Commit Graph
53 Commits
Author SHA1 Message Date
RCD e3302b694c Merge tag 'v6.9.16' into rust-replatform 2026-04-08 00:38:27 +07:00
mpfo0106 da3a498a28 Keep Claude Code compatibility work low-risk and reviewable
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
2026-04-02 20:35:39 +09:00
RCD 3d26dbadb0 Merge upstream CLIProxyAPI v6.8.40 2026-03-07 19:03:29 +07:00
hkfires c80ab8bf0d feat(thinking): improve provider family checks and clamp unsupported levels 2026-03-03 19:05:15 +08:00
hkfires d2e5857b82 feat(thinking): enhance adaptive thinking support across models and update test cases 2026-03-03 13:00:24 +08:00
RCD a987b9fb83 Merge upstream CLIProxyAPI v6.8.11 into ProxyPilot
Upstream changes (v6.8.0–v6.8.11):
- feat: add Kimi (Moonshot AI) provider support with OAuth
- feat: add iFlow provider with OAuth and cookie auth
- feat: support Claude thinking type adaptive
- feat: capture cached token count in usage metadata
- fix: correct max completion tokens for opus 4.6 thinking
- fix: improve content handling for system and user messages
- fix: rewrite model name in response.model for Responses API SSE
- refactor: simplify provider lifecycle and registration logic
- refactor: migrate config-access to internal package

Fork integration:
- Migrate configaccess from sdk/access/config to internal/access/config_access
- Update reconcile.go to use internalconfig types directly
- Add Kimi and iFlow login flags to ProxyPilot CLI
- Integrate managementasset auto-updater
- Keep all ProxyPilot fork features (TUI, agent setup, service, etc.)
2026-02-11 19:03:07 +07:00
hkfires 938a799263 feat(translator): support Claude thinking type adaptive 2026-02-10 16:20:32 +08:00
hkfires b7e4f00c5f fix(translator): correct gemini-cli log prefix 2026-02-07 08:40:09 +08:00
testandClaude Opus 4.6 f5f26f0cbe Add Kimi (Moonshot AI) provider support
- OAuth2 device authorization grant flow (RFC 8628) for authentication
- Streaming and non-streaming chat completions via OpenAI-compatible API
- Models: kimi-k2, kimi-k2-thinking, kimi-k2.5
- CLI `--kimi-login` command for device flow auth
- Token management with automatic refresh
- Thinking/reasoning effort support for thinking-enabled models

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-05 19:24:46 -05:00
RCD 6c0c0b3a44 Merge upstream CLIProxyAPI v6.7.48 into ProxyPilot
Changes:
- feat(registry): add Kimi-K2.5 model to static data
- refactor(util, executor): optimize payload handling and schema processing
- fix(thinking): support user-defined includeThoughts setting (camelCase/snake_case)
- fix(thinking): ensure includeThoughts is false for ModeNone
- fix(gemini): support snake_case thinking config fields from Python SDK
- feat(gemini-cli): support image content in Claude request conversion
- fix(test): upstream fixed the builtin tools test we also fixed

Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.48
2026-02-05 21:39:14 +07:00
hkfires 075e3ab69e fix(test): rename test function to reflect behavior change for builtin tools 2026-02-05 09:25:34 +08:00
RCD a6e817b72f Merge upstream CLIProxyAPI v6.7.47 into ProxyPilot
Changes from v6.7.43-v6.7.47:
- fix(logging): expand tilde in auth-dir and log resolution errors
- feat(pprof): add configurable pprof HTTP debug server
- feat(watcher): log auth field changes on reload
- fix(cliproxy): update auth before model registration
- docs: README updates, AICodeMirror sponsorship

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

Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.47
2026-02-04 22:50:54 +07:00
hkfires c8c27325dc feat(thinking): enable thinking toggle for qwen3 and deepseek models
Fix #1245
2026-01-28 09:54:05 +08:00
hkfires e641fde25c feat(registry): support provider-specific model info lookup 2026-01-20 10:01:17 +08:00
hkfires 1d2fe55310 fix(executor): stop rewriting thinkingLevel for gemini 2026-01-19 19:49:39 +08:00
hkfires cb6caf3f87 fix(thinking): update ValidateConfig to include fromSuffix parameter and adjust budget validation logic 2026-01-18 16:37:14 +08:00
hkfires 03005b5d29 refactor(thinking): add Gemini family provider grouping for strict validation 2026-01-18 11:30:53 +08:00
hkfires 97b67e0e49 test(thinking): split E2E coverage into suffix and body parameter test functions
Refactor thinking configuration tests by separating model name suffix-based
scenarios from request body parameter-based scenarios into distinct test
functions with independent case numbering.

