auto: sync OpenClaw config 2026-09-16 16:13

This commit is contained in:
2026-09-16 16:13:36 +08:00
parent c51006a57d
commit 5ac4289f66
35 changed files with 4827 additions and 65 deletions
@@ -0,0 +1,374 @@
# Entry Examples
Concrete examples of well-formatted entries with all fields.
## Learning: Correction
```markdown
## [LRN-20250115-001] correction
**Logged**: 2025-01-15T10:30:00Z
**Priority**: high
**Status**: pending
**Area**: tests
### Summary
Incorrectly assumed pytest fixtures are scoped to function by default
### Details
When writing test fixtures, I assumed all fixtures were function-scoped.
User corrected that while function scope is the default, the codebase
convention uses module-scoped fixtures for database connections to
improve test performance.
### Suggested Action
When creating fixtures that involve expensive setup (DB, network),
check existing fixtures for scope patterns before defaulting to function scope.
### Metadata
- Source: user_feedback
- Related Files: tests/conftest.py
- Tags: pytest, testing, fixtures
---
```
## Learning: Knowledge Gap (Resolved)
```markdown
## [LRN-20250115-002] knowledge_gap
**Logged**: 2025-01-15T14:22:00Z
**Priority**: medium
**Status**: resolved
**Area**: config
### Summary
Project uses pnpm not npm for package management
### Details
Attempted to run `npm install` but project uses pnpm workspaces.
Lock file is `pnpm-lock.yaml`, not `package-lock.json`.
### Suggested Action
Check for `pnpm-lock.yaml` or `pnpm-workspace.yaml` before assuming npm.
Use `pnpm install` for this project.
### Metadata
- Source: error
- Related Files: pnpm-lock.yaml, pnpm-workspace.yaml
- Tags: package-manager, pnpm, setup
### Resolution
- **Resolved**: 2025-01-15T14:30:00Z
- **Commit/PR**: N/A - knowledge update
- **Notes**: Added to TOOLS.md for future reference
---
```
## Learning: Promoted to TOOLS.md
```markdown
## [LRN-20250115-003] best_practice
**Logged**: 2025-01-15T16:00:00Z
**Priority**: high
**Status**: promoted
**Promoted**: TOOLS.md
**Area**: backend
### Summary
API responses must include correlation ID from request headers
### Details
All API responses should echo back the X-Correlation-ID header from
the request. This is required for distributed tracing. Responses
without this header break the observability pipeline.
### Suggested Action
Always include correlation ID passthrough in API handlers.
### Metadata
- Source: user_feedback
- Related Files: src/middleware/correlation.ts
- Tags: api, observability, tracing
---
```
## Learning: Promoted to AGENTS.md
```markdown
## [LRN-20250116-001] best_practice
**Logged**: 2025-01-16T09:00:00Z
**Priority**: high
**Status**: promoted
**Promoted**: AGENTS.md
**Area**: backend
### Summary
Must regenerate API client after OpenAPI spec changes
### Details
When modifying API endpoints, the TypeScript client must be regenerated.
Forgetting this causes type mismatches that only appear at runtime.
The generate script also runs validation.
### Suggested Action
Add to agent workflow: after any API changes, run `pnpm run generate:api`.
### Metadata
- Source: error
- Related Files: openapi.yaml, src/client/api.ts
- Tags: api, codegen, typescript
---
```
## Error Entry
```markdown
## [ERR-20250115-A3F] docker_build
**Logged**: 2025-01-15T09:15:00Z
**Priority**: high
**Status**: pending
**Area**: infra
### Summary
Docker build fails on M1 Mac due to platform mismatch
### Error
```
error: failed to solve: python:3.11-slim: no match for platform linux/arm64
```
### Context
- Command: `docker build -t myapp .`
- Dockerfile uses `FROM python:3.11-slim`
- Running on Apple Silicon (M1/M2)
### Suggested Fix
Add platform flag: `docker build --platform linux/amd64 -t myapp .`
Or update Dockerfile: `FROM --platform=linux/amd64 python:3.11-slim`
### Metadata
- Reproducible: yes
- Related Files: Dockerfile
---
```
## Error Entry: Recurring Issue
```markdown
## [ERR-20250120-B2C] api_timeout
**Logged**: 2025-01-20T11:30:00Z
**Priority**: critical
**Status**: pending
**Area**: backend
### Summary
Third-party API timeout during request processing
### Error
```
TimeoutError: Request to api.example.com timed out after 30000ms
```
### Context
- Command: POST /api/process
- Timeout set to 30s
- Occurs during peak hours (lunch, evening)
### Suggested Fix
Implement retry with exponential backoff. Consider circuit breaker pattern.
