Merge remote-tracking branch 'origin/main' into fix/thinking-model-reasoning-content

This commit is contained in:
mxrain 2026-02-16 20:13:48 +08:00
commit ad2cce7c1b
84 changed files with 6324 additions and 559 deletions

28
.github/ISSUE_TEMPLATE/bug_report.md vendored Normal file
View file

@ -0,0 +1,28 @@
---
name: Bug report
about: Report a bug or unexpected behavior
title: "[BUG]"
labels: bug
assignees: ''
---
## Quick Summary
## Environment & Tools
- **PicoClaw Version:** (e.g., v0.1.2 or commit hash)
- **Go Version:** (e.g., go 1.22)
- **AI Model & Provider:** (e.g., GPT-4o via OpenAI / DeepSeek via SiliconFlow)
- **Operating System:** (e.g., Ubuntu 22.04 / macOS / Android Termux)
- **Channels:** (e.g., Discord, Telegram, Feishu, ...)
## 📸 Steps to Reproduce
1.
2.
3.
## ❌ Actual Behavior
## ✅ Expected Behavior
## 💬 Additional Context

View file

@ -0,0 +1,23 @@
---
name: Feature request
about: Suggest a new idea or improvement
title: "[Feature]"
labels: enhancement
assignees: ''
---
## 🎯 The Goal / Use Case
## 💡 Proposed Solution
## 🛠 Potential Implementation (Optional)
## 🚦 Impact & Roadmap Alignment
- [ ] This is a Core Feature
- [ ] This is a Nice-to-Have / Enhancement
- [ ] This aligns with the current Roadmap
## 🔄 Alternatives Considered
## 💬 Additional Context

View file

@ -0,0 +1,26 @@
---
name: General Task / Todo
about: A specific piece of work like doc, refactoring, or maintenance.
title: "[Task]"
labels: ''
assignees: ''
---
## 📝 Objective
## 📋 To-Do List
- [ ] Step 1
- [ ] Step 2
- [ ] Step 3
## 🎯 Definition of Done (Acceptance Criteria)
- [ ] Documentation is updated in the README/docs folder.
- [ ] Code follows project linting standards.
- [ ] (If applicable) Basic tests pass.
## 💡 Context / Motivation
## 🔗 Related Issues / PRs
- Fixes #
- Relates to #

View file

@ -1,12 +1,18 @@
name: 🐳 Build & Push Docker Image
on:
release:
types: [published]
workflow_call:
inputs:
tag:
description: "Release tag"
required: true
type: string
env:
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository_owner }}/picoclaw
GHCR_REGISTRY: ghcr.io
GHCR_IMAGE_NAME: ${{ github.repository_owner }}/picoclaw
DOCKERHUB_REGISTRY: docker.io
DOCKERHUB_IMAGE_NAME: ${{ vars.DOCKERHUB_REPOSITORY }}
jobs:
build:
@ -20,6 +26,8 @@ jobs:
# ── Checkout ──────────────────────────────
- name: 📥 Checkout repository
uses: actions/checkout@v4
with:
ref: ${{ inputs.tag }}
# ── Docker Buildx ─────────────────────────
- name: 🔧 Set up Docker Buildx
@ -27,36 +35,42 @@ jobs:
# ── Login to GHCR ─────────────────────────
- name: 🔑 Login to GitHub Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
registry: ${{ env.REGISTRY }}
registry: ${{ env.GHCR_REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# ── Metadata (tags & labels) ──────────────
- name: 🏷️ Extract Docker metadata
id: meta
uses: docker/metadata-action@v5
# ── Login to Docker Hub ────────────────────
- name: 🔑 Login to Docker Hub
uses: docker/login-action@v3
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=pr
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
type=sha,prefix=
type=raw,value=latest,enable={{is_default_branch}}
type=raw,value={{date 'YYYYMMDD-HHmmss'}},enable={{is_default_branch}}
registry: ${{ env.DOCKERHUB_REGISTRY }}
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
# ── Metadata (tags & labels) ──────────────
- name: 🏷️ Prepare image tags
id: tags
shell: bash
run: |
tag="${{ inputs.tag }}"
echo "ghcr_tag=${{ env.GHCR_REGISTRY }}/${{ env.GHCR_IMAGE_NAME }}:${tag}" >> "$GITHUB_OUTPUT"
echo "ghcr_latest=${{ env.GHCR_REGISTRY }}/${{ env.GHCR_IMAGE_NAME }}:latest" >> "$GITHUB_OUTPUT"
echo "dockerhub_tag=${{ env.DOCKERHUB_REGISTRY }}/${{ env.DOCKERHUB_IMAGE_NAME }}:${tag}" >> "$GITHUB_OUTPUT"
echo "dockerhub_latest=${{ env.DOCKERHUB_REGISTRY }}/${{ env.DOCKERHUB_IMAGE_NAME }}:latest" >> "$GITHUB_OUTPUT"
# ── Build & Push ──────────────────────────
- name: 🚀 Build and push Docker image
uses: docker/build-push-action@v6
with:
context: .
push: ${{ github.event_name != 'pull_request' }}
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
push: true
tags: |
${{ steps.tags.outputs.ghcr_tag }}
${{ steps.tags.outputs.ghcr_latest }}
${{ steps.tags.outputs.dockerhub_tag }}
${{ steps.tags.outputs.dockerhub_latest }}
cache-from: type=gha
cache-to: type=gha,mode=max
platforms: linux/amd64,linux/arm64
platforms: linux/amd64,linux/arm64,linux/riscv64

View file

@ -32,6 +32,9 @@ jobs:
with:
go-version-file: go.mod
- name: Run go generate
run: go generate ./...
- name: Run go vet
run: go vet ./...
@ -47,6 +50,9 @@ jobs:
with:
go-version-file: go.mod
- name: Run go generate
run: go generate ./...
- name: Run go test
run: go test ./...

View file

@ -38,14 +38,18 @@ jobs:
git tag -a "${{ inputs.tag }}" -m "Release ${{ inputs.tag }}"
git push origin "${{ inputs.tag }}"
build-binaries:
name: Build Release Binaries
release:
name: GoReleaser Release
needs: create-tag
runs-on: ubuntu-latest
permissions:
contents: write
packages: write
steps:
- name: Checkout tag
uses: actions/checkout@v4
with:
fetch-depth: 0
ref: ${{ inputs.tag }}
- name: Setup Go from go.mod
@ -53,47 +57,42 @@ jobs:
with:
go-version-file: go.mod
- name: Build all binaries
run: make build-all
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Generate checksums
shell: bash
run: |
shasum -a 256 build/picoclaw-* > build/sha256sums.txt
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Upload release binaries artifact
uses: actions/upload-artifact@v4
- name: Login to GitHub Container Registry
uses: docker/login-action@v3
with:
name: picoclaw-binaries
path: |
build/picoclaw-*
build/sha256sums.txt
if-no-files-found: error
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
create-release:
name: Create GitHub Release
needs: [create-tag, build-binaries]
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- name: Download all artifacts
uses: actions/download-artifact@v4
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
path: release-artifacts
registry: docker.io
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Show downloaded files
run: ls -R release-artifacts
- name: Create release
uses: softprops/action-gh-release@v2
- name: Run GoReleaser
uses: goreleaser/goreleaser-action@v6
with:
tag_name: ${{ inputs.tag }}
name: ${{ inputs.tag }}
draft: ${{ inputs.draft }}
prerelease: ${{ inputs.prerelease }}
files: |
release-artifacts/**/*
generate_release_notes: true
distribution: goreleaser
version: ~> v2
args: release --clean
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
DOCKERHUB_IMAGE_NAME: ${{ vars.DOCKERHUB_REPOSITORY }}
- name: Apply release flags
shell: bash
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
gh release edit "${{ inputs.tag }}" \
--draft=${{ inputs.draft }} \
--prerelease=${{ inputs.prerelease }}

8
.gitignore vendored
View file

@ -10,6 +10,7 @@ build/
*.out
/picoclaw
/picoclaw-test
cmd/picoclaw/workspace
# Picoclaw specific
@ -36,3 +37,10 @@ coverage.html
ralph/
.ralph/
tasks/
# Editors
.vscode/
.idea/
# Added by goreleaser init:
dist/

79
.goreleaser.yaml Normal file
View file

@ -0,0 +1,79 @@
# yaml-language-server: $schema=https://goreleaser.com/static/schema.json
# vim: set ts=2 sw=2 tw=0 fo=cnqoj
version: 2
before:
hooks:
- go mod tidy
- go generate ./cmd/picoclaw
builds:
- id: picoclaw
env:
- CGO_ENABLED=0
goos:
- linux
- windows
- darwin
- freebsd
goarch:
- amd64
- arm64
- riscv64
- s390x
- mips64
- arm
main: ./cmd/picoclaw
ignore:
- goos: windows
goarch: arm
dockers_v2:
- id: picoclaw
dockerfile: Dockerfile.goreleaser
ids:
- picoclaw
images:
- "ghcr.io/{{ .Env.GITHUB_REPOSITORY_OWNER }}/picoclaw"
- "docker.io/{{ .Env.DOCKERHUB_IMAGE_NAME }}"
tags:
- "{{ .Tag }}"
- "latest"
platforms:
- linux/amd64
- linux/arm64
- linux/riscv64
archives:
- formats: [tar.gz]
# this name template makes the OS and Arch compatible with the results of `uname`.
name_template: >-
{{ .ProjectName }}_
{{- title .Os }}_
{{- if eq .Arch "amd64" }}x86_64
{{- else if eq .Arch "386" }}i386
{{- else }}{{ .Arch }}{{ end }}
{{- if .Arm }}v{{ .Arm }}{{ end }}
# use zip for windows archives
format_overrides:
- goos: windows
formats: [zip]
changelog:
sort: asc
filters:
exclude:
- "^docs:"
- "^test:"
# upx:
# - enabled: true
# compress: best
# lzma: true
release:
footer: >-
---
Released by [GoReleaser](https://github.com/goreleaser/goreleaser).

View file

@ -1,7 +1,7 @@
# ============================================================
# Stage 1: Build the picoclaw binary
# ============================================================
FROM golang:1.25.7-alpine AS builder
FROM golang:1.26.0-alpine AS builder
RUN apk add --no-cache git make
@ -18,19 +18,19 @@ RUN make build
# ============================================================
# Stage 2: Minimal runtime image
# ============================================================
FROM alpine:3.21
FROM alpine:3.23
RUN apk add --no-cache ca-certificates tzdata
RUN apk add --no-cache ca-certificates tzdata curl
# Health check
HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
CMD wget -q --spider http://localhost:18790/health || exit 1
# Copy binary
COPY --from=builder /src/build/picoclaw /usr/local/bin/picoclaw
# Copy builtin skills
COPY --from=builder /src/skills /opt/picoclaw/skills
# Create picoclaw home directory
RUN mkdir -p /root/.picoclaw/workspace/skills && \
cp -r /opt/picoclaw/skills/* /root/.picoclaw/workspace/skills/ 2>/dev/null || true
RUN /usr/local/bin/picoclaw onboard
ENTRYPOINT ["picoclaw"]
CMD ["gateway"]

10
Dockerfile.goreleaser Normal file
View file

@ -0,0 +1,10 @@
FROM alpine:3.21
ARG TARGETPLATFORM
RUN apk add --no-cache ca-certificates tzdata
COPY $TARGETPLATFORM/picoclaw /usr/local/bin/picoclaw
ENTRYPOINT ["picoclaw"]
CMD ["gateway"]

View file

@ -63,16 +63,23 @@ BINARY_PATH=$(BUILD_DIR)/$(BINARY_NAME)-$(PLATFORM)-$(ARCH)
# Default target
all: build
## generate: Run generate
generate:
@echo "Run generate..."
@rm -r ./$(CMD_DIR)/workspace 2>/dev/null || true
@$(GO) generate ./...
@echo "Run generate complete"
## build: Build the picoclaw binary for current platform
build:
build: generate
@echo "Building $(BINARY_NAME) for $(PLATFORM)/$(ARCH)..."
@mkdir -p $(BUILD_DIR)
$(GO) build $(GOFLAGS) $(LDFLAGS) -o $(BINARY_PATH) ./$(CMD_DIR)
@$(GO) build $(GOFLAGS) $(LDFLAGS) -o $(BINARY_PATH) ./$(CMD_DIR)
@echo "Build complete: $(BINARY_PATH)"
@ln -sf $(BINARY_NAME)-$(PLATFORM)-$(ARCH) $(BUILD_DIR)/$(BINARY_NAME)
## build-all: Build picoclaw for all platforms
build-all:
build-all: generate
@echo "Building for multiple platforms..."
@mkdir -p $(BUILD_DIR)
GOOS=linux GOARCH=amd64 $(GO) build $(LDFLAGS) -o $(BUILD_DIR)/$(BINARY_NAME)-linux-amd64 ./$(CMD_DIR)
@ -89,35 +96,8 @@ install: build
@cp $(BUILD_DIR)/$(BINARY_NAME) $(INSTALL_BIN_DIR)/$(BINARY_NAME)
@chmod +x $(INSTALL_BIN_DIR)/$(BINARY_NAME)
@echo "Installed binary to $(INSTALL_BIN_DIR)/$(BINARY_NAME)"
@echo "Installing builtin skills to $(WORKSPACE_SKILLS_DIR)..."
@mkdir -p $(WORKSPACE_SKILLS_DIR)
@for skill in $(BUILTIN_SKILLS_DIR)/*/; do \
if [ -d "$$skill" ]; then \
skill_name=$$(basename "$$skill"); \
if [ -f "$$skill/SKILL.md" ]; then \
cp -r "$$skill" $(WORKSPACE_SKILLS_DIR); \
echo " ✓ Installed skill: $$skill_name"; \
fi; \
fi; \
done
@echo "Installation complete!"
## install-skills: Install builtin skills to workspace
install-skills:
@echo "Installing builtin skills to $(WORKSPACE_SKILLS_DIR)..."
@mkdir -p $(WORKSPACE_SKILLS_DIR)
@for skill in $(BUILTIN_SKILLS_DIR)/*/; do \
if [ -d "$$skill" ]; then \
skill_name=$$(basename "$$skill"); \
if [ -f "$$skill/SKILL.md" ]; then \
mkdir -p $(WORKSPACE_SKILLS_DIR)/$$skill_name; \
cp -r "$$skill" $(WORKSPACE_SKILLS_DIR); \
echo " ✓ Installed skill: $$skill_name"; \
fi; \
fi; \
done
@echo "Skills installation complete!"
## uninstall: Remove picoclaw from system
uninstall:
@echo "Uninstalling $(BINARY_NAME)..."
@ -139,15 +119,31 @@ clean:
@rm -rf $(BUILD_DIR)
@echo "Clean complete"
## vet: Run go vet for static analysis
vet:
@$(GO) vet ./...
## fmt: Format Go code
test:
@$(GO) test ./...
## fmt: Format Go code
fmt:
@$(GO) fmt ./...
## deps: Update dependencies
## deps: Download dependencies
deps:
@$(GO) mod download
@$(GO) mod verify
## update-deps: Update dependencies
update-deps:
@$(GO) get -u ./...
@$(GO) mod tidy
## check: Run vet, fmt, and verify dependencies
check: deps fmt vet test
## run: Build and run picoclaw
run: build
@$(BUILD_DIR)/$(BINARY_NAME) $(ARGS)

View file

@ -223,7 +223,7 @@ picoclaw agent -m "What is 2+2?"
## 💬 チャットアプリ
Telegram、Discord、QQ、DingTalk で PicoClaw と会話できます
Telegram、Discord、QQ、DingTalk、LINE で PicoClaw と会話できます
| チャネル | セットアップ |
|---------|------------|
@ -231,6 +231,7 @@ Telegram、Discord、QQ、DingTalk で PicoClaw と会話できます
| **Discord** | 簡単Bot トークン + Intents |
| **QQ** | 簡単AppID + AppSecret |
| **DingTalk** | 普通(アプリ認証情報) |
| **LINE** | 普通(認証情報 + Webhook URL |
<details>
<summary><b>Telegram</b>(推奨)</summary>
@ -314,7 +315,7 @@ picoclaw gateway
**1. Bot を作成**
- [QQ オープンプラットフォーム](https://connect.qq.com/) にアクセス
- [QQ オープンプラットフォーム](https://q.qq.com/#) にアクセス
- アプリケーションを作成 → **AppID****AppSecret** を取得
**2. 設定**
@ -376,6 +377,56 @@ picoclaw gateway
</details>
<details>
<summary><b>LINE</b></summary>
**1. LINE 公式アカウントを作成**
- [LINE Developers Console](https://developers.line.biz/) にアクセス
- プロバイダーを作成 → Messaging API チャネルを作成
- **チャネルシークレット****チャネルアクセストークン** をコピー
**2. 設定**
```json
{
"channels": {
"line": {
"enabled": true,
"channel_secret": "YOUR_CHANNEL_SECRET",
"channel_access_token": "YOUR_CHANNEL_ACCESS_TOKEN",
"webhook_host": "0.0.0.0",
"webhook_port": 18791,
"webhook_path": "/webhook/line",
"allow_from": []
}
}
}
```
**3. Webhook URL を設定**
LINE の Webhook には HTTPS が必要です。リバースプロキシまたはトンネルを使用してください:
```bash
# ngrok の例
ngrok http 18791
```
LINE Developers Console で Webhook URL を `https://あなたのドメイン/webhook/line` に設定し、**Webhook の利用** を有効にしてください。
**4. 起動**
```bash
picoclaw gateway
```
> グループチャットでは @メンション時のみ応答します。返信は元メッセージを引用する形式です。
> **Docker Compose**: `picoclaw-gateway` サービスに `ports: ["18791:18791"]` を追加して Webhook ポートを公開してください。
</details>
## ⚙️ 設定
設定ファイル: `~/.picoclaw/config.json`

132
README.md
View file

@ -17,14 +17,12 @@
[中文](README.zh.md) | [日本語](README.ja.md) | **English**
</div>
---
🦐 PicoClaw is an ultra-lightweight personal AI Assistant inspired by [nanobot](https://github.com/HKUDS/nanobot), refactored from the ground up in Go through a self-bootstrapping process, where the AI agent itself drove the entire architectural migration and code optimization.
⚡️ Runs on $10 hardware with <10MB RAM: That's 99% less memory than OpenClaw and 98% cheaper than a Mac mini!
<table align="center">
<tr align="center">
<td align="center" valign="top">
@ -40,20 +38,22 @@
</tr>
</table>
> [!CAUTION]
> **🚨 SECURITY & OFFICIAL CHANNELS / 安全声明**
>
> * **NO CRYPTO:** PicoClaw has **NO** official token/coin. All claims on `pump.fun` or other trading platforms are **SCAMS**.
> * **OFFICIAL DOMAIN:** The **ONLY** official website is **[picoclaw.io](https://picoclaw.io)**, and company website is **[sipeed.com](https://sipeed.com)**
> * **Warning:** Many `.ai/.org/.com/.net/...` domains are registered by third parties.
>
> * **Warning:** picoclaw is in early development now and may have unresolved network security issues. Do not deploy to production environments before the v1.0 release.
> * **Note:** picoclaw has recently merged a lot of PRs, which may result in a larger memory footprint (1020MB) in the latest versions. We plan to prioritize resource optimization as soon as the current feature set reaches a stable state.
## 📢 News
2026-02-16 🎉 PicoClaw hit 12K stars in one week! Thank you all for your support! PicoClaw is growing faster than we ever imagined. Given the high volume of PRs, we urgently need community maintainers. Our volunteer roles and roadmap are officially posted [here](doc/picoclaw_community_roadmap_260216.md) —we cant wait to have you on board!
2026-02-13 🎉 PicoClaw hit 5000 stars in 4days! Thank you for the community! There are so many PRs&issues come in (during Chinese New Year holidays), we are finalizing the Project Roadmap and setting up the Developer Group to accelerate PicoClaw's development.
🚀 Call to Action: Please submit your feature requests in GitHub Discussions. We will review and prioritize them during our upcoming weekly meeting.
2026-02-09 🎉 PicoClaw Launched! Built in 1 day to bring AI Agents to $10 hardware with <10MB RAM. 🦐 PicoClawLet's Go
## ✨ Features
@ -225,8 +225,8 @@ picoclaw onboard
**3. Get API Keys**
- **LLM Provider**: [OpenRouter](https://openrouter.ai/keys) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) · [Anthropic](https://console.anthropic.com) · [OpenAI](https://platform.openai.com) · [Gemini](https://aistudio.google.com/api-keys)
- **Web Search** (optional): [Brave Search](https://brave.com/search/api) - Free tier available (2000 requests/month)
* **LLM Provider**: [OpenRouter](https://openrouter.ai/keys) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) · [Anthropic](https://console.anthropic.com) · [OpenAI](https://platform.openai.com) · [Gemini](https://aistudio.google.com/api-keys)
* **Web Search** (optional): [Brave Search](https://brave.com/search/api) - Free tier available (2000 requests/month)
> **Note**: See `config.example.json` for a complete configuration template.
@ -242,23 +242,24 @@ That's it! You have a working AI assistant in 2 minutes.
## 💬 Chat Apps
Talk to your picoclaw through Telegram, Discord, or DingTalk
Talk to your picoclaw through Telegram, Discord, DingTalk, or LINE
| Channel | Setup |
| ------------ | -------------------------- |
| ------------ | ---------------------------------- |
| **Telegram** | Easy (just a token) |
| **Discord** | Easy (bot token + intents) |
| **QQ** | Easy (AppID + AppSecret) |
| **DingTalk** | Medium (app credentials) |
| **LINE** | Medium (credentials + webhook URL) |
<details>
<summary><b>Telegram</b> (Recommended)</summary>
**1. Create a bot**
- Open Telegram, search `@BotFather`
- Send `/newbot`, follow prompts
- Copy the token
* Open Telegram, search `@BotFather`
* Send `/newbot`, follow prompts
* Copy the token
**2. Configure**
@ -289,19 +290,19 @@ picoclaw gateway
**1. Create a bot**
- Go to <https://discord.com/developers/applications>
- Create an application → Bot → Add Bot
- Copy the bot token
* Go to <https://discord.com/developers/applications>
* Create an application → Bot → Add Bot
* Copy the bot token
**2. Enable intents**
- In the Bot settings, enable **MESSAGE CONTENT INTENT**
- (Optional) Enable **SERVER MEMBERS INTENT** if you plan to use allow lists based on member data
* In the Bot settings, enable **MESSAGE CONTENT INTENT**
* (Optional) Enable **SERVER MEMBERS INTENT** if you plan to use allow lists based on member data
**3. Get your User ID**
- Discord Settings → Advanced → enable **Developer Mode**
- Right-click your avatar → **Copy User ID**
* Discord Settings → Advanced → enable **Developer Mode**
* Right-click your avatar → **Copy User ID**
**4. Configure**
@ -319,10 +320,10 @@ picoclaw gateway
**5. Invite the bot**
- OAuth2 → URL Generator
- Scopes: `bot`
- Bot Permissions: `Send Messages`, `Read Message History`
- Open the generated invite URL and add the bot to your server
* OAuth2 → URL Generator
* Scopes: `bot`
* Bot Permissions: `Send Messages`, `Read Message History`
* Open the generated invite URL and add the bot to your server
**6. Run**
@ -337,7 +338,7 @@ picoclaw gateway
**1. Create a bot**
- Go to [QQ Open Platform](https://connect.qq.com/)
- Go to [QQ Open Platform](https://q.qq.com/#)
- Create an application → Get **AppID** and **AppSecret**
**2. Configure**
@ -370,9 +371,9 @@ picoclaw gateway
**1. Create a bot**
- Go to [Open Platform](https://open.dingtalk.com/)
- Create an internal app
- Copy Client ID and Client Secret
* Go to [Open Platform](https://open.dingtalk.com/)
* Create an internal app
* Copy Client ID and Client Secret
**2. Configure**
@ -399,6 +400,56 @@ picoclaw gateway
</details>
<details>
<summary><b>LINE</b></summary>
**1. Create a LINE Official Account**
- Go to [LINE Developers Console](https://developers.line.biz/)
- Create a provider → Create a Messaging API channel
- Copy **Channel Secret** and **Channel Access Token**
**2. Configure**
```json
{
"channels": {
"line": {
"enabled": true,
"channel_secret": "YOUR_CHANNEL_SECRET",
"channel_access_token": "YOUR_CHANNEL_ACCESS_TOKEN",
"webhook_host": "0.0.0.0",
"webhook_port": 18791,
"webhook_path": "/webhook/line",
"allow_from": []
}
}
}
```
**3. Set up Webhook URL**
LINE requires HTTPS for webhooks. Use a reverse proxy or tunnel:
```bash
# Example with ngrok
ngrok http 18791
```
Then set the Webhook URL in LINE Developers Console to `https://your-domain/webhook/line` and enable **Use webhook**.
**4. Run**
```bash
picoclaw gateway
```
> In group chats, the bot responds only when @mentioned. Replies quote the original message.
> **Docker Compose**: Add `ports: ["18791:18791"]` to the `picoclaw-gateway` service to expose the webhook port.
</details>
## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Join the Agent Social Network
Connect Picoclaw to the Agent Social Network simply by sending a single message via the CLI or any integrated Chat App.
@ -467,12 +518,12 @@ When `restrict_to_workspace: true`, the following tools are sandboxed:
Even with `restrict_to_workspace: false`, the `exec` tool blocks these dangerous commands:
- `rm -rf`, `del /f`, `rmdir /s` — Bulk deletion
- `format`, `mkfs`, `diskpart` — Disk formatting
- `dd if=` — Disk imaging
- Writing to `/dev/sd[a-z]` — Direct disk writes
- `shutdown`, `reboot`, `poweroff` — System shutdown
- Fork bomb `:(){ :|:& };:`
* `rm -rf`, `del /f`, `rmdir /s` — Bulk deletion
* `format`, `mkfs`, `diskpart` — Disk formatting
* `dd if=` — Disk imaging
* Writing to `/dev/sd[a-z]` — Direct disk writes
* `shutdown`, `reboot`, `poweroff` — System shutdown
* Fork bomb `:(){ :|:& };:`
#### Error Examples
@ -491,6 +542,7 @@ Even with `restrict_to_workspace: false`, the `exec` tool blocks these dangerous
If you need the agent to access paths outside the workspace:
**Method 1: Config file**
```json
{
"agents": {
@ -502,6 +554,7 @@ If you need the agent to access paths outside the workspace:
```
**Method 2: Environment variable**
```bash
export PICOCLAW_AGENTS_DEFAULTS_RESTRICT_TO_WORKSPACE=false
```
@ -593,8 +646,9 @@ The subagent has access to tools (message, web_search, etc.) and can communicate
| `interval` | `30` | Check interval in minutes (min: 5) |
**Environment variables:**
- `PICOCLAW_HEARTBEAT_ENABLED=false` to disable
- `PICOCLAW_HEARTBEAT_INTERVAL=60` to change interval
* `PICOCLAW_HEARTBEAT_ENABLED=false` to disable
* `PICOCLAW_HEARTBEAT_INTERVAL=60` to change interval
### Providers
@ -616,7 +670,7 @@ The subagent has access to tools (message, web_search, etc.) and can communicate
**1. Get API key and base URL**
- Get [API key](https://bigmodel.cn/usercenter/proj-mgmt/apikeys)
* Get [API key](https://bigmodel.cn/usercenter/proj-mgmt/apikeys)
**2. Configure**
@ -733,9 +787,9 @@ picoclaw agent -m "Hello"
PicoClaw supports scheduled reminders and recurring tasks through the `cron` tool:
- **One-time reminders**: "Remind me in 10 minutes" → triggers once after 10min
- **Recurring tasks**: "Remind me every 2 hours" → triggers every 2 hours
- **Cron expressions**: "Remind me at 9am daily" → uses cron expression
* **One-time reminders**: "Remind me in 10 minutes" → triggers once after 10min
* **Recurring tasks**: "Remind me every 2 hours" → triggers every 2 hours
* **Cron expressions**: "Remind me at 9am daily" → uses cron expression
Jobs are stored in `~/.picoclaw/workspace/cron/` and processed automatically.

View file

@ -45,10 +45,12 @@
> * **无加密货币 (NO CRYPTO):** PicoClaw **没有** 发行任何官方代币、Token 或虚拟货币。所有在 `pump.fun` 或其他交易平台上的相关声称均为 **诈骗**
> * **官方域名:** 唯一的官方网站是 **[picoclaw.io](https://picoclaw.io)**,公司官网是 **[sipeed.com](https://sipeed.com)**。
> * **警惕:** 许多 `.ai/.org/.com/.net/...` 后缀的域名被第三方抢注,请勿轻信。
>
>
> * **注意:** picoclaw正在初期的快速功能开发阶段可能有尚未修复的网络安全问题在1.0正式版发布前,请不要将其部署到生产环境中
> * **注意:** picoclaw最近合并了大量PRs近期版本可能内存占用较大(10~20MB),我们将在功能较为收敛后进行资源占用优化.
## 📢 新闻 (News)
2026-02-16 🎉 PicoClaw 在一周内突破了12K star! 感谢大家的关注PicoClaw 的成长速度超乎我们预期. 由于PR数量的快速膨胀我们亟需社区开发者参与维护. 我们需要的志愿者角色和roadmap已经发布到了[这里](doc/picoclaw_community_roadmap_260216.md), 期待你的参与!
2026-02-13 🎉 **PicoClaw 在 4 天内突破 5000 Stars** 感谢社区的支持由于正值中国春节假期PR 和 Issue 涌入较多,我们正在利用这段时间敲定 **项目路线图 (Roadmap)** 并组建 **开发者群组**,以便加速 PicoClaw 的开发。
🚀 **行动号召:** 请在 GitHub Discussions 中提交您的功能请求 (Feature Requests)。我们将在接下来的周会上进行审查和优先级排序。
@ -342,7 +344,7 @@ picoclaw gateway
**1. 创建机器人**
* 前往 [QQ 开放平台](https://connect.qq.com/)
* 前往 [QQ 开放平台](https://q.qq.com/#)
* 创建应用 → 获取 **AppID** 和 **AppSecret**
**2. 配置**

Binary file not shown.

