goldyard/CLIProxyAPIPlus
1
0
Fork 0
mirror of https://github.com/githubhjs/CLIProxyAPIPlus.git synced 2026-07-14 18:38:40 +00:00
Code Issues Packages Projects Releases Wiki Activity
973 Commits 1 Branch 0 Tags
d9a65745df6eefbe0b69145d6544d7b6c3af555f
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Luis Pater d9a65745df fix(translator): handle empty item type and string content in OpenAI response parser 2025-12-15 20:35:52 +08:00
Luis PaterandGitHub f6720f8dfa Merge pull request #547 from router-for-me/amp 
feat(amp): require API key authentication for management routes
 2025-12-15 16:14:49 +08:00
Luis PaterandGitHub 8e4fbcaa7d Merge pull request #533 from router-for-me/think 
refactor(thinking): centralize reasoning effort mapping and normalize budget values
 2025-12-15 10:34:41 +08:00
Luis PaterandGitHub 707b07c5f5 Merge pull request #537 from sukakcoding/fix/function-response-fallback 
fix: handle malformed json in function response parsing
 2025-12-15 03:31:09 +08:00
Luis PaterandGitHub 5a75ef8ffd Merge pull request #536 from AoaoMH/feature/auth-model-check 
feat: using Client Model Infos;
 2025-12-15 00:29:33 +08:00
Luis Pater 71f788b13a fix(registry): remove unused ThinkingSupport from DeepSeek-R1 model 2025-12-14 21:30:17 +08:00
Luis Pater 59c62dc580 fix(registry): correct DeepSeek-V3.2 experimental model ID 2025-12-14 21:27:43 +08:00
Luis PaterandGitHub d5310a3300 Merge pull request #531 from AoaoMH/feature/auth-model-check 
feat: add API endpoint to query models for auth credentials
 2025-12-14 16:46:43 +08:00
Luis Pater f0a3eb574e fix(registry): update DeepSeek model definitions with new IDs and descriptions 2025-12-14 16:17:11 +08:00
Luis PaterandGitHub 14ce6aebd1 Merge pull request #449 from sususu98/fix/gemini-cli-429-retry-delay-parsing 
fix(gemini-cli): enhance 429 retry delay parsing
 2025-12-14 14:04:14 +08:00
Luis PaterandGitHub 2fe83723f2 Merge pull request #515 from teeverc/fix/response-rewriter-streaming-flush 
fix(amp): flush response buffer after each streaming chunk write
 2025-12-14 13:26:05 +08:00
Luis PaterandGitHub b6ad243e9e Merge pull request #498 from teeverc/fix/claude-streaming-flush 
fix(claude): flush Claude SSE chunks immediately
 2025-12-13 23:58:34 +08:00
Luis Pater 660aabc437 fix(executor): add allowCompat support for reasoning effort normalization 
Introduced `allowCompat` parameter to improve compatibility handling for reasoning effort in payloads across OpenAI and similar models.
 2025-12-13 04:06:02 +08:00
Luis PaterandGitHub 566120e8d5 Merge pull request #505 from router-for-me/think 
fix(thinking): map budgets to effort levels
 2025-12-12 22:17:11 +08:00
Luis PaterandGitHub f3f0f1717d Merge branch 'dev' into think 2025-12-12 22:16:44 +08:00
Luis PaterandGitHub 7621ec609e Merge pull request #501 from huynguyen03dev/fix/openai-compat-model-alias-resolution 
fix(openai-compat): prevent model alias from being overwritten
 2025-12-12 21:58:15 +08:00
Luis Pater 9f511f0024 fix(executor): improve model compatibility handling for OpenAI-compatibility 
Enhances payload handling by introducing OpenAI-compatibility checks and refining how reasoning metadata is resolved, ensuring broader model support.
