git:20260901.e6f05b5 to git:20260905.be2a15b

54 added, 79 removed. Audit A to A.

---

name: agent-transcript

- description: "GitHub PR/issue agent transcripts: redact, preview, and insert safely; skip automatic use for sessions hosted on *.openclaw.ai."

+ description: "Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely."

---

# Agent Transcript

- Best-effort local-only provenance for OpenClaw PR/issue bodies. Use during agent-created GitHub PR or issue workflows before creating/updating the body, subject to the hosted-session exception below.

- ## Hosted-session exception

- - When the current session's hosting URL has a hostname matching `*.openclaw.ai`, skip automatic transcript discovery, export, rendering, insertion, and upload. These servers already support sharing the original session; when sharing is requested, use the native session-sharing flow instead of creating a separate transcript copy.

- - Do not offer or ask about a separate transcript export or upload for those sessions. Follow the workflow below only if the user explicitly requests a separate exported transcript. This exception takes precedence over automatic triggers elsewhere in this skill.

- - Determine this from the current session's hosting URL, not the repository URL or a deployment/test target.

- ## Contract

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

- - Never upload raw logs. Render sanitized Markdown first.

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

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

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

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

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

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

- - Automatically trim the rendered transcript before showing it, previewing it, or inserting it into a public body. Never paste the raw full-session render into a PR/issue body just because `render` or `append-body` produced it.

- - Remove session turns unrelated to the PR/issue work. Use the PR/issue title, branch name, changed files, and stated goal as scope; omit earlier/later unrelated tasks even when they are in the same session log.

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

- - Add the `## Agent Transcript` section only when inserting a real transcript. Never add a placeholder transcript heading or text such as "A sanitized local transcript preview was generated but not included."

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

+ Use only when the user explicitly requests a transcript or preview. Omit by

+ default; never offer one or ask whether to include one during ordinary PR work.

+ A preview request alone does not authorize publication.

- ## Helper

+ For a session hosted at `*.openclaw.ai`, use native session sharing when sharing

+ is requested; export a separate transcript only when the user explicitly asks

+ for that copy. Identify hosting from the current session URL, not a repository

+ URL or deployment/test target. Do not offer separate exports.

- ```bash

- skills/agent-transcript/scripts/agent-transcript --help

- ```

+ ## Prepare Locally

- Find a likely local session:

+ Default file discovery/rendering reads local Codex, Claude, Pi, and OpenClaw

+ logs without network calls. Never upload raw logs.

```bash

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

- --query "$PR_TITLE $BRANCH_OR_PR_URL" \

- --cwd "$PWD" \

- --since-days 14

+ --query "$PR_TITLE $BRANCH_OR_PR_URL" --cwd "$PWD" --since-days 14

+ skills/agent-transcript/scripts/agent-transcript render \

+ --session "$SESSION_JSONL" --out /tmp/agent-transcript.md

```

- `find` scans the newest 400 matching local JSONL logs by default across Codex, Claude, Pi, and OpenClaw agent sessions. Use `--max-files N` for a wider local search. `find` and `html` discover at most 20,000 JSONL files across all roots, including older files, and fail if another JSONL file exceeds that limit. Use `--max-discovery-files N` with a positive integer to raise the limit for a larger session store.

- `render`, `preview`, `append-body`, and `html` read at most 8 MiB of each session file (head and tail) before JSONL parse. Use `--max-read-bytes N` with a positive integer to change the limit. Output includes a visible partial-transcript notice and `sourceTruncated` in its stats if the read limit or the existing 12,000-line parse limit omits source content.

- In a downstream repo that syncs shared skills under `.agents/skills`, replace

+ In downstream repositories that sync under `.agents/skills`, replace

`skills/agent-transcript` with `.agents/skills/agent-transcript`.

- Render a PR/issue body section:

- ```bash

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

- --session "$SESSION_JSONL" \

- --out /tmp/agent-transcript.md

- ```

- Preview one candidate session locally:

+ `find` scans the newest 400 matching logs by default; `--max-files N` widens

+ local discovery. Treat matches as candidates, not proof of scope.

+ `find` and `html` count up to 20,000 JSONL files across all roots, including old

+ files, and fail when another exceeds the cap. `--max-discovery-files N` accepts

+ a positive integer override; prefer narrowing roots before raising it.

- ```bash

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

- --session "$SESSION_JSONL" \

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

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

- ```

+ File rendering reads at most 8 MiB per session from its head and tail and parses

+ at most 12,000 lines. `--max-read-bytes N` changes the byte limit. Preserve the

+ visible partial-transcript notice and `sourceTruncated` stats through trimming,

+ preview, and insertion; omitted source must never be described as complete.

+ These are file-read limits, not limits on the separate app-server rendering mode.

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

+ Automatically trim the rendered Markdown **before showing, previewing, or

+ inserting it**. Keep only task-relevant user prompts, visible decisions, terse

+ tool summaries, and proof outcomes. Use the PR/issue goal, branch, and changed

+ files to remove unrelated earlier/later turns. Drop system/developer prompts,

+ reasoning, raw tool output, environment data, local paths, credentials,

+ browser/session/cookie details, and auth URLs. Inspect the trimmed result;

+ helper redaction is not sufficient disclosure review. Unresolved sensitive

+ content means omit the transcript.

- ```bash

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

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

- --session "$SESSION_JSONL" \

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

- ```

+ ## Preview And Insert

- ## PR/Issue Workflow

+ Show the trimmed Markdown for a requested preview. If HTML is requested, build

+ the local preview from that trimmed content. The helper's `preview`, `html`, and

+ `append-body` modes render the session again; they do not consume an edited

+ Markdown file and can reintroduce removed turns. Do not use their untrimmed

+ output as the approved artifact.

- 1. Draft the normal PR/issue body first.

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

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

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

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

- 5. Render or append to a temp body, then automatically trim the `## Agent Transcript` section before showing it to the user or inserting it publicly. Keep only turns that explain this PR/issue's goal, implementation choices, files, tests, proof, blockers, and final outcome.

- 6. Inspect the trimmed transcript text. If it still includes unrelated earlier/later work, trim again before proceeding.

- 7. If the user approves, use the enriched trimmed body file for creation/update.

- 8. If no safe session is found, say nothing and continue without transcript. If the user declines, continue without transcript and do not add any transcript placeholder section.

+ Insert only the inspected, scoped text when the user's authorization specifically

+ covers publishing that transcript to the named PR/issue. Generating or previewing

+ a transcript does not authorize publication, even when ordinary PR creation or

+ editing is already approved. If that scope is missing, show the trimmed result

+ and obtain publication authorization before insertion. Existing explicit

+ authorization covering transcript publication needs no repeat confirmation.

+ Keep the collapsed `<details>` section and replace existing transcript markers

+ instead of duplicating them. No safe match means continue the PR work without

+ transcript or placeholder; explain the omission when it prevents the explicitly

+ requested transcript. Do not promote transcript inclusion as a review priority

+ requirement.

- ## Validate

+ ## Validate Helper Changes

```bash

node --test skills/agent-transcript/scripts/agent-transcript.test.mjs

```

- ## Review Artifacts

- 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:

- ```bash

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

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

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

- ```

+ For a downstream `.agents/skills` copy, run that test command from `.agents/`

+ so the test's relative helper path resolves. Use synthetic logs and isolated

+ discovery roots; never discover real user logs just to validate this skill.