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
c7e8830a56
refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation
...
Update ApplyThinking signature to accept fromFormat and toFormat parameters
instead of a single provider string. This enables:
- Proper level-to-budget conversion when source is level-based (openai/codex)
and target is budget-based (gemini/claude)
- Strict budget range validation when source and target formats match
- Level clamping to nearest supported level for cross-format requests
- Format alias resolution in SDK translator registry for codex/openai-response
Also adds ErrBudgetOutOfRange error code and improves iflow config extraction
to fall back to openai format when iflow-specific config is not present.
2026-01-18 10:30:15 +08:00
hkfires
d5ef4a6d15
refactor(translator): remove registry model lookups from thinking config conversions
2026-01-18 10:30:14 +08:00
hkfires
97b67e0e49
test(thinking): split E2E coverage into suffix and body parameter test functions
...
Refactor thinking configuration tests by separating model name suffix-based
scenarios from request body parameter-based scenarios into distinct test
functions with independent case numbering.
Architectural improvements:
- Extract thinkingTestCase struct to package level for shared usage
- Add getTestModels() helper returning complete model fixture set
- Introduce runThinkingTests() runner with protocol-specific field detection
- Register level-subset-model fixture with constrained low/high level support
- Extend iflow protocol handling for glm-test and minimax-test models
- Add same-protocol strict boundary validation cases (80-89)
- Replace error responses with clamped values for boundary-exceeding budgets
2026-01-18 10:30:14 +08:00
hkfires
109cffc010
refactor(auth): simplify filename prefixes for qwen and iflow tokens
2026-01-17 12:20:58 +08:00
Chén Mù and GitHub
4dc7af5a5d
Merge pull request #1054 from router-for-me/codex
...
fix(codex): ensure instructions field exists
2026-01-16 15:40:12 +08:00
hkfires
902bea24b4
fix(codex): ensure instructions field exists
2026-01-16 15:38:10 +08:00
hkfires
c3ef46f409
feat(config): supplement missing default aliases during antigravity migration
2026-01-16 13:37:46 +08:00
hkfires
48cba39a12
feat(codex): add config toggle for codex instructions injection
2026-01-16 12:30:12 +08:00
Chén Mù and GitHub
22e1ad3d8a
Merge pull request #1018 from pikeman20/main
...
feat(docker): use environment variables for volume paths
2026-01-16 08:19:23 +08:00
hkfires
2b387e169b
feat(iflow): add iflow-rome model definition
2026-01-15 20:23:55 +08:00
hkfires
199cf480b0
refactor(thinking): remove support for non-standard thinking configurations
...
This change removes the translation logic for several non-standard, proprietary extensions used to configure thinking/reasoning. Specifically, support for `extra_body.google.thinking_config` and the Anthropic-style `thinking` object has been dropped from the OpenAI request translators.
This simplification streamlines the translators, focusing them on the standard `reasoning_effort` parameter. It also removes the need to look up model information from the registry within these components.
BREAKING CHANGE: Support for non-standard thinking configurations via `extra_body.google.thinking_config` and the Anthropic-style `thinking` object has been removed. Clients should now use the standard `reasoning_effort` parameter to control reasoning.
