@mmerterden/multi-agent-pipeline 14.2.1 → 15.0.0

package/pipeline/multi-agent-refs/phases/phase-4-review.md

@@ -75,7 +75,7 @@ If changes include UI files (iOS: `*View.swift`, `*Screen.swift`, `*Cell.swift`;
 - Missing `.accessibilityIdentifier` / `testTag` → **important**
 - Dynamic Type / font scaling not supported → **important**
 
-**iOS  -  Apple HIG compliance** (skills: `hig-patterns`, `hig-components-layout`, `hig-foundations`):
+**iOS  -  Apple HIG compliance** (skills: `ai-ios-toolkit:hig-patterns`, `ai-ios-toolkit:hig-components-layout`, `ai-ios-toolkit:hig-foundations`):
 - Navigation pattern mismatch (e.g. custom back button instead of system) → **important**
 - Non-standard gesture without discoverability hint → **suggestion**
 - Missing safe area / keyboard avoidance → **important**
@@ -83,12 +83,12 @@ If changes include UI files (iOS: `*View.swift`, `*Screen.swift`, `*Cell.swift`;
 
 **iOS  -  SwiftUI interaction & accessibility conventions.** Gated to changed SwiftUI files. These are rule-registry territory as of v14.0.0, not a list transcribed here: Step 1.78 resolves them from whichever registry declares SwiftUI scope, so the criteria and their severities live in one place instead of drifting between this doc and the skill. Reviewers receive the resolved rule IDs. Native-SwiftUI-first unless the project's `figma-config` `ui.*` declares a custom system, in which case check against that system. Reference skills, when no registry covers the change: `figma-navigation`, `figma-overlays`, `figma-bottom-sheets`, `figma-to-swiftui`.
 
-**Android  -  Material Design compliance** (skills: `compose-components`, `android-architecture`):
+**Android  -  Material Design compliance** (skills: `ai-android-toolkit:compose-components`, `ai-android-toolkit:android-architecture`):
 - Non-Material3 component when M3 equivalent exists → **suggestion**
 - Missing `contentDescription` on icons/images → **blocking**
 - Hardcoded dp values instead of Material spacing tokens → **suggestion**
 
-**App Store / Play Store readiness** (skills: `app-store-review`, `play-store-review`):
+**App Store / Play Store readiness** (skills: `ai-ios-toolkit:app-store-review`, `ai-android-toolkit:play-store-review`):
 - Privacy: API usage without purpose string / permission rationale → **blocking**
 - Deprecated API usage flagged by latest SDK → **important**
 
@@ -249,7 +249,7 @@ Launch Agent instances **in parallel** using the shared `code-reviewer` subagent
 | ---------- | --------------- | --- | --- | --- | --- | --- |
 | Reviewer 1 | `code-reviewer` | `claude-fable-5` | `claude-opus-5` | `gpt-5.6` @ `xhigh` | Deep security + architecture | `api-security-best-practices`, `architecture` |
 | Reviewer 2 | `code-reviewer` | (not dispatched) | `gpt-5.4` | `gpt-5.4` @ `high` | Edge cases, different perspective | cross-model diversity |
-| Reviewer 3 | `code-reviewer` | `claude-sonnet-5` | `claude-sonnet-5` | `gpt-5.6` @ `medium` | Quality + correctness + naming | `clean-code`, stack-specific skill |
+| Reviewer 3 | `code-reviewer` | `claude-sonnet-5` | `claude-sonnet-5` | `gpt-5.6` @ `medium` | Quality + correctness + naming | `ai-backend-toolkit:clean-code`, stack-specific skill |
 | Triage     | triage persona  | `claude-fable-5` | `claude-opus-5` | `gpt-5.6` @ `max` | Filter false positives + out-of-scope | - |
 
