47b9503112
chore: revert changes to internal/translator to comply with path guard
...
This commit reverts all modifications within internal/translator. A separate issue
will be created for the maintenance team to integrate SanitizeFunctionName into
the translators.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 02:19:26 +05:00
3b9253c2be
fix(translator): resolve invalid function name errors by sanitizing Claude tool names
...
This commit centralizes tool name sanitization in SanitizeFunctionName,
applying character compliance, starting character rules, and length limits.
It also fixes a regression in gemini_schema tests and preserves MCP-specific
shortening logic while ensuring compliance.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 02:14:46 +05:00
d241359153
fix(translator): address PR feedback for tool name sanitization
...
- Pre-compile sanitization regex for better performance.
- Optimize SanitizeFunctionName for conciseness and correctness.
- Handle 64-char edge cases by truncating before prepending underscore.
- Fix bug in Antigravity translator (incorrect join index).
- Refactor Gemini translators to avoid redundant sanitization calls.
- Add comprehensive unit tests including 64-char edge cases.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 01:54:41 +05:00
f4d4249ba5
feat(translator): sanitize tool/function names for upstream provider compatibility
...
Implemented SanitizeFunctionName utility to ensure Claude tool names meet
Gemini/Upstream strict naming conventions (alphanumeric, starts with letter/underscore, max 64 chars).
Applied sanitization to tool definitions and usage in all relevant translators.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2025-12-31 01:41:07 +05:00
e0381a6ae0
refactor(watcher): extract model summary functions to dedicated file
2025-12-30 22:39:12 +08:00
2c01b2ef64
feat(watcher): add Gemini models and OAuth model mappings change detection
2025-12-30 22:39:12 +08:00
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
c6b0e85b54
Fixed : #790
...
fix(gemini): include full text in response output events
2025-12-30 20:44:13 +08:00
26efbed05c
refactor(executor): remove redundant upstream model parameter from translateRequest
2025-12-30 20:20:42 +08:00
96340bf136
refactor(executor): resolve upstream model at conductor level before execution
2025-12-30 19:31:54 +08:00
b055e00c1a
fix(executor): use upstream model for thinking config and payload translation
2025-12-30 17:49:44 +08:00
414db44c00
fix(antigravity): parse retry-after delay from 429 response body
...
When receiving HTTP 429 (Too Many Requests) responses, parse the retry
delay from the response body using parseRetryDelay and populate the
statusErr.retryAfter field. This allows upstream callers to respect
the server's requested retry timing.
Applied to all error paths in Execute, executeClaudeNonStream,
ExecuteStream, CountTokens, and refreshToken functions.
2025-12-30 16:07:32 +08:00
ce7474d953
feat(cliproxy): propagate thinking support metadata to aliased models
2025-12-30 15:16:54 +08:00
70fdd70b84
refactor(cliproxy): extract generic buildConfigModels function for model info generation
2025-12-30 13:35:22 +08:00
08ab6a7d77
feat(gemini): add per-key model alias support for Gemini provider
2025-12-30 13:27:57 +08:00
d443c86620
refactor(config): rename model mapping fields from from/to to name/alias
2025-12-30 11:07:59 +08:00
7be3f1c36c
refactor(config): rename model-name-mappings to oauth-model-mappings
2025-12-30 11:07:58 +08:00
f6ab6d97b9
fix(logging): add isDirWritable utility to enhance log dir validation in ConfigureLogOutput
2025-12-30 10:48:25 +08:00
bc866bac49
fix(logging): refactor ConfigureLogOutput to accept config object and adjust log directory handling
2025-12-30 10:28:25 +08:00
50e6d845f4
feat(cliproxy): introduce global model name mappings for improved aliasing and routing
2025-12-30 08:13:06 +08:00
a8cb01819d
Merge pull request #772 from soffchen/main
...
fix: Implement fallback log directory for file logging on read-only system
2025-12-30 02:24:49 +08:00
06ddf575d9
fix(antigravity): inject required placeholder when properties exist without required
2025-12-29 23:55:59 +08:00
3099114cbb
refactor(api): simplify codex id token claims extraction
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
2025-12-29 19:48:02 +08:00
44b63f0767
fix: Return an error if the user home directory cannot be determined for the fallback log path.
2025-12-29 18:46:15 +08:00
6705d20194
fix: Implement fallback log directory for file logging on read-only systems.
