@mmerterden/multi-agent-pipeline 20.36.0 → 20.37.0

package/pipeline/skills/shared/core/multi-agent-autopilot-on/SKILL.md

@@ -13,10 +13,9 @@ metadata:
 Turns on the mode that picks work up without being asked. **No repo is included
 by default and none is ever added implicitly** - you choose, here, every time.
 
-Why a picker rather than a label alone: measured on one machine, 66 repos grant
-push and a good half belong to other people. A label is a filter; anyone who can
-open an issue in a repo you happen to have push on could add one. The gate is
-this selection, and it is per machine.
+The gate is this selection, per machine; a label alone is only a filter.
+Reasoning and detail for every step: `$HOME/.claude/multi-agent-refs/autopilot-on/details.md`. Read it
+when Jira is a source or a step's reasoning is needed.
 
 ## Steps
 
@@ -28,8 +27,7 @@ command -v jq >/dev/null 2>&1 || echo "BLOCKED: jq is required"
 node "$HOME/.claude/scripts/doctor.mjs" >/dev/null 2>&1; [ "$?" -ge 2 ] && echo "BLOCKED: doctor reports a blocking problem - fix it first"
 ```
 
-Any BLOCKED line stops here and is reported. Arming unattended work on an install
-that `doctor` calls broken produces a queue of failures, one per item.
+Any BLOCKED line stops here and is reported.
 
 ### 2. The repo list, both halves of it
 
@@ -42,9 +40,7 @@ Two states come back and **both are shown**:
 - `eligible` - push rights and a checkout on this machine
 - `unavailable` - push rights, no local checkout, listed WITH that reason
 
-Never hide the second list. Dropping 51 of 66 rows silently looks exactly like a
-permissions problem, and the user goes hunting for a token fault that does not
-exist.
+Never hide the second list.
 
 ### 3. Pick, with the current selection already checked
 
@@ -55,43 +51,29 @@ Read `~/.claude/autopilot/config.json` if it exists, then one `AskUserQuestion`
 - `header`: "Repos" (English, UI contract)
 - `options`: one per eligible repo, currently-selected ones marked "(seçili)" / "(selected)"
 
-**This is how repos are added and removed.** Checking a new one adds it;
-unchecking an existing one removes it. There is no `add-repo` / `remove-repo`
-command, because two entry points to one list is two lists.
+**This is how repos are added and removed** (check adds, uncheck removes); there
+is no `add-repo` / `remove-repo` command.
 
 Unavailable repos are printed above the question as a plain list with their
 reason, not offered as options.
 
 ### 4. Sources and label, per selected repo
 
-One `AskUserQuestion` per newly added repo (already-configured ones keep their
-answers - re-running must not re-ask what was already settled):
+One `AskUserQuestion` per newly added repo (never re-ask a configured one):
 
 - Sources: `GitHub issues` / `Jira` / both
 - Label: default **`agent-queue`** on both sides, editable
 
-The same name works on both sides and both mechanisms already exist:
-
-| Source | Query | Extra condition |
-|---|---|---|
-| GitHub | `gh issue list --repo <r> --label <label> --assignee @me --state open` | **assigned to you** (`githubAssignee`, `"*"` for any), so a label an issue form applies is not enough |
-| Jira | `assignee = currentUser() AND labels = "<label>" AND resolution = EMPTY AND status not in (Done, Closed, Cancelled)` | **assigned to you**, so a label somebody else adds is not enough |
-
-Two Jira caveats worth saying out loud when Jira is selected: labels are one
-global namespace across the whole instance and anyone can write them, so on a
-shared instance prefer a qualified name (`agent-queue-<team>`); and the Labels
-field has to be on the edit screen for the issue types in play. An instance where
-neither holds is a `jiraJql` config change - a saved filter, a component - not a
-redesign.
+Both sources pick up only items **assigned to you** that carry the label; the
+query per source is in `details.md`, "Source queries". When Jira is selected,
+state the two Jira caveats from that section (global label namespace, Labels
+field on the edit screen).
 
 ### 5. Keep the Mac awake: display on, or allowed to sleep
 
-While the mode is on, the Mac is kept awake by a second launchd agent,
-`com.multi-agent.autopilot-awake`, which runs `/usr/bin/caffeinate -s -i` from
-**Start** until `autopilot-off`. Without it the machine can sleep between ticks,
-and launchd does not wake it for the next one: the queue stops with nothing to
-say so. `-s` holds system sleep off on AC power; `-i` holds idle sleep off on
-battery too.
+While the mode is on, a second launchd agent, `com.multi-agent.autopilot-awake`,
+runs `/usr/bin/caffeinate -s -i` so the Mac does not sleep between ticks (why:
+`details.md`, "Keeping the Mac awake").
 
 One `AskUserQuestion` decides the display:
 
@@ -102,8 +84,7 @@ One `AskUserQuestion` decides the display:
 Branch on the option selected: **Display may sleep** writes `awake.display:
 false`, **Keep display on** writes `awake.display: true`, both with
 `awake.enabled: true`. A config that already carries `awake` shows its current
-answer as the first option. Display sleep does not lock the keychain; system
-sleep can, which is the part `-s -i` prevents regardless of this answer.
+answer as the first option.
 
 ### 6. Write the config
 
@@ -111,10 +92,9 @@ Validate against `schemas/autopilot-config.schema.json`, then write
 `~/.claude/autopilot/config.json` (0600, in a 0700 directory) via
 `ma_ap_write` in `lib/autopilot-state.sh`. Defaults that are not asked:
 `slots: 1`, `scanIntervalSeconds: 120`, `maxAttempts: 2`,
-`costCeilingUsd: 25`. `awake` carries the answer from the previous step. Keys the schema reserves and nothing reads
-(`askOnLowMaturity`, `reportStatus`, `sendItemKeys`) are not written. A config
-written by an older version may carry `depthRouter` or one of those; the schema
-still accepts them and nothing reads them, so drop them when rewriting the file.
+`costCeilingUsd: 25`. `awake` carries the answer from the previous step. Never
+write `askOnLowMaturity`, `reportStatus`, `sendItemKeys` or `depthRouter`; drop
+them when rewriting an older file.
 
 ### 7. Build the menu bar indicator (best effort)
 
@@ -126,15 +106,10 @@ if command -v swiftc >/dev/null 2>&1; then
 fi
 ```
 