 Reviewer count per host: **Claude Code 2, Copilot CLI 3, Codex CLI 3**.
@@ -285,12 +285,12 @@ Each reviewer inherits the `code-reviewer` agent's focus areas (Security, Archit
 
 | Stack | Reviewer 1 (Fable / Opus on Copilot) | Reviewer 2 (GPT-5.4  -  Copilot CLI only) | Reviewer 3 (Sonnet) |
 |-------|-------------------|-----------------------------------------|---------------------|
-| iOS/Swift | `ios-security`, `swiftui-performance`, `hig-patterns` | `swift-concurrency`, `ios-accessibility` | `swiftui-pro`, `swift-testing` |
-| Android/Kotlin | `android-security`, `android-performance` | `compose-testing`, `android-architecture` | `compose-components`, `kotlin-coroutines-expert` |
-| Python | `api-security-best-practices` | `fastapi-pro` | `python-patterns` |
-| Node.js | `api-security-best-practices` | `nodejs-backend-patterns` | `typescript-patterns` |
-| Docker | `docker-expert` | `docker-expert` | `ci-cd-pipelines` |
-| Generic | `security-review` | `clean-code` | `clean-code` |
+| iOS/Swift | `ai-ios-toolkit:ios-security`, `ai-ios-toolkit:swiftui-performance`, `ai-ios-toolkit:hig-patterns` | `ai-ios-toolkit:swift-concurrency`, `ai-ios-toolkit:ios-accessibility` | `ai-ios-toolkit:swiftui-pro`, `ai-ios-toolkit:swift-testing` |
+| Android/Kotlin | `ai-android-toolkit:android-security`, `ai-android-toolkit:android-performance` | `ai-android-toolkit:compose-testing`, `ai-android-toolkit:android-architecture` | `ai-android-toolkit:compose-components`, `ai-android-toolkit:kotlin-coroutines-expert` |
+| Python | `ai-backend-toolkit:api-security-best-practices` | `ai-backend-toolkit:fastapi-pro` | `ai-backend-toolkit:python-patterns` |
+| Node.js | `ai-backend-toolkit:api-security-best-practices` | `ai-backend-toolkit:nodejs-backend-patterns` | `ai-frontend-toolkit:typescript-patterns` |
+| Docker | `ai-backend-toolkit:docker-expert` | `ai-backend-toolkit:docker-expert` | `ai-backend-toolkit:ci-cd-pipelines` |
+| Generic | `security-review` | `ai-backend-toolkit:clean-code` | `ai-backend-toolkit:clean-code` |
 
 Skills are injected into reviewer prompt context  -  the reviewer uses them as reference, not as commands.
 
@@ -299,7 +299,7 @@ Skills are injected into reviewer prompt context  -  the reviewer uses them as r
 Runs when `state.taskType == "component"` **or** the diff touches SwiftUI UI files
 AND the task carried a Figma reference. Two checks, in order:
 
-1. **`ai-ios-engineering-toolkit:figma-review`** over the implemented frames  -  the
+1. **`ai-ios-toolkit:figma-review`** over the implemented frames  -  the
    plugin's own component review, including the 14-item checklist that covers design
    tokens, accessibility identifiers, previews and Code Connect.
 2. **`/multi-agent:design-check`** for pixel + spacing + typography + colour
@@ -320,7 +320,7 @@ reading a diff cannot see spacing; something has to compare against the design.
 Skip only when the diff has no UI change. Record the outcome in
 `consensus.visualConformance` so Phase 7 reports whether it ran.
 
-**iOS/Swift  -  interaction & convention checks (conditional).** Step 1.78 resolves these. Where no registry covers the change, reviewers fall back to the analysis doc (Section 14 Code Connect mapping) and, when `ai-ios-engineering-toolkit` is enabled, that plugin's navigation / overlay / bottom-sheet + accessibility conventions.
+**iOS/Swift  -  interaction & convention checks (conditional).** Step 1.78 resolves these. Where no registry covers the change, reviewers fall back to the analysis doc (Section 14 Code Connect mapping) and, when `ai-ios-toolkit` is enabled, that plugin's navigation / overlay / bottom-sheet + accessibility conventions.
 