Before

Width:  |  Height:  |  Size: 145 KiB

After

Width:  |  Height:  |  Size: 142 KiB

View file

@ -9,8 +9,11 @@ package main
import (
"bufio"
"context"
"embed"
"fmt"
"io"
"io/fs"
"net/http"
"os"
"os/signal"
"path/filepath"
@ -25,15 +28,22 @@ import (
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/cron"
"github.com/sipeed/picoclaw/pkg/devices"
"github.com/sipeed/picoclaw/pkg/health"
"github.com/sipeed/picoclaw/pkg/heartbeat"
"github.com/sipeed/picoclaw/pkg/logger"
"github.com/sipeed/picoclaw/pkg/migrate"
"github.com/sipeed/picoclaw/pkg/providers"
"github.com/sipeed/picoclaw/pkg/skills"
"github.com/sipeed/picoclaw/pkg/state"
"github.com/sipeed/picoclaw/pkg/tools"
"github.com/sipeed/picoclaw/pkg/voice"
)
//go:generate cp -r ../../workspace .
//go:embed workspace
var embeddedFiles embed.FS
var (
version = "dev"
gitCommit string
@ -227,10 +237,6 @@ func onboard() {
}
workspace := cfg.WorkspacePath()
os.MkdirAll(workspace, 0755)
os.MkdirAll(filepath.Join(workspace, "memory"), 0755)
os.MkdirAll(filepath.Join(workspace, "skills"), 0755)
createWorkspaceTemplates(workspace)
fmt.Printf("%s picoclaw is ready!\n", logo)
@ -240,170 +246,57 @@ func onboard() {
fmt.Println(" 2. Chat: picoclaw agent -m \"Hello!\"")
}
func copyEmbeddedToTarget(targetDir string) error {
// Ensure target directory exists
if err := os.MkdirAll(targetDir, 0755); err != nil {
return fmt.Errorf("Failed to create target directory: %w", err)
}
// Walk through all files in embed.FS
err := fs.WalkDir(embeddedFiles, "workspace", func(path string, d fs.DirEntry, err error) error {
if err != nil {
return err
}
// Skip directories
if d.IsDir() {
return nil
}
// Read embedded file
data, err := embeddedFiles.ReadFile(path)
if err != nil {
return fmt.Errorf("Failed to read embedded file %s: %w", path, err)
}
new_path, err := filepath.Rel("workspace", path)
if err != nil {
return fmt.Errorf("Failed to get relative path for %s: %v\n", path, err)
}
// Build target file path
targetPath := filepath.Join(targetDir, new_path)
// Ensure target file's directory exists
if err := os.MkdirAll(filepath.Dir(targetPath), 0755); err != nil {
return fmt.Errorf("Failed to create directory %s: %w", filepath.Dir(targetPath), err)
}
// Write file
if err := os.WriteFile(targetPath, data, 0644); err != nil {
return fmt.Errorf("Failed to write file %s: %w", targetPath, err)
}
return nil
})
return err
}
func createWorkspaceTemplates(workspace string) {
templates := map[string]string{
"AGENTS.md": `# Agent Instructions
You are a helpful AI assistant. Be concise, accurate, and friendly.
## Guidelines
- Always explain what you're doing before taking actions
- Ask for clarification when request is ambiguous
- Use tools to help accomplish tasks
- Remember important information in your memory files
- Be proactive and helpful
- Learn from user feedback
`,
"SOUL.md": `# Soul
I am picoclaw, a lightweight AI assistant powered by AI.
## Personality
- Helpful and friendly
- Concise and to the point
- Curious and eager to learn
- Honest and transparent
## Values
- Accuracy over speed
- User privacy and safety
- Transparency in actions
- Continuous improvement
`,
"USER.md": `# User
Information about user goes here.
## Preferences
- Communication style: (casual/formal)
- Timezone: (your timezone)
- Language: (your preferred language)
## Personal Information
- Name: (optional)
- Location: (optional)
- Occupation: (optional)
## Learning Goals
- What the user wants to learn from AI
- Preferred interaction style
- Areas of interest
`,
"IDENTITY.md": `# Identity
## Name
PicoClaw 🦞
## Description
Ultra-lightweight personal AI assistant written in Go, inspired by nanobot.
## Version
0.1.0
## Purpose
- Provide intelligent AI assistance with minimal resource usage
- Support multiple LLM providers (OpenAI, Anthropic, Zhipu, etc.)
- Enable easy customization through skills system
- Run on minimal hardware ($10 boards, <10MB RAM)
## Capabilities
- Web search and content fetching
- File system operations (read, write, edit)
- Shell command execution
- Multi-channel messaging (Telegram, WhatsApp, Feishu)
- Skill-based extensibility
- Memory and context management
## Philosophy
- Simplicity over complexity
- Performance over features
- User control and privacy
- Transparent operation
- Community-driven development
## Goals
- Provide a fast, lightweight AI assistant
- Support offline-first operation where possible
- Enable easy customization and extension
- Maintain high quality responses
- Run efficiently on constrained hardware
## License
MIT License - Free and open source
## Repository
https://github.com/sipeed/picoclaw
## Contact
Issues: https://github.com/sipeed/picoclaw/issues
Discussions: https://github.com/sipeed/picoclaw/discussions
---
"Every bit helps, every bit matters."
- Picoclaw
`,
}
for filename, content := range templates {
filePath := filepath.Join(workspace, filename)
if _, err := os.Stat(filePath); os.IsNotExist(err) {
os.WriteFile(filePath, []byte(content), 0644)
fmt.Printf(" Created %s\n", filename)
}
}
memoryDir := filepath.Join(workspace, "memory")
os.MkdirAll(memoryDir, 0755)
memoryFile := filepath.Join(memoryDir, "MEMORY.md")
if _, err := os.Stat(memoryFile); os.IsNotExist(err) {
memoryContent := `# Long-term Memory
This file stores important information that should persist across sessions.
## User Information
(Important facts about user)
## Preferences
(User preferences learned over time)
## Important Notes
(Things to remember)
## Configuration
- Model preferences
- Channel settings
- Skills enabled
`
os.WriteFile(memoryFile, []byte(memoryContent), 0644)
fmt.Println(" Created memory/MEMORY.md")
skillsDir := filepath.Join(workspace, "skills")
if _, err := os.Stat(skillsDir); os.IsNotExist(err) {
os.MkdirAll(skillsDir, 0755)
fmt.Println(" Created skills/")
}
}
for filename, content := range templates {
filePath := filepath.Join(workspace, filename)
if _, err := os.Stat(filePath); os.IsNotExist(err) {
os.WriteFile(filePath, []byte(content), 0644)
fmt.Printf(" Created %s\n", filename)
}
err := copyEmbeddedToTarget(workspace)
if err != nil {
fmt.Printf("Error copying workspace templates: %v\n", err)
}
}
@ -669,7 +562,7 @@ func gatewayCmd() {
})
// Setup cron tool and service
cronService := setupCronTool(agentLoop, msgBus, cfg.WorkspacePath())
cronService := setupCronTool(agentLoop, msgBus, cfg.WorkspacePath(), cfg.Agents.Defaults.RestrictToWorkspace)
heartbeatService := heartbeat.NewHeartbeatService(
cfg.WorkspacePath(),
@ -701,6 +594,9 @@ func gatewayCmd() {
os.Exit(1)
}
// Inject channel manager into agent loop for command handling
agentLoop.SetChannelManager(channelManager)
var transcriber *voice.GroqTranscriber
if cfg.Providers.Groq.APIKey != "" {
transcriber = voice.NewGroqTranscriber(cfg.Providers.Groq.APIKey)
@ -751,10 +647,30 @@ func gatewayCmd() {
}
fmt.Println("✓ Heartbeat service started")
stateManager := state.NewManager(cfg.WorkspacePath())
deviceService := devices.NewService(devices.Config{
Enabled: cfg.Devices.Enabled,
MonitorUSB: cfg.Devices.MonitorUSB,
}, stateManager)
deviceService.SetBus(msgBus)
if err := deviceService.Start(ctx); err != nil {
fmt.Printf("Error starting device service: %v\n", err)
} else if cfg.Devices.Enabled {
fmt.Println("✓ Device event service started")
}
if err := channelManager.StartAll(ctx); err != nil {
fmt.Printf("Error starting channels: %v\n", err)
}
healthServer := health.NewServer(cfg.Gateway.Host, cfg.Gateway.Port)
go func() {
if err := healthServer.Start(); err != nil && err != http.ErrServerClosed {
logger.ErrorCF("health", "Health server error", map[string]interface{}{"error": err.Error()})
}
}()
fmt.Printf("✓ Health endpoints available at http://%s:%d/health and /ready\n", cfg.Gateway.Host, cfg.Gateway.Port)
go agentLoop.Run(ctx)
sigChan := make(chan os.Signal, 1)
@ -763,6 +679,8 @@ func gatewayCmd() {
fmt.Println("\nShutting down...")
cancel()
healthServer.Stop(context.Background())
deviceService.Stop()
heartbeatService.Stop()
cronService.Stop()
agentLoop.Stop()
@ -1069,14 +987,14 @@ func getConfigPath() string {
return filepath.Join(home, ".picoclaw", "config.json")
}
func setupCronTool(agentLoop *agent.AgentLoop, msgBus *bus.MessageBus, workspace string) *cron.CronService {
func setupCronTool(agentLoop *agent.AgentLoop, msgBus *bus.MessageBus, workspace string, restrict bool) *cron.CronService {
cronStorePath := filepath.Join(workspace, "cron", "jobs.json")
// Create cron service
cronService := cron.NewCronService(cronStorePath, nil)
// Create and register CronTool
cronTool := tools.NewCronTool(cronService, agentLoop, msgBus, workspace)
cronTool := tools.NewCronTool(cronService, agentLoop, msgBus, workspace, restrict)
agentLoop.RegisterTool(cronTool)
// Set the onJob handler

View file

@ -60,6 +60,14 @@
"webhook_port": 18791,
"webhook_path": "/webhook/line",
"allow_from": []
},
"onebot": {
"enabled": false,
"ws_url": "ws://127.0.0.1:3001",
"access_token": "",
"reconnect_interval": 5,
"group_trigger_prefix": [],
"allow_from": []
}
},
"providers": {
@ -99,6 +107,10 @@
"moonshot": {
"api_key": "sk-xxx",
"api_base": ""
},
"ollama": {
"api_key": "",
"api_base": "http://localhost:11434/v1"
}
},
"tools": {
@ -113,6 +125,10 @@
"enabled": true,
"interval": 30
},
"devices": {
"enabled": false,
"monitor_usb": true
},
"gateway": {
"host": "0.0.0.0",
"port": 18790

View file

@ -0,0 +1,112 @@
## 🚀 Join the PicoClaw Journey: Call for Community Volunteers & Roadmap Reveal
**Hello, PicoClaw Community!**
First, a massive thank you to everyone for your enthusiasm and PR contributions. It is because of you that PicoClaw continues to iterate and evolve so rapidly. Thanks to the simplicity and accessibility of the **Go language**, weve seen a non-stop stream of high-quality PRs!
PicoClaw is growing much faster than we anticipated. As we are currently in the midst of the **Chinese New Year holiday**, we are looking to recruit community volunteers to help us maintain this incredible momentum.
This document outlines the specific volunteer roles we need right now and provides a look at our upcoming **Roadmap**.
### 🎁 Community Perks
To show our appreciation, developers who officially join our community operations will receive:
* **Exclusive AI Hardware:** Our upcoming, unreleased AI device.
* **Token Discounts:** Potential discounts on LLM tokens (currently in negotiations with major providers).
### 🎥 Calling All Content Creators!
Not a developer? You can still help! We welcome users to post **PicoClaw reviews or tutorials**.
* **Twitter:** Use the tag **#picoclaw** and mention **@SipeedIO**.
* **Bilibili:** Mention **@Sipeed矽速科技** or send us a DM.
We will be rewarding high-quality content creators with the same perks as our community developers!
---
## 🛠️ Urgent Volunteer Roles
We are looking for experts in the following areas:
1. **Issue/PR Reviewers**
* **The Mission:** With PRs and Issues exploding in volume, we need help with initial triage, evaluation, and merging.
* **Focus:** Preliminary merging and community health. Efficiency optimization and security audits will be handled by specialized roles.
2. **Resource Optimization Experts**
* **The Mission:** Rapid growth has introduced dependencies that are making PicoClaw a bit "heavy." We want to keep it lean.
* **Focus:** Analyzing resource growth between releases and trimming redundancy.
* **Priority:** **RAM usage optimization** > Binary size reduction.
3. **Security Audit & Bug Fixes**
* **The Mission:** Due to the "vibe coding" nature of our early stages, we need a thorough review of network security and AI permission management.
* **Focus:** Auditing the codebase for vulnerabilities and implementing robust fixes.
4. **Documentation & DX (Developer Experience)**
* **The Mission:** Our current README is a bit outdated. We need "step-by-step" guides that even beginners can follow.
* **Focus:** Creating clear, user-friendly documentation for both setup and development.
5. **AI-Powered CI/CD Optimization**
* **The Mission:** PicoClaw started as a "vibe coding" experiment; now we want to use AI to manage it.
* **Focus:** Automating builds with AI and exploring AI-driven issue resolution.
**How to Apply:** > If you are interested in any of the roles above, please send an email to support@sipeed.com with the subject line: [Apply: PicoClaw Expert Volunteer] + Your Desired Role.
Please include a brief introduction and any relevant experience or portfolio links. We will review all applications and grant project permissions to selected contributors!
---
## 📍 The Roadmap
Interested in a specific feature? You can "claim" these tasks and start building:
###
* **Provider:**
* **Provider Refactor:** Currently being handled by **@Daming** (ETA: 5 days)
* You can still submit code; Daming will merge it into the new implementation.
* **Channels:**
* Support for OneBot, additional platforms
* attachments (images, audio, video, files).
* **Skills:**
* Implementing `find_skill` to discover tools via [openclaw/skills](https://github.com/openclaw/skills) and other platforms.
* **Operations:** * MCP Support.
* Android operations (e.g., botdrop).
* Browser automation via CDP or ActionBook.
* **Multi-Agent Ecosystem:**
* **Basic Model-Agnet** S
* **Model Routing:** Small models for easy tasks, large models for hard ones (to save tokens).
* **Swarm Mode.**
* **AIEOS Integration.**
* **Branding:**
* **Logo**: We need a cute logo! Were leaning toward a **Mantis Shrimp**—small, but packs a legendary punch!
We have officially created these tasks as GitHub Issues, all marked with the roadmap tag.
This list will be updated continuously as we progress.
If you would like to claim a task, please feel free to start a conversation by commenting directly on the corresponding issue!
---
## 🤝 How to Join
**Everything is open to your creativity!** If you have a wild idea, just PR it.
1. **The Fast Track:** Once you have at least **one merged PR**, you are eligible to join our **Developer Discord** to help plan the future of PicoClaw.
2. **The Application Track:** If you havent submitted a PR yet but want to dive in, email **support@sipeed.com** with the subject:
> `[Apply Join PicoClaw Dev Group] + Your GitHub Account`
> Include the role you're interested in and any evidence of your development experience.
### Looking Ahead
Powered by PicoClaw, we are crafting a Swarm AI Assistant to transform your environment into a seamless network of personal stewards. By automating the friction of daily life, we empower you to transcend the ordinary and freely explore your creative potential.
**Finally, Happy Chinese New Year to everyone!** May PicoClaw gallop forward in this **Year of the Horse!** 🐎

11
go.mod
View file

@ -13,20 +13,29 @@ require (
github.com/larksuite/oapi-sdk-go/v3 v3.5.3
github.com/mymmrac/telego v1.6.0
github.com/open-dingtalk/dingtalk-stream-sdk-go v0.9.1
github.com/openai/openai-go/v3 v3.21.0
github.com/openai/openai-go/v3 v3.22.0
github.com/slack-go/slack v0.17.3
github.com/stretchr/testify v1.11.1
github.com/tencent-connect/botgo v0.2.1
golang.org/x/oauth2 v0.35.0
)
require (
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
)
require (
github.com/andybalholm/brotli v1.2.0 // indirect
github.com/bytedance/gopkg v0.1.3 // indirect
github.com/bytedance/sonic v1.15.0 // indirect
github.com/bytedance/sonic/loader v0.5.0 // indirect
github.com/cloudwego/base64x v0.1.6 // indirect
github.com/github/copilot-sdk/go v0.1.23
github.com/go-resty/resty/v2 v2.17.1 // indirect
github.com/gogo/protobuf v1.3.2 // indirect
github.com/google/jsonschema-go v0.4.2 // indirect
github.com/grbit/go-json v0.11.0 // indirect
github.com/klauspost/compress v1.18.4 // indirect
github.com/klauspost/cpuid/v2 v2.3.0 // indirect

14
go.sum
View file

@ -32,6 +32,8 @@ github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSs
github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
github.com/github/copilot-sdk/go v0.1.23 h1:uExtO/inZQndCZMiSAA1hvXINiz9tqo/MZgQzFzurxw=
github.com/github/copilot-sdk/go v0.1.23/go.mod h1:GdwwBfMbm9AABLEM3x5IZKw4ZfwCYxZ1BgyytmZenQ0=
github.com/go-redis/redis/v8 v8.11.4/go.mod h1:2Z2wHZXdQpCDXEGzqMockDpNyYvi2l4Pxt6RJr792+w=
github.com/go-resty/resty/v2 v2.6.0/go.mod h1:PwvJS6hvaPkjtjNg9ph+VrSD92bi5Zq73w/BIH7cC3Q=
github.com/go-resty/resty/v2 v2.17.1 h1:x3aMpHK1YM9e4va/TMDRlusDDoZiQ+ViDu/WpA6xTM4=
@ -56,6 +58,10 @@ github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
github.com/google/jsonschema-go v0.4.2 h1:tmrUohrwoLZZS/P3x7ex0WAVknEkBZM46iALbcqoRA8=
github.com/google/jsonschema-go v0.4.2/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9tgaYcxEYhJVE=
github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@ -74,9 +80,11 @@ github.com/klauspost/cpuid/v2 v2.3.0 h1:S4CRMLnYUhGeDFDqkGriYKdfoFlDnMtqTiI/sFzh
github.com/klauspost/cpuid/v2 v2.3.0/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/larksuite/oapi-sdk-go/v3 v3.5.3 h1:xvf8Dv29kBXC5/DNDCLhHkAFW8l/0LlQJimO5Zn+JUk=
github.com/larksuite/oapi-sdk-go/v3 v3.5.3/go.mod h1:ZEplY+kwuIrj/nqw5uSCINNATcH3KdxSN7y+UxYY5fI=
@ -92,12 +100,13 @@ github.com/onsi/gomega v1.10.1/go.mod h1:iN09h71vgCQne3DLsj+A5owkum+a2tYe+TOCB1y
github.com/onsi/gomega v1.16.0/go.mod h1:HnhC7FXeEQY45zxNK3PPoIUhzk/80Xly9PcubAlGdZY=
github.com/open-dingtalk/dingtalk-stream-sdk-go v0.9.1 h1:Lb/Uzkiw2Ugt2Xf03J5wmv81PdkYOiWbI8CNBi1boC8=
github.com/open-dingtalk/dingtalk-stream-sdk-go v0.9.1/go.mod h1:ln3IqPYYocZbYvl9TAOrG/cxGR9xcn4pnZRLdCTEGEU=
github.com/openai/openai-go/v3 v3.21.0 h1:3GpIR/W4q/v1uUOVuK3zYtQiF3DnRrZag/sxbtvEdtc=
github.com/openai/openai-go/v3 v3.21.0/go.mod h1:cdufnVK14cWcT9qA1rRtrXx4FTRsgbDPW7Ia7SS5cZo=
github.com/openai/openai-go/v3 v3.22.0 h1:6MEoNoV8sbjOVmXdvhmuX3BjVbVdcExbVyGixiyJ8ys=
github.com/openai/openai-go/v3 v3.22.0/go.mod h1:cdufnVK14cWcT9qA1rRtrXx4FTRsgbDPW7Ia7SS5cZo=
github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
github.com/slack-go/slack v0.17.3 h1:zV5qO3Q+WJAQ/XwbGfNFrRMaJ5T/naqaonyPV/1TP4g=
github.com/slack-go/slack v0.17.3/go.mod h1:X+UqOufi3LYQHDnMG1vxf0J8asC6+WllXrVrhl8/Prk=
@ -238,6 +247,7 @@ google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp0
google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
gopkg.in/fsnotify.v1 v1.4.7/go.mod h1:Tz8NjZHkW78fSQdbUxIjBTcgA1z1m8ZHf0WmKUhAMys=

View file

@ -16,8 +16,10 @@ import (
"sync"
"sync/atomic"
"time"
"unicode/utf8"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/constants"
"github.com/sipeed/picoclaw/pkg/logger"
@ -41,6 +43,7 @@ type AgentLoop struct {
tools *tools.ToolRegistry
running atomic.Bool
summarizing sync.Map // Tracks which sessions are currently being summarized
channelManager *channels.Manager
}
// processOptions configures how a message is processed
@ -81,6 +84,10 @@ func createToolRegistry(workspace string, restrict bool, cfg *config.Config, msg
}
registry.Register(tools.NewWebFetchTool(50000))
// Hardware tools (I2C, SPI) - Linux only, returns error on other platforms
registry.Register(tools.NewI2CTool())
registry.Register(tools.NewSPITool())
// Message tool - available to both agent and subagent
// Subagent uses it to communicate directly with user
messageTool := tools.NewMessageTool()
@ -194,6 +201,10 @@ func (al *AgentLoop) RegisterTool(tool tools.Tool) {
al.tools.Register(tool)
}
func (al *AgentLoop) SetChannelManager(cm *channels.Manager) {
al.channelManager = cm
}
// RecordLastChannel records the last active channel for this workspace.
// This uses the atomic state save mechanism to prevent data loss on crash.
func (al *AgentLoop) RecordLastChannel(channel string) error {
@ -258,6 +269,11 @@ func (al *AgentLoop) processMessage(ctx context.Context, msg bus.InboundMessage)
return al.processSystemMessage(ctx, msg)
}
// Check for commands
if response, handled := al.handleCommand(ctx, msg); handled {
return response, nil
}
// Process as user message
return al.runAgentLoop(ctx, processOptions{
SessionKey: msg.SessionKey,
@ -378,7 +394,7 @@ func (al *AgentLoop) runAgentLoop(ctx context.Context, opts processOptions) (str
// 7. Optional: summarization
if opts.EnableSummary {
al.maybeSummarize(opts.SessionKey)
al.maybeSummarize(opts.SessionKey, opts.Channel, opts.ChatID)
}
// 8. Optional: send response via bus
@ -440,19 +456,139 @@ func (al *AgentLoop) runLLMIteration(ctx context.Context, messages []providers.M
"tools_json": formatToolsForLog(providerToolDefs),
})
// Call LLM
response, err := al.provider.Chat(ctx, messages, providerToolDefs, al.model, map[string]interface{}{
var response *providers.LLMResponse
var err error
// Retry loop for context/token errors
maxRetries := 2
for retry := 0; retry <= maxRetries; retry++ {
response, err = al.provider.Chat(ctx, messages, providerToolDefs, al.model, map[string]interface{}{
"max_tokens": 8192,
"temperature": 0.7,
})
if err == nil {
break // Success
}
errMsg := strings.ToLower(err.Error())
// Check for context window errors (provider specific, but usually contain "token" or "invalid")
isContextError := strings.Contains(errMsg, "token") ||
strings.Contains(errMsg, "context") ||
strings.Contains(errMsg, "invalidparameter") ||
strings.Contains(errMsg, "length")
if isContextError && retry < maxRetries {
logger.WarnCF("agent", "Context window error detected, attempting compression", map[string]interface{}{
"error": err.Error(),
"retry": retry,
})
// Notify user on first retry only
if retry == 0 && !constants.IsInternalChannel(opts.Channel) && opts.SendResponse {
al.bus.PublishOutbound(bus.OutboundMessage{
Channel: opts.Channel,
ChatID: opts.ChatID,
Content: "⚠️ Context window exceeded. Compressing history and retrying...",
})
}
// Force compression
al.forceCompression(opts.SessionKey)
// Rebuild messages with compressed history
// Note: We need to reload history from session manager because forceCompression changed it
newHistory := al.sessions.GetHistory(opts.SessionKey)
newSummary := al.sessions.GetSummary(opts.SessionKey)
// Re-create messages for the next attempt
// We keep the current user message (opts.UserMessage) effectively
messages = al.contextBuilder.BuildMessages(
newHistory,
newSummary,
opts.UserMessage,
nil,
opts.Channel,
opts.ChatID,
)
// Important: If we are in the middle of a tool loop (iteration > 1),
// rebuilding messages from session history might duplicate the flow or miss context
// if intermediate steps weren't saved correctly.
// However, al.sessions.AddFullMessage is called after every tool execution,
// so GetHistory should reflect the current state including partial tool execution.
// But we need to ensure we don't duplicate the user message which is appended in BuildMessages.
// BuildMessages(history...) takes the stored history and appends the *current* user message.
// If iteration > 1, the "current user message" was already added to history in step 3 of runAgentLoop.
// So if we pass opts.UserMessage again, we might duplicate it?
// Actually, step 3 is: al.sessions.AddMessage(opts.SessionKey, "user", opts.UserMessage)
// So GetHistory ALREADY contains the user message!
// CORRECTION:
// BuildMessages combines: [System] + [History] + [CurrentMessage]
// But Step 3 added CurrentMessage to History.
// So if we use GetHistory now, it has the user message.
// If we pass opts.UserMessage to BuildMessages, it adds it AGAIN.
// For retry in the middle of a loop, we should rely on what's in the session.
// BUT checking BuildMessages implementation:
// It appends history... then appends currentMessage.
// Logic fix for retry:
// If iteration == 1, opts.UserMessage corresponds to the user input.
// If iteration > 1, we are processing tool results. The "messages" passed to Chat
// already accumulated tool outputs.
// Rebuilding from session history is safest because it persists state.
// Start fresh with rebuilt history.
// Special case: standard BuildMessages appends "currentMessage".
// If we are strictly retrying the *LLM call*, we want the exact same state as before but compressed.
// However, the "messages" argument passed to runLLMIteration is constructed by the caller.
// If we rebuild from Session, we need to know if "currentMessage" should be appended or is already in history.
// In runAgentLoop:
// 3. sessions.AddMessage(userMsg)
// 4. runLLMIteration(..., UserMessage)
// So History contains the user message.
// BuildMessages typically appends the user message as a *new* pending message.
// Wait, standard BuildMessages usage in runAgentLoop:
// messages := BuildMessages(history (has old), UserMessage)
// THEN AddMessage(UserMessage).
// So "history" passed to BuildMessages does NOT contain the current UserMessage yet.
// But here, inside the loop, we have already saved it.
// So GetHistory() includes the current user message.
// If we call BuildMessages(GetHistory(), UserMessage), we get duplicates.
// Hack/Fix:
// If we are retrying, we rebuild from Session History ONLY.
// We pass empty string as "currentMessage" to BuildMessages
// because the "current message" is already saved in history (step 3).
messages = al.contextBuilder.BuildMessages(
newHistory,
newSummary,
"", // Empty because history already contains the relevant messages
nil,
opts.Channel,
opts.ChatID,
)
continue
}
// Real error or success, break loop
break
}
if err != nil {
logger.ErrorCF("agent", "LLM call failed",
map[string]interface{}{
"iteration": iteration,
"error": err.Error(),
})
return "", iteration, fmt.Errorf("LLM call failed: %w", err)
return "", iteration, fmt.Errorf("LLM call failed after retries: %w", err)
}
// Check if no tool calls - we're done
@ -585,7 +721,7 @@ func (al *AgentLoop) updateToolContexts(channel, chatID string) {
}
// maybeSummarize triggers summarization if the session history exceeds thresholds.
func (al *AgentLoop) maybeSummarize(sessionKey string) {
func (al *AgentLoop) maybeSummarize(sessionKey, channel, chatID string) {
newHistory := al.sessions.GetHistory(sessionKey)
tokenEstimate := al.estimateTokens(newHistory)
threshold := al.contextWindow * 75 / 100
@ -594,12 +730,80 @@ func (al *AgentLoop) maybeSummarize(sessionKey string) {
if _, loading := al.summarizing.LoadOrStore(sessionKey, true); !loading {
go func() {
defer al.summarizing.Delete(sessionKey)
// Notify user about optimization if not an internal channel
if !constants.IsInternalChannel(channel) {
al.bus.PublishOutbound(bus.OutboundMessage{
Channel: channel,
ChatID: chatID,
Content: "⚠️ Memory threshold reached. Optimizing conversation history...",
})
}
al.summarizeSession(sessionKey)
}()
}
}
}
// forceCompression aggressively reduces context when the limit is hit.
// It drops the oldest 50% of messages (keeping system prompt and last user message).
func (al *AgentLoop) forceCompression(sessionKey string) {
history := al.sessions.GetHistory(sessionKey)
if len(history) <= 4 {
return
}
// Keep system prompt (usually [0]) and the very last message (user's trigger)
// We want to drop the oldest half of the *conversation*
// Assuming [0] is system, [1:] is conversation
conversation := history[1 : len(history)-1]
if len(conversation) == 0 {
return
}
// Helper to find the mid-point of the conversation
mid := len(conversation) / 2
// New history structure:
// 1. System Prompt
// 2. [Summary of dropped part] - synthesized
// 3. Second half of conversation
// 4. Last message
// Simplified approach for emergency: Drop first half of conversation
// and rely on existing summary if present, or create a placeholder.
droppedCount := mid
keptConversation := conversation[mid:]
newHistory := make([]providers.Message, 0)
newHistory = append(newHistory, history[0]) // System prompt
// Add a note about compression
compressionNote := fmt.Sprintf("[System: Emergency compression dropped %d oldest messages due to context limit]", droppedCount)
// If there was an existing summary, we might lose it if it was in the dropped part (which is just messages).
// The summary is stored separately in session.Summary, so it persists!
// We just need to ensure the user knows there's a gap.
// We only modify the messages list here
newHistory = append(newHistory, providers.Message{
Role: "system",
Content: compressionNote,
})
newHistory = append(newHistory, keptConversation...)
newHistory = append(newHistory, history[len(history)-1]) // Last message
// Update session
al.sessions.SetHistory(sessionKey, newHistory)
al.sessions.Save(sessionKey)
logger.WarnCF("agent", "Forced compression executed", map[string]interface{}{
"session_key": sessionKey,
"dropped_msgs": droppedCount,
"new_count": len(newHistory),
})
}
// GetStartupInfo returns information about loaded tools and skills for logging.
func (al *AgentLoop) GetStartupInfo() map[string]interface{} {
info := make(map[string]interface{})
@ -627,7 +831,7 @@ func formatMessagesForLog(messages []providers.Message) string {
result += "[\n"
for i, msg := range messages {
result += fmt.Sprintf(" [%d] Role: %s\n", i, msg.Role)
if msg.ToolCalls != nil && len(msg.ToolCalls) > 0 {
if len(msg.ToolCalls) > 0 {
result += " ToolCalls:\n"
for _, tc := range msg.ToolCalls {
result += fmt.Sprintf(" - ID: %s, Type: %s, Name: %s\n", tc.ID, tc.Type, tc.Name)
@ -694,7 +898,7 @@ func (al *AgentLoop) summarizeSession(sessionKey string) {
continue
}
// Estimate tokens for this message
msgTokens := len(m.Content) / 4
msgTokens := len(m.Content) / 2 // Use safer estimate here too (2.5 -> 2 for integer division safety)
if msgTokens > maxMessageTokens {
omitted = true
continue
@ -765,10 +969,96 @@ func (al *AgentLoop) summarizeBatch(ctx context.Context, batch []providers.Messa
}
// estimateTokens estimates the number of tokens in a message list.
// Uses a safe heuristic of 2.5 characters per token to account for CJK and other
// overheads better than the previous 3 chars/token.
func (al *AgentLoop) estimateTokens(messages []providers.Message) int {
total := 0
totalChars := 0
for _, m := range messages {
total += len(m.Content) / 4 // Simple heuristic: 4 chars per token
totalChars += utf8.RuneCountInString(m.Content)
}
return total
// 2.5 chars per token = totalChars * 2 / 5
return totalChars * 2 / 5
}
func (al *AgentLoop) handleCommand(ctx context.Context, msg bus.InboundMessage) (string, bool) {
content := strings.TrimSpace(msg.Content)
if !strings.HasPrefix(content, "/") {
return "", false
}
parts := strings.Fields(content)
if len(parts) == 0 {
return "", false
}
cmd := parts[0]
args := parts[1:]
switch cmd {
case "/show":
if len(args) < 1 {
return "Usage: /show [model|channel]", true
}
switch args[0] {
case "model":
return fmt.Sprintf("Current model: %s", al.model), true
case "channel":
return fmt.Sprintf("Current channel: %s", msg.Channel), true
default:
return fmt.Sprintf("Unknown show target: %s", args[0]), true
}
case "/list":
if len(args) < 1 {
return "Usage: /list [models|channels]", true
}
switch args[0] {
case "models":
// TODO: Fetch available models dynamically if possible
return "Available models: glm-4.7, claude-3-5-sonnet, gpt-4o (configured in config.json/env)", true
case "channels":
if al.channelManager == nil {
return "Channel manager not initialized", true
}
channels := al.channelManager.GetEnabledChannels()
if len(channels) == 0 {
return "No channels enabled", true
}
return fmt.Sprintf("Enabled channels: %s", strings.Join(channels, ", ")), true
default:
return fmt.Sprintf("Unknown list target: %s", args[0]), true
}
case "/switch":
if len(args) < 3 || args[1] != "to" {
return "Usage: /switch [model|channel] to <name>", true
}
target := args[0]
value := args[2]
switch target {
case "model":
oldModel := al.model
al.model = value
return fmt.Sprintf("Switched model from %s to %s", oldModel, value), true
case "channel":
// This changes the 'default' channel for some operations, or effectively redirects output?
// For now, let's just validate if the channel exists
if al.channelManager == nil {
return "Channel manager not initialized", true
}
if _, exists := al.channelManager.GetChannel(value); !exists && value != "cli" {
return fmt.Sprintf("Channel '%s' not found or not enabled", value), true
}
// If message came from CLI, maybe we want to redirect CLI output to this channel?
// That would require state persistence about "redirected channel"
// For now, just acknowledged.
return fmt.Sprintf("Switched target channel to %s (Note: this currently only validates existence)", value), true
default:
return fmt.Sprintf("Unknown switch target: %s", target), true
}
}
return "", false
}