-Built from source on demand, never shipped as a binary: the package contains only
-text today, and a compiled artifact in it would need signing and notarization to
-be distributable. No `swiftc` means no indicator and nothing else changes - say
-so in one line rather than failing. `autopilot-status` works either way.
-
-The compiled binary is the one thing an update does not replace, so the runner
-rebuilds it on the first tick after `autopilot-menubar.swift` becomes newer than
-`bin/menubar`. A machine that is already on picks up a new indicator without
-running this command again.
+Built from source on demand, never shipped as a binary. No `swiftc` means no
+indicator and nothing else changes - say so in one line rather than failing.
+`autopilot-status` works either way. The runner rebuilds it when the source is
+newer.
 
 ### 8. Confirm the schedule, naming the file
 
@@ -148,10 +123,7 @@ node "$HOME/.claude/scripts/autopilot-arming.mjs" probe
 `PROBE_READY=false` removes **Start** from the question below: each
 `PROBE_PROBLEM=` line names the logical key (or GitHub) and the fix, and is shown
 as it is. "Configure only" stays available. `PROBE_WARNING=` lines are shown and
-do not block: a login keychain that locks on sleep or after a timeout is readable
-now and locked for the tick after the Mac slept, which every tick checks again
-and refuses with the same message. `features/autopilot-operations.md` has the
-probe's rules.
+do not block (why: `details.md`, "Probe warnings").
 
 Render `templates/multi-agent-autopilot.plist.template` and show the resolved
 **path** and interval, then `AskUserQuestion`:
@@ -159,22 +131,17 @@ Render `templates/multi-agent-autopilot.plist.template` and show the resolved
 - `question`: install the schedule at `~/Library/LaunchAgents/com.multi-agent.autopilot.plist`, and the awake agent at `~/Library/LaunchAgents/com.multi-agent.autopilot-awake.plist`, and start picking work up?
 - options: `{ label: "Start" }` / `{ label: "Configure only", description: "Save the repo selection, do not schedule anything yet" }`
 
-"Configure only" is a real answer and the safe default to offer first: the queue
-can be watched with `autopilot-status` for a while before anything runs.
+"Configure only" is a real answer and the safe default to offer first.
 
-On **Start**, load the schedule and the awake agent with the same script the
-office panel's `POST /v1/autopilot/on` calls, naming every repo selected in step 3:
+On **Start**, load the schedule and the awake agent, naming every repo selected
+in step 3:
 
 ```bash
 node "$HOME/.claude/scripts/autopilot-control.mjs" on --repo <owner/name> [--repo <owner/name>...]
 ```
 
-It keeps exactly those repos in `config.json`, probes their credentials again
-(`autopilot-arming.mjs probeCredentials`), renders
-`templates/multi-agent-autopilot.plist.template` with its seven placeholders
-(NODE, TICK, LABEL, ROOT, INTERVAL, HOME, CLAUDE), loads it with `launchctl
-bootstrap` (falling back to `load`) and installs the awake agent with the
-`awake.display` answer saved above. `scheduled: false` with probe problems means
+It re-probes credentials, renders and loads the plist and installs the awake
+agent (detail: `details.md`). `scheduled: false` with probe problems means
 nothing was loaded; say so with the problems. Exit 1 with `launchd refused`
 means launchd refused the job: say so, with its path, and say the Mac may sleep
 between ticks until it is fixed. "Configure only" is `--configure-only`, which
@@ -182,21 +149,16 @@ saves the selection and installs neither.
 
