81a050555d
feat(provider,web,asr): enhance model management with explicit provider metadata ( #2701 )
...
* feat(provider,web): enhance model management with provider options
* fix(asr): enhance compatibility for ElevenLabs transcription model
* fix(provider,web): align provider availability predicates and add flow gating
* fix(web,asr): preserve legacy elevenlabs transcription configs
* fix(provider,web,asr): normalize elevenlabs configs and gate default chat models
* fix: tighten provider catalog and elevenlabs compatibility
2026-05-06 16:06:49 +08:00
828a7cba70
Merge pull request #2681 from afjcjsbx/fix/gemini-mcp-schema-sanitization
...
fix(mcp): sanitize MCP tool schemas for Gemini function calling
2026-05-03 20:25:35 +02:00
dbf5d9ce1f
fix(seahorse): persist reasoning_content in sqlite history ( #2707 )
...
* fix(seahorse): persist reasoning_content in sqlite history
* fix(openai_compat): clarify DeepSeek reasoning replay rules
* style(seahorse): format files of seahorse
* fix(openai_compat): cover DeepSeek replay requirements
* fix(seahorse): repair missing reasoning_content during bootstrap
* fix(seahorse): repair reasoning_content on bootstrap prefix
2026-04-30 16:07:38 +08:00
7b3e800407
fix test
2026-04-27 21:18:19 +02:00
cd7717bc15
feat(tool): tool schema semplification
2026-04-27 21:10:30 +02:00
4eeb69688e
fix lint
2026-04-26 22:33:35 +02:00
1ff8a418f6
fix(mcp): sanitize MCP tool schemas for Gemini function calling
2026-04-26 22:23:55 +02:00
41f4d95597
Merge pull request #2657 from lc6464/fix-deepseek-v4-thinking-history
...
fix(reasoning): persist canonical history for DeepSeek and web chat
2026-04-25 15:08:48 +08:00
979ff00cc3
fix(messageutil): remove dead code
...
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com >
2026-04-24 22:16:18 +08:00
bb0f983708
fix(reasoning): persist canonical history for DeepSeek and web chat
2026-04-24 21:45:41 +08:00
48d8952591
feat(agent): migrate tool prompts to capability slots
2026-04-24 19:36:46 +08:00
2e65b1be83
feat(agent): add structured prompt layering
2026-04-24 18:14:28 +08:00
7616470137
Revert deduplication
2026-04-23 05:50:38 +00:00
4ae11406d2
Deduplicate further functions
2026-04-23 05:50:37 +00:00
bc077db0ee
Deduplicate ParseDataAudioURL function
2026-04-23 05:50:37 +00:00
e901e70c14
Fix linting
2026-04-23 05:47:58 +00:00
c71146b1d5
Functions deduplication
2026-04-23 05:47:58 +00:00
451db2f5d8
Feat(channels): unify animated tool feedback across chat channels and Pico ( #2622 )
...
* feat(channels): unify tool feedback animation across discord telegram and feishu
* fix(tool-feedback): unify fallback and single-message delivery
* fix(channels): finalize tool feedback in place
* fix ci
* feat: improve tool feedback
* fix review blockers in pico token cache and tool feedback
fix(provider): preserve function thought signatures
fix(feishu): recover tool feedback after edit fallback
* * delete dead code
* fix(pico): clean up tool feedback progress state
* fix ci
* fix(web): preserve tool feedback line breaks in chat
* fix(channels): preserve tool feedback progress state
fix(pico): preserve context usage when finalizing tool feedback
chore: record branch review pass
fix: preserve tool feedback finalization state
fix(web): handle pico history update fallback
* fix ci
2026-04-23 10:35:50 +08:00
77b0c43392
refactor: support explicit provider field in model list entries ( #2609 )
...
* refactor: support explicit model list providers
* fix(web): preserve explicit model providers
* fix(web): preserve legacy provider prefixes on model updates
fix(models): normalize explicit provider-prefixed ids
fix(api): preserve legacy model updates across providers
fix(agent): preserve config identity for explicit provider refs
* fix ci
2026-04-22 11:28:47 +08:00
3316ee6923
feat(web): download files on frontend ( #2563 )
...
* feat(web): download attachments in frontend
* fix: proxy pico media and force svg downloads
* feat(web): hide ephemeral media refs from persisted session history
2026-04-22 11:28:04 +08:00
6421f146a9
Revert "Feat/channel tool feedback animation ( #2569 )" ( #2596 )
...
This reverts commit e556a816e4
2026-04-20 18:30:29 +08:00
e556a816e4
Feat/channel tool feedback animation ( #2569 )
...
* feat(channels): unify tool feedback animation across discord telegram and feishu
* fix(tool-feedback): unify fallback and single-message delivery
* fix(channels): finalize tool feedback in place
* fix ci
* feat: improve tool feedback
2026-04-20 15:20:26 +08:00
9b4efddd9b
fix(providers,tools): address linter issues after reorg
2026-04-17 14:16:18 +08:00
ee634dc8db
refactor(providers): reorganize provider packages and facades
2026-04-17 12:42:03 +08:00
2b844778ff
refactor(tests): extract common logic for fallback error handling into a helper function
2026-04-16 22:45:31 +08:00
7aa2d672ce
fix(network): classify timeout errors as FailoverTimeout
...