View file

@ -2,6 +2,7 @@ package agent
import (
"context"
"fmt"
"os"
"path/filepath"
"testing"
@ -527,3 +528,99 @@ func TestToolResult_UserFacingToolDoesSendMessage(t *testing.T) {
t.Errorf("Expected 'Command output: hello world', got: %s", response)
}
}
// failFirstMockProvider fails on the first N calls with a specific error
type failFirstMockProvider struct {
failures int
currentCall int
failError error
successResp string
}
func (m *failFirstMockProvider) Chat(ctx context.Context, messages []providers.Message, tools []providers.ToolDefinition, model string, opts map[string]interface{}) (*providers.LLMResponse, error) {
m.currentCall++
if m.currentCall <= m.failures {
return nil, m.failError
}
return &providers.LLMResponse{
Content: m.successResp,
ToolCalls: []providers.ToolCall{},
}, nil
}
func (m *failFirstMockProvider) GetDefaultModel() string {
return "mock-fail-model"
}
// TestAgentLoop_ContextExhaustionRetry verify that the agent retries on context errors
func TestAgentLoop_ContextExhaustionRetry(t *testing.T) {
tmpDir, err := os.MkdirTemp("", "agent-test-*")
if err != nil {
t.Fatalf("Failed to create temp dir: %v", err)
}
defer os.RemoveAll(tmpDir)
cfg := &config.Config{
Agents: config.AgentsConfig{
Defaults: config.AgentDefaults{
Workspace: tmpDir,
Model: "test-model",
MaxTokens: 4096,
MaxToolIterations: 10,
},
},
}
msgBus := bus.NewMessageBus()
// Create a provider that fails once with a context error
contextErr := fmt.Errorf("InvalidParameter: Total tokens of image and text exceed max message tokens")
provider := &failFirstMockProvider{
failures: 1,
failError: contextErr,
successResp: "Recovered from context error",
}
al := NewAgentLoop(cfg, msgBus, provider)
// Inject some history to simulate a full context
sessionKey := "test-session-context"
// Create dummy history
history := []providers.Message{
{Role: "system", Content: "System prompt"},
{Role: "user", Content: "Old message 1"},
{Role: "assistant", Content: "Old response 1"},
{Role: "user", Content: "Old message 2"},
{Role: "assistant", Content: "Old response 2"},
{Role: "user", Content: "Trigger message"},
}
al.sessions.SetHistory(sessionKey, history)
// Call ProcessDirectWithChannel
// Note: ProcessDirectWithChannel calls processMessage which will execute runLLMIteration
response, err := al.ProcessDirectWithChannel(context.Background(), "Trigger message", sessionKey, "test", "test-chat")
if err != nil {
t.Fatalf("Expected success after retry, got error: %v", err)
}
if response != "Recovered from context error" {
t.Errorf("Expected 'Recovered from context error', got '%s'", response)
}
// We expect 2 calls: 1st failed, 2nd succeeded
if provider.currentCall != 2 {
t.Errorf("Expected 2 calls (1 fail + 1 success), got %d", provider.currentCall)
}
// Check final history length
finalHistory := al.sessions.GetHistory(sessionKey)
// We verify that the history has been modified (compressed)
// Original length: 6
// Expected behavior: compression drops ~50% of history (mid slice)
// We can assert that the length is NOT what it would be without compression.
// Without compression: 6 + 1 (new user msg) + 1 (assistant msg) = 8
if len(finalHistory) >= 8 {
t.Errorf("Expected history to be compressed (len < 8), got %d", len(finalHistory))
}
}

View file

@ -22,6 +22,7 @@ type OAuthProviderConfig struct {
Issuer string
ClientID string
Scopes string
Originator string
Port int
}
@ -30,6 +31,7 @@ func OpenAIOAuthConfig() OAuthProviderConfig {
Issuer: "https://auth.openai.com",
ClientID: "app_EMoamEEZ73f0CkXaXp7hrann",
Scopes: "openid profile email offline_access",
Originator: "codex_cli_rs",
Port: 1455,
}
}
@ -279,7 +281,17 @@ func RefreshAccessToken(cred *AuthCredential, cfg OAuthProviderConfig) (*AuthCre
return nil, fmt.Errorf("token refresh failed: %s", string(body))
}
return parseTokenResponse(body, cred.Provider)
refreshed, err := parseTokenResponse(body, cred.Provider)
if err != nil {
return nil, err
}
if refreshed.RefreshToken == "" {
refreshed.RefreshToken = cred.RefreshToken
}
if refreshed.AccountID == "" {
refreshed.AccountID = cred.AccountID
}
return refreshed, nil
}
func BuildAuthorizeURL(cfg OAuthProviderConfig, pkce PKCECodes, state, redirectURI string) string {
@ -294,9 +306,17 @@ func buildAuthorizeURL(cfg OAuthProviderConfig, pkce PKCECodes, state, redirectU
"scope": {cfg.Scopes},
"code_challenge": {pkce.CodeChallenge},
"code_challenge_method": {"S256"},
"id_token_add_organizations": {"true"},
"codex_cli_simplified_flow": {"true"},
"state": {state},
}
return cfg.Issuer + "/authorize?" + params.Encode()
if strings.Contains(strings.ToLower(cfg.Issuer), "auth.openai.com") {
params.Set("originator", "picoclaw")
}
if cfg.Originator != "" {
params.Set("originator", cfg.Originator)
}
return cfg.Issuer + "/oauth/authorize?" + params.Encode()
}
func exchangeCodeForTokens(cfg OAuthProviderConfig, code, codeVerifier, redirectURI string) (*AuthCredential, error) {
@ -350,19 +370,57 @@ func parseTokenResponse(body []byte, provider string) (*AuthCredential, error) {
AuthMethod: "oauth",
}
if accountID := extractAccountID(tokenResp.AccessToken); accountID != "" {
if accountID := extractAccountID(tokenResp.IDToken); accountID != "" {
cred.AccountID = accountID
} else if accountID := extractAccountID(tokenResp.AccessToken); accountID != "" {
cred.AccountID = accountID
} else if accountID := extractAccountID(tokenResp.IDToken); accountID != "" {
// Recent OpenAI OAuth responses may only include chatgpt_account_id in id_token claims.
cred.AccountID = accountID
}
return cred, nil
}
func extractAccountID(accessToken string) string {
parts := strings.Split(accessToken, ".")
if len(parts) < 2 {
func extractAccountID(token string) string {
claims, err := parseJWTClaims(token)
if err != nil {
return ""
}
if accountID, ok := claims["chatgpt_account_id"].(string); ok && accountID != "" {
return accountID
}
if accountID, ok := claims["https://api.openai.com/auth.chatgpt_account_id"].(string); ok && accountID != "" {
return accountID
}
if authClaim, ok := claims["https://api.openai.com/auth"].(map[string]interface{}); ok {
if accountID, ok := authClaim["chatgpt_account_id"].(string); ok && accountID != "" {
return accountID
}
}
if orgs, ok := claims["organizations"].([]interface{}); ok {
for _, org := range orgs {
if orgMap, ok := org.(map[string]interface{}); ok {
if accountID, ok := orgMap["id"].(string); ok && accountID != "" {
return accountID
}
}
}
}
return ""
}
func parseJWTClaims(token string) (map[string]interface{}, error) {
parts := strings.Split(token, ".")
if len(parts) < 2 {
return nil, fmt.Errorf("token is not a JWT")
}
payload := parts[1]
switch len(payload) % 4 {
case 2:
@ -373,21 +431,15 @@ func extractAccountID(accessToken string) string {
decoded, err := base64URLDecode(payload)
if err != nil {
return ""
return nil, err
}
var claims map[string]interface{}
if err := json.Unmarshal(decoded, &claims); err != nil {
return ""
return nil, err
}
if authClaim, ok := claims["https://api.openai.com/auth"].(map[string]interface{}); ok {
if accountID, ok := authClaim["chatgpt_account_id"].(string); ok {
return accountID
}
}
return ""
return claims, nil
}
func base64URLDecode(s string) ([]byte, error) {

View file

@ -1,18 +1,33 @@
package auth
import (
"encoding/base64"
"encoding/json"
"net/http"
"net/http/httptest"
"net/url"
"strings"
"testing"
)
func makeJWTForClaims(t *testing.T, claims map[string]interface{}) string {
t.Helper()
header := base64.RawURLEncoding.EncodeToString([]byte(`{"alg":"none","typ":"JWT"}`))
payloadJSON, err := json.Marshal(claims)
if err != nil {
t.Fatalf("marshal claims: %v", err)
}
payload := base64.RawURLEncoding.EncodeToString(payloadJSON)
return header + "." + payload + ".sig"
}
func TestBuildAuthorizeURL(t *testing.T) {
cfg := OAuthProviderConfig{
Issuer: "https://auth.example.com",
ClientID: "test-client-id",
Scopes: "openid profile",
Originator: "codex_cli_rs",
Port: 1455,
}
pkce := PKCECodes{
@ -22,7 +37,7 @@ func TestBuildAuthorizeURL(t *testing.T) {
u := BuildAuthorizeURL(cfg, pkce, "test-state", "http://localhost:1455/auth/callback")
if !strings.HasPrefix(u, "https://auth.example.com/authorize?") {
if !strings.HasPrefix(u, "https://auth.example.com/oauth/authorize?") {
t.Errorf("URL does not start with expected prefix: %s", u)
}
if !strings.Contains(u, "client_id=test-client-id") {
@ -40,6 +55,37 @@ func TestBuildAuthorizeURL(t *testing.T) {
if !strings.Contains(u, "response_type=code") {
t.Error("URL missing response_type")
}
if !strings.Contains(u, "id_token_add_organizations=true") {
t.Error("URL missing id_token_add_organizations")
}
if !strings.Contains(u, "codex_cli_simplified_flow=true") {
t.Error("URL missing codex_cli_simplified_flow")
}
if !strings.Contains(u, "originator=codex_cli_rs") {
t.Error("URL missing originator")
}
}
func TestBuildAuthorizeURLOpenAIExtras(t *testing.T) {
cfg := OpenAIOAuthConfig()
pkce := PKCECodes{CodeVerifier: "test-verifier", CodeChallenge: "test-challenge"}
u := BuildAuthorizeURL(cfg, pkce, "test-state", "http://localhost:1455/auth/callback")
parsed, err := url.Parse(u)
if err != nil {
t.Fatalf("url.Parse() error: %v", err)
}
q := parsed.Query()
if q.Get("id_token_add_organizations") != "true" {
t.Errorf("id_token_add_organizations = %q, want true", q.Get("id_token_add_organizations"))
}
if q.Get("codex_cli_simplified_flow") != "true" {
t.Errorf("codex_cli_simplified_flow = %q, want true", q.Get("codex_cli_simplified_flow"))
}
if q.Get("originator") != "codex_cli_rs" {
t.Errorf("originator = %q, want codex_cli_rs", q.Get("originator"))
}
}
func TestParseTokenResponse(t *testing.T) {
@ -73,6 +119,37 @@ func TestParseTokenResponse(t *testing.T) {
}
}
func TestParseTokenResponseExtractsAccountIDFromIDToken(t *testing.T) {
idToken := makeJWTForClaims(t, map[string]interface{}{"chatgpt_account_id": "acc-id-from-id-token"})
resp := map[string]interface{}{
"access_token": "opaque-access-token",
"refresh_token": "test-refresh-token",
"expires_in": 3600,
"id_token": idToken,
}
body, _ := json.Marshal(resp)
cred, err := parseTokenResponse(body, "openai")
if err != nil {
t.Fatalf("parseTokenResponse() error: %v", err)
}
if cred.AccountID != "acc-id-from-id-token" {
t.Errorf("AccountID = %q, want %q", cred.AccountID, "acc-id-from-id-token")
}
}
func TestExtractAccountIDFromOrganizationsFallback(t *testing.T) {
token := makeJWTForClaims(t, map[string]interface{}{
"organizations": []interface{}{
map[string]interface{}{"id": "org_from_orgs"},
},
})
if got := extractAccountID(token); got != "org_from_orgs" {
t.Errorf("extractAccountID() = %q, want %q", got, "org_from_orgs")
}
}
func TestParseTokenResponseNoAccessToken(t *testing.T) {
body := []byte(`{"refresh_token": "test"}`)
_, err := parseTokenResponse(body, "openai")
@ -81,6 +158,32 @@ func TestParseTokenResponseNoAccessToken(t *testing.T) {
}
}
func TestParseTokenResponseAccountIDFromIDToken(t *testing.T) {
idToken := makeJWTWithAccountID("acc-from-id")
resp := map[string]interface{}{
"access_token": "not-a-jwt",
"refresh_token": "test-refresh-token",
"expires_in": 3600,
"id_token": idToken,
}
body, _ := json.Marshal(resp)
cred, err := parseTokenResponse(body, "openai")
if err != nil {
t.Fatalf("parseTokenResponse() error: %v", err)
}
if cred.AccountID != "acc-from-id" {
t.Errorf("AccountID = %q, want %q", cred.AccountID, "acc-from-id")
}
}
func makeJWTWithAccountID(accountID string) string {
header := base64.RawURLEncoding.EncodeToString([]byte(`{"alg":"none","typ":"JWT"}`))
payload := base64.RawURLEncoding.EncodeToString([]byte(`{"https://api.openai.com/auth":{"chatgpt_account_id":"` + accountID + `"}}`))
return header + "." + payload + ".sig"
}
func TestExchangeCodeForTokens(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/oauth/token" {
@ -185,6 +288,37 @@ func TestRefreshAccessTokenNoRefreshToken(t *testing.T) {
}
}
func TestRefreshAccessTokenPreservesRefreshAndAccountID(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
resp := map[string]interface{}{
"access_token": "new-access-token-only",
"expires_in": 3600,
}
json.NewEncoder(w).Encode(resp)
}))
defer server.Close()
cfg := OAuthProviderConfig{Issuer: server.URL, ClientID: "test-client"}
cred := &AuthCredential{
AccessToken: "old-access",
RefreshToken: "existing-refresh",
AccountID: "acc_existing",
Provider: "openai",
AuthMethod: "oauth",
}
refreshed, err := RefreshAccessToken(cred, cfg)
if err != nil {
t.Fatalf("RefreshAccessToken() error: %v", err)
}
if refreshed.RefreshToken != "existing-refresh" {
t.Errorf("RefreshToken = %q, want %q", refreshed.RefreshToken, "existing-refresh")
}
if refreshed.AccountID != "acc_existing" {
t.Errorf("AccountID = %q, want %q", refreshed.AccountID, "acc_existing")
}
}
func TestOpenAIOAuthConfig(t *testing.T) {
cfg := OpenAIOAuthConfig()
if cfg.Issuer != "https://auth.openai.com" {

View file

@ -9,6 +9,7 @@ type MessageBus struct {
inbound chan InboundMessage
outbound chan OutboundMessage
handlers map[string]MessageHandler
closed bool
mu sync.RWMutex
}
@ -21,6 +22,11 @@ func NewMessageBus() *MessageBus {
}
func (mb *MessageBus) PublishInbound(msg InboundMessage) {
mb.mu.RLock()
defer mb.mu.RUnlock()
if mb.closed {
return
}
mb.inbound <- msg
}
@ -34,6 +40,11 @@ func (mb *MessageBus) ConsumeInbound(ctx context.Context) (InboundMessage, bool)
}
func (mb *MessageBus) PublishOutbound(msg OutboundMessage) {
mb.mu.RLock()
defer mb.mu.RUnlock()
if mb.closed {
return
}
mb.outbound <- msg
}
@ -60,6 +71,12 @@ func (mb *MessageBus) GetHandler(channel string) (MessageHandler, bool) {
}
func (mb *MessageBus) Close() {
mb.mu.Lock()
defer mb.mu.Unlock()
if mb.closed {
return
}
mb.closed = true
close(mb.inbound)
close(mb.outbound)
}

View file

@ -4,6 +4,7 @@ import (
"context"
"fmt"
"os"
"strings"
"time"
"github.com/bwmarrin/discordgo"
@ -100,15 +101,156 @@ func (c *DiscordChannel) Send(ctx context.Context, msg bus.OutboundMessage) erro
return fmt.Errorf("channel ID is empty")
}
message := msg.Content
runes := []rune(msg.Content)
if len(runes) == 0 {
return nil
}
chunks := splitMessage(msg.Content, 1500) // Discord has a limit of 2000 characters per message, leave 500 for natural split e.g. code blocks
for _, chunk := range chunks {
if err := c.sendChunk(ctx, channelID, chunk); err != nil {
return err
}
}
return nil
}
// splitMessage splits long messages into chunks, preserving code block integrity
// Uses natural boundaries (newlines, spaces) and extends messages slightly to avoid breaking code blocks
func splitMessage(content string, limit int) []string {
var messages []string
for len(content) > 0 {
if len(content) <= limit {
messages = append(messages, content)
break
}
msgEnd := limit
// Find natural split point within the limit
msgEnd = findLastNewline(content[:limit], 200)
if msgEnd <= 0 {
msgEnd = findLastSpace(content[:limit], 100)
}
if msgEnd <= 0 {
msgEnd = limit
}
// Check if this would end with an incomplete code block
candidate := content[:msgEnd]
unclosedIdx := findLastUnclosedCodeBlock(candidate)
if unclosedIdx >= 0 {
// Message would end with incomplete code block
// Try to extend to include the closing ``` (with some buffer)
extendedLimit := limit + 500 // Allow 500 char buffer for code blocks
if len(content) > extendedLimit {
closingIdx := findNextClosingCodeBlock(content, msgEnd)
if closingIdx > 0 && closingIdx <= extendedLimit {
// Extend to include the closing ```
msgEnd = closingIdx
} else {
// Can't find closing, split before the code block
msgEnd = findLastNewline(content[:unclosedIdx], 200)
if msgEnd <= 0 {
msgEnd = findLastSpace(content[:unclosedIdx], 100)
}
if msgEnd <= 0 {
msgEnd = unclosedIdx
}
}
} else {
// Remaining content fits within extended limit
msgEnd = len(content)
}
}
if msgEnd <= 0 {
msgEnd = limit
}
messages = append(messages, content[:msgEnd])
content = strings.TrimSpace(content[msgEnd:])
}
return messages
}
// findLastUnclosedCodeBlock finds the last opening ``` that doesn't have a closing ```
// Returns the position of the opening ``` or -1 if all code blocks are complete
func findLastUnclosedCodeBlock(text string) int {
count := 0
lastOpenIdx := -1
for i := 0; i < len(text); i++ {
if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
if count == 0 {
lastOpenIdx = i
}
count++
i += 2
}
}
// If odd number of ``` markers, last one is unclosed
if count%2 == 1 {
return lastOpenIdx
}
return -1
}
// findNextClosingCodeBlock finds the next closing ``` starting from a position
// Returns the position after the closing ``` or -1 if not found
func findNextClosingCodeBlock(text string, startIdx int) int {
for i := startIdx; i < len(text); i++ {
if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
return i + 3
}
}
return -1
}
// findLastNewline finds the last newline character within the last N characters
// Returns the position of the newline or -1 if not found
func findLastNewline(s string, searchWindow int) int {
searchStart := len(s) - searchWindow
if searchStart < 0 {
searchStart = 0
}
for i := len(s) - 1; i >= searchStart; i-- {
if s[i] == '\n' {
return i
}
}
return -1
}
// findLastSpace finds the last space character within the last N characters
// Returns the position of the space or -1 if not found
func findLastSpace(s string, searchWindow int) int {
searchStart := len(s) - searchWindow
if searchStart < 0 {
searchStart = 0
}
for i := len(s) - 1; i >= searchStart; i-- {
if s[i] == ' ' || s[i] == '\t' {
return i
}
}
return -1
}
func (c *DiscordChannel) sendChunk(ctx context.Context, channelID, content string) error {
// 使用传入的 ctx 进行超时控制
sendCtx, cancel := context.WithTimeout(ctx, sendTimeout)
defer cancel()
done := make(chan error, 1)
go func() {
_, err := c.session.ChannelMessageSend(channelID, message)
_, err := c.session.ChannelMessageSend(channelID, content)
done <- err
}()
@ -140,6 +282,12 @@ func (c *DiscordChannel) handleMessage(s *discordgo.Session, m *discordgo.Messag
return
}
if err := c.session.ChannelTyping(m.ChannelID); err != nil {
logger.ErrorCF("discord", "Failed to send typing indicator", map[string]any{
"error": err.Error(),
})
}
// 检查白名单,避免为被拒绝的用户下载附件和转录
if !c.IsAllowed(m.Author.ID) {
logger.DebugCF("discord", "Message rejected by allowlist", map[string]any{

36
pkg/channels/feishu_32.go Normal file
View file

@ -0,0 +1,36 @@
//go:build !amd64 && !arm64 && !riscv64 && !mips64 && !ppc64
package channels
import (
"context"
"errors"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/config"
)
// FeishuChannel is a stub implementation for 32-bit architectures
type FeishuChannel struct {
*BaseChannel
}
// NewFeishuChannel returns an error on 32-bit architectures where the Feishu SDK is not supported
func NewFeishuChannel(cfg config.FeishuConfig, bus *bus.MessageBus) (*FeishuChannel, error) {
return nil, errors.New("feishu channel is not supported on 32-bit architectures (armv7l, 386, etc.). Please use a 64-bit system or disable feishu in your config")
}
// Start is a stub method to satisfy the Channel interface
func (c *FeishuChannel) Start(ctx context.Context) error {
return nil
}
// Stop is a stub method to satisfy the Channel interface
func (c *FeishuChannel) Stop(ctx context.Context) error {
return nil
}
// Send is a stub method to satisfy the Channel interface
func (c *FeishuChannel) Send(ctx context.Context, msg bus.OutboundMessage) error {
return errors.New("feishu channel is not supported on 32-bit architectures")
}

View file

@ -1,3 +1,5 @@
//go:build amd64 || arm64 || riscv64 || mips64 || ppc64
package channels
import (

View file

@ -48,7 +48,7 @@ func (m *Manager) initChannels() error {
if m.config.Channels.Telegram.Enabled && m.config.Channels.Telegram.Token != "" {
logger.DebugC("channels", "Attempting to initialize Telegram channel")
telegram, err := NewTelegramChannel(m.config.Channels.Telegram, m.bus)
telegram, err := NewTelegramChannel(m.config, m.bus)
if err != nil {
logger.ErrorCF("channels", "Failed to initialize Telegram channel", map[string]interface{}{
"error": err.Error(),
@ -163,6 +163,19 @@ func (m *Manager) initChannels() error {
}
}
if m.config.Channels.OneBot.Enabled && m.config.Channels.OneBot.WSUrl != "" {
logger.DebugC("channels", "Attempting to initialize OneBot channel")
onebot, err := NewOneBotChannel(m.config.Channels.OneBot, m.bus)
if err != nil {
logger.ErrorCF("channels", "Failed to initialize OneBot channel", map[string]interface{}{
"error": err.Error(),
})
} else {
m.channels["onebot"] = onebot
logger.InfoC("channels", "OneBot channel enabled successfully")
}
}
logger.InfoCF("channels", "Channel initialization completed", map[string]interface{}{
"enabled_channels": len(m.channels),
})