 2025-12-12 21:57:25 +08:00
Luis PaterandGitHub 1c52a89535 Merge pull request #502 from router-for-me/iflow 
fix(auth): prevent duplicate iflow BXAuth tokens
 2025-12-12 20:03:37 +08:00
Luis PaterandGitHub b8194e717c Merge pull request #500 from router-for-me/think 
fix(codex): raise default reasoning effort to medium
 2025-12-12 18:35:26 +08:00
Luis Pater 6e43669498 Fixed: #440 
feat(watcher): normalize auth file paths and implement debounce for remove events
 2025-12-12 16:50:56 +08:00
Luis PaterandGitHub fc054db51a Merge pull request #494 from ben-vargas/fix-gpt-reasoning-none 
fix(models): add "none" reasoning effort level to gpt-5.2
 2025-12-12 08:53:19 +08:00
Luis Pater 6e2306a5f2 refactor(handlers): improve request logging and payload handling 2025-12-12 08:52:52 +08:00
Luis Pater a68c97a40f Fixed: #492 2025-12-12 04:08:11 +08:00
Luis Pater cd2da152d4 feat(models): add GPT 5.2 model definition and prompts 2025-12-12 03:02:27 +08:00
Luis PaterandGitHub bb6312b4fc Merge pull request #488 from router-for-me/gemini 
Unify the Gemini executor style
 2025-12-11 22:14:17 +08:00
Luis PaterandGitHub a74ee3f319 Merge pull request #481 from sususu98/fix/increase-buffer-size 
fix: increase buffer size for stream scanners to 50MB across multiple executors
 2025-12-11 21:20:54 +08:00
Luis PaterandGitHub 564bcbaa54 Merge pull request #487 from router-for-me/amp 
fix(amp): set status on claude stream errors
 2025-12-11 21:18:19 +08:00
Luis PaterandGitHub 2760989401 Merge pull request #485 from router-for-me/think 
Think
 2025-12-11 18:27:00 +08:00
Luis PaterandGitHub 1da03bfe15 Merge pull request #479 from router-for-me/claude 
fix(claude): prevent final events when no content streamed
 2025-12-11 08:18:59 +08:00
Luis Pater 423ce97665 feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic 
- Added support for parsing and normalizing dynamic thinking model suffixes.
- Centralized budget resolution across executors and payload helpers.
- Retired legacy Gemini-specific thinking handlers in favor of unified logic.
- Updated executors to use metadata-based thinking configuration.
- Added `ResolveOriginalModel` utility for resolving normalized upstream models using request metadata.
- Updated executors (Gemini, Codex, iFlow, OpenAI, Qwen) to incorporate upstream model resolution and substitute model values in payloads and request URLs.
- Ensured fallbacks handle cases with missing or malformed metadata to derive models robustly.
- Refactored upstream model resolution to dynamically incorporate metadata for selecting and normalizing models.
- Improved handling of thinking configurations and model overrides in executors.
- Removed hardcoded thinking model entries and migrated logic to metadata-based resolution.
- Updated payload mutations to always include the resolved model.
 2025-12-11 03:10:50 +08:00
Luis Pater e717939edb Fixed: #478 
feat(antigravity): add support for inline image data in client responses
 2025-12-10 23:55:53 +08:00
Luis Pater 94d61c7b2b fix(logging): update response aggregation logic to include all attempts 2025-12-10 16:53:48 +08:00
Luis Pater 1249b07eb8 feat(responses): add unique identifiers for responses, function calls, and tool uses 2025-12-10 16:02:54 +08:00
Luis Pater 6b37f33d31 feat(antigravity): add unique identifier for tool use blocks in response 2025-12-10 15:27:57 +08:00
Luis Pater f25f419e5a fix(antigravity): remove references to autopush endpoint and update fallback logic 2025-12-10 00:13:20 +08:00
Luis PaterandGitHub b7e382008f Merge pull request #465 from router-for-me/think 
Move thinking budget normalization from translators to executor
 2025-12-09 21:10:33 +08:00
Luis PaterandGitHub 5db3b58717 Merge pull request #470 from router-for-me/agry 
fix(gemini): normalize model listing output
 2025-12-09 21:00:29 +08:00
Luis Pater 39b6b3b289 Fixed: #463 
