fully resolved because long, routine feedback messages can still wrap and hide guidance in the fixed-height footer."
"summary":"Reviewed the prior failed fix (`fix-tui-footer-and-passive-polling`) alongside the rerun fix commit `159a3b21`, the worker handoff, and the transcript skeleton. This rerun fully addresses the remaining footer-wrap blocker: the TUI now sizes the footer from its wrapped content instead of a fixed six-row region, and the regression test was updated to use the same long runtime-active-account failure wording that previously exposed clipping.",
"summary":"Pass. The rerun replaces the fixed-height footer with content-based sizing and adds realistic long-message regression coverage, so the prior footer-wrap visibility failure is adequately resolved."
"summary":"The TUI change now drives `R` from the runtime stats active account, preserves truthful runtime-unavailable and missing-runtime-active feedback, and relabels runtime-memory account counts so they are no longer presented as disk state. The scoped tests cover the new runtime-vs-disk selection logic and wording, and I found no high-confidence correctness issues in the reviewed change.",
"issues":[]
},
"sharedStateObservations":[
{
"area":"skills",
"observation":"Mission worker guidance does not explain that mission artifacts may live outside the repo under `/home/fsos/.factory/missions/<id>`. The reviewed worker initially tried repo-relative mission paths and hit ENOENT before switching to the absolute mission directory.",
"evidence":"The transcript skeleton for worker session `da34164d-4575-44bf-b059-608a68652407` shows failed reads of `/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/{mission.md,validation-contract.md,AGENTS.md}` followed by successful reads from `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/...`; `rust-operator-worker` step 1 requires reading mission artifacts but does not document this path fallback."
}
],
"addressesFailureFrom":null,
"summary":"Pass. Commit `cea7a0f4` resolves the reviewed TUI truthfulness blockers: `R` now follows runtime-active state from `/v0/runtime/stats`, runtime-unavailable cases remain explicit without hiding disk-backed state, and the runtime count label no longer claims to be disk-backed."
"summary":"Reviewed the original runtime-stats implementation commit (`1b3542d7`) plus the directly relevant follow-up fix commit (`f4ae033c`). The feature now satisfies the core HTTP contract: `/v0/runtime/stats` is local-only, counters stay in memory and reset on restart, supported proxied requests are counted once per client request, proactive and 401-triggered refresh outcomes are surfaced, and post-refresh auth health is recomputed truthfully. I found one remaining non-blocking truthfulness gap in mixed-provider saved state.",
"issues":[
{
"file":"rust/proxypilot-rs/src/proxy.rs",
"line":105,
"severity":"non_blocking",
"description":"`account_count` reports `accounts.accounts.len()`, which counts every saved entry loaded into memory, not just runtime-usable Codex accounts. That becomes untruthful in mixed-provider state because `AccountState` only treats `provider == \"codex\"` entries as active/refreshable (`rust/proxypilot-rs/src/state.rs:153`, `rust/proxypilot-rs/src/state.rs:170`, `rust/proxypilot-rs/src/state.rs:300`), while imported auth preserves arbitrary `provider_type` values from disk (`rust/proxypilot-rs/src/state.rs:232`). A non-Codex imported entry will inflate `/v0/runtime/stats.account_count` even though the runtime cannot actually use it."
}
]
},
"sharedStateObservations":[
{
"area":"conventions",
"observation":"This feature updated `docs/rust-replatform.md` even though the mission guidance says only docs-alignment work should touch that file. The rule exists, but the worker still crossed it in the runtime-stats feature commit.",
"evidence":"Mission AGENTS says `Docs ownership: only features explicitly scoped to docs alignment should update docs/rust-replatform.md or README.md` (`/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/AGENTS.md:59`), while commit `1b3542d7` changes `docs/rust-replatform.md` alongside `rust/proxypilot-rs/src/proxy.rs`."
},
{
"area":"services",
"observation":"Runtime-surface smoke verification depends on setup that is not represented in `.factory/services.yaml`: generating a config file and standing up a local mock upstream/refresh server. Workers had to do this ad hoc in the transcript instead of using shared service metadata.",
"evidence":"`.factory/services.yaml:8-12` only defines `proxypilot-rs` start/stop/healthcheck. The reviewed worker transcript for session `f8120536-90d3-4124-9b6f-a84412e716f4` shows manual `.factory/init.sh`, temporary config creation, and a background mock HTTP server before the `curl` smoke documented in the handoff `2026-04-05T09-14-14-581Z__proxy-runtime-stats-surface__f8120536-90d3-4124-9b6f-a84412e716f4.json`."
}
],
"addressesFailureFrom":null,
"summary":"Pass with one non-blocking issue. The runtime stats surface works as intended after the direct follow-up fix, but `account_count` still overstates runtime-usable accounts when saved state contains non-Codex imported entries."
"summary":"The feature successfully extracted shared auth/runtime primitives into `auth_runtime.rs` and both proxy and TUI consumers were moved onto the shared RFC3339 parsing, auth-health classification, and runtime snapshot types. The only blocking correctness gap from the original commit (impossible calendar dates being accepted, plus stale runtime auth-health after refresh) was addressed by the directly relevant follow-up fix `f4ae033c`, so there are no remaining high-confidence issues in this review scope.",
"issues":[]
},
"sharedStateObservations":[
{
"area":"skills",
"observation":"The worker had to deviate because the mission/bootstrap path guidance pointed at a repo-relative mission directory that did not exist; the recoverable fallback to `/home/fsos/.factory/missions/...` is not captured in the Rust worker guidance.",
"evidence":"Handoff `2026-04-05T08-56-54-173Z__shared-auth-runtime-domain__132757c8-6967-4cb2-b929-a387c3429b02.json`: lines 100-115 record `followedProcedure: false` and explicitly ask to clarify handling when bootstrap paths point to a repo-relative mission directory that does not exist."
},
{
"area":"services",
"observation":"Local smoke/runtime setup depends on generating `rust/proxypilot-rs.toml` first, but the services manifest only advertises a start command that assumes that file already exists. The canonical setup helper is discoverable only via `.factory/init.sh` rather than the shared service metadata.",
"evidence":"`.factory/services.yaml:9` starts proxypilot-rs with `--config rust/proxypilot-rs.toml`, while `.factory/init.sh:6-7` creates that file on demand before smoke validation."