### Metadata
- Reproducible: yes (during peak hours)
- Related Files: src/services/api-client.ts
- See Also: ERR-20250115-X1Y, ERR-20250118-Z3W
---
```
## Feature Request
```markdown
## [FEAT-20250115-001] export_to_csv
**Logged**: 2025-01-15T16:45:00Z
**Priority**: medium
**Status**: pending
**Area**: backend
### Requested Capability
Export analysis results to CSV format
### User Context
User runs weekly reports and needs to share results with non-technical
stakeholders in Excel. Currently copies output manually.
### Complexity Estimate
simple
### Suggested Implementation
Add `--output csv` flag to the analyze command. Use standard csv module.
Could extend existing `--output json` pattern.
### Metadata
- Frequency: recurring
- Related Features: analyze command, json output
---
```
## Feature Request: Resolved
```markdown
## [FEAT-20250110-002] dark_mode
**Logged**: 2025-01-10T14:00:00Z
**Priority**: low
**Status**: resolved
**Area**: frontend
### Requested Capability
Dark mode support for the dashboard
### User Context
User works late hours and finds the bright interface straining.
Several other users have mentioned this informally.
### Complexity Estimate
medium
### Suggested Implementation
Use CSS variables for colors. Add toggle in user settings.
Consider system preference detection.
### Metadata
- Frequency: recurring
- Related Features: user settings, theme system
### Resolution
- **Resolved**: 2025-01-18T16:00:00Z
- **Commit/PR**: #142
- **Notes**: Implemented with system preference detection and manual toggle
---
```
## Learning: Promoted to Skill
```markdown
## [LRN-20250118-001] best_practice
**Logged**: 2025-01-18T11:00:00Z
**Priority**: high
**Status**: promoted_to_skill
**Skill-Path**: skills/docker-m1-fixes
**Area**: infra
### Summary
Docker build fails on Apple Silicon due to platform mismatch
### Details
When building Docker images on M1/M2 Macs, the build fails because
the base image doesn't have an ARM64 variant. This is a common issue
that affects many developers.
### Suggested Action
Add `--platform linux/amd64` to docker build command, or use
`FROM --platform=linux/amd64` in Dockerfile.
### Metadata
- Source: error
- Related Files: Dockerfile
- Tags: docker, arm64, m1, apple-silicon
- See Also: ERR-20250115-A3F, ERR-20250117-B2D
---
```
## Extracted Skill Example
When the above learning is extracted as a skill, it becomes:
**File**: `skills/docker-m1-fixes/SKILL.md`
```markdown
---
name: docker-m1-fixes
description: "Fixes Docker build failures on Apple Silicon (M1/M2). Use when docker build fails with platform mismatch errors."
---
# Docker M1 Fixes
Solutions for Docker build issues on Apple Silicon Macs.
## Quick Reference
| Error | Fix |
|-------|-----|
| `no match for platform linux/arm64` | Add `--platform linux/amd64` to build |
| Image runs but crashes | Use emulation or find ARM-compatible base |
## The Problem
Many Docker base images don't have ARM64 variants. When building on
Apple Silicon (M1/M2/M3), Docker attempts to pull ARM64 images by
default, causing platform mismatch errors.
## Solutions
### Option 1: Build Flag (Recommended)
Add platform flag to your build command:
\`\`\`bash
docker build --platform linux/amd64 -t myapp .