fix(antigravity): remove `$ref` and `$defs` from JSON during key deletion
 2025-12-09 17:32:17 +08:00
Luis Pater c600519fa4 refactor(logging): replace log.Fatalf with log.Errorf and add error handling paths 2025-12-09 17:16:30 +08:00
Luis PaterandGitHub 92df0cada9 Merge pull request #461 from router-for-me/aistudio 
feat(aistudio): normalize thinking budget in request translation
 2025-12-09 08:41:46 +08:00
Luis Pater bb45fee1cf Merge remote-tracking branch 'origin/dev' into dev 2025-12-08 23:28:22 +08:00
Luis Pater af00304b0c fix(antigravity): remove exclusiveMaximum from JSON during key deletion 2025-12-08 23:28:01 +08:00
Luis Pater 6ad188921c refactor(logging): remove unused variable in ensureAttempt and redundant function call 2025-12-08 22:25:58 +08:00
Luis PaterandGitHub 15ed98d6a9 Merge pull request #458 from router-for-me/agry 
feat(antigravity): enforce thinking budget limits for Claude models
 2025-12-08 20:55:52 +08:00
Luis PaterandGitHub 3efbd865a8 Merge pull request #457 from router-for-me/requestlog 
style(logging): remove redundant separator line from response section
 2025-12-08 18:21:24 +08:00
Luis PaterandGitHub 5aa386d8b9 Merge pull request #453 from router-for-me/amp 
add ampcode management api
 2025-12-08 17:42:13 +08:00
Luis PaterandGitHub 0adc0ee6aa Merge pull request #455 from router-for-me/requestlog 
feat(logging): add upstream API request/response capture to streaming logs
 2025-12-08 17:40:10 +08:00
Luis PaterandGitHub de77903915 Merge pull request #450 from router-for-me/amp 
refactor(config): rename prioritize-model-mappings to force-model-mappings
 2025-12-08 10:51:32 +08:00
Luis PaterandGitHub 42e818ce05 Merge pull request #435 from heyhuynhgiabuu/fix/amp-model-mapping-priority 
fix: prioritize model mappings over local providers for Amp CLI
 2025-12-08 10:17:19 +08:00
Luis PaterandGitHub 2d4c54ba54 Merge pull request #448 from router-for-me/iflow 
Iflow
 2025-12-08 09:50:05 +08:00
Luis PaterandGitHub d26ed069fa Merge pull request #441 from huynguyen03dev/fix/claude-to-openai-whitespace-text 
fix: filter whitespace-only text in Claude to OpenAI translation
 2025-12-08 09:43:44 +08:00
Luis PaterandGitHub 6cf1d8a947 Merge pull request #444 from router-for-me/agry 
feat(registry): add explicit thinking support config for antigravity models
 2025-12-07 19:38:43 +08:00
Luis PaterandGitHub 1b638b3629 Merge pull request #432 from huynguyen03dev/fix/amp-gemini-model-mapping 
fix(amp): pass mapped model to gemini bridge via context
 2025-12-07 13:33:28 +08:00
Luis PaterandGitHub 6f5f81753d Merge pull request #439 from router-for-me/log 
feat(logging): add version info to request log output
 2025-12-07 13:31:06 +08:00
Luis Pater 76af454034 **feat(antigravity): enhance handling of "thinking" content and refine Claude model response processing** 2025-12-07 13:19:12 +08:00
Luis Pater f383840cf9 fix(antigravity): update toolNode role from "tool" to "user" in chat completions 2025-12-07 02:37:46 +08:00
Luis Pater fd29ab418a Fixed: #424 
**feat(antigravity): add support for maxOutputTokens and refine Claude model handling**
 2025-12-07 01:55:57 +08:00
Luis Pater 7a628426dc Fixed: #433 
refactor(translator): normalize finish reason casing across all OpenAI response handlers
 2025-12-07 01:48:24 +08:00
Luis Pater 56b4d7a76e docs(readme): add ProxyPal CLIProxyAPI GUI to project list 2025-12-07 01:13:30 +08:00
Luis PaterandGitHub b211c3546d Merge pull request #429 from heyhuynhgiabuu/feature/add-proxypal 
docs: add ProxyPal to 'Who is with us?' section
 2025-12-07 01:10:44 +08:00
Luis PaterandGitHub 7ea14479fb Merge pull request #428 from router-for-me/amp 
feat(amp): add response rewriter for model name substitution in responses
 2025-12-06 15:14:10 +08:00
Luis Pater 0ebabf5152 feat(antigravity): add FetchAntigravityProjectID function and integrate project ID retrieval 2025-12-06 01:32:12 +08:00