 ### 9. Report what is now true
 
-Say all five, because each one is something a user has asked about after the
-fact: which repos and which labels; that it survives a restart with no command to
-run (launchd loads at **login** - not boot, and that is correct, because the login
-keychain is what unlocks the tokens, so a run before login could not reach Jira or
-GitHub anyway); that the machine is kept awake for as long as the mode is on (system sleep on AC, idle sleep on battery too) and whether the display is kept on; the slot count
+Say all five: which repos and which labels; that it survives a restart with no
+command to run (launchd loads at **login**, not boot); that the machine is kept awake while the mode is on and whether the display is kept on; the slot count
 and the ceiling this machine would allow (`ma_ap_slot_ceiling`); and that
 `/multi-agent:autopilot-off` is the only way to stop it.
 
 ## What this does not do
 
-- **No cap on PRs.** As many items as carry the label become as many PRs. The
-  bounds are `costCeilingUsd` over a rolling 24 hours and what the machine can
-  hold - never a daily count.
+- **No cap on PRs.** Every labelled item becomes a PR; the bounds are
+  `costCeilingUsd` over a rolling 24 hours and machine capacity, never a daily count.
 - **Does not merge.** The runner stops at an open PR; the merge decision stays
   yours.
-- **Does not touch an attended run.** Both are worktrees and per-repo concurrency
-  is 1, so the queue skips a repo you are working in rather than competing for
-  `.git/index.lock`.
+- **Does not touch an attended run.** Per-repo concurrency is 1: the queue skips
+  a repo you are working in.

package/pipeline/skills/shared/core/multi-agent-channels/SKILL.md

@@ -7,362 +7,62 @@ metadata:
   language: en
 ---
 
-# multi-agent-channels  -  Multi-Channel Reporter
+# multi-agent-channels - Multi-Channel Reporter
 
-> **TLDR**  -  Single entry point for posting task reports to external channels. Supports Jira, Confluence, Wiki (component-only), and PR description updates. Multi-select channels × multi-select content sources. Phase 5 of the pipeline delegates to this skill; users can also invoke it post-hoc by Jira ID / PR URL / branch.
->
-> **Replaces the old enrich skill in v5.7+**  -  all enrich capabilities (diff auto-summarize, manual mode, reviewer-preserving Bitbucket PR PUT) are preserved and extended with two additional channels (Confluence, Wiki).
+Single entry point for posting a task report to Jira, Confluence, Wiki (component-only) and the PR description. Phase 5 delegates here; users also invoke it post-hoc by Jira ID / PR URL / branch. Copilot CLI: `multi-agent-channels <target>`; Claude Code: `/multi-agent:channels <target>`. Prompts are byte-identical between the two (`smoke-cross-cli-behavior.sh`).
 
-**Copilot CLI invocation:** `multi-agent-channels <target>` (top-level skill, dash-separated per Copilot no-namespace convention).
-**Claude Code equivalent:** `/multi-agent:channels <target>` (slash namespace).
-
-Both CLIs read the same underlying logic  -  see `~/.claude/commands/multi-agent/channels/SKILL.md` (Claude) or this file (Copilot). Prompts MUST be byte-identical; `smoke-cross-cli-behavior.sh` asserts parity.
-
-## Input
-
-```
-multi-agent-channels                                         # cwd + current branch
-multi-agent-channels PROJ-12345                            # Jira ID
-multi-agent-channels #42                                     # GitHub issue/PR number
-multi-agent-channels https://github.com/<org>/<repo>/pull/N
-multi-agent-channels https://<bitbucket-host>/projects/.../pull-requests/N
-multi-agent-channels https://<jira-host>/browse/PROJ-12345
-
-multi-agent-channels PROJ-12345 --channels jira,confluence # non-interactive channel
-multi-agent-channels PROJ-12345 --content auto-diff        # non-interactive content
-multi-agent-channels PROJ-12345 --message "root: ..."      # manual source
-multi-agent-channels PROJ-12345 --message-file notes.md    # manual, long
-multi-agent-channels PROJ-12345 --dry-run                  # preview, no POST
-```
+References under `$HOME/.claude/multi-agent-refs/channels/` are installed with Claude Code. Before step 1, read `reference.md` there: input forms, flags, target resolution, the mode table, error handling, examples and the Phase 5 delegation contract.
 