2026-01-15 19:32:12 +08:00
hkfires
4ad6189487
refactor(thinking): extract antigravity logic into a dedicated provider
2026-01-15 19:08:22 +08:00
hkfires
fe5b3c80cb
refactor(config): rename oauth-model-mappings to oauth-model-alias
2026-01-15 18:03:26 +08:00
hkfires
e0ffec885c
fix(aistudio): remove levels from model definitions
2026-01-15 16:06:46 +08:00
hkfires
ff4ff6bc2f
feat(thinking): support zero as a valid thinking budget for capable models
2026-01-15 15:41:10 +08:00
hkfires
5c40a2db21
refactor(thinking): simplify ModeNone and budget validation logic
2026-01-15 14:03:08 +08:00
hkfires
ee2976cca0
refactor(thinking): improve logging for user-defined models
2026-01-15 13:06:41 +08:00
hkfires
8bc6df329f
fix(auth): apply API key model mapping to request model
2026-01-15 13:06:41 +08:00
hkfires
bcd4d9595f
fix(thinking): refine ModeNone handling based on provider capabilities
2026-01-15 13:06:41 +08:00
hkfires
5a77b7728e
refactor(thinking): improve budget clamping and logging with provider/model context
2026-01-15 13:06:41 +08:00
hkfires
1fbbba6f59
feat(logging): order log fields for improved readability
2026-01-15 13:06:41 +08:00
hkfires
847be0e99d
fix(auth): use base model name for auth matching by stripping suffix
2026-01-15 13:06:41 +08:00
hkfires
f6a2d072e6
refactor(thinking): refine configuration logging
2026-01-15 13:06:41 +08:00
hkfires
ed8b0f25ee
fix(thinking): use LookupModelInfo for model data
2026-01-15 13:06:41 +08:00
hkfires
6e4a602c60
fix(thinking): map reasoning_effort to thinkingConfig
2026-01-15 13:06:40 +08:00
hkfires
2262479365
refactor(thinking): remove legacy utilities and simplify model mapping
2026-01-15 13:06:40 +08:00
hkfires
33d66959e9
test(thinking): remove legacy unit and integration tests
2026-01-15 13:06:40 +08:00
hkfires
7f1b2b3f6e
fix(thinking): improve model lookup and validation
2026-01-15 13:06:40 +08:00
hkfires
40ee065eff
fix(thinking): use static lookup to avoid alias issues
2026-01-15 13:06:40 +08:00
hkfires
a75fb6af90
refactor(antigravity): remove hardcoded model aliases
2026-01-15 13:06:39 +08:00
hkfires
72f2125668
fix(executor): properly handle thinking application errors
2026-01-15 13:06:39 +08:00
hkfires
e8f5888d8e
fix(thinking): fix auth matching for thinking suffix and json field conflicts
2026-01-15 13:06:39 +08:00
hkfires
0b06d637e7
refactor: improve thinking logic
2026-01-15 13:06:39 +08:00
hkfires
21ac161b21
fix(test): implement missing HttpRequest method in stream bootstrap mock
2026-01-12 16:33:43 +08:00
hkfires
220ca45f74
fix(codex): only override instructions when upstream provides them
2026-01-11 15:52:21 +08:00
hkfires
70a82d80ac
fix(codex): only override instructions in responses for OpenCode UA
2026-01-11 15:19:37 +08:00
hkfires
ac626111ac
feat(codex): add OpenCode instructions based on user agent
2026-01-11 13:36:35 +08:00
hkfires
6494330c6b
feat(codex): add subscription date fields to ID token claims
2026-01-10 11:15:20 +08:00
hkfires
7004295e1d
build(docker): move stats export execution after image build
2026-01-09 11:24:00 +08:00
hkfires
ee62ef4745
refactor(logging): clean up oauth logs and debugs
2026-01-09 11:20:55 +08:00
Chén Mù and GitHub
4adb9eed77
Merge pull request #921 from router-for-me/atgy
...
fix(executor): update gemini model identifier to gemini-3-pro-preview
2026-01-08 19:20:32 +08:00
hkfires
b6a0f7a07f
fix(executor): update gemini model identifier to gemini-3-pro-preview
...
Update the model name check in `buildRequest` to target "gemini-3-pro-preview" instead of "gemini-3-pro" when applying specific system instruction handling.