Architectural improvements:
- Extract thinkingTestCase struct to package level for shared usage
- Add getTestModels() helper returning complete model fixture set
- Introduce runThinkingTests() runner with protocol-specific field detection
- Register level-subset-model fixture with constrained low/high level support
- Extend iflow protocol handling for glm-test and minimax-test models
- Add same-protocol strict boundary validation cases (80-89)
- Replace error responses with clamped values for boundary-exceeding budgets
2026-01-18 10:30:14 +08:00
hkfires 4ad6189487 refactor(thinking): extract antigravity logic into a dedicated provider 2026-01-15 19:08:22 +08:00
hkfires ff4ff6bc2f feat(thinking): support zero as a valid thinking budget for capable models 2026-01-15 15:41:10 +08:00
hkfires 33d66959e9 test(thinking): remove legacy unit and integration tests 2026-01-15 13:06:40 +08:00
hkfires 0b06d637e7 refactor: improve thinking logic 2026-01-15 13:06:39 +08:00
Finessse a9cef821f9 sync(upstream): preserve built-in tools across openai<->responses
Cherry-picked from upstream 0b834fcb
2026-01-11 05:48:45 +07:00
Luis Pater 3d01b3cfe8 Merge pull request #553 from XInTheDark/fix/builtin-tools-web-search
fix(translator): preserve built-in tools (web_search) to Responses API
2026-01-09 04:40:13 +08:00
hkfires 8bf3305b2b fix(thinking): fallback to upstream model for thinking support when alias not in registry 2025-12-31 18:07:13 +08:00
hkfires d00e3ea973 feat(thinking): add numeric budget to thinkingLevel conversion fallback 2025-12-31 17:14:47 +08:00
hkfires 225e2c6797 feat(amp): add per-client upstream API key mapping support 2025-12-29 12:26:25 +08:00
FinessseandClaude Opus 4.5 c6d8e6abb1 chore: gitignore static and test folders
- 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>
2025-12-27 04:00:38 +07:00
FinessseandClaude Opus 4.5 221a386040 feat: sync with CLIProxyAPIPlus (excludes Amp, GitHub Copilot)
Synced all changes from router-for-me/CLIProxyAPIPlus including:

Executor updates:
- claude_executor: response decompression, beta extraction, model resolution
- gemini_executor/codex_executor: usage reporting
- antigravity_executor: fallback URLs, thinking metadata, token refresh
- kiro_executor: token refresh, profile ARN handling, quota fallback

Translator updates:
- Updated all translators for improved request/response handling
- Enhanced tool result formatting and streaming support

Configuration:
- Added IncognitoBrowser option for OAuth
- Updated KiroKey configuration
- Enhanced PayloadConfig options

SDK updates:
- Auth refresh registry improvements
- Cliproxy service enhancements
- Added ErrNotImplemented for executor interface

Excluded features (not synced):
- Amp CLI Integration module
- GitHub Copilot executor

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-26 02:10:20 +07:00
Finessse f97ef1f2a3 test: update regression tests for latest model versions 2025-12-25 05:47:41 +07:00
Ben Vargas 598f0af19b fix: apply thinkingLevel from model suffix metadata for Gemini 3
The previous commit added thinkingLevel support but didn't apply it
when the reasoning effort came from model name suffix (e.g., model(minimal)).

This was because ResolveThinkingConfigFromMetadata returns nil for
level-based models, bypassing the metadata application.