 ## Flow
 
-1. **Target resolution**  -  Parse argument, classify (Jira-id, Jira-url, PR-url GitHub or Bitbucket, GitHub-issue-number, empty→cwd+branch). Resolve linked entities (Jira→PR, PR→Jira). Detect remote type.
-2. **Context source detection**  -  auto-pick best available: pipeline log (`$HOME/.claude/logs/multi-agent/<project>/<task-id>/agent-log.md` matching jiraId), PR diff (`gh pr diff` or Bitbucket `/diff?contextLines=5`), or manual `--message`.
-3. **Menu (multi-select)**  -  channel + content, previous selections pre-ticked from `prefs.global.reportChannels` + `prefs.global.reportContent`. Greyed-out rules per context availability.
-4. **Mode short-circuit**  -  `--channels X,Y` + `--content A,B` flags skip menu. Autopilot ALWAYS pauses at the menu (v5.7+ Phase 5 exception). Under `MULTI_AGENT_UNATTENDED=1` nothing is posted: see "Unattended" below.
-5. **Generator**  -  for each selected content source, produce a section body. Humanizer pass per channel separately.
-6. **Body preview + approval gate**  -  interactive runs render every selected channel's final body and ask Approve & post / Edit (loop) / Skip channels / Cancel BEFORE any external write. Skipped only by autopilot and `--dry-run`. What is posted is byte-identical to the approved preview.
-7. **Channel dispatch**  -  parallel adapter calls, never before the gate resolves: PR description (reviewer-preserving PUT on Bitbucket), Jira comment (wiki markup), Confluence page (storage format + parent page), Wiki (component adapter  -  Case A scope multi-select or Case B precondition menu).
-8. **Summary**  -  per-adapter status line, persist selections to prefs.
-
-## Multi-select menu
-
-Rendered in English (`promptLanguage` is locked to `en`).
-
-```
-┌─ Kanallar ────────────────────────────────────────────
-│   [x] PR description      (replace / append)
-│   [x] Jira comment        (jiraId: PROJ-12345)
-│   [ ] Confluence page
-│   [ ] Wiki                (taskType=component + wiki.enabled gerekli)
-└───────────────────────────────────────────────────────
-
-┌─ İçerik ──────────────────────────────────────────────
-│   [x] Normal analiz       (Phase 1+2+4'ten  -  high-level impact + risks)
-│   [ ] Teknik analiz       (Changes · Architecture · Dependencies)
-│   [x] Test senaryoları    (Phase 1+2+4'ten)
-│   [ ] Test Koşumu (Xray)  (flow runner history.jsonl)
-│   [ ] PR diff'ten auto-gen (PR varsa diff'i summarize eder)
-│   [ ] Manuel not          (--message / --message-file)
-└───────────────────────────────────────────────────────
-```
-
-**Greyed-out rules:**
-- Wiki unselectable unless `state.taskType === "component"` AND `figmaConfig.wiki.enabled === true`.
-- Normal analiz + Test senaryoları unselectable if no pipeline log found.
-- Teknik analiz unselectable if no Phase 1 planning log AND no PR diff.
-- Auto-diff unselectable if no PR found.
-- Manuel not always available.
-- Test Koşumu (Xray) unselectable when `render-flow-run.mjs --json` reports `available: false`; its `reason` is shown.
+1. **Target resolution**: classify the argument (Jira id / url, GitHub or Bitbucket PR URL, `#N`, empty = cwd + branch), resolve Jira <-> PR, detect the remote type. A Phase 5 call passes a state bundle and skips this step.
+2. **Context source**: pipeline log (`$HOME/.claude/logs/multi-agent/<project>/<task-id>/agent-log.md`), PR diff, or `--message`. Read `channels/menu.md`.
+3. **Menu (multi-select)**: channels + content, pre-ticked from `prefs.global.reportChannels` / `prefs.global.reportContent`; unavailable rows greyed with a reason (`menu.md`).
+4. **Mode short-circuit**: `--channels` + `--content` skip the menu. Autopilot always pauses at the menu.
+5. **Generator**: one section per content source, humanizer per channel. Read `channels/generator.md`.
+6. **Body preview + approval gate**: interactive runs render every final body and ask Approve & post / Edit (loop) / Skip channels / Cancel BEFORE any external write. Skipped only by autopilot and `--dry-run`. What is posted is byte-identical to the approved preview. Read `channels/preview.md`.
+7. **Dispatch**: parallel adapters, never before the gate resolves.
+8. **Summary**: one status line per adapter; persist the selections to prefs.
 
