Commit graph

1995 commits

Author SHA1 Message Date
Leandro Barbosa
eeac7c7a67
Merge pull request #385 from Leeaandrob/docs/add-portuguese-br-readme
docs: add Brazilian Portuguese README (README.pt-br.md)
2026-02-17 17:56:36 -03:00
Leandro Barbosa
f820da42d7 docs: add Brazilian Portuguese README (README.pt-br.md)
Add complete pt-BR translation of the README and update language
navigation links across all existing READMEs (English, Chinese,
Japanese) to include the Portuguese option.
2026-02-17 17:52:28 -03:00
Artem Yadelskyi
d49ce32010
Merge branch 'main' into telegram-bot-commands 2026-02-17 20:21:46 +02:00
Artem Yadelskyi
0785a05a48
Merge branch 'main' into golangci-lint 2026-02-17 20:20:22 +02:00
Luna Reed
acac1972e6 fix(exec): terminate process tree on timeout 2026-02-18 02:01:29 +08:00
AlbertBui010
8428446d69 docs: fix allow_from typo in config examples 2026-02-18 00:17:56 +07:00
QUY BUI QUANG
2ee2858912
Merge branch 'main' into docs/add-vietnamese-readme 2026-02-17 23:46:19 +07:00
AlbertBui010
b83304845e docs: resolve conflict in README.ja.md 2026-02-17 23:39:17 +07:00
yinwm
5d1669ecc4 Merge PR #343: Add Google Antigravity provider and harden tool-call compatibility 2026-02-18 00:13:24 +08:00
Jared Mahotiere
c4cbb5fb35 providers: finalize PR213 review fixes
Phase 1: centralize protocol message/tool/response types in protocoltypes and keep compatibility aliases in providers and protocol packages.

Phase 1: preserve HTTPProvider constructor compatibility and route Anthropic api_base through factory auth/provider constructors with base URL normalization.

Phase 2: expand provider routing/auth tests (deepseek/nvidia/shengsuanyun, codex/claude oauth/codex-cli) and add openai_compat + anthropic coverage for proxy transport, model normalization, numeric option coercion, token-source refresh, and base URL behavior.

Phase 3: apply gofmt and validate with Dockerized tests (go test ./pkg/providers/... ./pkg/migrate and go test ./...).
2026-02-17 11:13:10 -05:00
Leandro Barbosa
ba47892bcf
Merge pull request #327 from humaid0x/fix-japanese-readme-link
docs: add missing Chinese language link to Japanese README
2026-02-17 13:12:47 -03:00
Leandro Barbosa
4fde0175cf
Merge pull request #227 from mattn/fix-shadowing-running
Fix shadowing field runnnig
2026-02-17 12:58:48 -03:00
yinwm
6913edbb5b Merge PR #368: Add Volcengine (doubao) provider 2026-02-17 23:51:40 +08:00
yinwm
6992012737 Merge PR #333: Add Cerebras provider 2026-02-17 23:41:19 +08:00
yinwm
de4ef9a8be Merge PR #365: Add Qwen provider 2026-02-17 23:37:55 +08:00
likeaturtle
bb0eadded0 Optimize ./picoclaw status output to support all config file configurations. 2026-02-17 23:29:27 +08:00
zenix.huang
0d16525fab fix: codex tool call 2026-02-17 22:56:31 +08:00
zenix.huang
4cd3f99dd6 fix: remove max_tokens 2026-02-17 22:56:31 +08:00
likeaturtle
6cd419b6e2 Fix the case sensitivity issue when automatically recognizing VolcEngine LLM model names. 2026-02-17 22:49:43 +08:00
mrbeandev
84110aa408 fix(antigravity): preserve thought signature on tool call parts 2026-02-17 20:05:47 +05:30
mrbeandev
99c32714f1 fix(antigravity): sanitize invalid tool-call history ordering 2026-02-17 20:05:41 +05:30
mrbeandev
caf3913347 fix(antigravity): normalize tool calls to avoid empty function names 2026-02-17 20:05:35 +05:30
mrbeandev
d1655d5996 fix(antigravity): update default model from gemini-3-flash-preview to gemini-3-flash 2026-02-17 20:05:29 +05:30
mrbeandev
1765f6d0e7 fix: strip antigravity prefix and improve model list for flash-preview 2026-02-17 20:05:25 +05:30
mrbeandev
d3fe8c5e17 feat: use gemini-3-flash-preview as default model name 2026-02-17 20:05:20 +05:30
mrbeandev
d28fc0d48d docs: update manual auth instructions 2026-02-17 20:05:15 +05:30
mrbeandev
29e07ec7b4 feat: add manual callback URL entry for headless OAuth flow 2026-02-17 20:05:10 +05:30
mrbeandev
848aaedc24 feat: complete Antigravity provider integration with robust error handling and docs 2026-02-17 20:05:06 +05:30
mrbeandev
33915fb712 fix(gemini): preserve thought_signature in tool calls to prevent 400 errors 2026-02-17 20:04:45 +05:30
likeaturtle
2f24be6c59 add Volcengine LLM (doubao) support 2026-02-17 22:31:19 +08:00
Jared Mahotiere
e3c246a36f Merge origin/main into refactor/provider-protocol-122 2026-02-17 09:28:56 -05:00
HansonJames
f0e90e6379 feat: Add the Qwen provider 2026-02-17 22:07:58 +08:00
Boris Bliznioukov
2d876eaa98
feat(goreleaser): enhance build flags with versioning and commit info
Signed-off-by: Boris Bliznioukov <blib@mail.com>
2026-02-17 15:00:06 +01:00
Boris Bliznioukov
2d758d714f
feat(goreleaser): add 'stdjson' tag to picoclaw build configuration
Signed-off-by: Boris Bliznioukov <blib@mail.com>
2026-02-17 14:55:37 +01:00
lxowalle
920e30a241
fix:pr-272 reverted the changes from pr-227 (#361) 2026-02-17 21:31:54 +08:00
Boris Bliznioukov
ad747e8e89
fix(Makefile): update LDFLAGS and GOFLAGS for optimized build size
Signed-off-by: Boris Bliznioukov <blib@mail.com>
2026-02-17 14:27:03 +01:00
daming大铭
7b9b8104c8
Merge pull request #225 from yinwm/feat/cron-exec-timeout-config
feat(cron): add configurable execution timeout for cron jobs
2026-02-17 21:12:59 +08:00
yinwm
881999aceb refactor(shell): interpret zero timeout as unlimited execution
Replace unconditional WithTimeout usage with conditional context creation
based on timeout configuration. Zero values now bypass timeout enforcement,
using WithCancel for graceful cancellation while preserving existing timeout
behavior for positive values. Simplifies CronTool initialization by removing
unnecessary conditional timeout assignment.
2026-02-17 21:10:20 +08:00
Hua Audio
f929268ab2
feat: Add Perplexity search provider integration (#138)
* feat: Add Perplexity search provider integration