\`\`\`
### Option 2: Dockerfile Modification
Specify platform in the FROM instruction:
\`\`\`dockerfile
FROM --platform=linux/amd64 python:3.11-slim
\`\`\`
### Option 3: Docker Compose
Add platform to your service:
\`\`\`yaml
services:
app:
platform: linux/amd64
build: .
\`\`\`
## Trade-offs
| Approach | Pros | Cons |
|----------|------|------|
| Build flag | No file changes | Must remember flag |
| Dockerfile | Explicit, versioned | Affects all builds |
| Compose | Convenient for dev | Requires compose |
## Performance Note
Running AMD64 images on ARM64 uses Rosetta 2 emulation. This works
for development but may be slower. For production, find ARM-native
alternatives when possible.
## Source
- Learning ID: LRN-20250118-001
- Category: best_practice
- Extraction Date: 2025-01-18
```
@@ -0,0 +1,333 @@
# OpenClaw Integration
Complete setup and usage guide for integrating the self-improvement skill with OpenClaw.
## Overview
OpenClaw uses workspace-based prompt injection combined with event-driven hooks. Context is injected from workspace files at session start, and hooks can trigger on lifecycle events.
## Workspace Structure
```
~/.openclaw/
├── workspace/ # Working directory
│ ├── AGENTS.md # Multi-agent coordination patterns
│ ├── SOUL.md # Behavioral guidelines and personality
│ ├── TOOLS.md # Tool capabilities and gotchas
│ ├── MEMORY.md # Long-term memory (main session only)
│ └── memory/ # Daily memory files
│ └── YYYY-MM-DD.md
├── skills/ # Installed skills
│ └── <skill-name>/
│ └── SKILL.md
└── hooks/ # Custom hooks
└── <hook-name>/
├── HOOK.md
└── handler.ts
```
## Quick Setup
### 1. Install the Skill
```bash
openclaw skills install @pskoett/self-improving-agent
```
Or with the ClawHub CLI (`npm i -g clawhub`) — note this installs into
`./skills` under the current working directory, not the workspace:
```bash
clawhub install @pskoett/self-improving-agent
```
Or copy manually — the skill package is the `self-improving-agent/`
subfolder of the repo, not the repo root:
```bash
git clone https://github.com/pskoett/self-improving-agent.git /tmp/self-improving-agent-repo
cp -r /tmp/self-improving-agent-repo/self-improving-agent ~/.openclaw/skills/self-improving-agent
```
### 2. Install the Hook (Optional)
Copy the hook to OpenClaw's hooks directory:
```bash
cp -r ~/.openclaw/skills/self-improving-agent/hooks/openclaw ~/.openclaw/hooks/self-improvement
```
Enable the hook:
```bash
openclaw hooks enable self-improvement
```
The hook does two things:
- **`agent:bootstrap`** — injects the self-improvement reminder into session
context (and flags auto-detected errors awaiting triage)
- **`command:new` / `command:reset`** — sweeps the transcript of the session
that just ended for error patterns and appends pending entries to
`<workspace>/.learnings/ERRORS.md` (only if `.learnings/` exists — see
[Error Detection](#error-detection))
### 3. Create Learning Files
Create the `.learnings/` directory in your workspace:
```bash
mkdir -p ~/.openclaw/workspace/.learnings
```
Or in the skill directory:
```bash
mkdir -p ~/.openclaw/skills/self-improving-agent/.learnings
```
## Injected Prompt Files
### AGENTS.md
Purpose: Multi-agent workflows and delegation patterns.
```markdown
# Agent Coordination
## Delegation Rules
- Use explore agent for open-ended codebase questions
- Spawn sub-agents for long-running tasks
- Use sessions_send for cross-session communication
## Session Handoff
When delegating to another session:
1. Provide full context in the handoff message
2. Include relevant file paths
3. Specify expected output format
```
### SOUL.md
Purpose: Behavioral guidelines and communication style.