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com >
2026-04-16 22:00:13 +08:00
c3f4000817
feat(network): implement network error classification and fallback handling
2026-04-16 19:59:37 +08:00
6fbd7e0a3f
fix(gemini): align thoughtSignature and stream tool IDs
2026-04-11 12:02:58 +08:00
e9f55d776d
fix(review): address copilot backpressure and SSE parse feedback
2026-04-11 11:18:41 +08:00
86917faa9b
fix(ci): resolve lint header casing and fallback test routing
2026-04-11 02:23:35 +08:00
cbae69ad64
fix(gemini): honor pro-model thinking constraints
2026-04-11 01:38:13 +08:00
83e93ca572
fix(gemini): align thinking-off and system prompt semantics
2026-04-11 01:15:38 +08:00
459e78c076
fix(gemini): harden dedicated provider compatibility
2026-04-11 00:50:24 +08:00
c8bac699fe
fix(pico): separate thought and normal messages
2026-04-10 20:23:12 +08:00
dde61365d4
Merge pull request #2420 from lahuman/docs/tool-escape-semantics
...
docs(tool): use provider-agnostic JSON escaping guidance
2026-04-09 20:50:06 +02:00
51eecde01e
Feat/support isolation ( #2423 )
...
* * completed
* * optimzie
* * fix format
* * fix pr check
* try to fix ci
* * Indicates that Windows does not support expos_paths, adding more mount paths for the Linux platform.
* fix isolation startup lifecycle and MCP transport wrapping
* fix isolation startup cleanup and optional Linux mounts
* fix isolation path handling for relative hooks
Preserve relative command and working-directory semantics when Linux isolation wraps subprocesses, and restore absolute argv path exposure to avoid startup regressions. Add hook coverage and docs updates so isolation-enabled process hooks keep working as configured.
* * fix ci
2026-04-08 18:15:42 +08:00
8f7eae8b37
docs(tool): use provider-agnostic JSON escaping guidance
2026-04-08 14:19:11 +09:00
38a498e202
feat(provider): support custom headers injection for HTTP providers ( #2402 )
...
* feat(provider): support custom headers injection for HTTP providers
* fix(provider): resolve lint problem
* fix(provider): align stream user-agent and header precedence docs
2026-04-07 16:05:21 +08:00
71337b6f52
fix(tool): clarify write_file nested-JSON escape semantics and add tests ( #2320 )
...
* fix(tool): clarify write_file nested-JSON escape semantics and add tests
* fix(tool): improve formatting of escaping rules in CLI tool prompt
* fix(tool): align escape notation with function.arguments layer
2026-04-04 17:56:49 +08:00
b114dcaeb1
feat(model): llm rate limiting ( #2198 )
...
* feat(model): rate limiting
* fix(agent): preserve per-model identity in rate limiting and fallback
* fix test
2026-04-02 19:26:26 +08:00
2c446e1e07
feat: add userAgent config for ModelConfig ( #2242 )
...
* feat: add userAgent config for ModelConfig
* update docs for ModelConfig.userAgent
* make defaut userAgent to PicoClaw and add test case
2026-04-02 11:44:13 +08:00
bbcfeaa361
feat(provider): add Venice AI support and update related documentation ( #2238 )
...
* feat(provider): add Venice AI support and update related documentation
* revert(asr): restore asr files to previous commit
* feat(config): add Venice API base URL and local LM Studio configuration
* fix(config): update Venice API base URL to correct endpoint
2026-04-01 23:50:29 +08:00
0f395ce110
Refactor/asr tts ( #1939 )
...
* refactor: update ASR and TTS implementations
* fix lint
* Integrating asr/tts models w/ new security config
* update documents
* add arbitrary whisper transcriptor support
* update documents
* fix lint
* add mimo tts
2026-04-01 12:21:21 +08:00
e4893d27d7
fix test and lint in web ( #2219 )
2026-03-31 15:50:55 +08:00
31fcf55297
fix linter ( #2206 )
2026-03-31 15:06:47 +08:00
ee02e30992
feat(provider): add lmstudio and align local provider default auth/base handling ( #2193 )
...
* feat(provider): add lmstudio vendor and local no-key behavior
* refactor(provider): consolidate protocol metadata and local tests
* fix(provider): sync lmstudio probing and model normalization
* test(web): format lmstudio model status cases for golines
2026-03-31 14:48:18 +08:00
4125f8ac14
Merge pull request #1849 from gaaralbakuu/main
...
Fix: Provider github copilot cannot create session
2026-03-30 23:37:26 +02:00
0fb45505bf
Merge pull request #1988 from loafoe/main
...
feat(bedrock): detect SSO token expiration and provide actionable error
2026-03-30 14:17:19 +02:00
4f90909af3
feat(bedrock): detect SSO token expiration and provide actionable error
...
When AWS SSO credentials expire, provide a clear error message instructing
the user to run 'aws sso login' to refresh their session.
2026-03-28 22:18:45 +01:00
e23eda5365
Update tests and error cases handling
2026-03-28 13:33:48 +00:00
LC