惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

月光博客
月光博客
罗磊的独立博客
The GitHub Blog
The GitHub Blog
V
V2EX
Last Week in AI
Last Week in AI
博客园 - 聂微东
MyScale Blog
MyScale Blog
美团技术团队
L
LangChain Blog
博客园 - Franky
腾讯CDC
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园_首页
S
SegmentFault 最新的问题
爱范儿
爱范儿
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Stack Overflow Blog
Stack Overflow Blog
量子位
小众软件
小众软件
宝玉的分享
宝玉的分享
J
Java Code Geeks
Google DeepMind News
Google DeepMind News
D
Docker
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4
chore: add agent transcript skill · openclaw/openclaw@d63...
steipete · 2026-05-25 · via Recent Commits to openclaw:main

@@ -0,0 +1,83 @@

1+

---

2+

name: agent-transcript

3+

description: "Add a redacted agent transcript section to GitHub PR or issue bodies during OpenClaw agent-created PR/issue workflows."

4+

---

5+6+

# Agent Transcript

7+8+

Best-effort local-only provenance for OpenClaw PR/issue bodies. Use during agent-created GitHub PR or issue workflows before creating/updating the body.

9+10+

## Contract

11+12+

- Never use network. Session discovery reads local agent logs only.

13+

- Never upload raw logs. Render sanitized Markdown first.

14+

- Always ask the user before adding transcript logs to a GitHub PR/issue body.

15+

- Tell the user sanitized session logs help reviewers and can make PRs easier to prioritize.

16+

- Offer a local HTML preview before insertion. If the user wants preview, open it and wait for confirmation before adding the section.

17+

- Fail closed on unresolved secrets, private keys, browser/session/cookie details, or auth URLs.

18+

- Drop system/developer prompts, raw tool outputs, reasoning, env, cookies, tokens, and broad local paths.

19+

- Keep user prompts, assistant visible decisions, terse tool summaries, and test/proof outcomes.

20+

- Best effort only: PR/issue creation must continue if no safe transcript is found.

21+

- Use a collapsed `<details>` section and update existing markers instead of duplicating sections.

22+23+

## Helper

24+25+

```bash

26+

.agents/skills/agent-transcript/scripts/agent-transcript --help

27+

```

28+29+

Find a likely local session:

30+31+

```bash

32+

.agents/skills/agent-transcript/scripts/agent-transcript find \

33+

--query "$PR_TITLE $BRANCH_OR_PR_URL" \

34+

--cwd "$PWD" \

35+

--since-days 14

36+

```

37+38+

Render a PR/issue body section:

39+40+

```bash

41+

.agents/skills/agent-transcript/scripts/agent-transcript render \

42+

--session "$SESSION_JSONL" \

43+

--out /tmp/agent-transcript.md

44+

```

45+46+

Preview one candidate session locally:

47+48+

```bash

49+

.agents/skills/agent-transcript/scripts/agent-transcript preview \

50+

--session "$SESSION_JSONL" \

51+

--out /tmp/agent-transcript-preview.html

52+

open /tmp/agent-transcript-preview.html

53+

```

54+55+

Append/update a body file before `gh pr create --body-file` or connector PR creation:

56+57+

```bash

58+

.agents/skills/agent-transcript/scripts/agent-transcript append-body \

59+

--body /tmp/pr-body.md \

60+

--session "$SESSION_JSONL" \

61+

--out /tmp/pr-body.with-transcript.md

62+

```

63+64+

## PR/Issue Workflow

65+66+

1. Draft the normal PR/issue body first.

67+

2. Run `find` with title, branch, PR URL/number if known, and cwd.

68+

3. If a high-confidence session is found, ask:

69+

`Include a redacted agent transcript? It helps reviewers and can make the PR easier to prioritize. I can open a local preview first.`

70+

4. If the user wants preview, run `preview`, open the HTML with `open`, and wait for confirmation.

71+

5. If the user approves, run `append-body`.

72+

6. Use the enriched body file for creation/update.

73+

7. If no safe session is found, say nothing and continue without transcript. If the user declines, continue without transcript.

74+75+

## Review Artifacts

76+77+

For manual audits across many PR/session candidates, create a local HTML preview from a local JSON file. This is for maintainers only and is not part of the PR/issue workflow:

78+79+

```bash

80+

.agents/skills/agent-transcript/scripts/agent-transcript html \

81+

--prs /tmp/recent-prs.json \

82+

--out /tmp/agent-transcript-preview.html

83+

```