```markdown
# Behavioral Guidelines
## Communication Style
- Be direct and concise
- Avoid unnecessary caveats and disclaimers
- Use technical language appropriate to context
## Error Handling
- Admit mistakes promptly
- Provide corrected information immediately
- Log significant errors to learnings
```
### TOOLS.md
Purpose: Tool capabilities, integration gotchas, local configuration.
```markdown
# Tool Knowledge
## Self-Improvement Skill
Log learnings to `.learnings/` for continuous improvement.
## Local Tools
- Document tool-specific gotchas here
- Note authentication requirements
- Track integration quirks
```
## Learning Workflow
### Capturing Learnings
1. **In-session**: Log to `.learnings/` as usual
2. **Cross-session**: Promote to workspace files
### Promotion Decision Tree
```
Is the learning project-specific?
├── Yes → Keep in .learnings/
└── No → Is it behavioral/style-related?
├── Yes → Promote to SOUL.md
└── No → Is it tool-related?
├── Yes → Promote to TOOLS.md
└── No → Promote to AGENTS.md (workflow)
```
### Promotion Format Examples
**From learning:**
> Git push to GitHub fails without auth configured - triggers desktop prompt
**To TOOLS.md:**
```markdown
## Git
- Don't push without confirming auth is configured
- Use `gh auth status` to check GitHub CLI auth
```
## Inter-Agent Communication
OpenClaw provides tools for cross-session communication:
Use these only when cross-session sharing is explicitly needed and the environment is trusted. Prefer short sanitized summaries over raw transcripts, command output, or secret-bearing content.
### sessions_list
View active and recent sessions:
```
sessions_list(activeMinutes=30, messageLimit=3)
```
### sessions_history
Read transcript from another session:
```
sessions_history(sessionKey="session-id", limit=50)
```
Only read another session's transcript when the user explicitly wants shared context or continuation across sessions.
### sessions_send
Send message to another session:
```
sessions_send(sessionKey="session-id", message="Learning: API requires X-Custom-Header")
```
Prefer sending a concise learning summary plus relevant paths rather than forwarding raw transcript content.
### sessions_spawn
Spawn a background sub-agent:
```
sessions_spawn(task="Research X and report back", label="research")
```
## Available Hook Events
| Event | When It Fires |
|-------|---------------|
| `agent:bootstrap` | Before workspace files inject |
| `command:new` | When `/new` command issued |
| `command:reset` | When `/reset` command issued |
| `command:stop` | When `/stop` command issued |
| `gateway:startup` | When gateway starts |
| `gateway:shutdown` | When gateway shuts down |
| `message:received` / `message:sent` | Around message delivery |
| `session:compact:before` / `:after` | Around session compaction |
**Important:** OpenClaw has **no per-tool-call event** — nothing fires after
each individual tool call, so real-time per-command error detection is not
possible. Error detection is done at session end instead (see below).
## Error Detection
The skill's hook (`hooks/openclaw/`) implements a **session-end error
sweep**:
1. When `/new` or `/reset` ends a session, the hook resolves the ended
session's transcript from `context.previousSessionEntry` (falling back to
`<workspace>/sessions/<sessionId>.jsonl`) — the same source OpenClaw's
bundled `session-memory` hook uses.
2. The transcript is scanned against a fixed error-pattern list (`Error:`,
`command not found`, `Traceback`, `npm ERR!`, `Permission denied`, …).
3. Matches are appended to `<workspace>/.learnings/ERRORS.md` as a `pending`
entry with `Source: openclaw-error-sweep`, containing at most 5 short
excerpts (truncated to 200 chars, common secret shapes redacted,
duplicates skipped). Each entry is stamped with deterministic
`Pattern-Key` values derived from the matched pattern (for example
`ModuleNotFoundError``deps.module-not-found`), so recurrences can be
counted by key during triage — see the Pattern-Key Taxonomy in `SKILL.md`.
4. At the next `agent:bootstrap`, the injected reminder includes a
**pending triage** note so the agent reviews the auto-detected entries —
confirming real errors, filling in fixes, or deleting noise.