686
pkg/channels/onebot.go Normal file
View file

@ -0,0 +1,686 @@
package channels
import (
"context"
"encoding/json"
"fmt"
"strconv"
"strings"
"sync"
"time"
"github.com/gorilla/websocket"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/logger"
)
type OneBotChannel struct {
*BaseChannel
config config.OneBotConfig
conn *websocket.Conn
ctx context.Context
cancel context.CancelFunc
dedup map[string]struct{}
dedupRing []string
dedupIdx int
mu sync.Mutex
writeMu sync.Mutex
echoCounter int64
}
type oneBotRawEvent struct {
PostType string `json:"post_type"`
MessageType string `json:"message_type"`
SubType string `json:"sub_type"`
MessageID json.RawMessage `json:"message_id"`
UserID json.RawMessage `json:"user_id"`
GroupID json.RawMessage `json:"group_id"`
RawMessage string `json:"raw_message"`
Message json.RawMessage `json:"message"`
Sender json.RawMessage `json:"sender"`
SelfID json.RawMessage `json:"self_id"`
Time json.RawMessage `json:"time"`
MetaEventType string `json:"meta_event_type"`
Echo string `json:"echo"`
RetCode json.RawMessage `json:"retcode"`
Status BotStatus `json:"status"`
}
type BotStatus struct {
Online bool `json:"online"`
Good bool `json:"good"`
}
type oneBotSender struct {
UserID json.RawMessage `json:"user_id"`
Nickname string `json:"nickname"`
Card string `json:"card"`
}
type oneBotEvent struct {
PostType string
MessageType string
SubType string
MessageID string
UserID int64
GroupID int64
Content string
RawContent string
IsBotMentioned bool
Sender oneBotSender
SelfID int64
Time int64
MetaEventType string
}
type oneBotAPIRequest struct {
Action string `json:"action"`
Params interface{} `json:"params"`
Echo string `json:"echo,omitempty"`
}
type oneBotSendPrivateMsgParams struct {
UserID int64 `json:"user_id"`
Message string `json:"message"`
}
type oneBotSendGroupMsgParams struct {
GroupID int64 `json:"group_id"`
Message string `json:"message"`
}
func NewOneBotChannel(cfg config.OneBotConfig, messageBus *bus.MessageBus) (*OneBotChannel, error) {
base := NewBaseChannel("onebot", cfg, messageBus, cfg.AllowFrom)
const dedupSize = 1024
return &OneBotChannel{
BaseChannel: base,
config: cfg,
dedup: make(map[string]struct{}, dedupSize),
dedupRing: make([]string, dedupSize),
dedupIdx: 0,
}, nil
}
func (c *OneBotChannel) Start(ctx context.Context) error {
if c.config.WSUrl == "" {
return fmt.Errorf("OneBot ws_url not configured")
}
logger.InfoCF("onebot", "Starting OneBot channel", map[string]interface{}{
"ws_url": c.config.WSUrl,
})
c.ctx, c.cancel = context.WithCancel(ctx)
if err := c.connect(); err != nil {
logger.WarnCF("onebot", "Initial connection failed, will retry in background", map[string]interface{}{
"error": err.Error(),
})
} else {
go c.listen()
}
if c.config.ReconnectInterval > 0 {
go c.reconnectLoop()
} else {
// If reconnect is disabled but initial connection failed, we cannot recover
if c.conn == nil {
return fmt.Errorf("failed to connect to OneBot and reconnect is disabled")
}
}
c.setRunning(true)
logger.InfoC("onebot", "OneBot channel started successfully")
return nil
}
func (c *OneBotChannel) connect() error {
dialer := websocket.DefaultDialer
dialer.HandshakeTimeout = 10 * time.Second
header := make(map[string][]string)
if c.config.AccessToken != "" {
header["Authorization"] = []string{"Bearer " + c.config.AccessToken}
}
conn, _, err := dialer.Dial(c.config.WSUrl, header)
if err != nil {
return err
}
c.mu.Lock()
c.conn = conn
c.mu.Unlock()
logger.InfoC("onebot", "WebSocket connected")
return nil
}
func (c *OneBotChannel) reconnectLoop() {
interval := time.Duration(c.config.ReconnectInterval) * time.Second
if interval < 5*time.Second {
interval = 5 * time.Second
}
for {
select {
case <-c.ctx.Done():
return
case <-time.After(interval):
c.mu.Lock()
conn := c.conn
c.mu.Unlock()
if conn == nil {
logger.InfoC("onebot", "Attempting to reconnect...")
if err := c.connect(); err != nil {
logger.ErrorCF("onebot", "Reconnect failed", map[string]interface{}{
"error": err.Error(),
})
} else {
go c.listen()
}
}
}
}
}
func (c *OneBotChannel) Stop(ctx context.Context) error {
logger.InfoC("onebot", "Stopping OneBot channel")
c.setRunning(false)
if c.cancel != nil {
c.cancel()
}
c.mu.Lock()
if c.conn != nil {
c.conn.Close()
c.conn = nil
}
c.mu.Unlock()
return nil
}
func (c *OneBotChannel) Send(ctx context.Context, msg bus.OutboundMessage) error {
if !c.IsRunning() {
return fmt.Errorf("OneBot channel not running")
}
c.mu.Lock()
conn := c.conn
c.mu.Unlock()
if conn == nil {
return fmt.Errorf("OneBot WebSocket not connected")
}
action, params, err := c.buildSendRequest(msg)
if err != nil {
return err
}
c.writeMu.Lock()
c.echoCounter++
echo := fmt.Sprintf("send_%d", c.echoCounter)
c.writeMu.Unlock()
req := oneBotAPIRequest{
Action: action,
Params: params,
Echo: echo,
}
data, err := json.Marshal(req)
if err != nil {
return fmt.Errorf("failed to marshal OneBot request: %w", err)
}
c.writeMu.Lock()
err = conn.WriteMessage(websocket.TextMessage, data)
c.writeMu.Unlock()
if err != nil {
logger.ErrorCF("onebot", "Failed to send message", map[string]interface{}{
"error": err.Error(),
})
return err
}
return nil
}
func (c *OneBotChannel) buildSendRequest(msg bus.OutboundMessage) (string, interface{}, error) {
chatID := msg.ChatID
if len(chatID) > 6 && chatID[:6] == "group:" {
groupID, err := strconv.ParseInt(chatID[6:], 10, 64)
if err != nil {
return "", nil, fmt.Errorf("invalid group ID in chatID: %s", chatID)
}
return "send_group_msg", oneBotSendGroupMsgParams{
GroupID: groupID,
Message: msg.Content,
}, nil
}
if len(chatID) > 8 && chatID[:8] == "private:" {
userID, err := strconv.ParseInt(chatID[8:], 10, 64)
if err != nil {
return "", nil, fmt.Errorf("invalid user ID in chatID: %s", chatID)
}
return "send_private_msg", oneBotSendPrivateMsgParams{
UserID: userID,
Message: msg.Content,
}, nil
}
userID, err := strconv.ParseInt(chatID, 10, 64)
if err != nil {
return "", nil, fmt.Errorf("invalid chatID for OneBot: %s", chatID)
}
return "send_private_msg", oneBotSendPrivateMsgParams{
UserID: userID,
Message: msg.Content,
}, nil
}
func (c *OneBotChannel) listen() {
for {
select {
case <-c.ctx.Done():
return
default:
c.mu.Lock()
conn := c.conn
c.mu.Unlock()
if conn == nil {
logger.WarnC("onebot", "WebSocket connection is nil, listener exiting")
return
}
_, message, err := conn.ReadMessage()
if err != nil {
logger.ErrorCF("onebot", "WebSocket read error", map[string]interface{}{
"error": err.Error(),
})
c.mu.Lock()
if c.conn != nil {
c.conn.Close()
c.conn = nil
}
c.mu.Unlock()
return
}
logger.DebugCF("onebot", "Raw WebSocket message received", map[string]interface{}{
"length": len(message),
"payload": string(message),
})
var raw oneBotRawEvent
if err := json.Unmarshal(message, &raw); err != nil {
logger.WarnCF("onebot", "Failed to unmarshal raw event", map[string]interface{}{
"error": err.Error(),
"payload": string(message),
})
continue
}
if raw.Echo != "" || raw.Status.Online || raw.Status.Good {
logger.DebugCF("onebot", "Received API response, skipping", map[string]interface{}{
"echo": raw.Echo,
"status": raw.Status,
})
continue
}
logger.DebugCF("onebot", "Parsed raw event", map[string]interface{}{
"post_type": raw.PostType,
"message_type": raw.MessageType,
"sub_type": raw.SubType,
"meta_event_type": raw.MetaEventType,
})
c.handleRawEvent(&raw)
}
}
}
func parseJSONInt64(raw json.RawMessage) (int64, error) {
if len(raw) == 0 {
return 0, nil
}
var n int64
if err := json.Unmarshal(raw, &n); err == nil {
return n, nil
}
var s string
if err := json.Unmarshal(raw, &s); err == nil {
return strconv.ParseInt(s, 10, 64)
}
return 0, fmt.Errorf("cannot parse as int64: %s", string(raw))
}
func parseJSONString(raw json.RawMessage) string {
if len(raw) == 0 {
return ""
}
var s string
if err := json.Unmarshal(raw, &s); err == nil {
return s
}
return string(raw)
}
type parseMessageResult struct {
Text string
IsBotMentioned bool
}
func parseMessageContentEx(raw json.RawMessage, selfID int64) parseMessageResult {
if len(raw) == 0 {
return parseMessageResult{}
}
var s string
if err := json.Unmarshal(raw, &s); err == nil {
mentioned := false
if selfID > 0 {
cqAt := fmt.Sprintf("[CQ:at,qq=%d]", selfID)
if strings.Contains(s, cqAt) {
mentioned = true
s = strings.ReplaceAll(s, cqAt, "")
s = strings.TrimSpace(s)
}
}
return parseMessageResult{Text: s, IsBotMentioned: mentioned}
}
var segments []map[string]interface{}
if err := json.Unmarshal(raw, &segments); err == nil {
var text string
mentioned := false
selfIDStr := strconv.FormatInt(selfID, 10)
for _, seg := range segments {
segType, _ := seg["type"].(string)
data, _ := seg["data"].(map[string]interface{})
switch segType {
case "text":
if data != nil {
if t, ok := data["text"].(string); ok {
text += t
}
}
case "at":
if data != nil && selfID > 0 {
qqVal := fmt.Sprintf("%v", data["qq"])
if qqVal == selfIDStr || qqVal == "all" {
mentioned = true
}
}
}
}
return parseMessageResult{Text: strings.TrimSpace(text), IsBotMentioned: mentioned}
}
return parseMessageResult{}
}
func (c *OneBotChannel) handleRawEvent(raw *oneBotRawEvent) {
switch raw.PostType {
case "message":
evt, err := c.normalizeMessageEvent(raw)
if err != nil {
logger.WarnCF("onebot", "Failed to normalize message event", map[string]interface{}{
"error": err.Error(),
})
return
}
c.handleMessage(evt)
case "meta_event":
c.handleMetaEvent(raw)
case "notice":
logger.DebugCF("onebot", "Notice event received", map[string]interface{}{
"sub_type": raw.SubType,
})
case "request":
logger.DebugCF("onebot", "Request event received", map[string]interface{}{
"sub_type": raw.SubType,
})
case "":
logger.DebugCF("onebot", "Event with empty post_type (possibly API response)", map[string]interface{}{
"echo": raw.Echo,
"status": raw.Status,
})
default:
logger.DebugCF("onebot", "Unknown post_type", map[string]interface{}{
"post_type": raw.PostType,
})
}
}
func (c *OneBotChannel) normalizeMessageEvent(raw *oneBotRawEvent) (*oneBotEvent, error) {
userID, err := parseJSONInt64(raw.UserID)
if err != nil {
return nil, fmt.Errorf("parse user_id: %w (raw: %s)", err, string(raw.UserID))
}
groupID, _ := parseJSONInt64(raw.GroupID)
selfID, _ := parseJSONInt64(raw.SelfID)
ts, _ := parseJSONInt64(raw.Time)
messageID := parseJSONString(raw.MessageID)
parsed := parseMessageContentEx(raw.Message, selfID)
isBotMentioned := parsed.IsBotMentioned
content := raw.RawMessage
if content == "" {
content = parsed.Text
} else if selfID > 0 {
cqAt := fmt.Sprintf("[CQ:at,qq=%d]", selfID)
if strings.Contains(content, cqAt) {
isBotMentioned = true
content = strings.ReplaceAll(content, cqAt, "")
content = strings.TrimSpace(content)
}
}
var sender oneBotSender
if len(raw.Sender) > 0 {
if err := json.Unmarshal(raw.Sender, &sender); err != nil {
logger.WarnCF("onebot", "Failed to parse sender", map[string]interface{}{
"error": err.Error(),
"sender": string(raw.Sender),
})
}
}
logger.DebugCF("onebot", "Normalized message event", map[string]interface{}{
"message_type": raw.MessageType,
"user_id": userID,
"group_id": groupID,
"message_id": messageID,
"content_len": len(content),
"nickname": sender.Nickname,
})
return &oneBotEvent{
PostType: raw.PostType,
MessageType: raw.MessageType,
SubType: raw.SubType,
MessageID: messageID,
UserID: userID,
GroupID: groupID,
Content: content,
RawContent: raw.RawMessage,
IsBotMentioned: isBotMentioned,
Sender: sender,
SelfID: selfID,
Time: ts,
MetaEventType: raw.MetaEventType,
}, nil
}
func (c *OneBotChannel) handleMetaEvent(raw *oneBotRawEvent) {
switch raw.MetaEventType {
case "lifecycle":
logger.InfoCF("onebot", "Lifecycle event", map[string]interface{}{
"sub_type": raw.SubType,
})
case "heartbeat":
logger.DebugC("onebot", "Heartbeat received")
default:
logger.DebugCF("onebot", "Unknown meta_event_type", map[string]interface{}{
"meta_event_type": raw.MetaEventType,
})
}
}
func (c *OneBotChannel) handleMessage(evt *oneBotEvent) {
if c.isDuplicate(evt.MessageID) {
logger.DebugCF("onebot", "Duplicate message, skipping", map[string]interface{}{
"message_id": evt.MessageID,
})
return
}
content := evt.Content
if content == "" {
logger.DebugCF("onebot", "Received empty message, ignoring", map[string]interface{}{
"message_id": evt.MessageID,
})
return
}
senderID := strconv.FormatInt(evt.UserID, 10)
var chatID string
metadata := map[string]string{
"message_id": evt.MessageID,
}
switch evt.MessageType {
case "private":
chatID = "private:" + senderID
logger.InfoCF("onebot", "Received private message", map[string]interface{}{
"sender": senderID,
"message_id": evt.MessageID,
"length": len(content),
"content": truncate(content, 100),
})
case "group":
groupIDStr := strconv.FormatInt(evt.GroupID, 10)
chatID = "group:" + groupIDStr
metadata["group_id"] = groupIDStr
senderUserID, _ := parseJSONInt64(evt.Sender.UserID)
if senderUserID > 0 {
metadata["sender_user_id"] = strconv.FormatInt(senderUserID, 10)
}
if evt.Sender.Card != "" {
metadata["sender_name"] = evt.Sender.Card
} else if evt.Sender.Nickname != "" {
metadata["sender_name"] = evt.Sender.Nickname
}
triggered, strippedContent := c.checkGroupTrigger(content, evt.IsBotMentioned)
if !triggered {
logger.DebugCF("onebot", "Group message ignored (no trigger)", map[string]interface{}{
"sender": senderID,
"group": groupIDStr,
"is_mentioned": evt.IsBotMentioned,
"content": truncate(content, 100),
})
return
}
content = strippedContent
logger.InfoCF("onebot", "Received group message", map[string]interface{}{
"sender": senderID,
"group": groupIDStr,
"message_id": evt.MessageID,
"is_mentioned": evt.IsBotMentioned,
"length": len(content),
"content": truncate(content, 100),
})
default:
logger.WarnCF("onebot", "Unknown message type, cannot route", map[string]interface{}{
"type": evt.MessageType,
"message_id": evt.MessageID,
"user_id": evt.UserID,
})
return
}
if evt.Sender.Nickname != "" {
metadata["nickname"] = evt.Sender.Nickname
}
logger.DebugCF("onebot", "Forwarding message to bus", map[string]interface{}{
"sender_id": senderID,
"chat_id": chatID,
"content": truncate(content, 100),
})
c.HandleMessage(senderID, chatID, content, []string{}, metadata)
}
func (c *OneBotChannel) isDuplicate(messageID string) bool {
if messageID == "" || messageID == "0" {
return false
}
c.mu.Lock()
defer c.mu.Unlock()
if _, exists := c.dedup[messageID]; exists {
return true
}
if old := c.dedupRing[c.dedupIdx]; old != "" {
delete(c.dedup, old)
}
c.dedupRing[c.dedupIdx] = messageID
c.dedup[messageID] = struct{}{}
c.dedupIdx = (c.dedupIdx + 1) % len(c.dedupRing)
return false
}
func truncate(s string, n int) string {
runes := []rune(s)
if len(runes) <= n {
return s
}
return string(runes[:n]) + "..."
}
func (c *OneBotChannel) checkGroupTrigger(content string, isBotMentioned bool) (triggered bool, strippedContent string) {
if isBotMentioned {
return true, strings.TrimSpace(content)
}
for _, prefix := range c.config.GroupTriggerPrefix {
if prefix == "" {
continue
}
if strings.HasPrefix(content, prefix) {
return true, strings.TrimSpace(strings.TrimPrefix(content, prefix))
}
}
return false, content
}

View file

@ -296,6 +296,13 @@ func (c *SlackChannel) handleAppMention(ev *slackevents.AppMentionEvent) {
return
}
if !c.IsAllowed(ev.User) {
logger.DebugCF("slack", "Mention rejected by allowlist", map[string]interface{}{
"user_id": ev.User,
})
return
}
senderID := ev.User
channelID := ev.Channel
threadTS := ev.ThreadTimeStamp
@ -345,6 +352,13 @@ func (c *SlackChannel) handleSlashCommand(event socketmode.Event) {
c.socketClient.Ack(*event.Request)
}
if !c.IsAllowed(cmd.UserID) {
logger.DebugCF("slack", "Slash command rejected by allowlist", map[string]interface{}{
"user_id": cmd.UserID,
})
return
}
senderID := cmd.UserID
channelID := cmd.ChannelID
chatID := channelID

View file

@ -11,7 +11,10 @@ import (
"sync"
"time"
th "github.com/mymmrac/telego/telegohandler"
"github.com/mymmrac/telego"
"github.com/mymmrac/telego/telegohandler"
tu "github.com/mymmrac/telego/telegoutil"
"github.com/sipeed/picoclaw/pkg/bus"
@ -24,7 +27,8 @@ import (
type TelegramChannel struct {
*BaseChannel
bot *telego.Bot
config config.TelegramConfig
commands TelegramCommander
config *config.Config
chatIDs map[string]int64
transcriber *voice.GroqTranscriber
placeholders sync.Map // chatID -> messageID
@ -41,13 +45,14 @@ func (c *thinkingCancel) Cancel() {
}
}
func NewTelegramChannel(cfg config.TelegramConfig, bus *bus.MessageBus) (*TelegramChannel, error) {
func NewTelegramChannel(cfg *config.Config, bus *bus.MessageBus) (*TelegramChannel, error) {
var opts []telego.BotOption
telegramCfg := cfg.Channels.Telegram
if cfg.Proxy != "" {
proxyURL, parseErr := url.Parse(cfg.Proxy)
if telegramCfg.Proxy != "" {
proxyURL, parseErr := url.Parse(telegramCfg.Proxy)
if parseErr != nil {
return nil, fmt.Errorf("invalid proxy URL %q: %w", cfg.Proxy, parseErr)
return nil, fmt.Errorf("invalid proxy URL %q: %w", telegramCfg.Proxy, parseErr)
}
opts = append(opts, telego.WithHTTPClient(&http.Client{
Transport: &http.Transport{
@ -56,15 +61,16 @@ func NewTelegramChannel(cfg config.TelegramConfig, bus *bus.MessageBus) (*Telegr
}))
}
bot, err := telego.NewBot(cfg.Token, opts...)
bot, err := telego.NewBot(telegramCfg.Token, opts...)
if err != nil {
return nil, fmt.Errorf("failed to create telegram bot: %w", err)
}
base := NewBaseChannel("telegram", cfg, bus, cfg.AllowFrom)
base := NewBaseChannel("telegram", telegramCfg, bus, telegramCfg.AllowFrom)
return &TelegramChannel{
BaseChannel: base,
commands: NewTelegramCommands(bot, cfg),
bot: bot,
config: cfg,
chatIDs: make(map[string]int64),
@ -88,31 +94,45 @@ func (c *TelegramChannel) Start(ctx context.Context) error {
return fmt.Errorf("failed to start long polling: %w", err)
}
bh, err := telegohandler.NewBotHandler(c.bot, updates)
if err != nil {
return fmt.Errorf("failed to create bot handler: %w", err)
}
bh.HandleMessage(func(ctx *th.Context, message telego.Message) error {
c.commands.Help(ctx, message)
return nil
}, th.CommandEqual("help"))
bh.HandleMessage(func(ctx *th.Context, message telego.Message) error {
return c.commands.Start(ctx, message)
}, th.CommandEqual("start"))
bh.HandleMessage(func(ctx *th.Context, message telego.Message) error {
return c.commands.Show(ctx, message)
}, th.CommandEqual("show"))
bh.HandleMessage(func(ctx *th.Context, message telego.Message) error {
return c.commands.List(ctx, message)
}, th.CommandEqual("list"))
bh.HandleMessage(func(ctx *th.Context, message telego.Message) error {
return c.handleMessage(ctx, &message)
}, th.AnyMessage())
c.setRunning(true)
logger.InfoCF("telegram", "Telegram bot connected", map[string]interface{}{
"username": c.bot.Username(),
})
go bh.Start()
go func() {
for {
select {
case <-ctx.Done():
return
case update, ok := <-updates:
if !ok {
logger.InfoC("telegram", "Updates channel closed, reconnecting...")
return
}
if update.Message != nil {
c.handleMessage(ctx, update)
}
}
}
<-ctx.Done()
bh.Stop()
}()
return nil
}
func (c *TelegramChannel) Stop(ctx context.Context) error {
logger.InfoC("telegram", "Stopping Telegram bot...")
c.setRunning(false)
@ -166,30 +186,27 @@ func (c *TelegramChannel) Send(ctx context.Context, msg bus.OutboundMessage) err
return nil
}
func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Update) {
message := update.Message
func (c *TelegramChannel) handleMessage(ctx context.Context, message *telego.Message) error {
if message == nil {
return
return fmt.Errorf("message is nil")
}
user := message.From
if user == nil {
return
return fmt.Errorf("message sender (user) is nil")
}
userID := fmt.Sprintf("%d", user.ID)
senderID := userID
senderID := fmt.Sprintf("%d", user.ID)
if user.Username != "" {
senderID = fmt.Sprintf("%s|%s", userID, user.Username)
senderID = fmt.Sprintf("%d|%s", user.ID, user.Username)
}
// 检查白名单,避免为被拒绝的用户下载附件
if !c.IsAllowed(userID) && !c.IsAllowed(senderID) {
if !c.IsAllowed(senderID) {
logger.DebugCF("telegram", "Message rejected by allowlist", map[string]interface{}{
"user_id": userID,
"username": user.Username,
"user_id": senderID,
})
return
return nil
}
chatID := message.Chat.ID
@ -222,7 +239,7 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
content += message.Caption
}
if message.Photo != nil && len(message.Photo) > 0 {
if len(message.Photo) > 0 {
photo := message.Photo[len(message.Photo)-1]
photoPath := c.downloadPhoto(ctx, photo.FileID)
if photoPath != "" {
@ -231,7 +248,7 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
if content != "" {
content += "\n"
}
content += fmt.Sprintf("[image: photo]")
content += "[image: photo]"
}
}
@ -252,7 +269,7 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
"error": err.Error(),
"path": voicePath,
})
transcribedText = fmt.Sprintf("[voice (transcription failed)]")
transcribedText = "[voice (transcription failed)]"
} else {
transcribedText = fmt.Sprintf("[voice transcription: %s]", result.Text)
logger.InfoCF("telegram", "Voice transcribed successfully", map[string]interface{}{
@ -260,7 +277,7 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
})
}
} else {
transcribedText = fmt.Sprintf("[voice]")
transcribedText = "[voice]"
}
if content != "" {
@ -278,7 +295,7 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
if content != "" {
content += "\n"
}
content += fmt.Sprintf("[audio]")
content += "[audio]"
}
}
@ -290,7 +307,7 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
if content != "" {
content += "\n"
}
content += fmt.Sprintf("[file]")
content += "[file]"
}
}
@ -320,37 +337,14 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
}
}
// Create new context for thinking animation with timeout
thinkCtx, thinkCancel := context.WithTimeout(ctx, 5*time.Minute)
// Create cancel function for thinking state
_, thinkCancel := context.WithTimeout(ctx, 5*time.Minute)
c.stopThinking.Store(chatIDStr, &thinkingCancel{fn: thinkCancel})
pMsg, err := c.bot.SendMessage(ctx, tu.Message(tu.ID(chatID), "Thinking... 💭"))
if err == nil {
pID := pMsg.MessageID
c.placeholders.Store(chatIDStr, pID)
go func(cid int64, mid int) {
dots := []string{".", "..", "..."}
emotes := []string{"💭", "🤔", "☁️"}
i := 0
ticker := time.NewTicker(2000 * time.Millisecond)
defer ticker.Stop()
for {
select {
case <-thinkCtx.Done():
return
case <-ticker.C:
i++
text := fmt.Sprintf("Thinking%s %s", dots[i%len(dots)], emotes[i%len(emotes)])
_, editErr := c.bot.EditMessageText(thinkCtx, tu.EditMessageText(tu.ID(chatID), mid, text))
if editErr != nil {
logger.DebugCF("telegram", "Failed to edit thinking message", map[string]interface{}{
"error": editErr.Error(),
})
}
}
}
}(chatID, pID)
}
metadata := map[string]string{
@ -361,7 +355,8 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
"is_group": fmt.Sprintf("%t", message.Chat.Type != "private"),
}
c.HandleMessage(senderID, fmt.Sprintf("%d", chatID), content, mediaPaths, metadata)
c.HandleMessage(fmt.Sprintf("%d", user.ID), fmt.Sprintf("%d", chatID), content, mediaPaths, metadata)
return nil
}
func (c *TelegramChannel) downloadPhoto(ctx context.Context, fileID string) string {

View file

@ -0,0 +1,153 @@
package channels
import (
"context"
"fmt"
"strings"
"github.com/mymmrac/telego"
"github.com/sipeed/picoclaw/pkg/config"
)
type TelegramCommander interface {
Help(ctx context.Context, message telego.Message) error
Start(ctx context.Context, message telego.Message) error
Show(ctx context.Context, message telego.Message) error
List(ctx context.Context, message telego.Message) error
}
type cmd struct {
bot *telego.Bot
config *config.Config
}
func NewTelegramCommands(bot *telego.Bot, cfg *config.Config) TelegramCommander {
return &cmd{
bot: bot,
config: cfg,
}
}
func commandArgs(text string) string {
parts := strings.SplitN(text, " ", 2)
if len(parts) < 2 {
return ""
}
return strings.TrimSpace(parts[1])
}
func (c *cmd) Help(ctx context.Context, message telego.Message) error {
msg := `/start - Start the bot
/help - Show this help message
/show [model|channel] - Show current configuration
/list [models|channels] - List available options
`
_, err := c.bot.SendMessage(ctx, &telego.SendMessageParams{
ChatID: telego.ChatID{ID: message.Chat.ID},
Text: msg,
ReplyParameters: &telego.ReplyParameters{
MessageID: message.MessageID,
},
})
return err
}
func (c *cmd) Start(ctx context.Context, message telego.Message) error {
_, err := c.bot.SendMessage(ctx, &telego.SendMessageParams{
ChatID: telego.ChatID{ID: message.Chat.ID},
Text: "Hello! I am PicoClaw 🦞",
ReplyParameters: &telego.ReplyParameters{
MessageID: message.MessageID,
},
})
return err
}
func (c *cmd) Show(ctx context.Context, message telego.Message) error {
args := commandArgs(message.Text)
if args == "" {
_, err := c.bot.SendMessage(ctx, &telego.SendMessageParams{
ChatID: telego.ChatID{ID: message.Chat.ID},
Text: "Usage: /show [model|channel]",
ReplyParameters: &telego.ReplyParameters{
MessageID: message.MessageID,
},
})
return err
}
var response string
switch args {
case "model":
response = fmt.Sprintf("Current Model: %s (Provider: %s)",
c.config.Agents.Defaults.Model,
c.config.Agents.Defaults.Provider)
case "channel":
response = "Current Channel: telegram"
default:
response = fmt.Sprintf("Unknown parameter: %s. Try 'model' or 'channel'.", args)
}
_, err := c.bot.SendMessage(ctx, &telego.SendMessageParams{
ChatID: telego.ChatID{ID: message.Chat.ID},
Text: response,
ReplyParameters: &telego.ReplyParameters{
MessageID: message.MessageID,
},
})
return err
}
func (c *cmd) List(ctx context.Context, message telego.Message) error {
args := commandArgs(message.Text)
if args == "" {
_, err := c.bot.SendMessage(ctx, &telego.SendMessageParams{
ChatID: telego.ChatID{ID: message.Chat.ID},
Text: "Usage: /list [models|channels]",
ReplyParameters: &telego.ReplyParameters{
MessageID: message.MessageID,
},
})
return err
}
var response string
switch args {
case "models":
provider := c.config.Agents.Defaults.Provider
if provider == "" {
provider = "configured default"
}
response = fmt.Sprintf("Configured Model: %s\nProvider: %s\n\nTo change models, update config.yaml",
c.config.Agents.Defaults.Model, provider)
case "channels":
var enabled []string
if c.config.Channels.Telegram.Enabled {
enabled = append(enabled, "telegram")
}
if c.config.Channels.WhatsApp.Enabled {
enabled = append(enabled, "whatsapp")
}
if c.config.Channels.Feishu.Enabled {
enabled = append(enabled, "feishu")
}
if c.config.Channels.Discord.Enabled {
enabled = append(enabled, "discord")
}
if c.config.Channels.Slack.Enabled {
enabled = append(enabled, "slack")
}
response = fmt.Sprintf("Enabled Channels:\n- %s", strings.Join(enabled, "\n- "))
default:
response = fmt.Sprintf("Unknown parameter: %s. Try 'models' or 'channels'.", args)
}
_, err := c.bot.SendMessage(ctx, &telego.SendMessageParams{
ChatID: telego.ChatID{ID: message.Chat.ID},
Text: response,
ReplyParameters: &telego.ReplyParameters{
MessageID: message.MessageID,
},
})
return err
}

View file

@ -50,6 +50,7 @@ type Config struct {
Gateway GatewayConfig `json:"gateway"`
Tools ToolsConfig `json:"tools"`
Heartbeat HeartbeatConfig `json:"heartbeat"`
Devices DevicesConfig `json:"devices"`
mu sync.RWMutex
}
@ -77,6 +78,7 @@ type ChannelsConfig struct {
DingTalk DingTalkConfig `json:"dingtalk"`
Slack SlackConfig `json:"slack"`
LINE LINEConfig `json:"line"`
OneBot OneBotConfig `json:"onebot"`
}
type WhatsAppConfig struct {
@ -132,7 +134,7 @@ type SlackConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_CHANNELS_SLACK_ENABLED"`
BotToken string `json:"bot_token" env:"PICOCLAW_CHANNELS_SLACK_BOT_TOKEN"`
AppToken string `json:"app_token" env:"PICOCLAW_CHANNELS_SLACK_APP_TOKEN"`
AllowFrom []string `json:"allow_from" env:"PICOCLAW_CHANNELS_SLACK_ALLOW_FROM"`
AllowFrom FlexibleStringSlice `json:"allow_from" env:"PICOCLAW_CHANNELS_SLACK_ALLOW_FROM"`
}
type LINEConfig struct {
@ -145,11 +147,25 @@ type LINEConfig struct {
AllowFrom FlexibleStringSlice `json:"allow_from" env:"PICOCLAW_CHANNELS_LINE_ALLOW_FROM"`
}
type OneBotConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_CHANNELS_ONEBOT_ENABLED"`
WSUrl string `json:"ws_url" env:"PICOCLAW_CHANNELS_ONEBOT_WS_URL"`
AccessToken string `json:"access_token" env:"PICOCLAW_CHANNELS_ONEBOT_ACCESS_TOKEN"`
ReconnectInterval int `json:"reconnect_interval" env:"PICOCLAW_CHANNELS_ONEBOT_RECONNECT_INTERVAL"`
GroupTriggerPrefix []string `json:"group_trigger_prefix" env:"PICOCLAW_CHANNELS_ONEBOT_GROUP_TRIGGER_PREFIX"`
AllowFrom FlexibleStringSlice `json:"allow_from" env:"PICOCLAW_CHANNELS_ONEBOT_ALLOW_FROM"`
}
type HeartbeatConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_HEARTBEAT_ENABLED"`
Interval int `json:"interval" env:"PICOCLAW_HEARTBEAT_INTERVAL"` // minutes, min 5
}
type DevicesConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_DEVICES_ENABLED"`
MonitorUSB bool `json:"monitor_usb" env:"PICOCLAW_DEVICES_MONITOR_USB"`
}
type ProvidersConfig struct {
Anthropic ProviderConfig `json:"anthropic"`
OpenAI ProviderConfig `json:"openai"`
@ -159,8 +175,11 @@ type ProvidersConfig struct {
VLLM ProviderConfig `json:"vllm"`
Gemini ProviderConfig `json:"gemini"`
Nvidia ProviderConfig `json:"nvidia"`
Ollama ProviderConfig `json:"ollama"`
Moonshot ProviderConfig `json:"moonshot"`
ShengSuanYun ProviderConfig `json:"shengsuanyun"`
DeepSeek ProviderConfig `json:"deepseek"`
GitHubCopilot ProviderConfig `json:"github_copilot"`
}
type ProviderConfig struct {
@ -168,6 +187,7 @@ type ProviderConfig struct {
APIBase string `json:"api_base" env:"PICOCLAW_PROVIDERS_{{.Name}}_API_BASE"`
Proxy string `json:"proxy,omitempty" env:"PICOCLAW_PROVIDERS_{{.Name}}_PROXY"`
AuthMethod string `json:"auth_method,omitempty" env:"PICOCLAW_PROVIDERS_{{.Name}}_AUTH_METHOD"`
ConnectMode string `json:"connect_mode,omitempty" env:"PICOCLAW_PROVIDERS_{{.Name}}_CONNECT_MODE"` //only for Github Copilot, `stdio` or `grpc`
}
type GatewayConfig struct {
@ -254,7 +274,7 @@ func DefaultConfig() *Config {
Enabled: false,
BotToken: "",
AppToken: "",
AllowFrom: []string{},
AllowFrom: FlexibleStringSlice{},
},
LINE: LINEConfig{
Enabled: false,
@ -265,6 +285,14 @@ func DefaultConfig() *Config {
WebhookPath: "/webhook/line",
AllowFrom: FlexibleStringSlice{},
},
OneBot: OneBotConfig{
Enabled: false,
WSUrl: "ws://127.0.0.1:3001",
AccessToken: "",
ReconnectInterval: 5,
GroupTriggerPrefix: []string{},
AllowFrom: FlexibleStringSlice{},
},
},
Providers: ProvidersConfig{
Anthropic: ProviderConfig{},
@ -299,6 +327,10 @@ func DefaultConfig() *Config {
Enabled: true,
Interval: 30, // default 30 minutes
},
Devices: DevicesConfig{
Enabled: false,
MonitorUSB: true,
},
}
}
@ -338,7 +370,7 @@ func SaveConfig(path string, cfg *Config) error {
return err
}
return os.WriteFile(path, data, 0644)
return os.WriteFile(path, data, 0600)
}
func (c *Config) WorkspacePath() string {

View file

@ -1,6 +1,9 @@
package config
import (
"os"
"path/filepath"
"runtime"
"testing"
)
@ -147,6 +150,30 @@ func TestDefaultConfig_WebTools(t *testing.T) {
}
}
func TestSaveConfig_FilePermissions(t *testing.T) {
if runtime.GOOS == "windows" {
t.Skip("file permission bits are not enforced on Windows")
}
tmpDir := t.TempDir()
path := filepath.Join(tmpDir, "config.json")
cfg := DefaultConfig()
if err := SaveConfig(path, cfg); err != nil {
t.Fatalf("SaveConfig failed: %v", err)
}
info, err := os.Stat(path)
if err != nil {
t.Fatalf("Stat failed: %v", err)
}
perm := info.Mode().Perm()
if perm != 0600 {
t.Errorf("config file has permission %04o, want 0600", perm)
}
}
// TestConfig_Complete verifies all config fields are set
func TestConfig_Complete(t *testing.T) {
cfg := DefaultConfig()

View file

@ -340,7 +340,7 @@ func (cs *CronService) saveStoreUnsafe() error {
return err
}
return os.WriteFile(cs.storePath, data, 0644)
return os.WriteFile(cs.storePath, data, 0600)
}
func (cs *CronService) AddJob(name string, schedule CronSchedule, message string, deliver bool, channel, to string) (*CronJob, error) {

38
pkg/cron/service_test.go Normal file
View file

@ -0,0 +1,38 @@
package cron
import (
"os"
"path/filepath"
"runtime"
"testing"
)
func TestSaveStore_FilePermissions(t *testing.T) {
if runtime.GOOS == "windows" {
t.Skip("file permission bits are not enforced on Windows")
}
tmpDir := t.TempDir()
storePath := filepath.Join(tmpDir, "cron", "jobs.json")
cs := NewCronService(storePath, nil)
_, err := cs.AddJob("test", CronSchedule{Kind: "every", EveryMS: int64Ptr(60000)}, "hello", false, "cli", "direct")
if err != nil {
t.Fatalf("AddJob failed: %v", err)
}
info, err := os.Stat(storePath)
if err != nil {
t.Fatalf("Stat failed: %v", err)
}
perm := info.Mode().Perm()
if perm != 0600 {
t.Errorf("cron store has permission %04o, want 0600", perm)
}
}
func int64Ptr(v int64) *int64 {
return &v
}

View file

@ -0,0 +1,57 @@
package events
import "context"
type EventSource interface {
Kind() Kind
Start(ctx context.Context) (<-chan *DeviceEvent, error)
Stop() error
}
type Action string
const (
ActionAdd Action = "add"
ActionRemove Action = "remove"
ActionChange Action = "change"
)
type Kind string
const (
KindUSB Kind = "usb"
KindBluetooth Kind = "bluetooth"
KindPCI Kind = "pci"
KindGeneric Kind = "generic"
)
type DeviceEvent struct {
Action Action
Kind Kind
DeviceID string // e.g. "1-2" for USB bus 1 dev 2
Vendor string // Vendor name or ID
Product string // Product name or ID
Serial string // Serial number if available
Capabilities string // Human-readable capability description
Raw map[string]string // Raw properties for extensibility
}
func (e *DeviceEvent) FormatMessage() string {
actionEmoji := "🔌"
actionText := "Connected"
if e.Action == ActionRemove {
actionEmoji = "🔌"
actionText = "Disconnected"
}
msg := actionEmoji + " Device " + actionText + "\n\n"
msg += "Type: " + string(e.Kind) + "\n"
msg += "Device: " + e.Vendor + " " + e.Product + "\n"
if e.Capabilities != "" {
msg += "Capabilities: " + e.Capabilities + "\n"
}
if e.Serial != "" {
msg += "Serial: " + e.Serial + "\n"
}
return msg
}