}
],
"addressesFailureFrom":null,
"summary":"Reviewed the shared auth/runtime domain commit (`1c3edd9f4a2493a2dcd27931a680c359c14c9f43`), its transcript/handoff, and the directly relevant follow-up fix (`f4ae033c`). Result: pass, with no remaining actionable code defects in scope after the follow-up fix, plus two shared-state observations about mission path guidance and init/service discoverability."
"summary":"Reviewed the original TUI feature commit `3da810d1` plus the directly relevant follow-up fix `cea7a0f4`. The console now shows runtime stats, handles runtime-unavailable cases more explicitly, and `R` now targets the runtime-reported active account, but two blocking truthfulness issues remain in the live console: the footer/help region is clipped by the fixed layout height, and the TUI's own background model polling mutates the runtime counters and refresh state it is supposed to observe.",
"issues":[
{
"file":"rust/proxypilot-rs/src/tui.rs",
"line":389,
"severity":"blocking",
"description":"The footer block is still allocated `Constraint::Length(3)` while the `Keys` paragraph renders four separate content lines (`feedback`, selected-account hint, runtime hint, and key help at lines 525-532). With a bordered ratatui block that leaves only one inner text row, so the newly added help/runtime guidance is clipped off-screen. The feature therefore does not actually deliver readable, truthful footer/help text in the running console."
},
{
"file":"rust/proxypilot-rs/src/tui.rs",
"line":113,
"severity":"blocking",
"description":"The idle poll path still calls `refresh_models()` whenever `/healthz` succeeds (`tui.rs:49-50`, `tui.rs:113-121`, `tui.rs:218-220`). That performs a real `GET /v1/models` through the local proxy, and the proxy counts every supported request and may trigger proactive refresh before forwarding (`proxy.rs:143-145`, `proxy.rs:264-267`). As a result, merely leaving the operator console open inflates `total_proxied_requests`/`successful_upstream_responses` and can change `last_refresh`, so the runtime counters and refresh outcome are not a truthful view of external runtime activity."
}
]
},
"sharedStateObservations":[
{
"area":"conventions",
"observation":"Mission guidance says only docs-scoped features should edit `docs/rust-replatform.md`, but this TUI feature commit changed that file anyway.",
"evidence":"Mission AGENTS `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/AGENTS.md:59` says `Docs ownership: only features explicitly scoped to docs alignment should update docs/rust-replatform.md or README.md`, while commit `3da810d1` changes `docs/rust-replatform.md` alongside `rust/proxypilot-rs/src/tui.rs`."
},
{
"area":"skills",
"observation":"For TUI work, helper-string tests are not enough; shared guidance should explicitly require a layout-fit check for any new multi-line regions.",
"evidence":"`rust/proxypilot-rs/src/tui.rs:743-840` tests helper string content, but no test or skill step verifies that those lines fit inside the fixed-height footer/runtime blocks (`tui.rs:387-389`, `tui.rs:523-534`). The worker handoff for session `b1f2df79-2748-4890-a74a-2cb5e38b416c` reported footer/help validation even though the clipped layout remained."
}
],
"addressesFailureFrom":null,
"summary":"Fail. The feature and direct `cea7a0f4` follow-up improved runtime visibility and `R` targeting, but the live TUI still hides much of the footer/help copy and its own background polling contaminates the runtime counters and refresh status it displays."
"description":"The TUI footer/help block still uses Constraint::Length(3) while rendering four content lines inside a bordered block, so the selected-account/runtime divergence copy and key help are clipped off-screen. This makes the console fail both the TUI readability contract and the CLI/runtime-truthfulness feature's operator-facing explanation goals."
},
{
"featureId":"terminal-tui-operator-console",
"severity":"blocking",
"description":"The TUI background polling path still calls GET /v1/models whenever /healthz succeeds, which goes through the proxy and mutates total_proxied_requests, successful_upstream_responses, and potentially last_refresh/auth state. Leaving the console open therefore contaminates the runtime stats it is supposed to observe."
}
],
"nonBlockingIssues":[
{
"featureId":"proxy-runtime-stats-surface",
"severity":"non_blocking",
"description":"runtime_stats.account_count currently reports all saved state entries rather than only runtime-usable Codex accounts, so mixed-provider saved state can overstate runtime-usable account count."
}
],
"appliedUpdates":[
{
"target":"services.yaml",
"description":"Added `init`, `typecheck`, and `lint` commands so scrutiny/user-testing workers can bootstrap the Rust slice and run the full validator suite from shared service metadata.",
"description":"Documented in `.factory/library/environment.md` that `./.factory/init.sh` fetches Rust dependencies and creates `rust/proxypilot-rs.toml` when missing before smoke validation.",
"sourceFeature":"shared-auth-runtime-domain"
}
],
"suggestedGuidanceUpdates":[
{
"target":"rust-operator-worker",
"suggestion":"Clarify that mission artifacts may live under `/home/fsos/.factory/missions/<id>` even when repo-relative `.factory/missions/...` paths are absent, and instruct workers to fall back to the absolute mission directory before treating missing files as blockers.",
"evidence":"Review reports for `shared-auth-runtime-domain` and `fix-tui-runtime-truthfulness` both recorded ENOENT attempts against repo-relative mission paths before successfully reading `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/...`.",
"isSystemic":true
},
{
"target":"rust-operator-worker",
"suggestion":"For TUI features that change visible copy or layout, require a layout-fit visibility check (render/snapshot or terminal smoke) in addition to helper-string assertions so multi-line regions are proven visible.",
"evidence":"Both `terminal-tui-operator-console` and `cli-state-runtime-truthfulness-and-docs` failed review because the footer stayed at `Constraint::Length(3)` while rendering four lines, yet the worker tests only asserted helper-string content.",
"isSystemic":true
},
{
"target":"rust-operator-worker",
"suggestion":"Reinforce the mission boundary that only docs-scoped features may edit `docs/rust-replatform.md` or `README.md`, and direct workers to defer such changes to the explicit docs-alignment feature when possible.",
"evidence":"Review reports for `proxy-runtime-stats-surface` and `terminal-tui-operator-console` both recorded edits to `docs/rust-replatform.md` despite mission AGENTS guidance reserving docs changes for docs-alignment work.",
"isSystemic":true
}
],
"rejectedObservations":[
{
"observation":"Add a dedicated mock upstream/refresh service definition to `.factory/services.yaml` for runtime smoke validation.",
"reason":"ambiguous: the reviewed mock servers were scenario-specific one-off fixtures with ad hoc ports and behavior, so a generic shared service entry would risk encoding the wrong workflow. The concrete bootstrap/config discovery gap was handled instead via additive command/library updates."