 ## Channel adapters
 
-### PR description (Bitbucket reviewer-preserving PUT)
-
-```bash
-PR_JSON=$(curl -s --config <(printf 'user = "%s:%s"\n' "$BB_USER" "$BB_TOKEN") "$PR_URL")
-REVIEWERS=$(jq '[.reviewers[] | {user: {name: .user.name}, approved, status}]' <<< "$PR_JSON")
-VERSION=$(jq -r '.version' <<< "$PR_JSON")
-TITLE=$(jq -r '.title' <<< "$PR_JSON")
-FROM_REF=$(jq '.fromRef | {id, repository}' <<< "$PR_JSON")
-TO_REF=$(jq '.toRef | {id, repository}' <<< "$PR_JSON")
-DRAFT=$(jq -r '.draft // false' <<< "$PR_JSON")
-
-jq -n --rawfile body /tmp/channels-$TASK_ID-pr.md \
-      --argjson version "$VERSION" --arg title "$TITLE" \
-      --argjson reviewers "$REVIEWERS" \
-      --argjson fromRef "$FROM_REF" --argjson toRef "$TO_REF" \
-      --argjson draft "$DRAFT" \
-      '{version: $version, title: $title, description: $body,
-        reviewers: $reviewers, fromRef: $fromRef, toRef: $toRef, draft: $draft}' \
-  > /tmp/channels-$TASK_ID-pr-payload.json
-
-curl -s -X PUT --config <(printf 'user = "%s:%s"\n' "$BB_USER" "$BB_TOKEN") -H "Content-Type: application/json" \
-     --data-binary @/tmp/channels-$TASK_ID-pr-payload.json "$PR_URL"
-```
-
-**(strict):** every Bitbucket PR PUT MUST include `reviewers`, `fromRef`, `toRef`, `draft`. Omitting any resets that field server-side (default reviewers wiped, branch link broken).
-
-GitHub uses `gh pr edit --body-file`  -  reviewers independent, no risk.
-
-### Jira comment (wiki markup)
-
-Four sections in this fixed order, the PR link on line 1. Jira is read by the
-person who filed the ticket and by whoever tests it, so the comment carries the
-development summary, the scenarios to run and the impact - never class names,
-never file paths, never a diff walk. The technical view lives in the PR, one
-click away through that first line.
-
-```
-PR: {prUrl}
-
-h2. Geliştirme Özeti
-
-{2-5 sentences: what changed, where the user meets it, and the size of the
-effect when it is measurable}
-
-h2. Test Senaryoları
-
-*1. {what this scenario exercises}*
-# {step the tester performs, in the app's own words}
-# {step}
-# *Beklenen:* {what they should see}
-
-*2. {regression scenario}*
-# {step}
-# *Beklenen:* {what should still behave as before}
-
-h2. Etki Analizi
-
-*1 - Problemin Tanımı*
-{what was wrong and since when}
-
-*2 - Yapılan Geliştirme*
-{what the change does, and why the behaviour around it is unchanged}
-
-*3 - Etkilenen Fonksiyonlar*
-{the screens and flows that must be tested}
-
-*4 - Diğer Sistemlere Etkisi*
-{none, or which service, contract or channel}
-
-h2. Bağlantılar
-
-* Crashlytics / Confluence / Figma: {url}
-```
-
-Reproduction scenarios first, then regressions for whatever the change could
-have disturbed. Full contract: `channels/jira.md`.
-
-`{{file.ext → func}}`, `*Root cause:*` and `*Changed files:*` are deliberately
-NOT this template. That shape puts a hash-table mutation walk in front of a
-tester, and `{{file → func}}` is exactly where a Swift selector like
-`hash(into:)` ends up - whose trailing `:)` Jira renders as a smiley.
-
-**Post through the publisher, never a hand-rolled `curl`:**
-
-```bash
-bash "$HOME/.claude/lib/jira-publish.sh" --issue "$JIRA_ID" --body-file "$F" --target comment
-```
-
-It escapes every body unconditionally before sending and keeps the token off
-argv. Jira turns `:)` `(x)` `(!)` `(/)` into emoticon images, including inside
-`{{monospace}}`; an escape that has to be remembered is one that is eventually
-forgotten, and that is how the selector above shipped.
-
-**Issue family** (`state.jiraFamily` set by Phase 0): the same body goes to the development sub-task, the test scenarios to the test sub-task (or, with none, the story) and a reformat of a story outside the story format to the story. `plan` prints one grouped confirmation ("3 yazma: story açıklaması, dev yorumu, test yorumu") and any question; show every write's body from `jira-family/plan.json` as one multi-select, re-run `plan` with `--skip <deselected ids>` (or `--dev-task` / `--test-task` for a question), then `apply`. Autopilot runs both back to back and records its choices in `state.decisions[]`:
-
-```bash
-bash "$HOME/.copilot/lib/jira-family-write.sh" plan --state "$STATE_FILE" --dev-body "$F"
-bash "$HOME/.copilot/lib/jira-family-write.sh" apply --state "$STATE_FILE"
-```
+- **PR description**: Bitbucket uses a reviewer-preserving PUT built with `jq -n --rawfile`; every PUT includes `reviewers`, `fromRef`, `toRef`, `draft` (and `version`), or the server resets them. GitHub uses `gh pr edit --body-file`. Payload snippet and retry: `channels/pr.md`.
+- **Jira comment**: PR link on line 1, then `h2. Geliştirme Özeti`, `h2. Test Senaryoları`, `h2. Etki Analizi`, `h2. Bağlantılar` in that order: never class names, file paths or a diff walk; the technical view stays in the PR. Template: `channels/jira.md`. Post through the publisher, never a hand-rolled `curl`:
 