2025-12-29 18:35:48 +08:00
8286caa366
feat(api): add id token claims extraction for codex auth entries
2025-12-29 16:34:16 +08:00
225e2c6797
feat(amp): add per-client upstream API key mapping support
2025-12-29 12:26:25 +08:00
d8fc485513
fix(translators): correct key path for system_instruction.parts in Claude request logic
2025-12-29 11:54:26 +08:00
ee171bc563
feat(api): add ManagementTokenRequester interface for management token request endpoints
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
2025-12-29 02:42:29 +08:00
457924828a
Merge pull request #757 from ben-vargas/fix-thinking-toolchoice-conflict
...
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
Fix: disable thinking when tool_choice forces tool use
2025-12-28 14:04:30 +08:00
aca2ef6359
Fix: disable thinking when tool_choice forces tool use
...
Anthropic API does not allow extended thinking when tool_choice is set
to "any" or a specific tool. This was causing 400 errors when using
features like Amp's /handoff command which forces tool_choice.
Added disableThinkingIfToolChoiceForced() that removes thinking config
when incompatible tool_choice is detected, applied to both streaming
and non-streaming paths.
Fixes router-for-me/CLIProxyAPI#630
2025-12-27 16:31:37 -07:00
ade7194792
feat(management): add generic API call handler to management endpoints
2025-12-28 04:40:32 +08:00
3a436e116a
feat(cliproxy): implement model aliasing and hashing for Codex configurations, enhance request routing logic, and normalize Codex model entries
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
2025-12-28 03:06:51 +08:00
6403ff4ec4
feat(iflow): add model-specific thinking configs for GLM-4.7 and MiniMax-M2.1
...
- GLM-4.7: Uses extra_body={"thinking": {"type": "enabled"}, "clear_thinking": false}
- MiniMax-M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
- Added preserveReasoningContentInMessages() to support re-injection of reasoning
content in assistant message history for multi-turn conversations
- Added ThinkingSupport to MiniMax-M2.1 model definition
2025-12-27 18:39:15 +01:00
7646a2b877
Fixed : #749
...
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
fix(translators): ensure `gjson.String` content is non-empty before setting `parts` in OpenAI request logic
2025-12-28 00:54:26 +08:00
62090f2568
Merge pull request #750 from router-for-me/config
...
fix(config): preserve original config structure and avoid default value pollution
2025-12-27 22:10:01 +08:00
c281f4cbaf
Fixed : #747
...
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
fix(translators): rename and integrate `usageMetadata` as `cpaUsageMetadata` in Claude processing logic
2025-12-27 22:02:11 +08:00
09455f9e85
fix(config): make streaming keepalive and retries ints
2025-12-27 20:56:47 +08:00
c8e72ba0dc
fix(config): smart merge writes non-default new keys only
2025-12-27 20:28:54 +08:00
375ef252ab
docs(config): clarify merge mapping behavior
2025-12-27 19:30:21 +08:00
2e88c4858e
fix(config): avoid adding new keys when merging
2025-12-27 19:00:47 +08:00
72274099aa
Fixed : #738
...
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
fix(translators): refine prompt token calculation by incorporating cached tokens in Claude response handling
2025-12-27 03:56:11 +08:00
dcae098e23
Fixed : #736
...
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
fix(translators): handle gjson string types in Claude request processing to ensure consistent content parsing
2025-12-27 01:25:47 +08:00
3ce0d76aa4
feat(usage): add import/export functionality for usage statistics and enhance deduplication logic
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
2025-12-26 11:49:51 +08:00
33e53a2a56
fix(translators): ensure correct handling and output of multimodal assistant content across request handlers
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
2025-12-26 05:08:04 +08:00
3f949b7f84
Merge pull request #704 from tinyc0der/add-index
...
fix(openai): add index field to image response for LiteLLM compatibility
2025-12-25 21:35:12 +08:00
443c4538bb
feat(config): add commercial-mode to optimize HTTP middleware for lower memory usage
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
2025-12-25 21:05:01 +08:00
a7fc2ee4cf
refactor(image): avoid using json.Marshal
2025-12-25 14:21:01 +07:00
06ad527e8c
Fixed : #696
...
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
fix(translators): adjust prompt token calculation by subtracting cached tokens across Gemini, OpenAI, and Claude handlers
2025-12-24 23:29:18 +08:00
b7409dd2de
Merge pull request #706 from router-for-me/log
...
docker-image / docker (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
Log
2025-12-24 22:24:39 +08:00
Saboor Hassan