152
pkg/devices/service.go Normal file
View file

@ -0,0 +1,152 @@
package devices
import (
"context"
"strings"
"sync"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/constants"
"github.com/sipeed/picoclaw/pkg/devices/events"
"github.com/sipeed/picoclaw/pkg/devices/sources"
"github.com/sipeed/picoclaw/pkg/logger"
"github.com/sipeed/picoclaw/pkg/state"
)
type Service struct {
bus *bus.MessageBus
state *state.Manager
sources []events.EventSource
enabled bool
ctx context.Context
cancel context.CancelFunc
mu sync.RWMutex
}
type Config struct {
Enabled bool
MonitorUSB bool // When true, monitor USB hotplug (Linux only)
// Future: MonitorBluetooth, MonitorPCI, etc.
}
func NewService(cfg Config, stateMgr *state.Manager) *Service {
s := &Service{
state: stateMgr,
enabled: cfg.Enabled,
sources: make([]EventSource, 0),
}
if cfg.Enabled && cfg.MonitorUSB {
s.sources = append(s.sources, sources.NewUSBMonitor())
}
return s
}
func (s *Service) SetBus(msgBus *bus.MessageBus) {
s.mu.Lock()
defer s.mu.Unlock()
s.bus = msgBus
}
func (s *Service) Start(ctx context.Context) error {
s.mu.Lock()
defer s.mu.Unlock()
if !s.enabled || len(s.sources) == 0 {
logger.InfoC("devices", "Device event service disabled or no sources")
return nil
}
s.ctx, s.cancel = context.WithCancel(ctx)
for _, src := range s.sources {
eventCh, err := src.Start(s.ctx)
if err != nil {
logger.ErrorCF("devices", "Failed to start source", map[string]interface{}{
"kind": src.Kind(),
"error": err.Error(),
})
continue
}
go s.handleEvents(src.Kind(), eventCh)
logger.InfoCF("devices", "Device source started", map[string]interface{}{
"kind": src.Kind(),
})
}
logger.InfoC("devices", "Device event service started")
return nil
}
func (s *Service) Stop() {
s.mu.Lock()
defer s.mu.Unlock()
if s.cancel != nil {
s.cancel()
s.cancel = nil
}
for _, src := range s.sources {
src.Stop()
}
logger.InfoC("devices", "Device event service stopped")
}
func (s *Service) handleEvents(kind events.Kind, eventCh <-chan *events.DeviceEvent) {
for ev := range eventCh {
if ev == nil {
continue
}
s.sendNotification(ev)
}
}
func (s *Service) sendNotification(ev *events.DeviceEvent) {
s.mu.RLock()
msgBus := s.bus
s.mu.RUnlock()
if msgBus == nil {
return
}
lastChannel := s.state.GetLastChannel()
if lastChannel == "" {
logger.DebugCF("devices", "No last channel, skipping notification", map[string]interface{}{
"event": ev.FormatMessage(),
})
return
}
platform, userID := parseLastChannel(lastChannel)
if platform == "" || userID == "" || constants.IsInternalChannel(platform) {
return
}
msg := ev.FormatMessage()
msgBus.PublishOutbound(bus.OutboundMessage{
Channel: platform,
ChatID: userID,
Content: msg,
})
logger.InfoCF("devices", "Device notification sent", map[string]interface{}{
"kind": ev.Kind,
"action": ev.Action,
"to": platform,
})
}
func parseLastChannel(lastChannel string) (platform, userID string) {
if lastChannel == "" {
return "", ""
}
parts := strings.SplitN(lastChannel, ":", 2)
if len(parts) != 2 || parts[0] == "" || parts[1] == "" {
return "", ""
}
return parts[0], parts[1]
}

5
pkg/devices/source.go Normal file
View file

@ -0,0 +1,5 @@
package devices
import "github.com/sipeed/picoclaw/pkg/devices/events"
type EventSource = events.EventSource

View file

@ -0,0 +1,198 @@
//go:build linux
package sources
import (
"bufio"
"context"
"fmt"
"os/exec"
"strings"
"sync"
"github.com/sipeed/picoclaw/pkg/devices/events"
"github.com/sipeed/picoclaw/pkg/logger"
)
var usbClassToCapability = map[string]string{
"00": "Interface Definition (by interface)",
"01": "Audio",
"02": "CDC Communication (Network Card/Modem)",
"03": "HID (Keyboard/Mouse/Gamepad)",
"05": "Physical Interface",
"06": "Image (Scanner/Camera)",
"07": "Printer",
"08": "Mass Storage (USB Flash Drive/Hard Disk)",
"09": "USB Hub",
"0a": "CDC Data",
"0b": "Smart Card",
"0e": "Video (Camera)",
"dc": "Diagnostic Device",
"e0": "Wireless Controller (Bluetooth)",
"ef": "Miscellaneous",
"fe": "Application Specific",
"ff": "Vendor Specific",
}
type USBMonitor struct {
cmd *exec.Cmd
cancel context.CancelFunc
mu sync.Mutex
}
func NewUSBMonitor() *USBMonitor {
return &USBMonitor{}
}
func (m *USBMonitor) Kind() events.Kind {
return events.KindUSB
}
func (m *USBMonitor) Start(ctx context.Context) (<-chan *events.DeviceEvent, error) {
m.mu.Lock()
defer m.mu.Unlock()
// udevadm monitor outputs: UDEV/KERNEL [timestamp] action devpath (subsystem)
// Followed by KEY=value lines, empty line separates events
// Use -s/--subsystem-match (eudev) or --udev-subsystem-match (systemd udev)
cmd := exec.CommandContext(ctx, "udevadm", "monitor", "--property", "--subsystem-match=usb")
stdout, err := cmd.StdoutPipe()
if err != nil {
return nil, fmt.Errorf("udevadm stdout pipe: %w", err)
}
if err := cmd.Start(); err != nil {
return nil, fmt.Errorf("udevadm start: %w (is udevadm installed?)", err)
}
m.cmd = cmd
eventCh := make(chan *events.DeviceEvent, 16)
go func() {
defer close(eventCh)
scanner := bufio.NewScanner(stdout)
var props map[string]string
var action string
isUdev := false // Only UDEV events have complete info (ID_VENDOR, ID_MODEL); KERNEL events come first with less info
for scanner.Scan() {
line := scanner.Text()
if line == "" {
// End of event block - only process UDEV events (skip KERNEL to avoid duplicate/incomplete notifications)
if isUdev && props != nil && (action == "add" || action == "remove") {
if ev := parseUSBEvent(action, props); ev != nil {
select {
case eventCh <- ev:
case <-ctx.Done():
return
}
}
}
props = nil
action = ""
isUdev = false
continue
}
idx := strings.Index(line, "=")
// First line of block: "UDEV [ts] action devpath" or "KERNEL[ts] action devpath" - no KEY=value
if idx <= 0 {
isUdev = strings.HasPrefix(strings.TrimSpace(line), "UDEV")
continue
}
// Parse KEY=value
key := line[:idx]
val := line[idx+1:]
if props == nil {
props = make(map[string]string)
}
props[key] = val
if key == "ACTION" {
action = val
}
}
if err := scanner.Err(); err != nil {
logger.ErrorCF("devices", "udevadm scan error", map[string]interface{}{"error": err.Error()})
}
cmd.Wait()
}()
return eventCh, nil
}
func (m *USBMonitor) Stop() error {
m.mu.Lock()
defer m.mu.Unlock()
if m.cmd != nil && m.cmd.Process != nil {
m.cmd.Process.Kill()
m.cmd = nil
}
return nil
}
func parseUSBEvent(action string, props map[string]string) *events.DeviceEvent {
// Only care about add/remove for physical devices (not interfaces)
subsystem := props["SUBSYSTEM"]
if subsystem != "usb" {
return nil
}
// Skip interface events - we want device-level only to avoid duplicates
devType := props["DEVTYPE"]
if devType == "usb_interface" {
return nil
}
// Prefer usb_device, but accept if DEVTYPE not set (varies by udev version)
if devType != "" && devType != "usb_device" {
return nil
}
ev := &events.DeviceEvent{
Raw: props,
}
switch action {
case "add":
ev.Action = events.ActionAdd
case "remove":
ev.Action = events.ActionRemove
default:
return nil
}
ev.Kind = events.KindUSB
ev.Vendor = props["ID_VENDOR"]
if ev.Vendor == "" {
ev.Vendor = props["ID_VENDOR_ID"]
}
if ev.Vendor == "" {
ev.Vendor = "Unknown Vendor"
}
ev.Product = props["ID_MODEL"]
if ev.Product == "" {
ev.Product = props["ID_MODEL_ID"]
}
if ev.Product == "" {
ev.Product = "Unknown Device"
}
ev.Serial = props["ID_SERIAL_SHORT"]
ev.DeviceID = props["DEVPATH"]
if bus := props["BUSNUM"]; bus != "" {
if dev := props["DEVNUM"]; dev != "" {
ev.DeviceID = bus + ":" + dev
}
}
// Map USB class to capability
if class := props["ID_USB_CLASS"]; class != "" {
ev.Capabilities = usbClassToCapability[strings.ToLower(class)]
}
if ev.Capabilities == "" {
ev.Capabilities = "USB Device"
}
return ev
}

View file

@ -0,0 +1,29 @@
//go:build !linux
package sources
import (
"context"
"github.com/sipeed/picoclaw/pkg/devices/events"
)
type USBMonitor struct{}
func NewUSBMonitor() *USBMonitor {
return &USBMonitor{}
}
func (m *USBMonitor) Kind() events.Kind {
return events.KindUSB
}
func (m *USBMonitor) Start(ctx context.Context) (<-chan *events.DeviceEvent, error) {
ch := make(chan *events.DeviceEvent)
close(ch) // Immediately close, no events
return ch, nil
}
func (m *USBMonitor) Stop() error {
return nil
}

164
pkg/health/server.go Normal file
View file

@ -0,0 +1,164 @@
package health
import (
"context"
"encoding/json"
"fmt"
"net/http"
"sync"
"time"
)
type Server struct {
server *http.Server
mu sync.RWMutex
ready bool
checks map[string]Check
startTime time.Time
}
type Check struct {
Name string `json:"name"`
Status string `json:"status"`
Message string `json:"message,omitempty"`
Timestamp time.Time `json:"timestamp"`
}
type StatusResponse struct {
Status string `json:"status"`
Uptime string `json:"uptime"`
Checks map[string]Check `json:"checks,omitempty"`
}
func NewServer(host string, port int) *Server {
mux := http.NewServeMux()
s := &Server{
ready: false,
checks: make(map[string]Check),
startTime: time.Now(),
}
mux.HandleFunc("/health", s.healthHandler)
mux.HandleFunc("/ready", s.readyHandler)
addr := fmt.Sprintf("%s:%d", host, port)
s.server = &http.Server{
Addr: addr,
Handler: mux,
ReadTimeout: 5 * time.Second,
WriteTimeout: 5 * time.Second,
}
return s
}
func (s *Server) Start() error {
s.mu.Lock()
s.ready = true
s.mu.Unlock()
return s.server.ListenAndServe()
}
func (s *Server) StartContext(ctx context.Context) error {
s.mu.Lock()
s.ready = true
s.mu.Unlock()
errCh := make(chan error, 1)
go func() {
errCh <- s.server.ListenAndServe()
}()
select {
case err := <-errCh:
return err
case <-ctx.Done():
return s.server.Shutdown(context.Background())
}
}
func (s *Server) Stop(ctx context.Context) error {
s.mu.Lock()
s.ready = false
s.mu.Unlock()
return s.server.Shutdown(ctx)
}
func (s *Server) SetReady(ready bool) {
s.mu.Lock()
s.ready = ready
s.mu.Unlock()
}
func (s *Server) RegisterCheck(name string, checkFn func() (bool, string)) {
s.mu.Lock()
defer s.mu.Unlock()
status, msg := checkFn()
s.checks[name] = Check{
Name: name,
Status: statusString(status),
Message: msg,
Timestamp: time.Now(),
}
}
func (s *Server) healthHandler(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(http.StatusOK)
uptime := time.Since(s.startTime)
resp := StatusResponse{
Status: "ok",
Uptime: uptime.String(),
}
json.NewEncoder(w).Encode(resp)
}
func (s *Server) readyHandler(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
s.mu.RLock()
ready := s.ready
checks := make(map[string]Check)
for k, v := range s.checks {
checks[k] = v
}
s.mu.RUnlock()
if !ready {
w.WriteHeader(http.StatusServiceUnavailable)
json.NewEncoder(w).Encode(StatusResponse{
Status: "not ready",
Checks: checks,
})
return
}
for _, check := range checks {
if check.Status == "fail" {
w.WriteHeader(http.StatusServiceUnavailable)
json.NewEncoder(w).Encode(StatusResponse{
Status: "not ready",
Checks: checks,
})
return
}
}
w.WriteHeader(http.StatusOK)
uptime := time.Since(s.startTime)
json.NewEncoder(w).Encode(StatusResponse{
Status: "ready",
Uptime: uptime.String(),
Checks: checks,
})
}
func statusString(ok bool) string {
if ok {
return "ok"
}
return "fail"
}

View file

@ -171,68 +171,14 @@ func (p *ClaudeCliProvider) parseClaudeCliResponse(output string) (*LLMResponse,
}, nil
}
// extractToolCalls parses tool call JSON from the response text.
// extractToolCalls delegates to the shared extractToolCallsFromText function.
func (p *ClaudeCliProvider) extractToolCalls(text string) []ToolCall {
start := strings.Index(text, `{"tool_calls"`)
if start == -1 {
return nil
}
end := findMatchingBrace(text, start)
if end == start {
return nil
}
jsonStr := text[start:end]
var wrapper struct {
ToolCalls []struct {
ID string `json:"id"`
Type string `json:"type"`
Function struct {
Name string `json:"name"`
Arguments string `json:"arguments"`
} `json:"function"`
} `json:"tool_calls"`
}
if err := json.Unmarshal([]byte(jsonStr), &wrapper); err != nil {
return nil
}
var result []ToolCall
for _, tc := range wrapper.ToolCalls {
var args map[string]interface{}
json.Unmarshal([]byte(tc.Function.Arguments), &args)
result = append(result, ToolCall{
ID: tc.ID,
Type: tc.Type,
Name: tc.Function.Name,
Arguments: args,
Function: &FunctionCall{
Name: tc.Function.Name,
Arguments: tc.Function.Arguments,
},
})
}
return result
return extractToolCallsFromText(text)
}
// stripToolCallsJSON removes tool call JSON from response text.
// stripToolCallsJSON delegates to the shared stripToolCallsFromText function.
func (p *ClaudeCliProvider) stripToolCallsJSON(text string) string {
start := strings.Index(text, `{"tool_calls"`)
if start == -1 {
return text
}
end := findMatchingBrace(text, start)
if end == start {
return text
}
return strings.TrimSpace(text[:start] + text[end:])
return stripToolCallsFromText(text)
}
// findMatchingBrace finds the index after the closing brace matching the opening brace at pos.

View file

@ -0,0 +1,79 @@
package providers
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"time"
)
// CodexCliAuth represents the ~/.codex/auth.json file structure.
type CodexCliAuth struct {
Tokens struct {
AccessToken string `json:"access_token"`
RefreshToken string `json:"refresh_token"`
AccountID string `json:"account_id"`
} `json:"tokens"`
}
// ReadCodexCliCredentials reads OAuth tokens from the Codex CLI's auth.json file.
// Expiry is estimated as file modification time + 1 hour (same approach as moltbot).
func ReadCodexCliCredentials() (accessToken, accountID string, expiresAt time.Time, err error) {
authPath, err := resolveCodexAuthPath()
if err != nil {
return "", "", time.Time{}, err
}
data, err := os.ReadFile(authPath)
if err != nil {
return "", "", time.Time{}, fmt.Errorf("reading %s: %w", authPath, err)
}
var auth CodexCliAuth
if err := json.Unmarshal(data, &auth); err != nil {
return "", "", time.Time{}, fmt.Errorf("parsing %s: %w", authPath, err)
}
if auth.Tokens.AccessToken == "" {
return "", "", time.Time{}, fmt.Errorf("no access_token in %s", authPath)
}
stat, err := os.Stat(authPath)
if err != nil {
expiresAt = time.Now().Add(time.Hour)
} else {
expiresAt = stat.ModTime().Add(time.Hour)
}
return auth.Tokens.AccessToken, auth.Tokens.AccountID, expiresAt, nil
}
// CreateCodexCliTokenSource creates a token source that reads from ~/.codex/auth.json.
// This allows the existing CodexProvider to reuse Codex CLI credentials.
func CreateCodexCliTokenSource() func() (string, string, error) {
return func() (string, string, error) {
token, accountID, expiresAt, err := ReadCodexCliCredentials()
if err != nil {
return "", "", fmt.Errorf("reading codex cli credentials: %w", err)
}
if time.Now().After(expiresAt) {
return "", "", fmt.Errorf("codex cli credentials expired (auth.json last modified > 1h ago). Run: codex login")
}
return token, accountID, nil
}
}
func resolveCodexAuthPath() (string, error) {
codexHome := os.Getenv("CODEX_HOME")
if codexHome == "" {
home, err := os.UserHomeDir()
if err != nil {
return "", fmt.Errorf("getting home dir: %w", err)
}
codexHome = filepath.Join(home, ".codex")
}
return filepath.Join(codexHome, "auth.json"), nil
}

View file

@ -0,0 +1,181 @@
package providers
import (
"os"
"path/filepath"
"testing"
"time"
)
func TestReadCodexCliCredentials_Valid(t *testing.T) {
tmpDir := t.TempDir()
authPath := filepath.Join(tmpDir, "auth.json")
authJSON := `{
"tokens": {
"access_token": "test-access-token",
"refresh_token": "test-refresh-token",
"account_id": "org-test123"
}
}`
if err := os.WriteFile(authPath, []byte(authJSON), 0600); err != nil {
t.Fatal(err)
}
t.Setenv("CODEX_HOME", tmpDir)
token, accountID, expiresAt, err := ReadCodexCliCredentials()
if err != nil {
t.Fatalf("ReadCodexCliCredentials() error: %v", err)
}
if token != "test-access-token" {
t.Errorf("token = %q, want %q", token, "test-access-token")
}
if accountID != "org-test123" {
t.Errorf("accountID = %q, want %q", accountID, "org-test123")
}
// Expiry should be within ~1 hour from now (file was just written)
if expiresAt.Before(time.Now()) {
t.Errorf("expiresAt = %v, should be in the future", expiresAt)
}
if expiresAt.After(time.Now().Add(2 * time.Hour)) {
t.Errorf("expiresAt = %v, should be within ~1 hour", expiresAt)
}
}
func TestReadCodexCliCredentials_MissingFile(t *testing.T) {
tmpDir := t.TempDir()
t.Setenv("CODEX_HOME", tmpDir)
_, _, _, err := ReadCodexCliCredentials()
if err == nil {
t.Fatal("expected error for missing auth.json")
}
}
func TestReadCodexCliCredentials_EmptyToken(t *testing.T) {
tmpDir := t.TempDir()
authPath := filepath.Join(tmpDir, "auth.json")
authJSON := `{"tokens": {"access_token": "", "refresh_token": "r", "account_id": "a"}}`
if err := os.WriteFile(authPath, []byte(authJSON), 0600); err != nil {
t.Fatal(err)
}
t.Setenv("CODEX_HOME", tmpDir)
_, _, _, err := ReadCodexCliCredentials()
if err == nil {
t.Fatal("expected error for empty access_token")
}
}
func TestReadCodexCliCredentials_InvalidJSON(t *testing.T) {
tmpDir := t.TempDir()
authPath := filepath.Join(tmpDir, "auth.json")
if err := os.WriteFile(authPath, []byte("not json"), 0600); err != nil {
t.Fatal(err)
}
t.Setenv("CODEX_HOME", tmpDir)
_, _, _, err := ReadCodexCliCredentials()
if err == nil {
t.Fatal("expected error for invalid JSON")
}
}
func TestReadCodexCliCredentials_NoAccountID(t *testing.T) {
tmpDir := t.TempDir()
authPath := filepath.Join(tmpDir, "auth.json")
authJSON := `{"tokens": {"access_token": "tok123", "refresh_token": "ref456"}}`
if err := os.WriteFile(authPath, []byte(authJSON), 0600); err != nil {
t.Fatal(err)
}
t.Setenv("CODEX_HOME", tmpDir)
token, accountID, _, err := ReadCodexCliCredentials()
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if token != "tok123" {
t.Errorf("token = %q, want %q", token, "tok123")
}
if accountID != "" {
t.Errorf("accountID = %q, want empty", accountID)
}
}
func TestReadCodexCliCredentials_CodexHomeEnv(t *testing.T) {
tmpDir := t.TempDir()
customDir := filepath.Join(tmpDir, "custom-codex")
if err := os.MkdirAll(customDir, 0755); err != nil {
t.Fatal(err)
}
authJSON := `{"tokens": {"access_token": "custom-token", "refresh_token": "r"}}`
if err := os.WriteFile(filepath.Join(customDir, "auth.json"), []byte(authJSON), 0600); err != nil {
t.Fatal(err)
}
t.Setenv("CODEX_HOME", customDir)
token, _, _, err := ReadCodexCliCredentials()
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if token != "custom-token" {
t.Errorf("token = %q, want %q", token, "custom-token")
}
}
func TestCreateCodexCliTokenSource_Valid(t *testing.T) {
tmpDir := t.TempDir()
authPath := filepath.Join(tmpDir, "auth.json")
authJSON := `{"tokens": {"access_token": "fresh-token", "refresh_token": "r", "account_id": "acc"}}`
if err := os.WriteFile(authPath, []byte(authJSON), 0600); err != nil {
t.Fatal(err)
}
t.Setenv("CODEX_HOME", tmpDir)
source := CreateCodexCliTokenSource()
token, accountID, err := source()
if err != nil {
t.Fatalf("token source error: %v", err)
}
if token != "fresh-token" {
t.Errorf("token = %q, want %q", token, "fresh-token")
}
if accountID != "acc" {
t.Errorf("accountID = %q, want %q", accountID, "acc")
}
}
func TestCreateCodexCliTokenSource_Expired(t *testing.T) {
tmpDir := t.TempDir()
authPath := filepath.Join(tmpDir, "auth.json")
authJSON := `{"tokens": {"access_token": "old-token", "refresh_token": "r"}}`
if err := os.WriteFile(authPath, []byte(authJSON), 0600); err != nil {
t.Fatal(err)
}
// Set file modification time to 2 hours ago
oldTime := time.Now().Add(-2 * time.Hour)
if err := os.Chtimes(authPath, oldTime, oldTime); err != nil {
t.Fatal(err)
}
t.Setenv("CODEX_HOME", tmpDir)
source := CreateCodexCliTokenSource()
_, _, err := source()
if err == nil {
t.Fatal("expected error for expired credentials")
}
}

View file

@ -0,0 +1,251 @@
package providers
import (
"bufio"
"bytes"
"context"
"encoding/json"
"fmt"
"os/exec"
"strings"
)
// CodexCliProvider implements LLMProvider by wrapping the codex CLI as a subprocess.
type CodexCliProvider struct {
command string
workspace string
}
// NewCodexCliProvider creates a new Codex CLI provider.
func NewCodexCliProvider(workspace string) *CodexCliProvider {
return &CodexCliProvider{
command: "codex",
workspace: workspace,
}
}
// Chat implements LLMProvider.Chat by executing the codex CLI in non-interactive mode.
func (p *CodexCliProvider) Chat(ctx context.Context, messages []Message, tools []ToolDefinition, model string, options map[string]interface{}) (*LLMResponse, error) {
if p.command == "" {
return nil, fmt.Errorf("codex command not configured")
}
prompt := p.buildPrompt(messages, tools)
args := []string{
"exec",
"--json",
"--dangerously-bypass-approvals-and-sandbox",
"--skip-git-repo-check",
"--color", "never",
}
if model != "" && model != "codex-cli" {
args = append(args, "-m", model)
}
if p.workspace != "" {
args = append(args, "-C", p.workspace)
}
args = append(args, "-") // read prompt from stdin
cmd := exec.CommandContext(ctx, p.command, args...)
cmd.Stdin = bytes.NewReader([]byte(prompt))
var stdout, stderr bytes.Buffer
cmd.Stdout = &stdout
cmd.Stderr = &stderr
err := cmd.Run()
// Parse JSONL from stdout even if exit code is non-zero,
// because codex writes diagnostic noise to stderr (e.g. rollout errors)
// but still produces valid JSONL output.
if stdoutStr := stdout.String(); stdoutStr != "" {
resp, parseErr := p.parseJSONLEvents(stdoutStr)
if parseErr == nil && resp != nil && (resp.Content != "" || len(resp.ToolCalls) > 0) {
return resp, nil
}
}
if err != nil {
if ctx.Err() == context.Canceled {
return nil, ctx.Err()
}
if stderrStr := stderr.String(); stderrStr != "" {
return nil, fmt.Errorf("codex cli error: %s", stderrStr)
}
return nil, fmt.Errorf("codex cli error: %w", err)
}
return p.parseJSONLEvents(stdout.String())
}
// GetDefaultModel returns the default model identifier.
func (p *CodexCliProvider) GetDefaultModel() string {
return "codex-cli"
}
// buildPrompt converts messages to a prompt string for the Codex CLI.
// System messages are prepended as instructions since Codex CLI has no --system-prompt flag.
func (p *CodexCliProvider) buildPrompt(messages []Message, tools []ToolDefinition) string {
var systemParts []string
var conversationParts []string
for _, msg := range messages {
switch msg.Role {
case "system":
systemParts = append(systemParts, msg.Content)
case "user":
conversationParts = append(conversationParts, msg.Content)
case "assistant":
conversationParts = append(conversationParts, "Assistant: "+msg.Content)
case "tool":
conversationParts = append(conversationParts,
fmt.Sprintf("[Tool Result for %s]: %s", msg.ToolCallID, msg.Content))
}
}
var sb strings.Builder
if len(systemParts) > 0 {
sb.WriteString("## System Instructions\n\n")
sb.WriteString(strings.Join(systemParts, "\n\n"))
sb.WriteString("\n\n## Task\n\n")
}
if len(tools) > 0 {
sb.WriteString(p.buildToolsPrompt(tools))
sb.WriteString("\n\n")
}
// Simplify single user message (no prefix)
if len(conversationParts) == 1 && len(systemParts) == 0 && len(tools) == 0 {
return conversationParts[0]
}
sb.WriteString(strings.Join(conversationParts, "\n"))
return sb.String()
}
// buildToolsPrompt creates a tool definitions section for the prompt.
func (p *CodexCliProvider) buildToolsPrompt(tools []ToolDefinition) string {
var sb strings.Builder
sb.WriteString("## Available Tools\n\n")
sb.WriteString("When you need to use a tool, respond with ONLY a JSON object:\n\n")
sb.WriteString("```json\n")
sb.WriteString(`{"tool_calls":[{"id":"call_xxx","type":"function","function":{"name":"tool_name","arguments":"{...}"}}]}`)
sb.WriteString("\n```\n\n")
sb.WriteString("CRITICAL: The 'arguments' field MUST be a JSON-encoded STRING.\n\n")
sb.WriteString("### Tool Definitions:\n\n")
for _, tool := range tools {
if tool.Type != "function" {
continue
}
sb.WriteString(fmt.Sprintf("#### %s\n", tool.Function.Name))
if tool.Function.Description != "" {
sb.WriteString(fmt.Sprintf("Description: %s\n", tool.Function.Description))
}
if len(tool.Function.Parameters) > 0 {
paramsJSON, _ := json.Marshal(tool.Function.Parameters)
sb.WriteString(fmt.Sprintf("Parameters:\n```json\n%s\n```\n", string(paramsJSON)))
}
sb.WriteString("\n")
}
return sb.String()
}
// codexEvent represents a single JSONL event from `codex exec --json`.
type codexEvent struct {
Type string `json:"type"`
ThreadID string `json:"thread_id,omitempty"`
Message string `json:"message,omitempty"`
Item *codexEventItem `json:"item,omitempty"`
Usage *codexUsage `json:"usage,omitempty"`
Error *codexEventErr `json:"error,omitempty"`
}
type codexEventItem struct {
ID string `json:"id"`
Type string `json:"type"`
Text string `json:"text,omitempty"`
Command string `json:"command,omitempty"`
Status string `json:"status,omitempty"`
ExitCode *int `json:"exit_code,omitempty"`
Output string `json:"output,omitempty"`
}
type codexUsage struct {
InputTokens int `json:"input_tokens"`
CachedInputTokens int `json:"cached_input_tokens"`
OutputTokens int `json:"output_tokens"`
}
type codexEventErr struct {
Message string `json:"message"`
}
// parseJSONLEvents processes the JSONL output from codex exec --json.
func (p *CodexCliProvider) parseJSONLEvents(output string) (*LLMResponse, error) {
var contentParts []string
var usage *UsageInfo
var lastError string
scanner := bufio.NewScanner(strings.NewReader(output))
for scanner.Scan() {
line := strings.TrimSpace(scanner.Text())
if line == "" {
continue
}
var event codexEvent
if err := json.Unmarshal([]byte(line), &event); err != nil {
continue // skip malformed lines
}
switch event.Type {
case "item.completed":
if event.Item != nil && event.Item.Type == "agent_message" && event.Item.Text != "" {
contentParts = append(contentParts, event.Item.Text)
}
case "turn.completed":
if event.Usage != nil {
promptTokens := event.Usage.InputTokens + event.Usage.CachedInputTokens
usage = &UsageInfo{
PromptTokens: promptTokens,
CompletionTokens: event.Usage.OutputTokens,
TotalTokens: promptTokens + event.Usage.OutputTokens,
}
}
case "error":
lastError = event.Message
case "turn.failed":
if event.Error != nil {
lastError = event.Error.Message
}
}
}
if lastError != "" && len(contentParts) == 0 {
return nil, fmt.Errorf("codex cli: %s", lastError)
}
content := strings.Join(contentParts, "\n")
// Extract tool calls from response text (same pattern as ClaudeCliProvider)
toolCalls := extractToolCallsFromText(content)
finishReason := "stop"
if len(toolCalls) > 0 {
finishReason = "tool_calls"
content = stripToolCallsFromText(content)
}
return &LLMResponse{
Content: strings.TrimSpace(content),
ToolCalls: toolCalls,
FinishReason: finishReason,
Usage: usage,
}, nil
}