 **Module review guides (conditional, all stacks).** Step 1.78 resolves them into `criteria-manifest.json` → `moduleGuides`. Inject with the directive: read each guide, apply its rules to the changed files under its directory  -  a guide governs only its own subtree, and its violations are findings triaged like any other. Same contract as `/multi-agent:review` Step 2b.
 

package/pipeline/multi-agent-refs/phases/phase-5-test.md

@@ -100,7 +100,7 @@ Tier 1 / Tier 2 records print `screenshotUrl` from the captured evidence (Tier 2
    bash $HOME/.claude/scripts/phase-tracker.sh now 5 "awaiting local test (user)"
    bash $HOME/.claude/scripts/phase-tracker.sh render
    ```
-   The waiting state persists in `tracker-state.json` across the handoff; `/multi-agent:ship` and `/multi-agent:manual-test` CONTINUE this state file and never re-init it (`$HOME/.claude/multi-agent-refs/tracker-contract.md` "Continuation runs").
+   The waiting state persists in `tracker-state.json` across the handoff; `/multi-agent:resume-local` and `/multi-agent:manual-test` CONTINUE this state file and never re-init it (`$HOME/.claude/multi-agent-refs/tracker-contract.md` "Continuation runs").
 6. If fix needed:
    - Branch already has WIP commit (from step 2)  -  changes are safe
    - **Heal stale admin state first** (same contract as Phase 0  -  step 3's

package/pipeline/multi-agent-refs/phases/phase-6-commit.md

@@ -106,6 +106,8 @@ Branch **deterministically**, no implicit fallback. Read `agent-state.json` and
 
 #### Step 3  -  PR Description (technical detail for reviewers)
 
+**Section set + markup dialect: `channels/pr.md`  -  read it first.** Phase 7 channels replaces this body with that section set, so build to it. Required reading: `payload-contracts.md`.
+
 Generate a structured PR description based on task type. The PR body targets **code reviewers**  -  it should be technical: what changed, why, architecture decisions, how to verify.
 
 **required**: Run all generated text (PR body, commit message) through the `humanizer` skill before posting. This removes AI-generated patterns (inflated language, filler phrases, repetitive structure) and makes the output sound like a developer wrote it.
@@ -116,49 +118,15 @@ Generate a structured PR description based on task type. The PR body targets **c
 - Bitbucket: similar patterns
 - Use `Ref: #N`, `Related: #N`, or `See: {jiraId}` instead
 
-**Default Reviewers**: If `prefs.projects[{project}].defaultReviewers` exists, add `--reviewer` flags. If not, ask on first PR and save to preferences:
-
-```
-Default reviewers for this project? (comma-separated GitHub usernames, or skip):
-```
-
-Save to `prefs.projects[{project}].defaultReviewers: ["user1", "user2", "user3", "user4"]`
+**Default Reviewers**: use `prefs.projects[{project}].defaultReviewers` when set; otherwise ask once ("Default reviewers for this project? comma-separated, or skip") and persist the answer there. Per-remote resolution rules are in "Default reviewers (required on every PR)" below  -  this is the prefs half only.
 
-**Standard PR (bug fix, feature, refactor):**
+**Standard PR (bug fix, feature, refactor)**  -  invocation shape; body comes from a file so newlines survive:
 
 ```bash
 REVIEWERS=$(jq -r '.projects["'$PROJECT'"].defaultReviewers // [] | map("--reviewer " + .) | join(" ")' "$PREFS_FILE")
 gh pr create --base {baseBranch} --head {branch} $REVIEWERS \
   --title "{type}({scope}): {summary} [{jiraId}]" \
-  --body "$(cat <<'EOF'
-## Summary
-{1-3 bullet points: what changed and why}
-
-## Jira
-{jiraId}  -  {jira summary or link}
-
-## Technical Details
-### Changes
-{For each changed file group, explain WHAT changed and WHY}
-
-### Architecture
-{Any structural decisions: new files, moved code, pattern changes}
-
-### Dependencies
-{New imports, framework changes, package updates  -  or "None"}
-
-## How to Test
-1. {Step-by-step manual test instructions}
-2. {Verify specific behavior}
-
-## Checklist
-- [ ] Build passes (0 errors, 0 warnings)
-- [ ] Tests pass
-- [ ] No hardcoded values (tokens used)
-- [ ] Accessibility verified
-- [ ] Dark mode verified
-EOF
-)"
+  --body-file /tmp/pr-body-$TASK_ID.md
 ```
 
 **UI Component PR (when SwiftUI component detected):**
@@ -175,9 +143,9 @@ Same `gh pr create` pattern with component-specific body sections:
 
 CRITICAL: PR description **MUST** preserve real newlines. Never embed `\n` literally  -  Bitbucket saves it verbatim. Never use HTML entities. Pattern: heredoc → `jq --rawfile` → `curl --data-binary @file`.
 