Changes:
- Add ApplyGemini3ThinkingLevelFromMetadata for standard Gemini API
- Add ApplyGemini3ThinkingLevelFromMetadataCLI for CLI API format
- Update gemini_cli_executor to apply Gemini 3 thinkingLevel from metadata
- Update antigravity_executor to apply Gemini 3 thinkingLevel from metadata
- Update aistudio_executor to apply Gemini 3 thinkingLevel from metadata
- Add comprehensive test coverage for Gemini 3 thinkingLevel functions
2025-12-17 16:08:38 -07:00
Finessse 13d1ba7137 remove amp support 2025-12-17 16:15:10 +07:00
Luis Pater 7481c0eaa0 Revert "Fix invalid thinking signature when proxying Claude via Antigravity" 2025-12-17 14:53:52 +08:00
Luis Pater f49e887fe6 Merge pull request #570 from fuguiKz/fix/antigravity-thinking-signature
Fix invalid thinking signature when proxying Claude via Antigravity
2025-12-17 03:04:41 +08:00
kz b602eae215 Fix antigravity Claude thinking signature handling 2025-12-17 02:28:58 +08:00
hkfires 9df96a4bb4 test(thinking): add effort to budget coverage 2025-12-16 18:34:43 +08:00
hkfires 28a428ae2f fix(thinking): align budget effort mapping across translators
Unify thinking budget-to-effort conversion in a shared helper, handle disabled/default thinking cases in translators, adjust zero-budget mapping, and drop the old OpenAI-specific helper with updated tests.
2025-12-16 18:34:43 +08:00
Finessse d7eacf9524 Fix Codex 400 from empty streaming done text 2025-12-16 13:46:27 +07:00
Finessse 153d2bec96 Responses: ensure message output precedes reasoning 2025-12-16 13:00:12 +07:00
Finessse 2298be6958 Fix antigravity OpenAI chat streaming parsing 2025-12-16 13:00:04 +07:00
Finessse 6558cbbc0a Fix gemini-cli OpenAI chat streaming parsing 2025-12-16 12:59:56 +07:00
Muzhen Gaming 0b834fcb54 fix(translator): preserve built-in tools across openai<->responses
- Pass through non-function tool definitions like web_search

- Translate tool_choice for built-in tools and function tools

- Add regression tests for built-in tool passthrough
2025-12-15 21:18:54 +08:00
hkfires 367a05bdf6 refactor(thinking): export thinking helpers
Expose thinking/effort normalization helpers from the executor package
so conversion tests use production code and stay aligned with runtime
validation behavior.
2025-12-15 09:16:15 +08:00
hkfires d20b71deb9 fix(thinking): normalize effort mapping
Route OpenAI reasoning effort through ThinkingEffortToBudget for Claude
translators, preserve "minimal" when translating OpenAI Responses, and
treat blank/unknown efforts as no-ops for Gemini thinking configs.

Also map budget -1 to "auto" and expand cross-protocol thinking tests.
2025-12-15 09:16:15 +08:00
hkfires a4a3274a55 test(thinking): expand conversion edge case coverage 2025-12-15 09:16:14 +08:00
hkfires 716aa71f6e fix(thinking): centralize reasoning_effort mapping
Move OpenAI `reasoning_effort` -> Gemini `thinkingConfig` budget logic into
shared helpers used by Gemini, Gemini CLI, and antigravity translators.

Normalize Claude thinking handling by preferring positive budgets, applying
budget token normalization, and gating by model support.

Always convert Gemini `thinkingBudget` back to OpenAI `reasoning_effort` to
support allowCompat models, and update tests for normalization behavior.
2025-12-15 09:16:14 +08:00
hkfires 8496cc2444 test(thinking): cover openai-compat reasoning passthrough 2025-12-15 09:16:14 +08:00
hkfires 5ef2d59e05 fix(thinking): gate reasoning effort by model support
Only map OpenAI reasoning effort to Claude thinking for models that support
thinking and use budget tokens (not level-based thinking).

Also add "xhigh" effort mapping and adjust minimal/low budgets, with new
raw-payload conversion tests across protocols and models.
2025-12-15 09:16:14 +08:00
Finessse 4b4cd108ce Fix tool result ordering for Droid CLI 2025-12-14 23:34:54 +07:00
hkfires 374faa2640 fix(thinking): map budgets to effort levels
Ensure thinking settings translate correctly across providers:
- Only apply reasoning_effort to level-based models and derive it from numeric
  budget suffixes when present
- Strip effort string fields for budget-based models and skip Claude/Gemini
  budget resolution for level-based or unsupported models
- Default Gemini include_thoughts when a nonzero budget override is set
- Add cross-protocol conversion and budget range tests
2025-12-12 21:33:20 +08:00