View file

@ -0,0 +1,585 @@
package providers
import (
"context"
"encoding/json"
"fmt"
"os"
"os/exec"
"path/filepath"
"strings"
"testing"
)
// --- JSONL Event Parsing Tests ---
func TestParseJSONLEvents_AgentMessage(t *testing.T) {
p := &CodexCliProvider{}
events := `{"type":"thread.started","thread_id":"abc-123"}
{"type":"turn.started"}
{"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"Hello from Codex!"}}
{"type":"turn.completed","usage":{"input_tokens":100,"cached_input_tokens":50,"output_tokens":20}}`
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("parseJSONLEvents() error: %v", err)
}
if resp.Content != "Hello from Codex!" {
t.Errorf("Content = %q, want %q", resp.Content, "Hello from Codex!")
}
if resp.FinishReason != "stop" {
t.Errorf("FinishReason = %q, want %q", resp.FinishReason, "stop")
}
if resp.Usage == nil {
t.Fatal("Usage should not be nil")
}
if resp.Usage.PromptTokens != 150 {
t.Errorf("PromptTokens = %d, want 150", resp.Usage.PromptTokens)
}
if resp.Usage.CompletionTokens != 20 {
t.Errorf("CompletionTokens = %d, want 20", resp.Usage.CompletionTokens)
}
if resp.Usage.TotalTokens != 170 {
t.Errorf("TotalTokens = %d, want 170", resp.Usage.TotalTokens)
}
if len(resp.ToolCalls) != 0 {
t.Errorf("ToolCalls should be empty, got %d", len(resp.ToolCalls))
}
}
func TestParseJSONLEvents_ToolCallExtraction(t *testing.T) {
p := &CodexCliProvider{}
toolCallText := `Let me read that file.
{"tool_calls":[{"id":"call_1","type":"function","function":{"name":"read_file","arguments":"{\"path\":\"/tmp/test.txt\"}"}}]}`
// Build valid JSONL by marshaling the event
item := codexEvent{
Type: "item.completed",
Item: &codexEventItem{ID: "item_1", Type: "agent_message", Text: toolCallText},
}
itemJSON, _ := json.Marshal(item)
usageEvt := `{"type":"turn.completed","usage":{"input_tokens":50,"cached_input_tokens":0,"output_tokens":20}}`
events := `{"type":"turn.started"}` + "\n" + string(itemJSON) + "\n" + usageEvt
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("parseJSONLEvents() error: %v", err)
}
if resp.FinishReason != "tool_calls" {
t.Errorf("FinishReason = %q, want %q", resp.FinishReason, "tool_calls")
}
if len(resp.ToolCalls) != 1 {
t.Fatalf("ToolCalls count = %d, want 1", len(resp.ToolCalls))
}
if resp.ToolCalls[0].Name != "read_file" {
t.Errorf("ToolCalls[0].Name = %q, want %q", resp.ToolCalls[0].Name, "read_file")
}
if resp.ToolCalls[0].ID != "call_1" {
t.Errorf("ToolCalls[0].ID = %q, want %q", resp.ToolCalls[0].ID, "call_1")
}
if resp.ToolCalls[0].Function.Arguments != `{"path":"/tmp/test.txt"}` {
t.Errorf("ToolCalls[0].Function.Arguments = %q", resp.ToolCalls[0].Function.Arguments)
}
// Content should have the tool call JSON stripped
if strings.Contains(resp.Content, "tool_calls") {
t.Errorf("Content should not contain tool_calls JSON, got: %q", resp.Content)
}
}
func TestParseJSONLEvents_MultipleToolCalls(t *testing.T) {
p := &CodexCliProvider{}
toolCallText := `{"tool_calls":[{"id":"call_1","type":"function","function":{"name":"read_file","arguments":"{\"path\":\"a.txt\"}"}},{"id":"call_2","type":"function","function":{"name":"write_file","arguments":"{\"path\":\"b.txt\",\"content\":\"hello\"}"}}]}`
item := codexEvent{
Type: "item.completed",
Item: &codexEventItem{ID: "item_1", Type: "agent_message", Text: toolCallText},
}
itemJSON, _ := json.Marshal(item)
events := `{"type":"turn.started"}` + "\n" + string(itemJSON) + "\n" + `{"type":"turn.completed"}`
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("parseJSONLEvents() error: %v", err)
}
if len(resp.ToolCalls) != 2 {
t.Fatalf("ToolCalls count = %d, want 2", len(resp.ToolCalls))
}
if resp.ToolCalls[0].Name != "read_file" {
t.Errorf("ToolCalls[0].Name = %q, want %q", resp.ToolCalls[0].Name, "read_file")
}
if resp.ToolCalls[1].Name != "write_file" {
t.Errorf("ToolCalls[1].Name = %q, want %q", resp.ToolCalls[1].Name, "write_file")
}
if resp.FinishReason != "tool_calls" {
t.Errorf("FinishReason = %q, want %q", resp.FinishReason, "tool_calls")
}
}
func TestParseJSONLEvents_MultipleMessages(t *testing.T) {
p := &CodexCliProvider{}
events := `{"type":"turn.started"}
{"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"First part."}}
{"type":"item.completed","item":{"id":"item_2","type":"command_execution","command":"ls","status":"completed"}}
{"type":"item.completed","item":{"id":"item_3","type":"agent_message","text":"Second part."}}
{"type":"turn.completed"}`
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("parseJSONLEvents() error: %v", err)
}
if resp.Content != "First part.\nSecond part." {
t.Errorf("Content = %q, want %q", resp.Content, "First part.\nSecond part.")
}
}
func TestParseJSONLEvents_ErrorEvent(t *testing.T) {
p := &CodexCliProvider{}
events := `{"type":"thread.started","thread_id":"abc"}
{"type":"turn.started"}
{"type":"error","message":"token expired"}
{"type":"turn.failed","error":{"message":"token expired"}}`
_, err := p.parseJSONLEvents(events)
if err == nil {
t.Fatal("expected error")
}
if !strings.Contains(err.Error(), "token expired") {
t.Errorf("error = %q, want to contain 'token expired'", err.Error())
}
}
func TestParseJSONLEvents_TurnFailed(t *testing.T) {
p := &CodexCliProvider{}
events := `{"type":"turn.started"}
{"type":"turn.failed","error":{"message":"rate limit exceeded"}}`
_, err := p.parseJSONLEvents(events)
if err == nil {
t.Fatal("expected error")
}
if !strings.Contains(err.Error(), "rate limit exceeded") {
t.Errorf("error = %q, want to contain 'rate limit exceeded'", err.Error())
}
}
func TestParseJSONLEvents_ErrorWithContent(t *testing.T) {
p := &CodexCliProvider{}
// If there's an error but also content, return the content (partial success)
events := `{"type":"turn.started"}
{"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"Partial result."}}
{"type":"error","message":"connection reset"}
{"type":"turn.failed","error":{"message":"connection reset"}}`
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("should not error when content exists: %v", err)
}
if resp.Content != "Partial result." {
t.Errorf("Content = %q, want %q", resp.Content, "Partial result.")
}
}
func TestParseJSONLEvents_EmptyOutput(t *testing.T) {
p := &CodexCliProvider{}
resp, err := p.parseJSONLEvents("")
if err != nil {
t.Fatalf("empty output should not error: %v", err)
}
if resp.Content != "" {
t.Errorf("Content = %q, want empty", resp.Content)
}
}
func TestParseJSONLEvents_MalformedLines(t *testing.T) {
p := &CodexCliProvider{}
events := `not json at all
{"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"Good line."}}
another bad line
{"type":"turn.completed","usage":{"input_tokens":10,"output_tokens":5}}`
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("should skip malformed lines: %v", err)
}
if resp.Content != "Good line." {
t.Errorf("Content = %q, want %q", resp.Content, "Good line.")
}
if resp.Usage == nil || resp.Usage.TotalTokens != 15 {
t.Errorf("Usage.TotalTokens = %v, want 15", resp.Usage)
}
}
func TestParseJSONLEvents_CommandExecution(t *testing.T) {
p := &CodexCliProvider{}
events := `{"type":"turn.started"}
{"type":"item.started","item":{"id":"item_1","type":"command_execution","command":"bash -lc ls","status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_1","type":"command_execution","command":"bash -lc ls","status":"completed","exit_code":0,"output":"file1.go\nfile2.go"}}
{"type":"item.completed","item":{"id":"item_2","type":"agent_message","text":"Found 2 files."}}
{"type":"turn.completed"}`
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("parseJSONLEvents() error: %v", err)
}
// command_execution items should be skipped; only agent_message text is returned
if resp.Content != "Found 2 files." {
t.Errorf("Content = %q, want %q", resp.Content, "Found 2 files.")
}
}
func TestParseJSONLEvents_NoUsage(t *testing.T) {
p := &CodexCliProvider{}
events := `{"type":"turn.started"}
{"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"No usage info."}}
{"type":"turn.completed"}`
resp, err := p.parseJSONLEvents(events)
if err != nil {
t.Fatalf("parseJSONLEvents() error: %v", err)
}
if resp.Usage != nil {
t.Errorf("Usage should be nil when turn.completed has no usage, got %+v", resp.Usage)
}
}
// --- Prompt Building Tests ---
func TestBuildPrompt_SystemAsInstructions(t *testing.T) {
p := &CodexCliProvider{}
messages := []Message{
{Role: "system", Content: "You are helpful."},
{Role: "user", Content: "Hi there"},
}
prompt := p.buildPrompt(messages, nil)
if !strings.Contains(prompt, "## System Instructions") {
t.Error("prompt should contain '## System Instructions'")
}
if !strings.Contains(prompt, "You are helpful.") {
t.Error("prompt should contain system content")
}
if !strings.Contains(prompt, "## Task") {
t.Error("prompt should contain '## Task'")
}
if !strings.Contains(prompt, "Hi there") {
t.Error("prompt should contain user message")
}
}
func TestBuildPrompt_NoSystem(t *testing.T) {
p := &CodexCliProvider{}
messages := []Message{
{Role: "user", Content: "Just a question"},
}
prompt := p.buildPrompt(messages, nil)
if strings.Contains(prompt, "## System Instructions") {
t.Error("prompt should not contain system instructions header")
}
if prompt != "Just a question" {
t.Errorf("prompt = %q, want %q", prompt, "Just a question")
}
}
func TestBuildPrompt_WithTools(t *testing.T) {
p := &CodexCliProvider{}
messages := []Message{
{Role: "user", Content: "Get weather"},
}
tools := []ToolDefinition{
{
Type: "function",
Function: ToolFunctionDefinition{
Name: "get_weather",
Description: "Get current weather",
Parameters: map[string]interface{}{
"type": "object",
"properties": map[string]interface{}{
"city": map[string]interface{}{"type": "string"},
},
},
},
},
}
prompt := p.buildPrompt(messages, tools)
if !strings.Contains(prompt, "## Available Tools") {
t.Error("prompt should contain tools section")
}
if !strings.Contains(prompt, "get_weather") {
t.Error("prompt should contain tool name")
}
if !strings.Contains(prompt, "Get current weather") {
t.Error("prompt should contain tool description")
}
}
func TestBuildPrompt_MultipleMessages(t *testing.T) {
p := &CodexCliProvider{}
messages := []Message{
{Role: "user", Content: "Hello"},
{Role: "assistant", Content: "Hi! How can I help?"},
{Role: "user", Content: "Tell me about Go"},
}
prompt := p.buildPrompt(messages, nil)
if !strings.Contains(prompt, "Hello") {
t.Error("prompt should contain first user message")
}
if !strings.Contains(prompt, "Assistant: Hi! How can I help?") {
t.Error("prompt should contain assistant message with prefix")
}
if !strings.Contains(prompt, "Tell me about Go") {
t.Error("prompt should contain second user message")
}
}
func TestBuildPrompt_ToolResults(t *testing.T) {
p := &CodexCliProvider{}
messages := []Message{
{Role: "user", Content: "Weather?"},
{Role: "tool", Content: `{"temp": 72}`, ToolCallID: "call_1"},
}
prompt := p.buildPrompt(messages, nil)
if !strings.Contains(prompt, "[Tool Result for call_1]") {
t.Error("prompt should contain tool result")
}
if !strings.Contains(prompt, `{"temp": 72}`) {
t.Error("prompt should contain tool result content")
}
}
func TestBuildPrompt_SystemAndTools(t *testing.T) {
p := &CodexCliProvider{}
messages := []Message{
{Role: "system", Content: "Be concise."},
{Role: "user", Content: "Do something"},
}
tools := []ToolDefinition{
{
Type: "function",
Function: ToolFunctionDefinition{
Name: "my_tool",
Description: "A tool",
},
},
}
prompt := p.buildPrompt(messages, tools)
// System instructions should come first
sysIdx := strings.Index(prompt, "## System Instructions")
toolIdx := strings.Index(prompt, "## Available Tools")
taskIdx := strings.Index(prompt, "## Task")
if sysIdx == -1 || toolIdx == -1 || taskIdx == -1 {
t.Fatal("prompt should contain all sections")
}
if sysIdx >= taskIdx {
t.Error("system instructions should come before task")
}
if taskIdx >= toolIdx {
t.Error("task section should come before tools in the output")
}
}
// --- CLI Argument Tests ---
func TestCodexCliProvider_GetDefaultModel(t *testing.T) {
p := NewCodexCliProvider("")
if got := p.GetDefaultModel(); got != "codex-cli" {
t.Errorf("GetDefaultModel() = %q, want %q", got, "codex-cli")
}
}
// --- Mock CLI Integration Test ---
func createMockCodexCLI(t *testing.T, events []string) string {
t.Helper()
tmpDir := t.TempDir()
scriptPath := filepath.Join(tmpDir, "codex")
var sb strings.Builder
sb.WriteString("#!/bin/bash\n")
for _, event := range events {
sb.WriteString(fmt.Sprintf("echo '%s'\n", event))
}
if err := os.WriteFile(scriptPath, []byte(sb.String()), 0755); err != nil {
t.Fatal(err)
}
return scriptPath
}
func TestCodexCliProvider_MockCLI_Success(t *testing.T) {
scriptPath := createMockCodexCLI(t, []string{
`{"type":"thread.started","thread_id":"test-123"}`,
`{"type":"turn.started"}`,
`{"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"Mock response from Codex CLI"}}`,
`{"type":"turn.completed","usage":{"input_tokens":50,"cached_input_tokens":10,"output_tokens":15}}`,
})
p := &CodexCliProvider{
command: scriptPath,
workspace: "",
}
messages := []Message{{Role: "user", Content: "Hello"}}
resp, err := p.Chat(context.Background(), messages, nil, "", nil)
if err != nil {
t.Fatalf("Chat() error: %v", err)
}
if resp.Content != "Mock response from Codex CLI" {
t.Errorf("Content = %q, want %q", resp.Content, "Mock response from Codex CLI")
}
if resp.Usage == nil {
t.Fatal("Usage should not be nil")
}
if resp.Usage.PromptTokens != 60 {
t.Errorf("PromptTokens = %d, want 60", resp.Usage.PromptTokens)
}
if resp.Usage.CompletionTokens != 15 {
t.Errorf("CompletionTokens = %d, want 15", resp.Usage.CompletionTokens)
}
}
func TestCodexCliProvider_MockCLI_Error(t *testing.T) {
scriptPath := createMockCodexCLI(t, []string{
`{"type":"thread.started","thread_id":"test-err"}`,
`{"type":"turn.started"}`,
`{"type":"error","message":"auth token expired"}`,
`{"type":"turn.failed","error":{"message":"auth token expired"}}`,
})
p := &CodexCliProvider{
command: scriptPath,
workspace: "",
}
messages := []Message{{Role: "user", Content: "Hello"}}
_, err := p.Chat(context.Background(), messages, nil, "", nil)
if err == nil {
t.Fatal("expected error")
}
if !strings.Contains(err.Error(), "auth token expired") {
t.Errorf("error = %q, want to contain 'auth token expired'", err.Error())
}
}
func TestCodexCliProvider_MockCLI_WithModel(t *testing.T) {
// Mock script that captures args to verify model flag is passed
tmpDir := t.TempDir()
scriptPath := filepath.Join(tmpDir, "codex")
script := `#!/bin/bash
# Write args to a file for verification
echo "$@" > "` + filepath.Join(tmpDir, "args.txt") + `"
echo '{"type":"item.completed","item":{"id":"1","type":"agent_message","text":"ok"}}'
echo '{"type":"turn.completed"}'`
if err := os.WriteFile(scriptPath, []byte(script), 0755); err != nil {
t.Fatal(err)
}
p := &CodexCliProvider{
command: scriptPath,
workspace: "/tmp/test-workspace",
}
messages := []Message{{Role: "user", Content: "test"}}
_, err := p.Chat(context.Background(), messages, nil, "gpt-5.2-codex", nil)
if err != nil {
t.Fatalf("Chat() error: %v", err)
}
// Verify the args
argsData, err := os.ReadFile(filepath.Join(tmpDir, "args.txt"))
if err != nil {
t.Fatalf("reading args: %v", err)
}
args := string(argsData)
if !strings.Contains(args, "-m gpt-5.2-codex") {
t.Errorf("args should contain model flag, got: %s", args)
}
if !strings.Contains(args, "-C /tmp/test-workspace") {
t.Errorf("args should contain workspace flag, got: %s", args)
}
if !strings.Contains(args, "--json") {
t.Errorf("args should contain --json, got: %s", args)
}
if !strings.Contains(args, "--dangerously-bypass-approvals-and-sandbox") {
t.Errorf("args should contain bypass flag, got: %s", args)
}
}
func TestCodexCliProvider_MockCLI_ContextCancel(t *testing.T) {
// Script that sleeps forever
tmpDir := t.TempDir()
scriptPath := filepath.Join(tmpDir, "codex")
script := "#!/bin/bash\nsleep 60"
if err := os.WriteFile(scriptPath, []byte(script), 0755); err != nil {
t.Fatal(err)
}
p := &CodexCliProvider{
command: scriptPath,
workspace: "",
}
ctx, cancel := context.WithCancel(context.Background())
cancel() // cancel immediately
messages := []Message{{Role: "user", Content: "test"}}
_, err := p.Chat(ctx, messages, nil, "", nil)
if err == nil {
t.Fatal("expected error on canceled context")
}
}
func TestCodexCliProvider_EmptyCommand(t *testing.T) {
p := &CodexCliProvider{command: ""}
messages := []Message{{Role: "user", Content: "test"}}
_, err := p.Chat(context.Background(), messages, nil, "", nil)
if err == nil {
t.Fatal("expected error for empty command")
}
}
// --- Integration Test (requires real codex CLI with valid auth) ---
func TestCodexCliProvider_Integration(t *testing.T) {
if os.Getenv("PICOCLAW_INTEGRATION_TESTS") == "" {
t.Skip("skipping integration test (set PICOCLAW_INTEGRATION_TESTS=1 to enable)")
}
// Verify codex is available
codexPath, err := exec.LookPath("codex")
if err != nil {
t.Skip("codex CLI not found in PATH")
}
p := &CodexCliProvider{
command: codexPath,
workspace: "",
}
messages := []Message{
{Role: "user", Content: "Respond with just the word 'hello' and nothing else."},
}
resp, err := p.Chat(context.Background(), messages, nil, "", nil)
if err != nil {
t.Fatalf("Chat() error: %v", err)
}
lower := strings.ToLower(strings.TrimSpace(resp.Content))
if !strings.Contains(lower, "hello") {
t.Errorf("Content = %q, expected to contain 'hello'", resp.Content)
}
}

View file

@ -3,6 +3,7 @@ package providers
import (
"context"
"encoding/json"
"errors"
"fmt"
"strings"
@ -10,18 +11,26 @@ import (
"github.com/openai/openai-go/v3/option"
"github.com/openai/openai-go/v3/responses"
"github.com/sipeed/picoclaw/pkg/auth"
"github.com/sipeed/picoclaw/pkg/logger"
)
const codexDefaultModel = "gpt-5.2"
const codexDefaultInstructions = "You are Codex, a coding assistant."
type CodexProvider struct {
client *openai.Client
accountID string
tokenSource func() (string, string, error)
}
const defaultCodexInstructions = "You are Codex, a coding assistant."
func NewCodexProvider(token, accountID string) *CodexProvider {
opts := []option.RequestOption{
option.WithBaseURL("https://chatgpt.com/backend-api/codex"),
option.WithAPIKey(token),
option.WithHeader("originator", "codex_cli_rs"),
option.WithHeader("OpenAI-Beta", "responses=experimental"),
}
if accountID != "" {
opts = append(opts, option.WithHeader("Chatgpt-Account-Id", accountID))
@ -41,6 +50,15 @@ func NewCodexProviderWithTokenSource(token, accountID string, tokenSource func()
func (p *CodexProvider) Chat(ctx context.Context, messages []Message, tools []ToolDefinition, model string, options map[string]interface{}) (*LLMResponse, error) {
var opts []option.RequestOption
accountID := p.accountID
resolvedModel, fallbackReason := resolveCodexModel(model)
if fallbackReason != "" {
logger.WarnCF("provider.codex", "Requested model is not compatible with Codex backend, using fallback", map[string]interface{}{
"requested_model": model,
"resolved_model": resolvedModel,
"reason": fallbackReason,
})
}
if p.tokenSource != nil {
tok, accID, err := p.tokenSource()
if err != nil {
@ -48,22 +66,120 @@ func (p *CodexProvider) Chat(ctx context.Context, messages []Message, tools []To
}
opts = append(opts, option.WithAPIKey(tok))
if accID != "" {
opts = append(opts, option.WithHeader("Chatgpt-Account-Id", accID))
accountID = accID
}
}
if accountID != "" {
opts = append(opts, option.WithHeader("Chatgpt-Account-Id", accountID))
} else {
logger.WarnCF("provider.codex", "No account id found for Codex request; backend may reject with 400", map[string]interface{}{
"requested_model": model,
"resolved_model": resolvedModel,
})
}
params := buildCodexParams(messages, tools, model, options)
params := buildCodexParams(messages, tools, resolvedModel, options)
resp, err := p.client.Responses.New(ctx, params, opts...)
stream := p.client.Responses.NewStreaming(ctx, params, opts...)
defer stream.Close()
var resp *responses.Response
for stream.Next() {
evt := stream.Current()
if evt.Type == "response.completed" || evt.Type == "response.failed" || evt.Type == "response.incomplete" {
evtResp := evt.Response
if evtResp.ID != "" {
copy := evtResp
resp = &copy
}
}
}
err := stream.Err()
if err != nil {
fields := map[string]interface{}{
"requested_model": model,
"resolved_model": resolvedModel,
"messages_count": len(messages),
"tools_count": len(tools),
"account_id_present": accountID != "",
"error": err.Error(),
}
var apiErr *openai.Error
if errors.As(err, &apiErr) {
fields["status_code"] = apiErr.StatusCode
fields["api_type"] = apiErr.Type
fields["api_code"] = apiErr.Code
fields["api_param"] = apiErr.Param
fields["api_message"] = apiErr.Message
if apiErr.StatusCode == 400 {
fields["hint"] = "verify account id header and model compatibility for codex backend"
}
if apiErr.Response != nil {
fields["request_id"] = apiErr.Response.Header.Get("x-request-id")
}
}
logger.ErrorCF("provider.codex", "Codex API call failed", fields)
return nil, fmt.Errorf("codex API call: %w", err)
}
if resp == nil {
fields := map[string]interface{}{
"requested_model": model,
"resolved_model": resolvedModel,
"messages_count": len(messages),
"tools_count": len(tools),
"account_id_present": accountID != "",
}
logger.ErrorCF("provider.codex", "Codex stream ended without completed response event", fields)
return nil, fmt.Errorf("codex API call: stream ended without completed response")
}
return parseCodexResponse(resp), nil
}
func (p *CodexProvider) GetDefaultModel() string {
return "gpt-4o"
return codexDefaultModel
}
func resolveCodexModel(model string) (string, string) {
m := strings.ToLower(strings.TrimSpace(model))
if m == "" {
return codexDefaultModel, "empty model"
}
if strings.HasPrefix(m, "openai/") {
m = strings.TrimPrefix(m, "openai/")
} else if strings.Contains(m, "/") {
return codexDefaultModel, "non-openai model namespace"
}
unsupportedPrefixes := []string{
"glm",
"claude",
"anthropic",
"gemini",
"google",
"moonshot",
"kimi",
"qwen",
"deepseek",
"llama",
"meta-llama",
"mistral",
"grok",
"xai",
"zhipu",
}
for _, prefix := range unsupportedPrefixes {
if strings.HasPrefix(m, prefix) {
return codexDefaultModel, "unsupported model prefix"
}
}
if strings.HasPrefix(m, "gpt-") || strings.HasPrefix(m, "o3") || strings.HasPrefix(m, "o4") {
return m, ""
}
return codexDefaultModel, "unsupported model family"
}
func buildCodexParams(messages []Message, tools []ToolDefinition, model string, options map[string]interface{}) responses.ResponseNewParams {
@ -133,21 +249,21 @@ func buildCodexParams(messages []Message, tools []ToolDefinition, model string,
Input: responses.ResponseNewParamsInputUnion{
OfInputItemList: inputItems,
},
Instructions: openai.Opt(instructions),
Store: openai.Opt(false),
}
if instructions != "" {
params.Instructions = openai.Opt(instructions)
} else {
// ChatGPT Codex backend requires instructions to be present.
params.Instructions = openai.Opt(defaultCodexInstructions)
}
if maxTokens, ok := options["max_tokens"].(int); ok {
params.MaxOutputTokens = openai.Opt(int64(maxTokens))
}
if temp, ok := options["temperature"].(float64); ok {
params.Temperature = openai.Opt(temp)
}
if len(tools) > 0 {
params.Tools = translateToolsForCodex(tools)
}
@ -237,6 +353,9 @@ func createCodexTokenSource() func() (string, string, error) {
if err != nil {
return "", "", fmt.Errorf("refreshing token: %w", err)
}
if refreshed.AccountID == "" {
refreshed.AccountID = cred.AccountID
}
if err := auth.SetCredential("openai", refreshed); err != nil {
return "", "", fmt.Errorf("saving refreshed token: %w", err)
}

View file

@ -2,6 +2,7 @@ package providers
import (
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"testing"
@ -17,10 +18,17 @@ func TestBuildCodexParams_BasicMessage(t *testing.T) {
}
params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{
"max_tokens": 2048,
"temperature": 0.7,
})
if params.Model != "gpt-4o" {
t.Errorf("Model = %q, want %q", params.Model, "gpt-4o")
}
if !params.Instructions.Valid() {
t.Fatal("Instructions should be set")
}
if params.Instructions.Or("") != defaultCodexInstructions {
t.Errorf("Instructions = %q, want %q", params.Instructions.Or(""), defaultCodexInstructions)
}
}
func TestBuildCodexParams_SystemAsInstructions(t *testing.T) {
@ -197,6 +205,16 @@ func TestCodexProvider_ChatRoundTrip(t *testing.T) {
return
}
var reqBody map[string]interface{}
if err := json.NewDecoder(r.Body).Decode(&reqBody); err != nil {
http.Error(w, "invalid json", http.StatusBadRequest)
return
}
if reqBody["stream"] != true {
http.Error(w, "stream must be true", http.StatusBadRequest)
return
}
resp := map[string]interface{}{
"id": "resp_test",
"object": "response",
@ -220,8 +238,7 @@ func TestCodexProvider_ChatRoundTrip(t *testing.T) {
"output_tokens_details": map[string]interface{}{"reasoning_tokens": 0},
},
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(resp)
writeCompletedSSE(w, resp)
}))
defer server.Close()
@ -244,10 +261,185 @@ func TestCodexProvider_ChatRoundTrip(t *testing.T) {
}
}
func TestCodexProvider_ChatRoundTrip_TokenSourceFallbackAccountID(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/responses" {
http.Error(w, "not found: "+r.URL.Path, http.StatusNotFound)
return
}
if r.Header.Get("Authorization") != "Bearer refreshed-token" {
http.Error(w, "unauthorized", http.StatusUnauthorized)
return
}
if r.Header.Get("Chatgpt-Account-Id") != "acc-123" {
http.Error(w, "missing account id", http.StatusBadRequest)
return
}
var reqBody map[string]interface{}
if err := json.NewDecoder(r.Body).Decode(&reqBody); err != nil {
http.Error(w, "invalid json", http.StatusBadRequest)
return
}
if _, ok := reqBody["instructions"]; !ok {
http.Error(w, "missing instructions", http.StatusBadRequest)
return
}
if reqBody["instructions"] == "" {
http.Error(w, "instructions must not be empty", http.StatusBadRequest)
return
}
if _, ok := reqBody["temperature"]; ok {
http.Error(w, "temperature is not supported", http.StatusBadRequest)
return
}
if reqBody["stream"] != true {
http.Error(w, "stream must be true", http.StatusBadRequest)
return
}
resp := map[string]interface{}{
"id": "resp_test",
"object": "response",
"status": "completed",
"output": []map[string]interface{}{
{
"id": "msg_1",
"type": "message",
"role": "assistant",
"status": "completed",
"content": []map[string]interface{}{
{"type": "output_text", "text": "Hi from Codex!"},
},
},
},
"usage": map[string]interface{}{
"input_tokens": 8,
"output_tokens": 4,
"total_tokens": 12,
"input_tokens_details": map[string]interface{}{"cached_tokens": 0},
"output_tokens_details": map[string]interface{}{"reasoning_tokens": 0},
},
}
writeCompletedSSE(w, resp)
}))
defer server.Close()
provider := NewCodexProvider("stale-token", "acc-123")
provider.client = createOpenAITestClient(server.URL, "stale-token", "")
provider.tokenSource = func() (string, string, error) {
return "refreshed-token", "", nil
}
messages := []Message{{Role: "user", Content: "Hello"}}
resp, err := provider.Chat(t.Context(), messages, nil, "gpt-4o", map[string]interface{}{"temperature": 0.7})
if err != nil {
t.Fatalf("Chat() error: %v", err)
}
if resp.Content != "Hi from Codex!" {
t.Errorf("Content = %q, want %q", resp.Content, "Hi from Codex!")
}
}
func TestCodexProvider_ChatRoundTrip_ModelFallbackFromUnsupported(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/responses" {
http.Error(w, "not found: "+r.URL.Path, http.StatusNotFound)
return
}
var reqBody map[string]interface{}
if err := json.NewDecoder(r.Body).Decode(&reqBody); err != nil {
http.Error(w, "invalid json", http.StatusBadRequest)
return
}
if reqBody["model"] != codexDefaultModel {
http.Error(w, "unsupported model", http.StatusBadRequest)
return
}
if reqBody["stream"] != true {
http.Error(w, "stream must be true", http.StatusBadRequest)
return
}
if reqBody["instructions"] != codexDefaultInstructions {
http.Error(w, "missing default instructions", http.StatusBadRequest)
return
}
resp := map[string]interface{}{
"id": "resp_test",
"object": "response",
"status": "completed",
"output": []map[string]interface{}{
{
"id": "msg_1",
"type": "message",
"role": "assistant",
"status": "completed",
"content": []map[string]interface{}{
{"type": "output_text", "text": "Hi from Codex!"},
},
},
},
"usage": map[string]interface{}{
"input_tokens": 8,
"output_tokens": 4,
"total_tokens": 12,
"input_tokens_details": map[string]interface{}{"cached_tokens": 0},
"output_tokens_details": map[string]interface{}{"reasoning_tokens": 0},
},
}
writeCompletedSSE(w, resp)
}))
defer server.Close()
provider := NewCodexProvider("test-token", "acc-123")
provider.client = createOpenAITestClient(server.URL, "test-token", "acc-123")
messages := []Message{{Role: "user", Content: "Hello"}}
resp, err := provider.Chat(t.Context(), messages, nil, "gpt-5.2", nil)
if err != nil {
t.Fatalf("Chat() error: %v", err)
}
if resp.Content != "Hi from Codex!" {
t.Errorf("Content = %q, want %q", resp.Content, "Hi from Codex!")
}
}
func TestCodexProvider_GetDefaultModel(t *testing.T) {
p := NewCodexProvider("test-token", "")
if got := p.GetDefaultModel(); got != "gpt-4o" {
t.Errorf("GetDefaultModel() = %q, want %q", got, "gpt-4o")
if got := p.GetDefaultModel(); got != codexDefaultModel {
t.Errorf("GetDefaultModel() = %q, want %q", got, codexDefaultModel)
}
}
func TestResolveCodexModel(t *testing.T) {
tests := []struct {
name string
input string
wantModel string
wantFallback bool
}{
{name: "empty", input: "", wantModel: codexDefaultModel, wantFallback: true},
{name: "unsupported namespace", input: "anthropic/claude-3.5", wantModel: codexDefaultModel, wantFallback: true},
{name: "non-openai prefixed", input: "glm-4.7", wantModel: codexDefaultModel, wantFallback: true},
{name: "openai prefix", input: "openai/gpt-5.2", wantModel: "gpt-5.2", wantFallback: false},
{name: "direct gpt", input: "gpt-4o", wantModel: "gpt-4o", wantFallback: false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
gotModel, reason := resolveCodexModel(tt.input)
if gotModel != tt.wantModel {
t.Fatalf("resolveCodexModel(%q) model = %q, want %q", tt.input, gotModel, tt.wantModel)
}
if tt.wantFallback && reason == "" {
t.Fatalf("resolveCodexModel(%q) expected fallback reason", tt.input)
}
if !tt.wantFallback && reason != "" {
t.Fatalf("resolveCodexModel(%q) unexpected fallback reason: %q", tt.input, reason)
}
})
}
}
@ -262,3 +454,16 @@ func createOpenAITestClient(baseURL, token, accountID string) *openai.Client {
c := openai.NewClient(opts...)
return &c
}
func writeCompletedSSE(w http.ResponseWriter, response map[string]interface{}) {
event := map[string]interface{}{
"type": "response.completed",
"sequence_number": 1,
"response": response,
}
b, _ := json.Marshal(event)
w.Header().Set("Content-Type", "text/event-stream")
fmt.Fprintf(w, "event: response.completed\n")
fmt.Fprintf(w, "data: %s\n\n", string(b))
fmt.Fprintf(w, "data: [DONE]\n\n")
}