2026-01-08 19:14:52 +08:00
hkfires
05444cf32d
fix(gemini): abort default injection on existing thinking keys
2026-01-05 10:24:30 +08:00
hkfires
fdf5720217
fix(gemini): remove default thinking for gemini 3 models
2026-01-02 10:55:59 +08:00
hkfires
f40bd0cd51
feat(script): add usage statistics preservation across container rebuilds
2026-01-02 10:01:20 +08:00
hkfires
e33676bb87
fix(util): disable default thinking for gemini-3 series
2026-01-02 09:43:40 +08:00
hkfires
3902fd7501
fix(iflow): remove thinking field from request body in thinking config handler
2026-01-01 19:40:28 +08:00
hkfires
4fc3d5e935
refactor(iflow): simplify thinking config handling for GLM and MiniMax models
2026-01-01 19:31:08 +08:00
hkfires
2d2f4572a7
fix(translator): remove unnecessary whitespace trimming in reasoning text collection
2026-01-01 12:39:09 +08:00
hkfires
8f4c46f38d
fix(translator): emit tool_result messages before user content in Claude-to-OpenAI conversion
2026-01-01 11:11:43 +08:00
hkfires
b6ba51bc2a
feat(translator): add thinking block and tool result handling for Claude-to-OpenAI conversion
2026-01-01 09:41:25 +08:00
Chén Mù and GitHub
736e0aae86
Merge pull request #814 from router-for-me/aistudio
...
Fix model alias thinking suffix
2025-12-31 03:08:05 -08:00
hkfires
8bf3305b2b
fix(thinking): fallback to upstream model for thinking support when alias not in registry
2025-12-31 18:07:13 +08:00
hkfires
d00e3ea973
feat(thinking): add numeric budget to thinkingLevel conversion fallback
2025-12-31 17:14:47 +08:00
hkfires
89db4e9481
fix(thinking): use model alias for thinking config resolution in mapped models
2025-12-31 17:09:22 +08:00
hkfires
e332419081
feat(registry): add thinking support for gemini-2.5-computer-use-preview model
2025-12-31 17:09:22 +08:00
Chén Mù and GitHub
cb56cb250e
Merge pull request #800 from router-for-me/modelmappings
...
feat(watcher): add model mappings change detection
2025-12-30 06:50:42 -08:00
hkfires
e0381a6ae0
refactor(watcher): extract model summary functions to dedicated file
2025-12-30 22:39:12 +08:00
hkfires
2c01b2ef64
feat(watcher): add Gemini models and OAuth model mappings change detection
2025-12-30 22:39:12 +08:00
Chén Mù and GitHub
e947266743
Merge pull request #795 from router-for-me/modelmappings
...
refactor(executor): resolve upstream model at conductor level before execution
2025-12-30 05:31:19 -08:00
hkfires
26efbed05c
refactor(executor): remove redundant upstream model parameter from translateRequest
2025-12-30 20:20:42 +08:00
hkfires
96340bf136
refactor(executor): resolve upstream model at conductor level before execution
2025-12-30 19:31:54 +08:00
hkfires
b055e00c1a
fix(executor): use upstream model for thinking config and payload translation
2025-12-30 17:49:44 +08:00
Chén Mù and GitHub
857c880f99
Merge pull request #785 from router-for-me/gemini
...
feat(gemini): add per-key model alias support for Gemini provider
2025-12-29 23:32:40 -08:00
hkfires
ce7474d953
feat(cliproxy): propagate thinking support metadata to aliased models
2025-12-30 15:16:54 +08:00
hkfires
70fdd70b84
refactor(cliproxy): extract generic buildConfigModels function for model info generation
2025-12-30 13:35:22 +08:00
hkfires
08ab6a7d77
feat(gemini): add per-key model alias support for Gemini provider
2025-12-30 13:27:57 +08:00
hkfires
d443c86620
refactor(config): rename model mapping fields from from/to to name/alias
2025-12-30 11:07:59 +08:00
hkfires
7be3f1c36c
refactor(config): rename model-name-mappings to oauth-model-mappings
2025-12-30 11:07:58 +08:00
hkfires
3099114cbb
refactor(api): simplify codex id token claims extraction
2025-12-29 19:48:02 +08:00
Chén Mù and GitHub
a38a9c0b0f
Merge pull request #770 from router-for-me/api
...