- Add PerplexityConfig struct to config package
- Add PerplexitySearchProvider implementing SearchProvider interface
- Update WebSearchTool to support Perplexity with priority system (Perplexity > Brave > DuckDuckGo)
- Update agent loop to pass Perplexity config options
- Update config.example.json with Perplexity configuration template
- Uses Perplexity's 'sonar' model for web search capabilities

* Edit config example

* make fmt

---------

Co-authored-by: Hua <zhangmikoto@gmail.com>
2026-02-17 21:02:56 +08:00
yinwm
684e7413e1 Merge remote-tracking branch 'origin/main' into feat/cron-exec-timeout-config 2026-02-17 20:53:31 +08:00
zepan
da79c201c7 1. fix typo 2026-02-17 18:03:02 +08:00
zepan
5fb2721d22 1. add android phone termux quick guide 2026-02-17 18:01:39 +08:00
zepan
951b05d255 1. add AI Code Generation selection in pr template 2026-02-17 17:15:40 +08:00
zepan
ac4b16dfb4 1. rename doc to docs 2026-02-17 16:51:38 +08:00
zepan
0fadbcd340 1. add roadmap.md 2026-02-17 16:03:07 +08:00
Guoguo
a961a2df87
fix(ci): use env var for release tag (#342)
Signed-off-by: Guoguo <i@qwq.trade>
2026-02-17 14:32:51 +08:00
yuchou87
e38364b08a build(docker): migrate full image from Debian to Alpine base
Replace node:24-bookworm-slim with node:24-alpine3.23 to reduce
image size and improve build efficiency.

Changes:
- Base image: node:24-bookworm-slim → node:24-alpine3.23
- Package manager: apt-get → apk
- Package names: python3-pip → py3-pip
- Remove python3-venv (included in Alpine Python3)
- Use apk --no-cache for cleaner image layers

Expected benefits:
- Reduce base image size by ~100-200MB (30-40% reduction)
- Faster image pulls and container startup
- Full MCP support maintained (Node.js, Python, uv)

Estimated final image size: ~600-700MB (vs ~800MB before)
2026-02-17 10:57:38 +08:00
yuchou87
4113190c2a chore(config): remove example MCP servers from default config
Remove pre-populated example servers (filesystem, github, brave-search,
postgres) from DefaultConfig() to reduce memory footprint per instance.

Changes:
- Set MCP.Servers to empty map instead of 4 example servers
- Reduces default config size by ~500 bytes per instance
- Users should add MCP servers via config.json or documentation

Example configurations are still available in:
- README.md MCP section
- config.example.json
- Official MCP documentation

This optimization benefits deployments with many agent instances.
2026-02-17 10:41:29 +08:00
yuchou87
6892d006d6 perf(agent): reduce memory footprint by storing minimal MCP dependencies
Replace full *config.Config reference with config.MCPConfig value type
in AgentLoop to allow garbage collection of unused configuration data.

Changes:
- AgentLoop now stores only MCPConfig and workspacePath (minimal deps)
- Add mcp.Manager.LoadFromMCPConfig() for minimal dependency version
- Keep LoadFromConfig() for backward compatibility
- Full Config object can be GC'd after NewAgentLoop() returns

This optimization reduces memory usage by not holding references to
unused channel, provider, gateway, and device configurations.
2026-02-17 10:39:39 +08:00
AlbertBui010
75fb728a11 docs: add Vietnamese README (README.vi.md)
- Add full Vietnamese translation of README.md
- Update language selector links in README.md, README.zh.md, README.ja.md
2026-02-17 09:17:03 +07:00