View file

@ -0,0 +1,82 @@
package providers
import (
"context"
"fmt"
json "encoding/json"
copilot "github.com/github/copilot-sdk/go"
)
type GitHubCopilotProvider struct {
uri string
connectMode string // `stdio` or `grpc``
session *copilot.Session
}
func NewGitHubCopilotProvider(uri string, connectMode string, model string) (*GitHubCopilotProvider, error) {
var session *copilot.Session
if connectMode == "" {
connectMode = "grpc"
}
switch connectMode {
case "stdio":
//todo
case "grpc":
client := copilot.NewClient(&copilot.ClientOptions{
CLIUrl: uri,
})
if err := client.Start(context.Background()); err != nil {
return nil, fmt.Errorf("Can't connect to Github Copilot, https://github.com/github/copilot-sdk/blob/main/docs/getting-started.md#connecting-to-an-external-cli-server for details")
}
defer client.Stop()
session, _ = client.CreateSession(context.Background(), &copilot.SessionConfig{
Model: model,
Hooks: &copilot.SessionHooks{},
})
}
return &GitHubCopilotProvider{
uri: uri,
connectMode: connectMode,
session: session,
}, nil
}
// Chat sends a chat request to GitHub Copilot
func (p *GitHubCopilotProvider) Chat(ctx context.Context, messages []Message, tools []ToolDefinition, model string, options map[string]interface{}) (*LLMResponse, error) {
type tempMessage struct {
Role string `json:"role"`
Content string `json:"content"`
}
out := make([]tempMessage, 0, len(messages))
for _, msg := range messages {
out = append(out, tempMessage{
Role: msg.Role,
Content: msg.Content,
})
}
fullcontent, _ := json.Marshal(out)
content, _ := p.session.Send(ctx, copilot.MessageOptions{
Prompt: string(fullcontent),
})
return &LLMResponse{
FinishReason: "stop",
Content: content,
}, nil
}
func (p *GitHubCopilotProvider) GetDefaultModel() string {
return "gpt-4.1"
}

View file

@ -15,6 +15,7 @@ import (
"net/http"
"net/url"
"strings"
"time"
"github.com/sipeed/picoclaw/pkg/auth"
"github.com/sipeed/picoclaw/pkg/config"
@ -28,7 +29,7 @@ type HTTPProvider struct {
func NewHTTPProvider(apiKey, apiBase, proxy string) *HTTPProvider {
client := &http.Client{
Timeout: 0,
Timeout: 120 * time.Second,
}
if proxy != "" {
@ -52,10 +53,10 @@ func (p *HTTPProvider) Chat(ctx context.Context, messages []Message, tools []Too
return nil, fmt.Errorf("API base not configured")
}
// Strip provider prefix from model name (e.g., moonshot/kimi-k2.5 -> kimi-k2.5)
// Strip provider prefix from model name (e.g., moonshot/kimi-k2.5 -> kimi-k2.5, groq/openai/gpt-oss-120b -> openai/gpt-oss-120b, ollama/qwen2.5:14b -> qwen2.5:14b)
if idx := strings.Index(model, "/"); idx != -1 {
prefix := model[:idx]
if prefix == "moonshot" || prefix == "nvidia" {
if prefix == "moonshot" || prefix == "nvidia" || prefix == "groq" || prefix == "ollama" {
model = model[idx+1:]
}
}
@ -241,6 +242,9 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
}
case "openai", "gpt":
if cfg.Providers.OpenAI.APIKey != "" || cfg.Providers.OpenAI.AuthMethod != "" {
if cfg.Providers.OpenAI.AuthMethod == "codex-cli" {
return NewCodexProviderWithTokenSource("", "", CreateCodexCliTokenSource()), nil
}
if cfg.Providers.OpenAI.AuthMethod == "oauth" || cfg.Providers.OpenAI.AuthMethod == "token" {
return createCodexAuthProvider()
}
@ -300,12 +304,38 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
}
}
case "claude-cli", "claudecode", "claude-code":
workspace := cfg.Agents.Defaults.Workspace
workspace := cfg.WorkspacePath()
if workspace == "" {
workspace = "."
}
return NewClaudeCliProvider(workspace), nil
case "codex-cli", "codex-code":
workspace := cfg.WorkspacePath()
if workspace == "" {
workspace = "."
}
return NewCodexCliProvider(workspace), nil
case "deepseek":
if cfg.Providers.DeepSeek.APIKey != "" {
apiKey = cfg.Providers.DeepSeek.APIKey
apiBase = cfg.Providers.DeepSeek.APIBase
if apiBase == "" {
apiBase = "https://api.deepseek.com/v1"
}
if model != "deepseek-chat" && model != "deepseek-reasoner" {
model = "deepseek-chat"
}
}
case "github_copilot", "copilot":
if cfg.Providers.GitHubCopilot.APIBase != "" {
apiBase = cfg.Providers.GitHubCopilot.APIBase
} else {
apiBase = "localhost:4321"
}
return NewGitHubCopilotProvider(apiBase, cfg.Providers.GitHubCopilot.ConnectMode, model)
}
}
// Fallback: detect provider from model name
@ -381,7 +411,15 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
if apiBase == "" {
apiBase = "https://integrate.api.nvidia.com/v1"
}
case (strings.Contains(lowerModel, "ollama") || strings.HasPrefix(model, "ollama/")) && cfg.Providers.Ollama.APIKey != "":
fmt.Println("Ollama provider selected based on model name prefix")
apiKey = cfg.Providers.Ollama.APIKey
apiBase = cfg.Providers.Ollama.APIBase
proxy = cfg.Providers.Ollama.Proxy
if apiBase == "" {
apiBase = "http://localhost:11434/v1"
}
fmt.Println("Ollama apiBase:", apiBase)
case cfg.Providers.VLLM.APIBase != "":
apiKey = cfg.Providers.VLLM.APIKey
apiBase = cfg.Providers.VLLM.APIBase

View file

@ -0,0 +1,72 @@
package providers
import (
"encoding/json"
"strings"
)
// extractToolCallsFromText parses tool call JSON from response text.
// Both ClaudeCliProvider and CodexCliProvider use this to extract
// tool calls that the model outputs in its response text.
func extractToolCallsFromText(text string) []ToolCall {
start := strings.Index(text, `{"tool_calls"`)
if start == -1 {
return nil
}
end := findMatchingBrace(text, start)
if end == start {
return nil
}
jsonStr := text[start:end]
var wrapper struct {
ToolCalls []struct {
ID string `json:"id"`
Type string `json:"type"`
Function struct {
Name string `json:"name"`
Arguments string `json:"arguments"`
} `json:"function"`
} `json:"tool_calls"`
}
if err := json.Unmarshal([]byte(jsonStr), &wrapper); err != nil {
return nil
}
var result []ToolCall
for _, tc := range wrapper.ToolCalls {
var args map[string]interface{}
json.Unmarshal([]byte(tc.Function.Arguments), &args)
result = append(result, ToolCall{
ID: tc.ID,
Type: tc.Type,
Name: tc.Function.Name,
Arguments: args,
Function: &FunctionCall{
Name: tc.Function.Name,
Arguments: tc.Function.Arguments,
},
})
}
return result
}
// stripToolCallsFromText removes tool call JSON from response text.
func stripToolCallsFromText(text string) string {
start := strings.Index(text, `{"tool_calls"`)
if start == -1 {
return text
}
end := findMatchingBrace(text, start)
if end == start {
return text
}
return strings.TrimSpace(text[:start] + text[end:])
}

View file

@ -145,13 +145,27 @@ func (sm *SessionManager) TruncateHistory(key string, keepLast int) {
session.Updated = time.Now()
}
// sanitizeFilename converts a session key into a cross-platform safe filename.
// Session keys use "channel:chatID" (e.g. "telegram:123456") but ':' is the
// volume separator on Windows, so filepath.Base would misinterpret the key.
// We replace it with '_'. The original key is preserved inside the JSON file,
// so loadSessions still maps back to the right in-memory key.
func sanitizeFilename(key string) string {
return strings.ReplaceAll(key, ":", "_")
}
func (sm *SessionManager) Save(key string) error {
if sm.storage == "" {
return nil
}
// Validate key to avoid invalid filenames and path traversal.
if key == "" || key == "." || key == ".." || key != filepath.Base(key) || strings.Contains(key, "/") || strings.Contains(key, "\\") {
filename := sanitizeFilename(key)
// filepath.IsLocal rejects empty names, "..", absolute paths, and
// OS-reserved device names (NUL, COM1 … on Windows).
// The extra checks reject "." and any directory separators so that
// the session file is always written directly inside sm.storage.
if filename == "." || !filepath.IsLocal(filename) || strings.ContainsAny(filename, `/\`) {
return os.ErrInvalid
}
@ -182,7 +196,7 @@ func (sm *SessionManager) Save(key string) error {
return err
}
sessionPath := filepath.Join(sm.storage, key+".json")
sessionPath := filepath.Join(sm.storage, filename+".json")
tmpFile, err := os.CreateTemp(sm.storage, "session-*.tmp")
if err != nil {
return err
@ -250,3 +264,19 @@ func (sm *SessionManager) loadSessions() error {
return nil
}
// SetHistory updates the messages of a session.
func (sm *SessionManager) SetHistory(key string, history []providers.Message) {
sm.mu.Lock()
defer sm.mu.Unlock()
session, ok := sm.sessions[key]
if ok {
// Create a deep copy to strictly isolate internal state
// from the caller's slice.
msgs := make([]providers.Message, len(history))
copy(msgs, history)
session.Messages = msgs
session.Updated = time.Now()
}
}

View file

@ -0,0 +1,74 @@
package session
import (
"os"
"path/filepath"
"testing"
)
func TestSanitizeFilename(t *testing.T) {
tests := []struct {
input string
expected string
}{
{"simple", "simple"},
{"telegram:123456", "telegram_123456"},
{"discord:987654321", "discord_987654321"},
{"slack:C01234", "slack_C01234"},
{"no-colons-here", "no-colons-here"},
{"multiple:colons:here", "multiple_colons_here"},
}
for _, tt := range tests {
t.Run(tt.input, func(t *testing.T) {
got := sanitizeFilename(tt.input)
if got != tt.expected {
t.Errorf("sanitizeFilename(%q) = %q, want %q", tt.input, got, tt.expected)
}
})
}
}
func TestSave_WithColonInKey(t *testing.T) {
tmpDir := t.TempDir()
sm := NewSessionManager(tmpDir)
// Create a session with a key containing colon (typical channel session key).
key := "telegram:123456"
sm.GetOrCreate(key)
sm.AddMessage(key, "user", "hello")
// Save should succeed even though the key contains ':'
if err := sm.Save(key); err != nil {
t.Fatalf("Save(%q) failed: %v", key, err)
}
// The file on disk should use sanitized name.
expectedFile := filepath.Join(tmpDir, "telegram_123456.json")
if _, err := os.Stat(expectedFile); os.IsNotExist(err) {
t.Fatalf("expected session file %s to exist", expectedFile)
}
// Load into a fresh manager and verify the session round-trips.
sm2 := NewSessionManager(tmpDir)
history := sm2.GetHistory(key)
if len(history) != 1 {
t.Fatalf("expected 1 message after reload, got %d", len(history))
}
if history[0].Content != "hello" {
t.Errorf("expected message content %q, got %q", "hello", history[0].Content)
}
}
func TestSave_RejectsPathTraversal(t *testing.T) {
tmpDir := t.TempDir()
sm := NewSessionManager(tmpDir)
badKeys := []string{"", ".", "..", "foo/bar", "foo\\bar"}
for _, key := range badKeys {
sm.GetOrCreate(key)
if err := sm.Save(key); err == nil {
t.Errorf("Save(%q) should have failed but didn't", key)
}
}
}

View file

@ -2,13 +2,22 @@ package skills
import (
"encoding/json"
"errors"
"fmt"
"log/slog"
"os"
"path/filepath"
"regexp"
"strings"
)
var namePattern = regexp.MustCompile(`^[a-zA-Z0-9]+(-[a-zA-Z0-9]+)*$`)
const (
MaxNameLength = 64
MaxDescriptionLength = 1024
)
type SkillMetadata struct {
Name string `json:"name"`
Description string `json:"description"`
@ -21,6 +30,27 @@ type SkillInfo struct {
Description string `json:"description"`
}
func (info SkillInfo) validate() error {
var errs error
if info.Name == "" {
errs = errors.Join(errs, errors.New("name is required"))
} else {
if len(info.Name) > MaxNameLength {
errs = errors.Join(errs, fmt.Errorf("name exceeds %d characters", MaxNameLength))
}
if !namePattern.MatchString(info.Name) {
errs = errors.Join(errs, errors.New("name must be alphanumeric with hyphens"))
}
}
if info.Description == "" {
errs = errors.Join(errs, errors.New("description is required"))
} else if len(info.Description) > MaxDescriptionLength {
errs = errors.Join(errs, fmt.Errorf("description exceeds %d character", MaxDescriptionLength))
}
return errs
}
type SkillsLoader struct {
workspace string
workspaceSkills string // workspace skills (项目级别)
@ -54,6 +84,11 @@ func (sl *SkillsLoader) ListSkills() []SkillInfo {
metadata := sl.getSkillMetadata(skillFile)
if metadata != nil {
info.Description = metadata.Description
info.Name = metadata.Name
}
if err := info.validate(); err != nil {
slog.Warn("invalid skill from workspace", "name", info.Name, "error", err)
continue
}
skills = append(skills, info)
}
@ -89,6 +124,11 @@ func (sl *SkillsLoader) ListSkills() []SkillInfo {
metadata := sl.getSkillMetadata(skillFile)
if metadata != nil {
info.Description = metadata.Description
info.Name = metadata.Name
}
if err := info.validate(); err != nil {
slog.Warn("invalid skill from global", "name", info.Name, "error", err)
continue
}
skills = append(skills, info)
}
@ -123,6 +163,11 @@ func (sl *SkillsLoader) ListSkills() []SkillInfo {
metadata := sl.getSkillMetadata(skillFile)
if metadata != nil {
info.Description = metadata.Description
info.Name = metadata.Name
}
if err := info.validate(); err != nil {
slog.Warn("invalid skill from builtin", "name", info.Name, "error", err)
continue
}
skills = append(skills, info)
}

77
pkg/skills/loader_test.go Normal file
View file

@ -0,0 +1,77 @@
package skills
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestSkillsInfoValidate(t *testing.T) {
testcases := []struct {
name string
skillName string
description string
wantErr bool
errContains []string
}{
{
name: "valid-skill",
skillName: "valid-skill",
description: "a valid skill description",
wantErr: false,
},
{
name: "empty-name",
skillName: "",
description: "description without name",
wantErr: true,
errContains: []string{"name is required"},
},
{
name: "empty-description",
skillName: "skill-without-description",
description: "",
wantErr: true,
errContains: []string{"description is required"},
},
{
name: "empty-both",
skillName: "",
description: "",
wantErr: true,
errContains: []string{"name is required", "description is required"},
},
{
name: "name-with-spaces",
skillName: "skill with spaces",
description: "invalid name with spaces",
wantErr: true,
errContains: []string{"name must be alphanumeric with hyphens"},
},
{
name: "name-with-underscore",
skillName: "skill_underscore",
description: "invalid name with underscore",
wantErr: true,
errContains: []string{"name must be alphanumeric with hyphens"},
},
}
for _, tc := range testcases {
t.Run(tc.name, func(t *testing.T) {
info := SkillInfo{
Name: tc.skillName,
Description: tc.description,
}
err := info.validate()
if tc.wantErr {
assert.Error(t, err)
for _, msg := range tc.errContains {
assert.ErrorContains(t, err, msg)
}
} else {
assert.NoError(t, err)
}
})
}
}

View file

@ -28,12 +28,12 @@ type CronTool struct {
}
// NewCronTool creates a new CronTool
func NewCronTool(cronService *cron.CronService, executor JobExecutor, msgBus *bus.MessageBus, workspace string) *CronTool {
func NewCronTool(cronService *cron.CronService, executor JobExecutor, msgBus *bus.MessageBus, workspace string, restrict bool) *CronTool {
return &CronTool{
cronService: cronService,
executor: executor,
msgBus: msgBus,
execTool: NewExecTool(workspace, false),
execTool: NewExecTool(workspace, restrict),
}
}

View file

@ -29,13 +29,54 @@ func validatePath(path, workspace string, restrict bool) (string, error) {
}
}
if restrict && !strings.HasPrefix(absPath, absWorkspace) {
if restrict {
if !isWithinWorkspace(absPath, absWorkspace) {
return "", fmt.Errorf("access denied: path is outside the workspace")
}
workspaceReal := absWorkspace
if resolved, err := filepath.EvalSymlinks(absWorkspace); err == nil {
workspaceReal = resolved
}
if resolved, err := filepath.EvalSymlinks(absPath); err == nil {
if !isWithinWorkspace(resolved, workspaceReal) {
return "", fmt.Errorf("access denied: symlink resolves outside workspace")
}
} else if os.IsNotExist(err) {
if parentResolved, err := resolveExistingAncestor(filepath.Dir(absPath)); err == nil {
if !isWithinWorkspace(parentResolved, workspaceReal) {
return "", fmt.Errorf("access denied: symlink resolves outside workspace")
}
} else if !os.IsNotExist(err) {
return "", fmt.Errorf("failed to resolve path: %w", err)
}
} else {
return "", fmt.Errorf("failed to resolve path: %w", err)
}
}
return absPath, nil
}
func resolveExistingAncestor(path string) (string, error) {
for current := filepath.Clean(path); ; current = filepath.Dir(current) {
if resolved, err := filepath.EvalSymlinks(current); err == nil {
return resolved, nil
} else if !os.IsNotExist(err) {
return "", err
}
if filepath.Dir(current) == current {
return "", os.ErrNotExist
}
}
}
func isWithinWorkspace(candidate, workspace string) bool {
rel, err := filepath.Rel(filepath.Clean(workspace), filepath.Clean(candidate))
return err == nil && rel != ".." && !strings.HasPrefix(rel, ".."+string(os.PathSeparator))
}
type ReadFileTool struct {
workspace string
restrict bool

View file

@ -247,3 +247,35 @@ func TestFilesystemTool_ListDir_DefaultPath(t *testing.T) {
t.Errorf("Expected success with default path '.', got IsError=true: %s", result.ForLLM)
}
}
// Block paths that look inside workspace but point outside via symlink.
func TestFilesystemTool_ReadFile_RejectsSymlinkEscape(t *testing.T) {
root := t.TempDir()
workspace := filepath.Join(root, "workspace")
if err := os.MkdirAll(workspace, 0755); err != nil {
t.Fatalf("failed to create workspace: %v", err)
}
secret := filepath.Join(root, "secret.txt")
if err := os.WriteFile(secret, []byte("top secret"), 0644); err != nil {
t.Fatalf("failed to write secret file: %v", err)
}
link := filepath.Join(workspace, "leak.txt")
if err := os.Symlink(secret, link); err != nil {
t.Skipf("symlink not supported in this environment: %v", err)
}
tool := NewReadFileTool(workspace, true)
result := tool.Execute(context.Background(), map[string]interface{}{
"path": link,
})
if !result.IsError {
t.Fatalf("expected symlink escape to be blocked")
}
if !strings.Contains(result.ForLLM, "symlink resolves outside workspace") {
t.Fatalf("expected symlink escape error, got: %s", result.ForLLM)
}
}

147
pkg/tools/i2c.go Normal file
View file

@ -0,0 +1,147 @@
package tools
import (
"context"
"encoding/json"
"fmt"
"path/filepath"
"regexp"
"runtime"
)
// I2CTool provides I2C bus interaction for reading sensors and controlling peripherals.
type I2CTool struct{}
func NewI2CTool() *I2CTool {
return &I2CTool{}
}
func (t *I2CTool) Name() string {
return "i2c"
}
func (t *I2CTool) Description() string {
return "Interact with I2C bus devices for reading sensors and controlling peripherals. Actions: detect (list buses), scan (find devices on a bus), read (read bytes from device), write (send bytes to device). Linux only."
}
func (t *I2CTool) Parameters() map[string]interface{} {
return map[string]interface{}{
"type": "object",
"properties": map[string]interface{}{
"action": map[string]interface{}{
"type": "string",
"enum": []string{"detect", "scan", "read", "write"},
"description": "Action to perform: detect (list available I2C buses), scan (find devices on a bus), read (read bytes from a device), write (send bytes to a device)",
},
"bus": map[string]interface{}{
"type": "string",
"description": "I2C bus number (e.g. \"1\" for /dev/i2c-1). Required for scan/read/write.",
},
"address": map[string]interface{}{
"type": "integer",
"description": "7-bit I2C device address (0x03-0x77). Required for read/write.",
},
"register": map[string]interface{}{
"type": "integer",
"description": "Register address to read from or write to. If set, sends register byte before read/write.",
},
"data": map[string]interface{}{
"type": "array",
"items": map[string]interface{}{"type": "integer"},
"description": "Bytes to write (0-255 each). Required for write action.",
},
"length": map[string]interface{}{
"type": "integer",
"description": "Number of bytes to read (1-256). Default: 1. Used with read action.",
},
"confirm": map[string]interface{}{
"type": "boolean",
"description": "Must be true for write operations. Safety guard to prevent accidental writes.",
},
},
"required": []string{"action"},
}
}
func (t *I2CTool) Execute(ctx context.Context, args map[string]interface{}) *ToolResult {
if runtime.GOOS != "linux" {
return ErrorResult("I2C is only supported on Linux. This tool requires /dev/i2c-* device files.")
}
action, ok := args["action"].(string)
if !ok {
return ErrorResult("action is required")
}
switch action {
case "detect":
return t.detect()
case "scan":
return t.scan(args)
case "read":
return t.readDevice(args)
case "write":
return t.writeDevice(args)
default:
return ErrorResult(fmt.Sprintf("unknown action: %s (valid: detect, scan, read, write)", action))
}
}
// detect lists available I2C buses by globbing /dev/i2c-*
func (t *I2CTool) detect() *ToolResult {
matches, err := filepath.Glob("/dev/i2c-*")
if err != nil {
return ErrorResult(fmt.Sprintf("failed to scan for I2C buses: %v", err))
}
if len(matches) == 0 {
return SilentResult("No I2C buses found. You may need to:\n1. Load the i2c-dev module: modprobe i2c-dev\n2. Check that I2C is enabled in device tree\n3. Configure pinmux for your board (see hardware skill)")
}
type busInfo struct {
Path string `json:"path"`
Bus string `json:"bus"`
}
buses := make([]busInfo, 0, len(matches))
re := regexp.MustCompile(`/dev/i2c-(\d+)`)
for _, m := range matches {
if sub := re.FindStringSubmatch(m); sub != nil {
buses = append(buses, busInfo{Path: m, Bus: sub[1]})
}
}
result, _ := json.MarshalIndent(buses, "", " ")
return SilentResult(fmt.Sprintf("Found %d I2C bus(es):\n%s", len(buses), string(result)))
}
// isValidBusID checks that a bus identifier is a simple number (prevents path injection)
func isValidBusID(id string) bool {
matched, _ := regexp.MatchString(`^\d+$`, id)
return matched
}
// parseI2CAddress extracts and validates an I2C address from args
func parseI2CAddress(args map[string]interface{}) (int, *ToolResult) {
addrFloat, ok := args["address"].(float64)
if !ok {
return 0, ErrorResult("address is required (e.g. 0x38 for AHT20)")
}
addr := int(addrFloat)
if addr < 0x03 || addr > 0x77 {
return 0, ErrorResult("address must be in valid 7-bit range (0x03-0x77)")
}
return addr, nil
}
// parseI2CBus extracts and validates an I2C bus from args
func parseI2CBus(args map[string]interface{}) (string, *ToolResult) {
bus, ok := args["bus"].(string)
if !ok || bus == "" {
return "", ErrorResult("bus is required (e.g. \"1\" for /dev/i2c-1)")
}
if !isValidBusID(bus) {
return "", ErrorResult("invalid bus identifier: must be a number (e.g. \"1\")")
}
return bus, nil
}

282
pkg/tools/i2c_linux.go Normal file
View file

@ -0,0 +1,282 @@
package tools
import (
"encoding/json"
"fmt"
"syscall"
"unsafe"
)
// I2C ioctl constants from Linux kernel headers (<linux/i2c-dev.h>, <linux/i2c.h>)
const (
i2cSlave = 0x0703 // Set slave address (fails if in use by driver)
i2cFuncs = 0x0705 // Query adapter functionality bitmask
i2cSmbus = 0x0720 // Perform SMBus transaction
// I2C_FUNC capability bits
i2cFuncSmbusQuick = 0x00010000
i2cFuncSmbusReadByte = 0x00020000
// SMBus transaction types
i2cSmbusRead = 0
i2cSmbusWrite = 1
// SMBus protocol sizes
i2cSmbusQuick = 0
i2cSmbusByte = 1
)
// i2cSmbusData matches the kernel union i2c_smbus_data (34 bytes max).
// For quick and byte transactions only the first byte is used (if at all).
type i2cSmbusData [34]byte
// i2cSmbusArgs matches the kernel struct i2c_smbus_ioctl_data.
type i2cSmbusArgs struct {
readWrite uint8
command uint8
size uint32
data *i2cSmbusData
}
// smbusProbe performs a single SMBus probe at the given address.
// Uses SMBus Quick Write (safest) or falls back to SMBus Read Byte for
// EEPROM address ranges where quick write can corrupt AT24RF08 chips.
// This matches i2cdetect's MODE_AUTO behavior.
func smbusProbe(fd int, addr int, hasQuick bool) bool {
// EEPROM ranges: use read byte (quick write can corrupt AT24RF08)
useReadByte := (addr >= 0x30 && addr <= 0x37) || (addr >= 0x50 && addr <= 0x5F)
if !useReadByte && hasQuick {
// SMBus Quick Write: [START] [ADDR|W] [ACK/NACK] [STOP]
// Safest probe — no data transferred
args := i2cSmbusArgs{
readWrite: i2cSmbusWrite,
command: 0,
size: i2cSmbusQuick,
data: nil,
}
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), i2cSmbus, uintptr(unsafe.Pointer(&args)))
return errno == 0
}
// SMBus Read Byte: [START] [ADDR|R] [ACK/NACK] [DATA] [STOP]
var data i2cSmbusData
args := i2cSmbusArgs{
readWrite: i2cSmbusRead,
command: 0,
size: i2cSmbusByte,
data: &data,
}
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), i2cSmbus, uintptr(unsafe.Pointer(&args)))
return errno == 0
}
// scan probes valid 7-bit addresses on a bus for connected devices.
// Uses the same hybrid probe strategy as i2cdetect's MODE_AUTO:
// SMBus Quick Write for most addresses, SMBus Read Byte for EEPROM ranges.
func (t *I2CTool) scan(args map[string]interface{}) *ToolResult {
bus, errResult := parseI2CBus(args)
if errResult != nil {
return errResult
}
devPath := fmt.Sprintf("/dev/i2c-%s", bus)
fd, err := syscall.Open(devPath, syscall.O_RDWR, 0)
if err != nil {
return ErrorResult(fmt.Sprintf("failed to open %s: %v (check permissions and i2c-dev module)", devPath, err))
}
defer syscall.Close(fd)
// Query adapter capabilities to determine available probe methods.
// I2C_FUNCS writes an unsigned long, which is word-sized on Linux.
var funcs uintptr
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), i2cFuncs, uintptr(unsafe.Pointer(&funcs)))
if errno != 0 {
return ErrorResult(fmt.Sprintf("failed to query I2C adapter capabilities on %s: %v", devPath, errno))
}
hasQuick := funcs&i2cFuncSmbusQuick != 0
hasReadByte := funcs&i2cFuncSmbusReadByte != 0
if !hasQuick && !hasReadByte {
return ErrorResult(fmt.Sprintf("I2C adapter %s supports neither SMBus Quick nor Read Byte — cannot probe safely", devPath))
}
type deviceEntry struct {
Address string `json:"address"`
Status string `json:"status,omitempty"`
}
var found []deviceEntry
// Scan 0x08-0x77, skipping I2C reserved addresses 0x00-0x07
for addr := 0x08; addr <= 0x77; addr++ {
// Set slave address — EBUSY means a kernel driver owns this address
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), i2cSlave, uintptr(addr))
if errno != 0 {
if errno == syscall.EBUSY {
found = append(found, deviceEntry{
Address: fmt.Sprintf("0x%02x", addr),
Status: "busy (in use by kernel driver)",
})
}
continue
}
if smbusProbe(fd, addr, hasQuick) {
found = append(found, deviceEntry{
Address: fmt.Sprintf("0x%02x", addr),
})
}
}
if len(found) == 0 {
return SilentResult(fmt.Sprintf("No devices found on %s. Check wiring and pull-up resistors.", devPath))
}
result, _ := json.MarshalIndent(map[string]interface{}{
"bus": devPath,
"devices": found,
"count": len(found),
}, "", " ")
return SilentResult(fmt.Sprintf("Scan of %s:\n%s", devPath, string(result)))
}
// readDevice reads bytes from an I2C device, optionally at a specific register
func (t *I2CTool) readDevice(args map[string]interface{}) *ToolResult {
bus, errResult := parseI2CBus(args)
if errResult != nil {
return errResult
}
addr, errResult := parseI2CAddress(args)
if errResult != nil {
return errResult
}
length := 1
if l, ok := args["length"].(float64); ok {
length = int(l)
}
if length < 1 || length > 256 {
return ErrorResult("length must be between 1 and 256")
}
devPath := fmt.Sprintf("/dev/i2c-%s", bus)
fd, err := syscall.Open(devPath, syscall.O_RDWR, 0)
if err != nil {
return ErrorResult(fmt.Sprintf("failed to open %s: %v", devPath, err))
}
defer syscall.Close(fd)
// Set slave address
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), i2cSlave, uintptr(addr))
if errno != 0 {
return ErrorResult(fmt.Sprintf("failed to set I2C address 0x%02x: %v", addr, errno))
}
// If register is specified, write it first
if regFloat, ok := args["register"].(float64); ok {
reg := int(regFloat)
if reg < 0 || reg > 255 {
return ErrorResult("register must be between 0x00 and 0xFF")
}
_, err := syscall.Write(fd, []byte{byte(reg)})
if err != nil {
return ErrorResult(fmt.Sprintf("failed to write register 0x%02x: %v", reg, err))
}
}
// Read data
buf := make([]byte, length)
n, err := syscall.Read(fd, buf)
if err != nil {
return ErrorResult(fmt.Sprintf("failed to read from device 0x%02x: %v", addr, err))
}
// Format as hex bytes
hexBytes := make([]string, n)
intBytes := make([]int, n)
for i := 0; i < n; i++ {
hexBytes[i] = fmt.Sprintf("0x%02x", buf[i])
intBytes[i] = int(buf[i])
}
result, _ := json.MarshalIndent(map[string]interface{}{
"bus": devPath,
"address": fmt.Sprintf("0x%02x", addr),
"bytes": intBytes,
"hex": hexBytes,
"length": n,
}, "", " ")
return SilentResult(string(result))
}
// writeDevice writes bytes to an I2C device, optionally at a specific register
func (t *I2CTool) writeDevice(args map[string]interface{}) *ToolResult {
confirm, _ := args["confirm"].(bool)
if !confirm {
return ErrorResult("write operations require confirm: true. Please confirm with the user before writing to I2C devices, as incorrect writes can misconfigure hardware.")
}
bus, errResult := parseI2CBus(args)
if errResult != nil {
return errResult
}
addr, errResult := parseI2CAddress(args)
if errResult != nil {
return errResult
}
dataRaw, ok := args["data"].([]interface{})
if !ok || len(dataRaw) == 0 {
return ErrorResult("data is required for write (array of byte values 0-255)")
}
if len(dataRaw) > 256 {
return ErrorResult("data too long: maximum 256 bytes per I2C transaction")
}
data := make([]byte, 0, len(dataRaw)+1)
// If register is specified, prepend it to the data
if regFloat, ok := args["register"].(float64); ok {
reg := int(regFloat)
if reg < 0 || reg > 255 {
return ErrorResult("register must be between 0x00 and 0xFF")
}
data = append(data, byte(reg))
}
for i, v := range dataRaw {
f, ok := v.(float64)
if !ok {
return ErrorResult(fmt.Sprintf("data[%d] is not a valid byte value", i))
}
b := int(f)
if b < 0 || b > 255 {
return ErrorResult(fmt.Sprintf("data[%d] = %d is out of byte range (0-255)", i, b))
}
data = append(data, byte(b))
}
devPath := fmt.Sprintf("/dev/i2c-%s", bus)
fd, err := syscall.Open(devPath, syscall.O_RDWR, 0)
if err != nil {
return ErrorResult(fmt.Sprintf("failed to open %s: %v", devPath, err))
}
defer syscall.Close(fd)
// Set slave address
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), i2cSlave, uintptr(addr))
if errno != 0 {
return ErrorResult(fmt.Sprintf("failed to set I2C address 0x%02x: %v", addr, errno))
}
// Write data
n, err := syscall.Write(fd, data)
if err != nil {
return ErrorResult(fmt.Sprintf("failed to write to device 0x%02x: %v", addr, err))
}
return SilentResult(fmt.Sprintf("Wrote %d byte(s) to device 0x%02x on %s", n, addr, devPath))
}