feat(api): add id token claims extraction for codex auth entries
2025-12-29 00:44:41 -08:00
hkfires
8286caa366
feat(api): add id token claims extraction for codex auth entries
2025-12-29 16:34:16 +08:00
Chén Mù and GitHub
bd1ec8424d
Merge pull request #767 from router-for-me/amp
...
feat(amp): add per-client upstream API key mapping support
2025-12-28 22:10:11 -08:00
hkfires
225e2c6797
feat(amp): add per-client upstream API key mapping support
2025-12-29 12:26:25 +08:00
hkfires
f137eb0ac4
chore: add codex, agents, and opencode dirs to ignore files
2025-12-29 08:42:29 +08:00
Chén Mù and GitHub
f39a460487
Merge pull request #761 from router-for-me/log
...
fix(logging): improve request/response capture
2025-12-28 16:13:10 -08:00
hkfires
a95428f204
fix(handlers): preserve upstream response logs before duplicate detection
2025-12-28 22:35:36 +08:00
hkfires
3ca5fb1046
fix(handlers): match raw error text before JSON body for duplicate detection
2025-12-28 19:35:36 +08:00
hkfires
a091d12f4e
fix(logging): improve request/response capture
2025-12-28 19:04:31 +08:00
hkfires
09455f9e85
fix(config): make streaming keepalive and retries ints
2025-12-27 20:56:47 +08:00
hkfires
c8e72ba0dc
fix(config): smart merge writes non-default new keys only
2025-12-27 20:28:54 +08:00
hkfires
375ef252ab
docs(config): clarify merge mapping behavior
2025-12-27 19:30:21 +08:00
hkfires
ee552f8720
chore(config): update ignore patterns
2025-12-27 19:13:14 +08:00
hkfires
2e88c4858e
fix(config): avoid adding new keys when merging
2025-12-27 19:00:47 +08:00
hkfires
8be06255f7
fix(auth): make provider rotation atomic
2025-12-27 12:56:48 +08:00
hkfires
5ba325a8fc
refactor(logging): standardize request id formatting and layout
2025-12-24 22:03:07 +08:00
hkfires
99238a4b59
fix(logging): normalize warning level to warn
2025-12-24 21:11:37 +08:00
hkfires
6d43a2ff9a
refactor(logging): inline request id in log output
2025-12-24 21:07:18 +08:00
hkfires
2a6d8b78d4
feat(api): add endpoint to retrieve request logs by ID
2025-12-24 19:24:51 +08:00
hkfires
26fbb77901
refactor(sdk/auth): rename manager.go to conductor.go
2025-12-24 15:21:03 +08:00
hkfires
007c3304f2
feat(logging): scope request ID tracking to AI API endpoints
2025-12-24 09:17:09 +08:00
hkfires
e76ba0ede9
feat(logging): implement request ID tracking and propagation
2025-12-24 08:32:17 +08:00
hkfires
3fc410a253
fix(amp): add /settings routes to proxy
2025-12-21 12:51:35 +08:00
hkfires
c84ff42bcd
fix(amp): add /docs routes to proxy
2025-12-20 10:15:25 +08:00
hkfires
2039062845
fix(gemini): add optional skip for gemini3 thinking conversion
2025-12-19 22:07:43 +08:00
hkfires
9d9b9e7a0d
fix(amp): add management auth skipper
2025-12-19 13:57:47 +08:00
hkfires
13aa82f3f3
fix(util): disable default thinking for gemini 3 flash
2025-12-19 13:11:15 +08:00
Chén Mù and GitHub
718ff7a73f
Merge pull request #609 from router-for-me/codex
...
feat(registry): add gpt 5.2 codex model definition
2025-12-19 09:54:34 +08:00
hkfires