"description":"The TUI footer still has a fixed six-row outer height, which leaves only four inner text rows inside the bordered keys block. Long routine feedback such as the runtime-active-account failure copy wraps at the validated terminal width, so one of the footer status/help lines becomes clipped again and the operator console still fails the footer-visibility contract."
}
],
"nonBlockingIssues":[],
"appliedUpdates":[],
"suggestedGuidanceUpdates":[
{
"target":"rust-operator-worker",
"suggestion":"When validating fixed-height TUI regions, explicitly exercise long wrapped operator feedback (not just short placeholder strings) so layout-fit checks prove realistic messages remain visible.",
"evidence":"The follow-up review for `fix-tui-footer-and-passive-polling` found the new snapshot test only covered a short `Feedback line`, while real footer messages in `rust/proxypilot-rs/src/tui.rs` are long enough to wrap and clip help text again within the fixed six-row footer.",
"isSystemic":true
},
{
"target":"rust-operator-worker",
"suggestion":"Document when label-only TUI/runtime wording changes may use lightweight non-interactive verification instead of full `tuistory` validation, so narrow observability fixes can follow a clear exception path.",
"evidence":"The pass review for `fix-runtime-account-count-semantics` noted the worker intentionally skipped manual `tuistory` verification because the change only aligned runtime/TUI labels, but the current skill does not describe that small-change exception.",
"title":"Refresh commands handle both refreshable and static accounts clearly",
"status":"pass",
"steps":[
{
"action":"Import a refreshable saved Codex account into isolated state and add a static account",
"expected":"Fixture state contains one active refreshable account and one static account",
"observed":"account list showed `refreshable-local` active with `refresh=refreshable` and `static-local` present with `refresh=static`"
},
{
"action":"Run `account refresh-codex` with no `--name` while the refreshable account is active",
"expected":"Refresh succeeds through the configured local refresh endpoint and updates saved account metadata",
"observed":"Command printed `refreshed saved Codex account `refreshable-local` in local state`; the local stub received one POST to `/oauth/token`; state updated access token, refresh token, email, account id, plan, and expiry"
"expected":"Static account refresh is rejected with a clear operator-readable error and no state corruption",
"observed":"Command exited non-zero with `account `static-local` is static and has no refresh token`; follow-up state snapshot matched the post-success state byte-for-byte"
"expected":"Missing account refresh is rejected with a clear operator-readable error and no state corruption",
"observed":"Command exited non-zero with `no saved Codex account named missing-local`; follow-up state snapshot remained unchanged and list output still showed the same active/static accounts"
"summary":"VAL-CLI-003 passed: refresh succeeded for the active refreshable Codex account through `codex.refresh_token_url`, static and missing account refreshes failed clearly, and saved state stayed coherent after all runs."
"details":"Used isolated fixture config /home/fsos/code-lean/ai-tools/ProxyPilot/.factory/validation/terminal-operator-console/user-testing/fixtures/cli-shell/20260405T121714Z/proxypilot-rs.toml. Successful init printed the written path. Re-running init returned exit code 1 with \"config already exists ... (pass --force to overwrite)\". The captured config file includes server.bind=127.0.0.1:8318, state.path=proxypilot-rs.state.toml, and codex.upstream_base_url=https://api.openai.com."
},
{
"id":"VAL-CLI-002",
"status":"pass",
"summary":"Add, list, activate, and remove commands kept saved active-account state coherent, including promotion back to the remaining account and explicit empty-state output after removing the final account.",
"details":"primary became active when first added; list output marked it with `*`. After activating backup, list output switched the marker to backup and the saved state snapshot shows active_account=\"backup\". Removing backup reported \"local active account is now `primary`\" and the next state snapshot shows active_account=\"primary\". Removing primary reported \"no local active account remains\" and follow-up list output showed \"No local Rust accounts saved yet.\" with an empty accounts snapshot."
},
{
"id":"VAL-CLI-003",
"status":"blocked",
"summary":"Negative refresh paths behaved clearly for static and missing accounts, but the required refresh-success path could not be exercised within the isolated fixture because refresh-codex is hardwired to the live OpenAI OAuth refresh endpoint.",
"details":"Imported a refreshable local fixture account and added a static account inside the assigned fixture state. Refreshing the static account failed cleanly with \"account `static-local` is static and has no refresh token\"; refreshing a missing account failed with \"no saved Codex account named missing-local\". Follow-up list/state evidence shows saved state remained unchanged after both failures. The assertion remains blocked because the CLI refresh path uses the built-in OpenAI OAuth refresh endpoint and the supported config surface does not expose a way to redirect refresh-codex to a local mock endpoint without live credentials."
}
],
"frictions":[],
"blockers":[
"VAL-CLI-003 success-path refresh is not isolatable in this shell fixture: refresh-codex uses the built-in live OpenAI OAuth refresh endpoint, and the allowed CLI/config surface provides no local mock override. Live device-login/private credentials were explicitly disallowed, so the refresh-success portion of the assertion was recorded as blocked with evidence."
],
"overallSummary":"Validated 3 CLI shell assertions for terminal-operator-console: VAL-CLI-001 pass, VAL-CLI-002 pass, VAL-CLI-003 blocked due to non-mockable live refresh dependency. Report and evidence were written under the requested flow-report and mission evidence paths."