-### Confluence page
+  ```bash
+  bash "$HOME/.claude/lib/jira-publish.sh" --issue "$JIRA_ID" --body-file "$F" --target comment
+  ```
 
-1. Token from `keychainMapping.confluence` via `~/.copilot/lib/credential-store.sh get`  -  missing→Token Save Flow from setup skill.
-2. Parent page URL prompt; recent URLs from `prefs.projects[<project>].confluenceUrls` (LRU, max 5).
-3. Extract `spaceKey` + `parentId` from URL.
-4. Auto-suggest page title `"{jiraId}  -  {taskTitle}"`, editable.
-5. POST `/rest/api/content`  -  humanizer'd storage-format body.
-6. Save URL to prefs for next run.
+  Issue family (`state.jiraFamily` set): show every write from `jira-family/plan.json` as one multi-select, re-plan with `--skip` for deselected ids, then apply (`$HOME/.claude/multi-agent-refs/features/jira-family.md`):
 
-### Wiki (component tasks only)
+  ```bash
+  bash "$HOME/.copilot/lib/jira-family-write.sh" plan --state "$STATE_FILE" --dev-body "$F"
+  bash "$HOME/.copilot/lib/jira-family-write.sh" apply --state "$STATE_FILE"
+  ```
 
-**Case A  -  preconditions met** (`taskType=component` + `wiki.enabled=true`): scope multi-select menu offers Main page / iOS sub-page / Screenshots / Index updates / Other. Adapter dispatches with selected scope.
+- **Confluence page**: token from `keychainMapping.confluence` via `~/.copilot/lib/credential-store.sh get` (missing: Token Save Flow from the setup skill); parent page from recents or a pasted URL. Contract: `channels/confluence.md`.
+- **Wiki** (component tasks only): Case A scope multi-select when `taskType=component` and `wiki.enabled=true`, otherwise the Case B menu in `refs/wiki-capture.md`. Contract: `channels/wiki.md`.
 
-**Case B  -  preconditions missing**: actionable menu  -  [1] setup Figma config, [2] skip this run, [3] disable forever, [4] manual note. Full contract in `refs/wiki-capture.md`.
+## Store compliance
 