Luis Pater d7564173dd fix(antigravity): restore production base URL in the executor 2025-12-06 01:11:37 +08:00
Luis Pater c44c46dd80 Fixed: #421 
feat(antigravity): implement project ID retrieval and integration in payload processing
 2025-12-06 00:40:55 +08:00
Luis Pater 412148af0e feat(antigravity): add function ID to FunctionCall and FunctionResponse models 2025-12-05 23:05:35 +08:00
Luis PaterandGitHub d28258501a Merge pull request #423 from router-for-me/amp 
fix(amp): suppress ErrAbortHandler panics in reverse proxy handler
 2025-12-05 21:36:01 +08:00
Luis PaterandGitHub c5df8e7897 Merge pull request #422 from router-for-me/amp 
Amp
 2025-12-05 21:25:43 +08:00
Luis Pater d4d529833d **refactor(antigravity): handle anyOf property, remove exclusiveMinimum, and comment unused prod URL** 2025-12-05 21:24:12 +08:00
Luis Pater 361443db10 **feat(api): add GetLatestVersion endpoint to fetch latest release version from GitHub** 2025-12-05 10:29:12 +08:00
Luis Pater d6352dd4d4 **feat(util): add DeleteKey function and update antigravity executor for Claude model compatibility** 2025-12-05 01:55:45 +08:00
Luis PaterandGitHub a7eeb06f3d Merge pull request #418 from router-for-me/amp 
Amp
 2025-12-05 00:43:15 +08:00
Luis PaterandGitHub b87b9b455f Merge pull request #416 from router-for-me/amp 
Amp
 2025-12-04 20:52:33 +08:00
Luis Pater bceecfb2e3 Fixed: #414 
**refactor(gemini): comment out unused CLI preview entry**
 2025-12-04 17:55:13 +08:00
Luis Pater 6a2906e3e5 **feat(antigravity): add support for Claude-Opus-4-5-Thinking model** 2025-12-04 16:13:13 +08:00
Luis PaterandGitHub d72886c801 Merge pull request #405 from thurstonsand/fix/amp-missing-proxy-routes 
fix(amp): add missing /auth/* and /api/tab/* proxy routes for AMP CLI
 2025-12-03 22:23:41 +08:00
Luis PaterandGitHub 6efba3d829 Merge pull request #406 from router-for-me/api 
refactor(api): remove legacy generative-language-api-key endpoints and duplicate GetConfigYAML
 2025-12-03 22:21:15 +08:00
Luis Pater 897c40bed8 feat(registry): add DeepSeek-V3.2-Chat model definition 
Add new DeepSeek-V3.2-Chat model to the registry with standard chat configuration, positioned before the experimental variant for better organization.
 2025-12-03 21:34:50 +08:00
Luis PaterandGitHub 6eb94dac33 Merge pull request #404 from router-for-me/config 
Legacy Config Migration and Amp Consolidation
 2025-12-03 16:11:06 +08:00
Luis Pater 8b13c91132 **docs(internal): add Codex instruction guides for GPT-5 CLI** 
- Added `gpt_5_1_prompt.md` and `gpt_5_codex_prompt.md` to document Codex instruction guidelines.
- These detail the behavior, constraints, and execution policies for GPT-5-based Codex agents in the CLI environment.
 2025-12-03 07:23:01 +08:00
Luis Pater e93f87294a refactor(antigravity): uncomment prod environment URL in fallback chain 2025-12-02 22:47:18 +08:00
Luis Pater a67b6811d1 Fixed: #397 
fix(auth): use proxy HTTP client for Gemini CLI token requests
 2025-12-02 22:39:01 +08:00
Luis PaterandGitHub 35fdc4cfd3 fix some bugs (#399) 
* feat(config): add pruning of stale YAML mapping keys during config save

* Revert watcher.go in "fix: enable hot reload for amp-model-mappings config"
 2025-12-02 22:28:30 +08:00
Luis Pater 41ee44432d **fix(translator): rename responseSchema key for generationConfig** 
- Renamed `generationConfig.responseSchema` to `generationConfig.responseJsonSchema` in Gemini request transformation to align with updated schema expectations.
 2025-12-02 18:32:23 +08:00
Luis Pater 1434bc38e5 **refactor(registry): remove Qwen3-Coder from model definitions** 2025-12-02 11:34:38 +08:00
Luis Pater 0fd2abbc3b **refactor(cliproxy, config): remove vertex-compat flow, streamline Vertex API key handling** 
- Removed `vertex-compat` executor and related configuration.