"title":"Proactive refresh is visible before forwarding expired or near-expiry requests",
"status":"pass",
"steps":[
{
"action":"Start proxypilot-rs with an expired refreshable active account plus a local OAuth/upstream stub",
"expected":"Runtime stats start with expired auth health and zero counters",
"observed":"/v0/runtime/stats reported auth_health.state=expired with total_proxied_requests=0 and auth_refresh_attempts=0"
},
{
"action":"Send GET /v1/models through the proxy",
"expected":"Proxy refreshes before forwarding and the client request succeeds with the refreshed token",
"observed":"Client received 200 JSON showing received_authorization=Bearer preemptive-fresh-token"
},
{
"action":"Inspect runtime stats and stub traffic after the request",
"expected":"Stats show one refresh attempt/success and upstream sees only refreshed-token traffic",
"observed":"Stats showed total_proxied_requests=1, successful_upstream_responses=1, auth_refresh_attempts=1, upstream_401_count=0, last_refresh.kind=success; stub log recorded POST /oauth/token before GET /v1/models with Bearer preemptive-fresh-token"
"summary":"Retested 2 assertions: VAL-HTTP-007 passed with proactive refresh before forwarding, and VAL-HTTP-008 passed with one 401-triggered refresh-and-retry path counted exactly once."
"details":"Observed status=ok, provider=codex, listen=127.0.0.1:18318, upstream=http://127.0.0.1:18319 on the reachable fixture and the same local health response with upstream=http://127.0.0.1:18339.",
"summary":"Health checks returned 200 with local proxy identity fields both with the mock upstream and with an unreachable local upstream port."
},
{
"details":"The stats call returned HTTP 200 with a JSON payload and the mock log remained empty (request_count=0), confirming the operator surface is read-only and local.",
"summary":"The local /v0/runtime/stats surface returned 200 without auth and did not create any upstream mock traffic."
},
{
"details":"Before and after mutating the state file on disk, /v0/runtime/stats continued to report active_account_name=runtime-valid and auth_health.state=valid for the running process while exposing bind_address, upstream_base_url, account_count, auth_health, request_counters, and last_refresh.",
"summary":"The runtime stats payload exposed the expected stable schema and stayed pinned to runtime-memory state after the disk state file was mutated externally."
},
{
"details":"Observed auth_health.state values: fallback-key -> static with source=config_fallback_key and no active_account_name; static saved account -> static with source=active_account; valid fixture -> valid; expiring fixture -> expiring_soon; expired fixture -> expired; malformed expiry fixture -> unknown with metadata_state=malformed.",
"summary":"Representative fixtures produced explicit auth-health states for fallback static, saved static, valid, expiring_soon, expired, and malformed unknown cases."
},
{
"details":"Initial stats showed all request counters at 0 and last_refresh.kind=unknown with null timestamps; after two successful requests the counters rose; after restarting the proxy with the same fixture they reset to zero again.",
"summary":"Fresh runtime counters started at zero, last-refresh metadata was null-like before any attempt, and a restart cleared in-memory stats after traffic."
},
{
"details":"Starting from zero, one GET /v1/models and one POST /v1/chat/completions produced total_proxied_requests=2 and successful_upstream_responses=2, with two corresponding mock upstream calls.",
"summary":"Successful supported proxy requests incremented both total_proxied_requests and successful_upstream_responses."
},
{
"details":"With an expired refreshable account, the next proxied request returned 502, auth_refresh_attempts/auth_refresh_failures incremented, last_refresh.kind became failure, and the local upstream mock saw zero calls. This confirms the pre-forward refresh attempt, but successful local stubbed refresh remains blocked because the available config surface has no OAuth token endpoint override.",
"summary":"A proactive refresh attempt was observable before forwarding, but the success path could not be validated because the runtime cannot be redirected from the user surface to a local OAuth token stub."
},
{
"details":"The local mock forced one upstream 401 and the proxy recorded upstream_401_count=1 with a single proxied request, but the refresh attempt failed with a 502 response and the mock saw no /oauth/token call. A successful refresh-and-retry path therefore remains blocked under the current user-surface configuration.",
"summary":"The 401-triggered refresh path is visible, but the success retry case cannot be validated locally because the runtime cannot point refresh traffic at a local OAuth token stub from the user surface."
},
{
"details":"The client received HTTP 502 with a local JSON error after the mock upstream returned 401, while /v0/runtime/stats showed total_proxied_requests=1, upstream_401_count=1, auth_refresh_attempts=1, auth_refresh_failures=1, and last_refresh.kind=failure with a failure timestamp/message.",
"summary":"A 401-triggered refresh failure remained visible to the operator surface and did not masquerade as success."
},
{
"details":"POST /v1/files returned HTTP 404 with an error naming /v1/files and the supported routes list; successful_upstream_responses and total_proxied_requests stayed unchanged across the before/after stats captures.",
"summary":"Unsupported /v1/* routes returned a clear 404 JSON error and did not change success counters."
}
],
"blockers":[
"VAL-HTTP-007 and VAL-HTTP-008 remain blocked for success-path validation because proxypilot-rs exposes no user-surface config knob to redirect refresh token exchange from the hardwired OAuth endpoint to a local stub."
],
"frictions":[],
"groupId":"http-runtime",
"overallSummary":"Validated 10 HTTP runtime assertions: 8 passed and 2 were blocked (refresh-success paths VAL-HTTP-007 and VAL-HTTP-008).",
"summary":"The TUI opened as a readable Codex operator console with overview, runtime, runtime-stats, models, accounts, selected-account, feedback, and key-help regions visible.",
"details":"Launching `cargo run --manifest-path rust/Cargo.toml -p proxypilot-rs -- tui --config .../config-live.toml` rendered the Codex Operator Console immediately. The initial surface showed readable runtime health, live runtime stats, a disk-backed account list, selected-account details, and footer/help text rather than a blank or cryptic screen."
},
{
"id":"VAL-TUI-002",
"status":"pass",
"summary":"The footer/help text matched the shipped key bindings, and each listed action was exercised through the TUI during validation.",
"details":"Visible help text listed `q`, `r`, arrows, `a`, `f`, `R`, `d`, and `c`. Those bindings were exercised across the live, runtime-down, and auth-trouble sessions: reload/poll updated state, arrows changed selection, activate/delete changed local state, selected refresh and active refresh produced targeted feedback, clear removed feedback, and `q` exited the TUI process back to the launcher shell."