-## Output template (aggregated across selected content)
-
-```markdown
-### Analysis                        ← if "Normal analiz" selected
-{impact summary, risks  -  high-level}
-
-### Technical Details               ← if "Teknik analiz" selected
-#### Changes
-{Per changed-file-group, what changed + why  -  from Phase 2 dev log}
-#### Architecture
-{Structural decisions, pattern changes  -  from Phase 1 plan}
-#### Dependencies
-{New imports / frameworks / packages  -  from git diff --stat, or "None"}
-
-### Root Cause                      ← if "Auto-diff" selected
-{single paragraph  -  from diff}
-
-- `path/to/File.ext → funcName`: {why it broke}
-
-### Solution                        ← if "Auto-diff" selected
-- `path/to/File.ext:LINE-LINE`  -  {change, one line}
-
-### Changed Files                   ← if "Auto-diff" selected
-| File | +/- |
-|------|-----|
-| `path/to/File.ext` | +N / -M |
-
-### Test Scenarios                  ← if "Test senaryoları" OR "Auto-diff"
-**1. {what this scenario exercises}**
-1. {step the tester performs}
-2. **Expected:** {what they should see}
-
-**2. {regression scenario}**
-1. {step}
-2. **Expected:** {what should still behave as before}
-
-### Test Koşumu                     ← if "Test Koşumu (Xray)" selected
-{`render-flow-run.mjs` output, unedited: Xray Test Execution, Test Set / Plan, run, results, one row per scenario. Read-only; a key the run history does not record is never written. Full contract: `channels/test-run.md`.}
-
-### Notes                           ← if "Manuel not" selected
-{user message}
-
-### Store compliance                ← auto-appended if cached compliance report exists
-{summary line  -  see below}
-
-Ref: {jiraId}
-```
-
-**Store compliance auto-augmentation:**
-
-After content sections are generated, check for cached compliance reports from recent `multi-agent-test "store-ready"` runs:
-
-```bash
-find /tmp -maxdepth 1 \( -name 'archiveguard-*.json' -o -name 'play-compliance-*.json' \) \
-  -newermt "-6 hours" -print 2>/dev/null | head -1
-```
-
-If cached report exists AND any selected channel is PR / Jira / Confluence, append:
-
-| Blocker count | Output |
-|---|---|
-| `errors > 0` | `### Store compliance` + `⚠️ {N} blocker(s), {M} warning(s)` + per-blocker `- \`{ruleID}\`  -  {ref}: {message}` (cap 5 rows, rest `+N more`) |
-| `errors == 0, warnings > 0` | `### Store compliance` + `✅ No blockers. {M} warning(s)  -  see multi-agent-test "store-ready" for detail.` |
-| `errors == 0, warnings == 0` | Skip  -  don't pollute PR body |
-
-`ruleID` + policy ref stay verbatim (apple-archive-compliance / google-play-compliance catalog identifiers  -  no translation).
-
-If no cached report: skip silently. Augmentation, not a gate.
-
-Target length: < 80 lines (fits one screen). Auto-diff capped at 5 lines per section.
-
-## Flags
-
-| Flag | Effect |
-|------|--------|
-| `--channels pr,jira,confluence,wiki` | Non-interactive channel selection. |
-| `--content normal,test,auto-diff,note,test-run` | Non-interactive content selection. |
-| `--flow-run <runId>[,<runId>...]` | Runs reported by the Test Koşumu (Xray) block; wins over `state.evidence.flowRuns[]` and discovery. |
-| `--message "..."` | Manual mode  -  user text as source. Forces `content=note`. |
-| `--message-file path` | Manual mode, long message from file. |
-| `--append` | PR description: append instead of replace. |
-| `--dry-run` | Generate + print, no POST. |
-| `--lang=tr\|en\|both` | Output language override (default: `en`; `promptLanguage` is locked to `en`). |
-| `--ready` | If PR draft, promote to READY after dispatch. |
+After the content sections, a cached `archiveguard-*.json` or `play-compliance-*.json` report from the last 6 hours appends a `### Store compliance` block when a PR / Jira / Confluence channel is selected; none found: skip silently. Augmentation, not a gate. Table and wording: `channels/generator.md`.
 