18
pkg/tools/i2c_other.go Normal file
View file

@ -0,0 +1,18 @@
//go:build !linux
package tools
// scan is a stub for non-Linux platforms.
func (t *I2CTool) scan(args map[string]interface{}) *ToolResult {
return ErrorResult("I2C is only supported on Linux")
}
// readDevice is a stub for non-Linux platforms.
func (t *I2CTool) readDevice(args map[string]interface{}) *ToolResult {
return ErrorResult("I2C is only supported on Linux")
}
// writeDevice is a stub for non-Linux platforms.
func (t *I2CTool) writeDevice(args map[string]interface{}) *ToolResult {
return ErrorResult("I2C is only supported on Linux")
}

156
pkg/tools/spi.go Normal file
View file

@ -0,0 +1,156 @@
package tools
import (
"context"
"encoding/json"
"fmt"
"path/filepath"
"regexp"
"runtime"
)
// SPITool provides SPI bus interaction for high-speed peripheral communication.
type SPITool struct{}
func NewSPITool() *SPITool {
return &SPITool{}
}
func (t *SPITool) Name() string {
return "spi"
}
func (t *SPITool) Description() string {
return "Interact with SPI bus devices for high-speed peripheral communication. Actions: list (find SPI devices), transfer (full-duplex send/receive), read (receive bytes). Linux only."
}
func (t *SPITool) Parameters() map[string]interface{} {
return map[string]interface{}{
"type": "object",
"properties": map[string]interface{}{
"action": map[string]interface{}{
"type": "string",
"enum": []string{"list", "transfer", "read"},
"description": "Action to perform: list (find available SPI devices), transfer (full-duplex send/receive), read (receive bytes by sending zeros)",
},
"device": map[string]interface{}{
"type": "string",
"description": "SPI device identifier (e.g. \"2.0\" for /dev/spidev2.0). Required for transfer/read.",
},
"speed": map[string]interface{}{
"type": "integer",
"description": "SPI clock speed in Hz. Default: 1000000 (1 MHz).",
},
"mode": map[string]interface{}{
"type": "integer",
"description": "SPI mode (0-3). Default: 0. Mode sets CPOL and CPHA: 0=0,0 1=0,1 2=1,0 3=1,1.",
},
"bits": map[string]interface{}{
"type": "integer",
"description": "Bits per word. Default: 8.",
},
"data": map[string]interface{}{
"type": "array",
"items": map[string]interface{}{"type": "integer"},
"description": "Bytes to send (0-255 each). Required for transfer action.",
},
"length": map[string]interface{}{
"type": "integer",
"description": "Number of bytes to read (1-4096). Required for read action.",
},
"confirm": map[string]interface{}{
"type": "boolean",
"description": "Must be true for transfer operations. Safety guard to prevent accidental writes.",
},
},
"required": []string{"action"},
}
}
func (t *SPITool) Execute(ctx context.Context, args map[string]interface{}) *ToolResult {
if runtime.GOOS != "linux" {
return ErrorResult("SPI is only supported on Linux. This tool requires /dev/spidev* device files.")
}
action, ok := args["action"].(string)
if !ok {
return ErrorResult("action is required")
}
switch action {
case "list":
return t.list()
case "transfer":
return t.transfer(args)
case "read":
return t.readDevice(args)
default:
return ErrorResult(fmt.Sprintf("unknown action: %s (valid: list, transfer, read)", action))
}
}
// list finds available SPI devices by globbing /dev/spidev*
func (t *SPITool) list() *ToolResult {
matches, err := filepath.Glob("/dev/spidev*")
if err != nil {
return ErrorResult(fmt.Sprintf("failed to scan for SPI devices: %v", err))
}
if len(matches) == 0 {
return SilentResult("No SPI devices found. You may need to:\n1. Enable SPI in device tree\n2. Configure pinmux for your board (see hardware skill)\n3. Check that spidev module is loaded")
}
type devInfo struct {
Path string `json:"path"`
Device string `json:"device"`
}
devices := make([]devInfo, 0, len(matches))
re := regexp.MustCompile(`/dev/spidev(\d+\.\d+)`)
for _, m := range matches {
if sub := re.FindStringSubmatch(m); sub != nil {
devices = append(devices, devInfo{Path: m, Device: sub[1]})
}
}
result, _ := json.MarshalIndent(devices, "", " ")
return SilentResult(fmt.Sprintf("Found %d SPI device(s):\n%s", len(devices), string(result)))
}
// parseSPIArgs extracts and validates common SPI parameters
func parseSPIArgs(args map[string]interface{}) (device string, speed uint32, mode uint8, bits uint8, errMsg string) {
dev, ok := args["device"].(string)
if !ok || dev == "" {
return "", 0, 0, 0, "device is required (e.g. \"2.0\" for /dev/spidev2.0)"
}
matched, _ := regexp.MatchString(`^\d+\.\d+$`, dev)
if !matched {
return "", 0, 0, 0, "invalid device identifier: must be in format \"X.Y\" (e.g. \"2.0\")"
}
speed = 1000000 // default 1 MHz
if s, ok := args["speed"].(float64); ok {
if s < 1 || s > 125000000 {
return "", 0, 0, 0, "speed must be between 1 Hz and 125 MHz"
}
speed = uint32(s)
}
mode = 0
if m, ok := args["mode"].(float64); ok {
if int(m) < 0 || int(m) > 3 {
return "", 0, 0, 0, "mode must be 0-3"
}
mode = uint8(m)
}
bits = 8
if b, ok := args["bits"].(float64); ok {
if int(b) < 1 || int(b) > 32 {
return "", 0, 0, 0, "bits must be between 1 and 32"
}
bits = uint8(b)
}
return dev, speed, mode, bits, ""
}

196
pkg/tools/spi_linux.go Normal file
View file

@ -0,0 +1,196 @@
package tools
import (
"encoding/json"
"fmt"
"runtime"
"syscall"
"unsafe"
)
// SPI ioctl constants from Linux kernel headers.
// Calculated from _IOW('k', nr, size) macro:
//
// direction(1)<<30 | size<<16 | type(0x6B)<<8 | nr
const (
spiIocWrMode = 0x40016B01 // _IOW('k', 1, __u8)
spiIocWrBitsPerWord = 0x40016B03 // _IOW('k', 3, __u8)
spiIocWrMaxSpeedHz = 0x40046B04 // _IOW('k', 4, __u32)
spiIocMessage1 = 0x40206B00 // _IOW('k', 0, struct spi_ioc_transfer) — 32 bytes
)
// spiTransfer matches Linux kernel struct spi_ioc_transfer (32 bytes on all architectures).
type spiTransfer struct {
txBuf uint64
rxBuf uint64
length uint32
speedHz uint32
delayUsecs uint16
bitsPerWord uint8
csChange uint8
txNbits uint8
rxNbits uint8
wordDelay uint8
pad uint8
}
// configureSPI opens an SPI device and sets mode, bits per word, and speed
func configureSPI(devPath string, mode uint8, bits uint8, speed uint32) (int, *ToolResult) {
fd, err := syscall.Open(devPath, syscall.O_RDWR, 0)
if err != nil {
return -1, ErrorResult(fmt.Sprintf("failed to open %s: %v (check permissions and spidev module)", devPath, err))
}
// Set SPI mode
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), spiIocWrMode, uintptr(unsafe.Pointer(&mode)))
if errno != 0 {
syscall.Close(fd)
return -1, ErrorResult(fmt.Sprintf("failed to set SPI mode %d: %v", mode, errno))
}
// Set bits per word
_, _, errno = syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), spiIocWrBitsPerWord, uintptr(unsafe.Pointer(&bits)))
if errno != 0 {
syscall.Close(fd)
return -1, ErrorResult(fmt.Sprintf("failed to set bits per word %d: %v", bits, errno))
}
// Set max speed
_, _, errno = syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), spiIocWrMaxSpeedHz, uintptr(unsafe.Pointer(&speed)))
if errno != 0 {
syscall.Close(fd)
return -1, ErrorResult(fmt.Sprintf("failed to set SPI speed %d Hz: %v", speed, errno))
}
return fd, nil
}
// transfer performs a full-duplex SPI transfer
func (t *SPITool) transfer(args map[string]interface{}) *ToolResult {
confirm, _ := args["confirm"].(bool)
if !confirm {
return ErrorResult("transfer operations require confirm: true. Please confirm with the user before sending data to SPI devices.")
}
dev, speed, mode, bits, errMsg := parseSPIArgs(args)
if errMsg != "" {
return ErrorResult(errMsg)
}
dataRaw, ok := args["data"].([]interface{})
if !ok || len(dataRaw) == 0 {
return ErrorResult("data is required for transfer (array of byte values 0-255)")
}
if len(dataRaw) > 4096 {
return ErrorResult("data too long: maximum 4096 bytes per SPI transfer")
}
txBuf := make([]byte, len(dataRaw))
for i, v := range dataRaw {
f, ok := v.(float64)
if !ok {
return ErrorResult(fmt.Sprintf("data[%d] is not a valid byte value", i))
}
b := int(f)
if b < 0 || b > 255 {
return ErrorResult(fmt.Sprintf("data[%d] = %d is out of byte range (0-255)", i, b))
}
txBuf[i] = byte(b)
}
devPath := fmt.Sprintf("/dev/spidev%s", dev)
fd, errResult := configureSPI(devPath, mode, bits, speed)
if errResult != nil {
return errResult
}
defer syscall.Close(fd)
rxBuf := make([]byte, len(txBuf))
xfer := spiTransfer{
txBuf: uint64(uintptr(unsafe.Pointer(&txBuf[0]))),
rxBuf: uint64(uintptr(unsafe.Pointer(&rxBuf[0]))),
length: uint32(len(txBuf)),
speedHz: speed,
bitsPerWord: bits,
}
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), spiIocMessage1, uintptr(unsafe.Pointer(&xfer)))
runtime.KeepAlive(txBuf)
runtime.KeepAlive(rxBuf)
if errno != 0 {
return ErrorResult(fmt.Sprintf("SPI transfer failed: %v", errno))
}
// Format received bytes
hexBytes := make([]string, len(rxBuf))
intBytes := make([]int, len(rxBuf))
for i, b := range rxBuf {
hexBytes[i] = fmt.Sprintf("0x%02x", b)
intBytes[i] = int(b)
}
result, _ := json.MarshalIndent(map[string]interface{}{
"device": devPath,
"sent": len(txBuf),
"received": intBytes,
"hex": hexBytes,
}, "", " ")
return SilentResult(string(result))
}
// readDevice reads bytes from SPI by sending zeros (read-only, no confirm needed)
func (t *SPITool) readDevice(args map[string]interface{}) *ToolResult {
dev, speed, mode, bits, errMsg := parseSPIArgs(args)
if errMsg != "" {
return ErrorResult(errMsg)
}
length := 0
if l, ok := args["length"].(float64); ok {
length = int(l)
}
if length < 1 || length > 4096 {
return ErrorResult("length is required for read (1-4096)")
}
devPath := fmt.Sprintf("/dev/spidev%s", dev)
fd, errResult := configureSPI(devPath, mode, bits, speed)
if errResult != nil {
return errResult
}
defer syscall.Close(fd)
txBuf := make([]byte, length) // zeros
rxBuf := make([]byte, length)
xfer := spiTransfer{
txBuf: uint64(uintptr(unsafe.Pointer(&txBuf[0]))),
rxBuf: uint64(uintptr(unsafe.Pointer(&rxBuf[0]))),
length: uint32(length),
speedHz: speed,
bitsPerWord: bits,
}
_, _, errno := syscall.Syscall(syscall.SYS_IOCTL, uintptr(fd), spiIocMessage1, uintptr(unsafe.Pointer(&xfer)))
runtime.KeepAlive(txBuf)
runtime.KeepAlive(rxBuf)
if errno != 0 {
return ErrorResult(fmt.Sprintf("SPI read failed: %v", errno))
}
hexBytes := make([]string, len(rxBuf))
intBytes := make([]int, len(rxBuf))
for i, b := range rxBuf {
hexBytes[i] = fmt.Sprintf("0x%02x", b)
intBytes[i] = int(b)
}
result, _ := json.MarshalIndent(map[string]interface{}{
"device": devPath,
"bytes": intBytes,
"hex": hexBytes,
"length": len(rxBuf),
}, "", " ")
return SilentResult(string(result))
}

13
pkg/tools/spi_other.go Normal file
View file

@ -0,0 +1,13 @@
//go:build !linux
package tools
// transfer is a stub for non-Linux platforms.
func (t *SPITool) transfer(args map[string]interface{}) *ToolResult {
return ErrorResult("SPI is only supported on Linux")
}
// readDevice is a stub for non-Linux platforms.
func (t *SPITool) readDevice(args map[string]interface{}) *ToolResult {
return ErrorResult("SPI is only supported on Linux")
}

View file

@ -171,13 +171,6 @@ func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query
return strings.Join(lines, "\n"), nil
}
func min(a, b int) int {
if a < b {
return a
}
return b
}
func stripTags(content string) string {
re := regexp.MustCompile(`<[^>]+>`)
return re.ReplaceAllString(content, "")

View file

@ -173,19 +173,23 @@ func TestWebTool_WebFetch_Truncation(t *testing.T) {
}
}
// TestWebTool_WebSearch_NoApiKey verifies that nil is returned when no provider is configured
// TestWebTool_WebSearch_NoApiKey verifies that no tool is created when API key is missing
func TestWebTool_WebSearch_NoApiKey(t *testing.T) {
tool := NewWebSearchTool(WebSearchToolOptions{BraveAPIKey: "", BraveMaxResults: 5})
// Should return nil when no provider is enabled
tool := NewWebSearchTool(WebSearchToolOptions{BraveEnabled: true, BraveAPIKey: ""})
if tool != nil {
t.Errorf("Expected nil when no search provider is configured")
t.Errorf("Expected nil tool when Brave API key is empty")
}
// Also nil when nothing is enabled
tool = NewWebSearchTool(WebSearchToolOptions{})
if tool != nil {
t.Errorf("Expected nil tool when no provider is enabled")
}
}
// TestWebTool_WebSearch_MissingQuery verifies error handling for missing query
func TestWebTool_WebSearch_MissingQuery(t *testing.T) {
tool := NewWebSearchTool(WebSearchToolOptions{BraveAPIKey: "test-key", BraveMaxResults: 5, BraveEnabled: true})
tool := NewWebSearchTool(WebSearchToolOptions{BraveEnabled: true, BraveAPIKey: "test-key", BraveMaxResults: 5})
ctx := context.Background()
args := map[string]interface{}{}

View file

@ -73,9 +73,8 @@ func DownloadFile(url, filename string, opts DownloadOptions) string {
}
// Generate unique filename with UUID prefix to prevent conflicts
ext := filepath.Ext(filename)
safeName := SanitizeFilename(filename)
localPath := filepath.Join(mediaDir, uuid.New().String()[:8]+"_"+safeName+ext)
localPath := filepath.Join(mediaDir, uuid.New().String()[:8]+"_"+safeName)
// Create HTTP request
req, err := http.NewRequest("GET", url, nil)

12
workspace/AGENT.md Normal file
View file

@ -0,0 +1,12 @@
# Agent Instructions
You are a helpful AI assistant. Be concise, accurate, and friendly.
## Guidelines
- Always explain what you're doing before taking actions
- Ask for clarification when request is ambiguous
- Use tools to help accomplish tasks
- Remember important information in your memory files
- Be proactive and helpful
- Learn from user feedback

56
workspace/IDENTITY.md Normal file
View file

@ -0,0 +1,56 @@
# Identity
## Name
PicoClaw 🦞
## Description
Ultra-lightweight personal AI assistant written in Go, inspired by nanobot.
## Version
0.1.0
## Purpose
- Provide intelligent AI assistance with minimal resource usage
- Support multiple LLM providers (OpenAI, Anthropic, Zhipu, etc.)
- Enable easy customization through skills system
- Run on minimal hardware ($10 boards, <10MB RAM)
## Capabilities
- Web search and content fetching
- File system operations (read, write, edit)
- Shell command execution
- Multi-channel messaging (Telegram, WhatsApp, Feishu)
- Skill-based extensibility
- Memory and context management
## Philosophy
- Simplicity over complexity
- Performance over features
- User control and privacy
- Transparent operation
- Community-driven development
## Goals
- Provide a fast, lightweight AI assistant
- Support offline-first operation where possible
- Enable easy customization and extension
- Maintain high quality responses
- Run efficiently on constrained hardware
## License
MIT License - Free and open source
## Repository
https://github.com/sipeed/picoclaw
## Contact
Issues: https://github.com/sipeed/picoclaw/issues
Discussions: https://github.com/sipeed/picoclaw/discussions
---
"Every bit helps, every bit matters."
- Picoclaw

17
workspace/SOUL.md Normal file
View file

@ -0,0 +1,17 @@
# Soul
I am picoclaw, a lightweight AI assistant powered by AI.
## Personality
- Helpful and friendly
- Concise and to the point
- Curious and eager to learn
- Honest and transparent
## Values
- Accuracy over speed
- User privacy and safety
- Transparency in actions
- Continuous improvement

21
workspace/USER.md Normal file
View file

@ -0,0 +1,21 @@
# User
Information about user goes here.
## Preferences
- Communication style: (casual/formal)
- Timezone: (your timezone)
- Language: (your preferred language)
## Personal Information
- Name: (optional)
- Location: (optional)
- Occupation: (optional)
## Learning Goals
- What the user wants to learn from AI
- Preferred interaction style
- Areas of interest

View file

@ -0,0 +1,21 @@
# Long-term Memory
This file stores important information that should persist across sessions.
## User Information
(Important facts about user)
## Preferences
(User preferences learned over time)
## Important Notes
(Things to remember)
## Configuration
- Model preferences
- Channel settings
- Skills enabled

View file

@ -0,0 +1,64 @@
---
name: hardware
description: Read and control I2C and SPI peripherals on Sipeed boards (LicheeRV Nano, MaixCAM, NanoKVM).
homepage: https://wiki.sipeed.com/hardware/en/lichee/RV_Nano/1_intro.html
metadata: {"nanobot":{"emoji":"🔧","requires":{"tools":["i2c","spi"]}}}
---
# Hardware (I2C / SPI)
Use the `i2c` and `spi` tools to interact with sensors, displays, and other peripherals connected to the board.
## Quick Start
```
# 1. Find available buses
i2c detect
# 2. Scan for connected devices
i2c scan (bus: "1")
# 3. Read from a sensor (e.g. AHT20 temperature/humidity)
i2c read (bus: "1", address: 0x38, register: 0xAC, length: 6)
# 4. SPI devices
spi list
spi read (device: "2.0", length: 4)
```
## Before You Start — Pinmux Setup
Most I2C/SPI pins are shared with WiFi on Sipeed boards. You must configure pinmux before use.
See `references/board-pinout.md` for board-specific commands.
**Common steps:**
1. Stop WiFi if using shared pins: `/etc/init.d/S30wifi stop`
2. Load i2c-dev module: `modprobe i2c-dev`
3. Configure pinmux with `devmem` (board-specific)
4. Verify with `i2c detect` and `i2c scan`
## Safety
- **Write operations** require `confirm: true` — always confirm with the user first
- I2C addresses are validated to 7-bit range (0x03-0x77)
- SPI modes are validated (0-3 only)
- Maximum per-transaction: 256 bytes (I2C), 4096 bytes (SPI)
## Common Devices
See `references/common-devices.md` for register maps and usage of popular sensors:
AHT20, BME280, SSD1306 OLED, MPU6050 IMU, DS3231 RTC, INA219 power monitor, PCA9685 PWM, and more.
## Troubleshooting
| Problem | Solution |
|---------|----------|
| No I2C buses found | `modprobe i2c-dev` and check device tree |
| Permission denied | Run as root or add user to `i2c` group |
| No devices on scan | Check wiring, pull-up resistors (4.7k typical), and pinmux |
| Bus number changed | I2C adapter numbers can shift between boots; use `i2c detect` to find current assignment |
| WiFi stopped working | I2C-1/SPI-2 share pins with WiFi SDIO; can't use both simultaneously |
| `devmem` not found | Download separately or use `busybox devmem` |
| SPI transfer returns all zeros | Check MISO wiring and device power |
| SPI transfer returns all 0xFF | Device not responding; check CS pin and clock polarity (mode) |

View file

@ -0,0 +1,131 @@
# Board Pinout & Pinmux Reference
## LicheeRV Nano (SG2002)
### I2C Buses
| Bus | Pins | Notes |
|-----|------|-------|
| I2C-1 | P18 (SCL), P21 (SDA) | **Shared with WiFi SDIO** — must stop WiFi first |
| I2C-3 | Available on header | Check device tree for pin assignment |
| I2C-5 | Software (BitBang) | Slower but no pin conflicts |
### SPI Buses
| Bus | Pins | Notes |
|-----|------|-------|
| SPI-2 | P18 (CS), P21 (MISO), P22 (MOSI), P23 (SCK) | **Shared with WiFi** — must stop WiFi first |
| SPI-4 | Software (BitBang) | Slower but no pin conflicts |
### Setup Steps for I2C-1
```bash
# 1. Stop WiFi (shares pins with I2C-1)
/etc/init.d/S30wifi stop
# 2. Configure pinmux for I2C-1
devmem 0x030010D0 b 0x2 # P18 → I2C1_SCL
devmem 0x030010DC b 0x2 # P21 → I2C1_SDA
# 3. Load i2c-dev module
modprobe i2c-dev
# 4. Verify
ls /dev/i2c-*
```
### Setup Steps for SPI-2
```bash
# 1. Stop WiFi (shares pins with SPI-2)
/etc/init.d/S30wifi stop
# 2. Configure pinmux for SPI-2
devmem 0x030010D0 b 0x1 # P18 → SPI2_CS
devmem 0x030010DC b 0x1 # P21 → SPI2_MISO
devmem 0x030010E0 b 0x1 # P22 → SPI2_MOSI
devmem 0x030010E4 b 0x1 # P23 → SPI2_SCK
# 3. Verify
ls /dev/spidev*
```
### Max Tested SPI Speed
- SPI-2 hardware: tested up to **93 MHz**
- `spidev_test` is pre-installed on the official image for loopback testing
---
## MaixCAM
### I2C Buses
| Bus | Pins | Notes |
|-----|------|-------|
| I2C-1 | Overlaps with WiFi | Not recommended |
| I2C-3 | Overlaps with WiFi | Not recommended |
| I2C-5 | A15 (SCL), A27 (SDA) | **Recommended** — software I2C, no conflicts |
### Setup Steps for I2C-5
```bash
# Configure pins using pinmap utility
# (MaixCAM uses a pinmap tool instead of devmem)
# Refer to: https://wiki.sipeed.com/hardware/en/maixcam/gpio.html
# Load i2c-dev
modprobe i2c-dev
# Verify
ls /dev/i2c-*
```
---
## MaixCAM2
### I2C Buses
| Bus | Pins | Notes |
|-----|------|-------|
| I2C-6 | A1 (SCL), A0 (SDA) | Available on header |
| I2C-7 | Available | Check device tree |
### Setup Steps
```bash
# Configure pinmap for I2C-6
# A1 → I2C6_SCL, A0 → I2C6_SDA
# Refer to MaixCAM2 documentation for pinmap commands
modprobe i2c-dev
ls /dev/i2c-*
```
---
## NanoKVM
Uses the same SG2002 SoC as LicheeRV Nano. GPIO and I2C access follows the same pinmux procedure. Refer to the LicheeRV Nano section above.
Check NanoKVM-specific pin headers for available I2C/SPI lines:
- https://wiki.sipeed.com/hardware/en/kvm/NanoKVM/introduction.html
---
## Common Issues
### devmem not found
The `devmem` utility may not be in the default image. Options:
- Use `busybox devmem` if busybox is installed
- Download devmem from the Sipeed package repository
- Cross-compile from source (single C file)
### Dynamic bus numbering
I2C adapter numbers can change between boots depending on driver load order. Always use `i2c detect` to find current bus assignments rather than hardcoding bus numbers.
### Permissions
`/dev/i2c-*` and `/dev/spidev*` typically require root access. Options:
- Run picoclaw as root
- Add user to `i2c` and `spi` groups
- Create udev rules: `SUBSYSTEM=="i2c-dev", MODE="0666"`

View file

@ -0,0 +1,78 @@
# Common I2C/SPI Device Reference
## I2C Devices
### AHT20 — Temperature & Humidity
- **Address:** 0x38
- **Init:** Write `[0xBE, 0x08, 0x00]` then wait 10ms
- **Measure:** Write `[0xAC, 0x33, 0x00]`, wait 80ms, read 6 bytes
- **Parse:** Status=byte[0], Humidity=(byte[1]<<12|byte[2]<<4|byte[3]>>4)/2^20*100, Temp=(byte[3]&0x0F<<16|byte[4]<<8|byte[5])/2^20*200-50
- **Notes:** No register addressing — write command bytes directly (omit `register` param)
### BME280 / BMP280 — Temperature, Humidity, Pressure
- **Address:** 0x76 or 0x77 (SDO pin selects)
- **Chip ID register:** 0xD0 → BMP280=0x58, BME280=0x60
- **Data registers:** 0xF7-0xFE (pressure, temperature, humidity)
- **Config:** Write 0xF2 (humidity oversampling), 0xF4 (temp/press oversampling + mode), 0xF5 (standby, filter)
- **Forced measurement:** Write `[0x25]` to register 0xF4, wait 40ms, read 8 bytes from 0xF7
- **Calibration:** Read 26 bytes from 0x88 and 7 bytes from 0xE1 for compensation formulas
- **Also available via SPI** (mode 0 or 3)
### SSD1306 — 128x64 OLED Display
- **Address:** 0x3C (or 0x3D if SA0 high)
- **Command prefix:** 0x00 (write to register 0x00)
- **Data prefix:** 0x40 (write to register 0x40)
- **Init sequence:** `[0xAE, 0xD5, 0x80, 0xA8, 0x3F, 0xD3, 0x00, 0x40, 0x8D, 0x14, 0x20, 0x00, 0xA1, 0xC8, 0xDA, 0x12, 0x81, 0xCF, 0xD9, 0xF1, 0xDB, 0x40, 0xA4, 0xA6, 0xAF]`
- **Display on:** 0xAF, **Display off:** 0xAE
- **Also available via SPI** (faster, recommended for animations)
### MPU6050 — 6-axis Accelerometer + Gyroscope
- **Address:** 0x68 (or 0x69 if AD0 high)
- **WHO_AM_I:** Register 0x75 → should return 0x68
- **Wake up:** Write `[0x00]` to register 0x6B (clear sleep bit)
- **Read accel:** 6 bytes from register 0x3B (XH,XL,YH,YL,ZH,ZL) — signed 16-bit, default ±2g
- **Read gyro:** 6 bytes from register 0x43 — signed 16-bit, default ±250°/s
- **Read temp:** 2 bytes from register 0x41 — Temp°C = value/340 + 36.53
### DS3231 — Real-Time Clock
- **Address:** 0x68
- **Read time:** 7 bytes from register 0x00 (seconds, minutes, hours, day, date, month, year) — BCD encoded
- **Set time:** Write 7 BCD bytes to register 0x00
- **Temperature:** 2 bytes from register 0x11 (signed, 0.25°C resolution)
- **Status:** Register 0x0F — bit 2 = busy, bit 0 = alarm 1 flag
### INA219 — Current & Power Monitor
- **Address:** 0x40-0x4F (A0,A1 pin selectable)
- **Config:** Register 0x00 — set voltage range, gain, ADC resolution
- **Shunt voltage:** Register 0x01 (signed 16-bit, LSB=10µV)
- **Bus voltage:** Register 0x02 (bits 15:3, LSB=4mV)
- **Power:** Register 0x03 (after calibration)
- **Current:** Register 0x04 (after calibration)
- **Calibration:** Register 0x05 — set based on shunt resistor value
### PCA9685 — 16-Channel PWM / Servo Controller
- **Address:** 0x40-0x7F (A0-A5 selectable, default 0x40)
- **Mode 1:** Register 0x00 — bit 4=sleep, bit 5=auto-increment
- **Set PWM freq:** Sleep → write prescale to 0xFE → wake. Prescale = round(25MHz / (4096 × freq)) - 1
- **Channel N on/off:** Registers 0x06+4*N to 0x09+4*N (ON_L, ON_H, OFF_L, OFF_H)
- **Servo 0°-180°:** ON=0, OFF=150-600 (at 50Hz). Typical: 0°=150, 90°=375, 180°=600
### AT24C256 — 256Kbit EEPROM
- **Address:** 0x50-0x57 (A0-A2 selectable)
- **Read:** Write 2-byte address (high, low), then read N bytes
- **Write:** Write 2-byte address + up to 64 bytes (page write), wait 5ms for write cycle
- **Page size:** 64 bytes. Writes that cross page boundary wrap around.
## SPI Devices
### MCP3008 — 8-Channel 10-bit ADC
- **Interface:** SPI mode 0, max 3.6 MHz @ 5V
- **Read channel N:** Send `[0x01, (0x80 | N<<4), 0x00]`, result in last 10 bits of bytes 1-2
- **Formula:** value = ((byte[1] & 0x03) << 8) | byte[2]
- **Voltage:** value × Vref / 1024
### W25Q128 — 128Mbit SPI Flash
- **Interface:** SPI mode 0 or 3, up to 104 MHz
- **Read ID:** Send `[0x9F, 0, 0, 0]` → manufacturer + device ID
- **Read data:** Send `[0x03, addr_high, addr_mid, addr_low]` + N zero bytes
- **Status:** Send `[0x05, 0]` → bit 0 = BUSY