},
{
"id":"VAL-TUI-003",
"status":"pass",
"summary":"With no proxy running on the configured port, the TUI explicitly showed runtime unavailability while keeping the local disk-backed account list and selected-account details visible.",
"details":"Using the isolated runtime-down fixture on 127.0.0.1:18430 without starting a proxy produced `Health: proxy not running yet` and `Runtime unavailable` copy, while still rendering six saved accounts and full selected-account details from the local fixture state file."
},
{
"id":"VAL-TUI-004",
"status":"pass",
"summary":"Pressing `r` refreshed both disk-backed state and runtime-observed data without restarting the TUI.",
"details":"After changing the saved active account externally through the CLI and generating runtime traffic through `/v1/models`, pressing `r` in the live TUI updated the disk active account from `alpha` to `beta`, loaded the model list, and refreshed runtime counters to `total=1 success=1` while still truthfully showing the runtime active account as `alpha`."
},
{
"id":"VAL-TUI-005",
"status":"pass",
"summary":"The activate action updated active markers, selected-account details, and feedback coherently.",
"details":"Before pressing `a`, the selected row was `alpha` while the disk active marker was on `beta`. After `a`, the footer reported `Activated account \\`alpha\\`.` and the active marker moved to `alpha` without corrupting selection or the selected-account panel."
},
{
"id":"VAL-TUI-006",
"status":"pass",
"summary":"The delete action removed the selected account, kept selection in bounds, and updated visible account state coherently.",
"details":"With `beta` selected, pressing `d` removed that row, reduced the saved-account count from two to one, moved selection to the remaining `alpha` row, and showed `Deleted account \\`beta\\`.` in the footer without leaving stale details on screen."
},
{
"id":"VAL-TUI-007",
"status":"pass",
"summary":"Selected-account refresh targeted the selected row and named that account clearly in feedback.",
"details":"On the live fixture, `beta` was selected while `alpha` remained active; pressing `f` produced `Failed to refresh account \\`beta\\`: account \\`beta\\` is static and has no refresh token`. In the runtime-down fixture, selecting `soon` and pressing `f` produced feedback naming `soon`, confirming the action targets the selected row rather than the active row."
},
{
"id":"VAL-TUI-008",
"status":"pass",
"summary":"Active-account refresh-now targeted the active account even when another row was selected.",
"details":"In the live fixture, `beta` was selected while `alpha` was the active disk/runtime account; pressing `R` produced feedback naming `alpha`, not `beta`. In the runtime-down fixture, `valid` was selected while disk active remained `soon`, and `R` reported `Disk active account remains \\`soon\\``, again proving the action targeted the active account rather than the selected row."
},
{
"id":"VAL-TUI-009",
"status":"pass",
"summary":"Clear-feedback removed transient status text without altering selection or account state.",
"details":"After visible failure feedback in both live and runtime-down sessions, pressing `c` cleared the footer message back to blank while keeping the selected row, disk active account, runtime panel, and counters unchanged."
},
{
"id":"VAL-TUI-010",
"status":"pass",
"summary":"The TUI used explicit operator-readable auth labels for valid, expiring soon, expired, static, and unknown, with distinct missing-vs-malformed expiry details.",
"details":"The idle live fixture showed zeroed counters and `Last refresh: unknown`. After proxied traffic, the live runtime panel updated to `total=1 success=1`. After a proxy-triggered refresh failure, the auth-trouble TUI showed `refresh_attempts=1 refresh_failures=1` and `Last refresh: failure for \\`refresh-fail\\` at ...`, making runtime refresh outcome visible without reading files or logs."
},
{
"id":"VAL-TUI-012",
"status":"pass",
"summary":"When runtime was down, local disk-backed actions still worked where feasible and runtime-dependent refresh paths failed with readable copy while local state stayed visible.",
"details":"With runtime unavailable, pressing `a` still updated the local disk active account from `valid` to `soon`; `f` failed with readable refresh-token-exchange copy naming the selected account; `R` failed with explicit `runtime stats unavailable` copy while preserving the disk active account label; and `d` still deleted a locally saved account without hiding the local account list."
},
{
"id":"VAL-CROSS-001",
"status":"pass",
"summary":"CLI active-account changes became visible in the TUI after reload while runtime state remained truthfully separate.",
"details":"After CLI activation changed the saved active account to `beta`, TUI reload showed `Local disk active account: beta` while still showing `Runtime active account: alpha`. After CLI removal of `alpha`, reload again showed the saved state change (`beta` on disk, one saved account left) while runtime stats still truthfully reported the still-running proxy's runtime state as `alpha`."
},
{
"id":"VAL-CROSS-002",
"status":"pass",
"summary":"A proxy-triggered refresh attempt became visible across runtime surfaces without reading the state file manually.",
"details":"A proxied `GET /v1/models` against the auth-trouble fixture triggered an expired-account refresh attempt and returned a local 502. `/v0/runtime/stats` then showed `auth_refresh_attempts=1`, `auth_refresh_failures=1`, and a failed `last_refresh`, and the auth-trouble TUI showed the same failed refresh outcome in its runtime panel after reload."
},
{
"id":"VAL-CROSS-003",
"status":"pass",
"summary":"When runtime was down, reload and feedback clearing preserved local state while keeping runtime failures separate from local actions.",
"details":"In the runtime-down fixture, local actions changed disk state, `R` surfaced runtime unavailability separately from that local state, `c` cleared only the transient footer message, and `r` reloaded the current disk-backed account list without hiding local accounts or collapsing the separate `Runtime unavailable` messaging."
}
],
"frictions":[
"tuistory keeps the PTY session alive after `q` exits the TUI binary, so explicit `tuistory close` cleanup was still required even though the application quit successfully.",
"With runtime down, `f` still attempts the hardwired Codex OAuth refresh exchange and surfaces the resulting OAuth 401 text instead of a pure local runtime-unavailable message; this was truthful but not called out in user-testing guidance."
],
"blockers":[],
"overallSummary":"Validated 15 assigned TUI/cross-surface assertions for terminal-operator-console: 15 passed, 0 failed, 0 blocked. Evidence and the flow report were written under the requested mission and validation paths."
"blockedBy":"Negative refresh paths behaved clearly for static and missing accounts, but the required refresh-success path could not be exercised within the isolated fixture because refresh-codex is hardwired to the live OpenAI OAuth refresh endpoint."