 ## Required rules
 
-- Bitbucket reviewer preservation  -  every PR PUT MUST carry current `reviewers`, `fromRef`, `toRef`, `draft`.
-- Default is **replace** (not append) for PR description; `--append` opt-in.
-- Real newlines + no HTML entities in ALL bodies (Jira, Confluence, PR).
-- Humanizer per-channel  -  each body runs humanizer independently (tones differ).
-- No markers  -  full replace each run, no `<!-- channels:start -->` bookmarks.
-- Every body item references a file/symbol/line from diff or pipeline log. No generic sentences.
-- Adapter failures are non-blocking  -  one channel failing does NOT abort others.
-- Approval before post  -  interactive runs never write to an external channel without the step 6 preview + approval. Autopilot and `--dry-run` are the only bypasses.
-
-## Error handling
-
-| Condition | Behavior |
-|-----------|----------|
-| No target resolvable | Error, exit 1 |
-| PR not found + Jira selected | Proceed Jira-only, log reason |
-| PR merged/closed | Warn, confirm continue |
-| Author bot / dependabot | Skip entire run |
-| Diff > 2 MB | Ask: skip / top-20-files / cancel |
-| No pipeline log + Normal analiz selected | Greyed at menu; error if `--content` forces it |
-| Bitbucket version mismatch | Refetch once, retry; fail on second |
-| Jira token missing/expired | Token Save Flow inline; skip on user-skip |
-| Wiki preconditions not met | Case B menu per `refs/wiki-capture.md` |
-
-## Phase 5 delegation contract
-
-Phase 5 builds a state bundle and invokes this skill internally. Responsibilities:
-
-| Who | What |
-|---|---|
-| Phase 5 | Progress tracker (3 sub-steps), agent-log finalization, knowledge+memory capture, telemetry emission |
-| `multi-agent-channels` | All external delivery: PR description update, Jira comment, Confluence page, Wiki pages |
-
-**State bundle** passed from Phase 5:
-```json
-{
-  "jiraId": "PROJ-12345",
-  "prUrl": "https://.../pull/42",
-  "remoteType": "github" | "bitbucket",
-  "taskType": "component" | "bugfix" | "feature" | "refactor",
-  "figmaConfig": { /* or null */ },
-  "agentState": { /* agent-state.json */ },
-  "pipelineLogPath": "$HOME/.claude/logs/multi-agent/...",
-  "invokedFrom": "phase-5"
-}
-```
-
-**Autopilot pause contract:** Phase 5 ALWAYS pauses at the channels menu  -  30-min timeout → session ends cleanly → resumable via `/multi-agent:resume`. Full contract in `refs/phases/modes.md` + `refs/phases/phase-5-report.md`.
-
-**Unattended (`MULTI_AGENT_UNATTENDED=1`): channels posts nothing.** A run nobody watches does not call it: Phase 5 skips Step 1 and records `step1.status = "deferred-to-runner"`, and a direct invocation stops before the menu with that status. After the run exits the autopilot runner verifies `pr-request.json`, pushes, opens the draft PR, and only then, when `~/.claude/autopilot/config.json` sets `reportChannels: true`, runs channels itself with the `channels.mode` / `channels.targets` selection from that file. Without the opt-in nothing beyond the draft PR is published. The guard enforces it: every publisher script and every `gh` / `curl` write is blocked under the variable. Contract: `$HOME/.claude/multi-agent-refs/features/unattended-security.md`.
-
-## Cross-CLI parity
-
-Prompts MUST be byte-identical between Claude and Copilot. `smoke-cross-cli-behavior.sh` asserts spacing, brackets, numbering, log-line format.
-
-Progress emission on Copilot (no native TaskCreate UI):
-
-```bash
-bash ~/.copilot/scripts/phase-tracker.sh sub 5 1 "Channels dispatch" in_progress
-# ... adapter runs ...
-bash ~/.copilot/scripts/phase-tracker.sh sub 5 1 "Channels dispatch" completed
-```
-
-Same shape as Phase 5 sub-step tracking.
+- Bitbucket reviewer preservation: every PR PUT carries current `reviewers`, `fromRef`, `toRef`, `draft`.
+- Default is **replace** for the PR description; `--append` opt-in.
+- Real newlines + no HTML entities in every body.
+- Humanizer per channel; no `<!-- channels:start -->` markers; every body item cites a file / symbol / line.
+- Adapter failures are non-blocking.
+- Approval before post: autopilot and `--dry-run` are the only bypasses.
+- Target length under 80 lines; auto-diff capped at 5 lines per section.
 
-## Examples
+## Autopilot and unattended
 
-```
-multi-agent-channels
-  → resolves from cwd+branch → PROJ-12345 + PR #3433
-  → menu: PR ✓ Jira ✓ / Normal analiz ✓ Test senaryoları ✓
-  → PR description replaced (v3→4, 23 reviewers preserved)
-  → Jira comment posted (id 2484780)
+Phase 5 always pauses at the channels menu: a 30-min timeout ends the session cleanly, resumable via `/multi-agent:resume` (`refs/phases/modes.md`).
 
-multi-agent-channels PROJ-12345 --channels confluence --content note --message-file notes.md
-  → non-interactive: only Confluence, content from notes.md
-  → asks: parent page URL (or recent [1] / [2])
-  → page created → https://<host>/pages/12345
+**Unattended (`MULTI_AGENT_UNATTENDED=1`): channels posts nothing.** Phase 5 records `step1.status = "deferred-to-runner"`, and a direct invocation stops before the menu with that status. The autopilot runner publishes only through its own opt-in, and the guard blocks every publisher script and `gh` / `curl` write under the variable. Contract: `$HOME/.claude/multi-agent-refs/features/unattended-security.md`.
 
-multi-agent-channels https://<bitbucket>/.../pull-requests/42 --dry-run
-  → resolves → PROJ-67890
-  → prints Jira + PR body preview to stdout, no POST
+## Progress on Copilot
 
-multi-agent-channels --message "root: order id empty, UI silent. fix: length>0 guard in HomeVC.m"
-  → auto-diff from cwd+branch PR + user note combined
-  → posts to default channels (PR + Jira)
-```
+No native TaskCreate UI: `bash ~/.copilot/scripts/phase-tracker.sh sub 5 1 "Channels dispatch" in_progress`, then `completed` after the adapters run.