- Consolidated Vertex compatibility checks into `vertex` handling with `apikey`-based model resolution.
- Streamlined model generation logic for Vertex API key entries.
 2025-12-02 09:18:24 +08:00
Luis PaterandGitHub 08a1d2edf9 Merge pull request #390 from NguyenSiTrung/main 
feat(amp): add model mapping support for routing unavailable models to alternatives
 2025-12-02 08:07:56 +08:00
Luis PaterandGitHub 54e24110ec Merge pull request #386 from auroraflux/feat/dedupe-thinking-metadata-helpers 
refactor(executor): dedupe thinking metadata helpers across Gemini executors
 2025-12-01 09:00:27 +08:00
Luis Pater 717c703bff docs(readme): add CCS (Claude Code Switch) to projects list 2025-12-01 07:22:42 +08:00
Luis PaterandGitHub 0de2560cee Merge pull request #379 from kaitranntt/docs/add-ccs-project 
docs: add CCS (Claude Code Switch) to projects list
 2025-12-01 07:20:04 +08:00
Luis PaterandGitHub cb580cd083 Merge pull request #377 from router-for-me/gemini 
feat(registry): add thinking support to gemini models
 2025-11-30 21:27:54 +08:00
Luis PaterandGitHub 73208c4e55 Merge pull request #376 from auroraflux/feat/reasoning-suffix-support 
feat(util): add -reasoning suffix support for Gemini models
 2025-11-30 20:55:38 +08:00
Luis Pater a748e93fd9 **fix(executor, auth): ensure index assignment consistency for auth objects** 
- Updated `usage_helpers.go` to call `EnsureIndex()` for proper index assignment in reporter initialization.
- Adjusted `auth/manager.go` to assign auth indices inside a locked section when they are unassigned, ensuring thread safety and consistency.
 2025-11-30 16:56:29 +08:00
Luis PaterandGitHub 54a9c4c3c7 Merge pull request #371 from ben-vargas/test-amp-tools 
fix(amp): add /threads.rss root-level route for AMP CLI
 2025-11-30 15:18:23 +08:00
Luis PaterandGitHub 18b5c35dea Merge pull request #366 from router-for-me/blacklist 
Add Model Blacklist
 2025-11-30 15:17:46 +08:00
Luis Pater 72c7ef7647 **fix(translator): handle non-JSON output parsing for OpenAI function responses** 
- Updated `antigravity_openai_request.go` to process non-JSON outputs gracefully by verifying and distinguishing between JSON and plain string formats.
- Ensured proper assignment of parsed or raw response to `functionResponse`.
 2025-11-27 16:18:49 +08:00
Luis Pater d2e4639b2a **feat(registry): add context length and update max tokens for Claude model configurations** 
- Added `ContextLength` field with a value of 200,000 to all applicable Claude model definitions.
- Standardized `MaxCompletionTokens` values across models for consistency and alignment.
 2025-11-27 16:13:25 +08:00
Luis PaterandGitHub 08321223c4 Merge pull request #340 from nestharus/fix/339-thinking-openai-gemini-compat 
fix(thinking): resolve OpenAI/Gemini compatibility for thinking model…
 2025-11-27 16:03:24 +08:00
Luis Pater 7e30157590 Fixed: #354 
**fix(translator): add support for "xhigh" reasoning effort in OpenAI responses**

- Updated handling in `openai_openai-responses_request.go` to include the new "xhigh" reasoning effort level.
 2025-11-27 15:59:15 +08:00
Luis Pater 39621a0340 **fix(translator): normalize function calls and outputs for consistent input processing** 
- Implemented logic to pair consecutive function calls and their outputs, ensuring proper sequencing for processing.
- Adjusted `gemini_openai-responses_request.go` to normalize message structures and maintain expected flow.
 2025-11-27 10:25:45 +08:00
Luis Pater 346b663079 **fix(translator): handle non-JSON output gracefully in function call outputs** 
- Updated handling of `output` in `gemini_openai-responses_request.go` to use `.Str` instead of `.Raw` when parsing non-JSON string outputs.
- Added checks to distinguish between JSON and non-JSON `output` types for accurate `functionResponse` construction.
 2025-11-27 09:40:00 +08:00