},
{
"id":"VAL-HTTP-007",
"blockedBy":"A proactive refresh attempt was observable before forwarding, but the success path could not be validated because the runtime cannot be redirected from the user surface to a local OAuth token stub."
},
{
"id":"VAL-HTTP-008",
"blockedBy":"The 401-triggered refresh path is visible, but the success retry case cannot be validated locally because the runtime cannot point refresh traffic at a local OAuth token stub from the user surface."
}
],
"appliedUpdates":[
{
"target":"user-testing.md",
"description":"Added flow validator guidance for shell, curl, and tuistory surfaces plus isolated fixture/evidence boundaries for terminal-operator-console validation.",
"source":"setup"
},
{
"target":"user-testing.md",
"description":"Documented discovered validation quirks: hardwired OAuth refresh paths block local success-path refresh testing, tuistory PTYs need explicit close, and runtime-down selected refresh still surfaces remote OAuth failure text.",
This is the Plus version of [CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI), adding support for third-party providers on top of the mainline project.
<a href="https://x.com/Finessse377721"><img src="https://img.shields.io/badge/Follow-%F0%9D%95%8F%2F%40Finessse377721-1c9bf0" alt="Follow on 𝕏"></a>
<a href="https://github.com/Finesssee/ProxyPilot"><img src="https://img.shields.io/github/stars/Finesssee/ProxyPilot.svg?style=social&label=Star%20this%20repo" alt="Star this repo"></a>
</p>
All third-party provider support is maintained by community contributors; CLIProxyAPI does not provide technical support. Please contact the corresponding community maintainer if you need assistance.
<p align="center">
<strong>Stop juggling API keys.</strong> 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.
</p>
The Plus release stays in lockstep with the mainline features.
<p align="center">
Built in Go, it handles OAuth authentication, token management, and API translation automatically. One server to route them all.
</p>
## Differences from the Mainline
<p align="center">
An experimental Rust replatform now lives on the <code>rust-replatform</code> branch with a terminal-first <code>proxypilot-rs</code> binary under <code>rust/</code>.
</p>
- Added Kiro (AWS CodeWhisperer) support (OAuth login), provided by [fuko2935](https://github.com/fuko2935/CLIProxyAPI/tree/feature/kiro-integration), [Ravens2121](https://github.com/Ravens2121/CLIProxyAPIPlus/)
---
## Contributing
> [!TIP]
> 📣 **Latest models supported:**
> Claude Opus 4.5 / Sonnet 4.5 with extended thinking, GPT-5.2 / GPT-5.2 Codex, Gemini 3 Pro/Flash, and Kiro (AWS CodeWhisperer)! 🚀
This project only accepts pull requests that relate to third-party provider support. Any pull requests unrelated to third-party provider support will be rejected.
OAuth tokens are stored locally and auto-refreshed before expiry.
### Security Defaults (Auth + CORS)
- Proxy requests require API keys by default. To allow unauthenticated access (not recommended), set `allow-unauthenticated: true` in `config.yaml`.
- CORS is enabled for non-management endpoints by default (wildcard `*`). Management endpoints **do not** emit CORS headers unless you explicitly allow origins under `cors.management-allow-origins`.
Example:
```yaml
allow-unauthenticated:false
cors:
allow-origins:
- "http://localhost:5173"
management-allow-origins:
- "http://localhost:5173"
```
### Configure Your Tools
**Claude Code** (`~/.claude/settings.json`):
```json
{
"env":{
"ANTHROPIC_BASE_URL":"http://127.0.0.1:8317",
"ANTHROPIC_AUTH_TOKEN":"your-api-key"
}
}
```
**Codex CLI** (`~/.codex/config.toml`):
```toml
[openai]
api_base_url="http://127.0.0.1:8317"
```
**Factory Droid** (`~/.factory/settings.json`):
```json
{
"customModels":[{
"name":"ProxyPilot",
"baseUrl":"http://127.0.0.1:8317"
}]
}
```
---
## API Endpoints
```
POST /v1/chat/completions # OpenAI Chat Completions
POST /v1/responses # OpenAI Responses API
POST /v1/messages # Anthropic Messages API
GET /v1/models # List available models
GET /healthz # Health check
```
All endpoints auto-translate between formats based on the target provider.
---
## Caching
ProxyPilot includes two caching layers to reduce latency and token usage.
### Response Cache
Caches full API responses for identical requests. Useful for repeated queries during development.
**Config** (`config.yaml`):
```yaml
response-cache:
enabled:true# Default: false
max-size:1000# Max entries (default: 1000)
max-bytes:0# Optional total cache size cap in bytes
ttl-seconds:300# Cache TTL (default: 300 = 5 min)
exclude-models:# Models to skip (supports wildcards)
- "*-thinking"
- "o1-*"
```
### Prompt Cache
Synthetic prompt caching for providers without native support. Tracks repeated system prompts and estimates token savings.
**Config** (`config.yaml`):
```yaml
prompt-cache:
enabled:true# Default: false
max-size:500# Max entries (default: 500)
max-bytes:0# Optional total cache size cap in bytes
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 |
|--------|-------------|
| `proxypilot` | Main CLI with server and config switching |
| `proxypilot-tray` | System tray app |
---
## Tool Integrations
Works with these AI coding tools:
- **Claude Code** - Auto-configure via settings.json
- **Codex CLI** - Auto-configure via config.toml
- **Factory Droid** - Auto-configure via settings.json
- **Cursor IDE** - Manual endpoint configuration
- **Continue** - Manual endpoint configuration
---
## Requirements
- macOS, Linux, or Windows
- Go 1.24+ (for building from source)
---
## Author
ProxyPilot is developed and maintained by [@Finesssee](https://github.com/Finesssee). Some contributors shown in the git history are from upstream [CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI) merges. Direct contributors to ProxyPilot will be listed here as the project grows.
---
## Credits
ProxyPilot builds upon excellent work from the open-source community:
- **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** - The original unified proxy server that inspired this project
- **[VibeProxy](https://github.com/automazeio/vibeproxy)** - Native macOS menu bar app showcasing clean proxy UX
Long-context features are inspired by research from the AI community:
- **[Factory.ai](https://factory.ai/news/evaluating-compression)** - Context compression techniques for long-running coding agents
- **[Anthropic](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents)** - Effective harnesses for long-running agents
Special thanks to these teams for sharing their work and insights.