### Enabling / Disabling the Sweep
The sweep is opt-in and gated on the `.learnings/` directory:
```bash
# Enable
mkdir -p ~/.openclaw/workspace/.learnings
# Disable (reminder injection keeps working)
rm -r ~/.openclaw/workspace/.learnings
```
### Sweep Limitations
- Sessions that are never ended with `/new` or `/reset` are not swept.
- Detection happens at session end, not immediately after the failing
command — there is no per-tool-call event to hook.
- Pattern matching is heuristic; it can flag false positives such as prose
containing the word "failed" — that's what the triage step is for.
- Excerpts are redacted with best-effort rules; treat `.learnings/` as
potentially sensitive and keep it out of version control by default.
## Detection Triggers
### Standard Triggers
- User corrections ("No, that's wrong...")
- Command failures (non-zero exit codes)
- API errors
- Knowledge gaps
### OpenClaw-Specific Triggers
| Trigger | Action |
|---------|--------|
| Tool call error | Log to TOOLS.md with tool name |
| Session handoff confusion | Log to AGENTS.md with delegation pattern |
| Model behavior surprise | Log to SOUL.md with expected vs actual |
| Skill issue | Log to .learnings/ or report upstream |
## Verification
Check hook is registered:
```bash
openclaw hooks list
```
Check skill is loaded:
```bash
openclaw status
```
## Troubleshooting
### Hook not firing
1. Ensure hooks enabled in config
2. Restart gateway after config changes
3. Check gateway logs for errors
### Learnings not persisting
1. Verify `.learnings/` directory exists
2. Check file permissions
3. Ensure workspace path is configured correctly
### Error sweep not writing entries
1. Verify `<workspace>/.learnings/` exists (the sweep is opt-in and skips
silently without it)
2. End the session with `/new` or `/reset` — the sweep only runs on those
commands
3. Confirm a transcript exists in `<workspace>/sessions/`
4. Run the gateway with `SELF_IMPROVEMENT_HOOK_DEBUG=1` to surface hook errors
5. Remember excerpts already present in `ERRORS.md` are skipped (dedupe)
### Skill not loading
1. Check skill is in skills directory
2. Verify SKILL.md has correct frontmatter
3. Run `openclaw status` to see loaded skills
@@ -0,0 +1,55 @@
# Uninstall Guide
How to disable or fully remove the self-improvement skill. **Disabling** turns
off automatic behavior but keeps your data; **removing** deletes the skill's
files. They are different operations — do the one you mean.
> **Your learnings are data, not skill machinery.** `.learnings/` contains the
> errors, corrections, and insights the skill captured for you. Review or
> archive it before deleting anything. Content the skill *promoted* into
> `SOUL.md`, `TOOLS.md`, or `AGENTS.md` is part of those files now — removing
> the skill does not (and should not) automatically remove it.
## Disable only
```bash
# Stop the hook (reminder injection + session-end error sweep)
openclaw hooks disable self-improvement
```
To keep the bootstrap reminder but disable only the error sweep, remove the
learnings directory instead (archive it first if it has entries):
```bash
rm -r ~/.openclaw/workspace/.learnings
```
Restart the gateway after hook changes.
## Remove completely
```bash
# 1. Disable and remove the hook
openclaw hooks disable self-improvement
rm -r ~/.openclaw/hooks/self-improvement
# 2. Remove the skill
rm -r ~/.openclaw/skills/self-improving-agent
# 3. Optional — remove captured learnings (REVIEW FIRST, this is your data)
rm -r ~/.openclaw/workspace/.learnings
```
Then restart the gateway and verify with `openclaw hooks list` and
`openclaw status`.
Manually review `SOUL.md`, `TOOLS.md`, and `AGENTS.md` in
`~/.openclaw/workspace/` for sections promoted by this skill and delete the
ones you no longer want. If the skill logged `.learnings/` directories into
project repos you worked in, review and remove those separately.
## Verification
- `openclaw hooks list` no longer shows `self-improvement`
- New sessions no longer contain `SELF_IMPROVEMENT_REMINDER.md`
- No stray `.learnings/` directories remain that you didn't choose to keep