---
## License
This project is licensed under the MIT License - see `LICENSE`.
This project is intended for educational and interoperability research purposes only. It interacts with various internal or undocumented APIs (such as Google's `v1internal`) to provide compatibility layers.
This project is for educational and interoperability research purposes. It interacts with various APIs to provide compatibility layers.
- **Use at your own risk.** The authors are not responsible for any consequences arising from the use of this software, including but not limited to account suspensions or service interruptions.
-This project is **not** affiliated with, endorsed by, or associated with Google, OpenAI, Anthropic, or any other service provider mentioned.
- Users are expected to comply with the Terms of Service of the respective platforms they connect to.
- **Use at your own risk.** Authors are not responsible for account suspensions or service interruptions.
- **Not affiliated** with Google, OpenAI, Anthropic, Amazon, or any other provider.
- Users must comply with the Terms of Service of connected platforms.
The following versions of ProxyPilot are currently supported with security updates:
| Version | Supported |
| ------- | ------------------ |
| latest | :white_check_mark: |
| < 1.0 | :x: |
## Reporting a Vulnerability
We take the security of ProxyPilot seriously. If you discover a security vulnerability, please report it responsibly.
### How to Report
You can report a vulnerability through one of the following methods:
1.**GitHub Security Advisory (Preferred)**: Open a private security advisory through [GitHub Security Advisories](https://github.com/smat-dev/ProxyPilot/security/advisories/new). This allows for private discussion and coordination.
2.**Email**: Send an email to the project maintainers with details of the vulnerability. Please include:
- A description of the vulnerability
- Steps to reproduce the issue
- Potential impact of the vulnerability
- Any suggested fixes (if available)
### What to Expect
After submitting a vulnerability report:
- **Initial Response**: You will receive an acknowledgment within **48 hours** confirming we have received your report.
- **Assessment**: We will investigate and assess the vulnerability within **7 days**.
- **Resolution Timeline**: We aim to release a fix for confirmed vulnerabilities within **30 days**, depending on complexity.
- **Disclosure**: Once a fix is released, we will coordinate with you on public disclosure timing.
We will keep you informed throughout the process and credit you for the discovery (unless you prefer to remain anonymous).
## Responsible Disclosure Guidelines
To protect our users, we ask that you:
- **DO NOT** disclose the vulnerability publicly until a fix has been released.
- **DO NOT** exploit the vulnerability beyond what is necessary to demonstrate the issue.
- **DO NOT** access, modify, or delete data belonging to other users.
- **DO** provide us with reasonable time to address the issue before any public disclosure.
- **DO** act in good faith to avoid privacy violations, data destruction, or service disruption.
We are committed to working with security researchers and will not take legal action against individuals who discover and report vulnerabilities responsibly.
## Security Best Practices for Users
- Always use the latest version of ProxyPilot.
- Review and understand the proxy configurations before deployment.
- Use secure connections (HTTPS) where applicable.
- Regularly review access logs for suspicious activity.
Thank you for helping keep ProxyPilot and its users safe.
**Subject:** Gemini/Antigravity API Key & Quota Issues
## 1. Issue Summary
The user encountered `[HTTP 400] API key not valid` and `[HTTP 429] Resource Exhausted` errors when using the `droid` CLI with the `gemini-3-pro-preview` model.
## 2. Root Causes Identified
### A. Wrong Model Routing (Primary Cause of Quota Error)
***Symbol:**`gemini-3-pro-preview`
***Issue:** In ProxyPilot's registry, `gemini-3-pro-preview` is defined as a **Google/Gemini CLI** model, not an Antigravity model. Requests were routing directly to Google using personal CLI keys/quota, which were exhausted (429).
***Fix:** Switched Droid configuration to use **`gemini-3-pro-high`** (or `low`), which are the correct aliases for Antigravity-routed models. These are now confirmed working.
### B. Antigravity Account Rotation Failure
***Issue:** Even when using Antigravity, only 1 of the 3 available accounts was being utilized.
***Cause:** The Auth Selector (`selector.go`) uses a "Strict Fallback" heuristic. If exactly *one* auth file contains a `project_id` field, it is designated as the "Primary" account, and others are ignored until the primary is effectively invalid.
***Discovery:** Only the account `truongnamphong8` had a `project_id`.
***Fix:** Removed the `project_id` field from the auth file so all 3 accounts are treated as "peers" and rotated via Round Robin.
### C. "API Key Not Valid" Startup Error
***Issue:** ProxyPilot server logs showed API key errors on startup.
***Cause:**`config.yaml` contained a placeholder line: `api-key: "YOUR_LEGIT_API_KEY_HERE"`.
***Fix:** Commented out the invalid line in `config.yaml`.
### D. Droid CLI Config Corruption
***Issue:** Droid failed to load with "Failed to parse custom models config".
***Cause:** The `config.json` file was saved with a UTF-8 **BOM** (Byte Order Mark) by PowerShell during debugging/editing.
***Fix:** Rewrote `config.json` with UTF-8 (No BOM) encoding.
## 3. Preventative Measures & Best Practices
### Model Naming
**ALWAYS** use the Antigravity-specific model IDs to ensure requests route through the shared pool rather than personal quota:
* ✅ `gemini-3-pro-high`
* ✅ `gemini-3-pro-low`
* ✅ `gemini-3-flash` (if available via Antigravity)
* ✅ `antigravity-claude-sonnet-4-5-thinking`
* ❌ `gemini-3-pro-preview` (Routes to Google CLI)
### Auth File Management
When adding new Antigravity accounts (`.json` files in `~/.cli-proxy-api/`):
* Ensure **uniformity**. Either *all* files should have a `project_id`, or *none* should.
* If mixed, the one with `project_id` will monopolize traffic.
### Configuration
* Do not leave placeholder values (like "YOUR_KEY_HERE") in `config.yaml`; comment them out.
* When editing JSON configuration files on Windows, ensure your editor saves as **UTF-8 (No BOM)**.
## 4. Current Configuration (Verified)
***Droid Config:**`~/.factory/config.json` updated with correct Antigravity model names.
***ProxyPilot Config:**`d:\code\ProxyPilot\config.yaml` cleaned of invalid keys.
***Auth Status:** 3 Antigravity accounts active and rotating.
## 5. Issue: Rate Limit Rotation "Stuck" on One Account
**Date:** 2025-12-20
**Subject:** HTTP 429 Handling in Antigravity Executor & Manager
### A. Issue Summary
The user experienced repeated 429 Too Many Requests errors from the *same* account (yuhh0704@gmail.com) despite having multiple healthy backup accounts (nnq2366) available. The rotation logic refused to switch to the backup, effectively blocking the user.
### B. Root Causes
1.**Missing Retry-After Parsing:** The AntigravityExecutor was receiving a Retry-After header (e.g., 1 hour) from the upstream API but was ignoring it. It only returned a generic error message.
***Effect:** The AuthManager used a default backoff of only **1 second**.
2.**Model State Not Updated:** When the global Auth object was marked as "Rate Limited", the specific ModelState for the requested model (e.g., claude-opus-4-5-thinking) remained "Active".
***Effect:** The RoundRobinSelector checked the *model* state, saw it was valid, and re-selected the same "Primary Fallback" account (due to strict fallback logic preferences) immediately after the 1-second backoff expired.
### C. The Fix
1.**Updated AntigravityExecutor:** Added logic to parse the Retry-After header (supporting both integer seconds and HTTP date formats) and pass it to the statusErr struct.
2.**Updated AuthManager (MarkResult):** Modified the result handling to explicitly update the ModelState with the error and cooldown info, not just the parent Auth object.
3.**Updated Selector (isAuthBlockedForModel):** Added a defensive check to respect NextRetryAfter timestamps even if the Unavailable boolean flag wasn't explicitly set, ensuring blocked models are strictly filtered out.
### D. Result
System now respects long cooldowns (e.g., 3 hours) and correctly skips the blocked "Primary" account to use the "Secondary" backups like nnq2366.
- OAuth callbacks like `/codex/callback`, `/google/callback`, etc. persist short-lived state for the login goroutines.
Core handler layer:
-`sdk/api/handlers/*` contains provider-specific API adapters (OpenAI/Gemini/Claude) and schema/streaming shims.
-`internal/api/handlers/management/*` contains management endpoints mounted under `/v0/management/*`.
### Management + desktop UX
- Management endpoints are only enabled when a secret is configured:
-`remote-management.secret-key` in `config.yaml`, or
- environment `MANAGEMENT_PASSWORD`.
- The tray app starts the engine via `internal/desktopctl.Start()` and injects a per-user `MANAGEMENT_PASSWORD` so the desktop UX can use `/v0/management/*` locally.
- The ProxyPilot dashboard page (`/proxypilot.html`) is served **localhost-only** and injects the management key into the HTML so users don’t paste keys manually.
Key components:
-`internal/desktopctl`: process management (start/stop/status), log file locations, and per-user UI state.
# 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
# experimental-cch-signing: false # optional: default is false; when true, sign the final /v1/messages body using the current Claude Code cch algorithm
# # keep this disabled unless you explicitly need the behavior, so upstream seed changes fall back to legacy proxy behavior
**proxypilot** is the unified command-line interface for the ProxyPilot local AI proxy. It provides both **server** functionality (running the proxy server) and **switch** functionality (toggling AI agents between proxy mode and native mode).
## Installation
### Via bun (recommended)
```bash
bun install -g proxypilot
```
### Via npm
```bash
npm install -g proxypilot
```
### Via Go
```bash
go install github.com/Finesssee/ProxyPilot/cmd/server@latest
```
### Manual Download
Download pre-built binaries from [GitHub Releases](https://github.com/Finesssee/ProxyPilot/releases).
Available binaries:
- `proxypilot-darwin-amd64` - macOS Intel
- `proxypilot-darwin-arm64` - macOS Apple Silicon
- `proxypilot-linux-amd64` - Linux x64
- `proxypilot-linux-arm64` - Linux ARM64
- `proxypilot-windows-amd64.exe` - Windows x64
## Server Mode
Run ProxyPilot as a local proxy server:
```bash
proxypilot # Start server on default port (8317)
proxypilot -config /path/to/config # Use custom config file
```
### Server Features
- Routes AI requests through configured providers
- Automatic model aliasing and translation
- OAuth login helpers for various providers
- Agent configuration management
### Login Commands
```bash
proxypilot --login # Login to Google Account (Gemini)
proxypilot --codex-login # Login to Codex using OAuth
proxypilot --claude-login # Login to Claude using OAuth
proxypilot --qwen-login # Login to Qwen using OAuth
proxypilot --antigravity-login # Login to Antigravity using OAuth
proxypilot --kiro-login # Login to Kiro using Google OAuth
proxypilot --kiro-aws-login # Login to Kiro using AWS Builder ID
proxypilot --minimax-login # Add MiniMax API key
proxypilot --zhipu-login # Add Zhipu AI API key
```
### Login Options
```bash
--no-browser # Don't open browser automatically for OAuth
--incognito # Use incognito/private mode (useful for multiple accounts)
--no-incognito # Force disable incognito mode
```
### Import Commands
```bash
proxypilot --vertex-import <file> # Import Vertex service account key JSON
proxypilot --kiro-import # Import Kiro token from Kiro IDE
```
## Agent Configuration
ProxyPilot can automatically configure AI CLI tools to use the proxy.
### Detect Installed Agents
```bash
proxypilot --detect-agents
```
Example output:
```
Detecting installed CLI agents...
Claude Code: [+] Installed
Binary: /usr/local/bin/claude
Config: ~/.claude/settings.json
Codex CLI: [+] Installed
Binary: /usr/local/bin/codex
Config: ~/.codex
Gemini CLI: [-] Not found
```
### Setup Commands
```bash
proxypilot --setup-all # Configure all detected agents
Switch AI agents between proxy mode (through ProxyPilot) and native mode (direct API access). Think of it like `nvm` for Node versions, but for AI agent configurations.
### Usage
```bash
proxypilot --switch <agent> # Show status of specific agent
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.