-Required payload fields: `title`, `description` (via rawfile), `fromRef` (id + repo slug + project key), `toRef` (same structure), `state: "OPEN"`, `open: true`, `closed: false`, `locked: false`, `reviewers: []`.
+Required payload fields: `title`, `description` (via rawfile), `fromRef` (id + repo slug + project key), `toRef` (same structure), `state: "OPEN"`, `open: true`, `closed: false`, `locked: false`, `reviewers` (the fetched list  -  `[]` only if that endpoint really returned empty).
 
-To **update** an existing PR: fetch `version`, PUT with same rawfile pattern (version +1). GitHub: prefer `--body-file` over inline `--body`.
+To **update** an existing PR: use the `channels/pr.md` PUT payload  -  required, not illustrative. It carries `reviewers`/`fromRef`/`toRef`/`draft` (a PUT clears omitted fields) and the GET's `version` unmodified (`version + 1` → 409). Refetch after, assert the reviewer count held. GitHub: `--body-file`.
 
 **Default reviewers (required on every PR)**
 
@@ -307,7 +275,7 @@ update_sibling_links "${PR_URLS[@]}"
 
 **Then finalize each repo's worktree**, serially and only now  -  `update_sibling_links` updates one PR per repo and the loop `cd`s per repo, so removing repo 1's worktree mid-loop breaks 2..N. Run `worktree-finalize.sh` once per repo with that repo's `--worktree` / `--project-root` / `--project`; each skips or removes independently.
 
-`update_sibling_links` does an UPDATE call per PR (Bitbucket: PUT with `version+1`; GitHub: `gh pr edit --body-file`). Idempotent: re-running with the same set is a no-op.
+`update_sibling_links` does an UPDATE call per PR (Bitbucket: the `channels/pr.md` PUT payload, current `version`; GitHub: `gh pr edit --body-file`). Idempotent.
 
 ##### GitHub issue body  -  list all PRs
 

package/pipeline/multi-agent-refs/phases/phase-7-report.md

@@ -153,8 +153,8 @@ Skipped sections: when `planTodos.enabled` is false or no `plan.todos[]` was emi
 
 ## Timeline
 
-| #   | Phase | Model | Duration | Status | Detail |
-| --- | ----- | ----- | -------- | ------ | ------ |
+| #   | Phase | Agent | Model | Duration | Tokens (in/out) | Status | Detail |
+| --- | ----- | ----- | ----- | -------- | --------------- | ------ | ------ |
 
 ## Agent Activity Report
 
@@ -200,7 +200,7 @@ $HOME/.claude/scripts/log-metric.sh "$TASK_ID" 7 task.completed \
 
 **Per-run outcome metrics (evidence corpus):** also emit `run-metrics.mjs --state <agent-state.json>` and append/persist its JSON. It records the numbers that actually answer "did this run go well" - review iterations (rework loops), first-pass-clean, reviewer signal-to-noise (accepted / raw findings), consensus verdict, build outcome. Accumulating these across real runs is the real-world validation that golden tasks + benchmarks only approximate; keep the corpus so the pipeline's quality can be measured, not asserted.
 
-**Cost Breakdown emission (mandatory):** as part of agent-log compose, append the per-task cost block produced by `render-agent-log-cost.sh`. Best-effort  -  exit 2 (no tracker data) silently skipped:
+**Cost Breakdown emission (mandatory):** as part of agent-log compose, append the per-task cost block produced by `render-agent-log-cost.sh`:
 
 ```bash
 COST_BLOCK=$(bash $HOME/.claude/scripts/render-agent-log-cost.sh "$TASK_ID" 2>/dev/null) && \
@@ -209,6 +209,8 @@ COST_BLOCK=$(bash $HOME/.claude/scripts/render-agent-log-cost.sh "$TASK_ID" 2>/d
 
 This is independent of the channels-side `reportContent.costSummary` (which gates the PR-body Cost Summary). agent-log always carries the breakdown when telemetry is present.
 
+**Missing-telemetry disclosure (required).** Name untracked phase ids as cost-unavailable in the report and closing summary. Mechanic: `payload-contracts.md`.
+
 **Triage memory ingest (mandatory):** after Phase 4 produces a final triage output, persist the accepted/deferred/rejected rows into the per-repo triage corpus so Phase 1 enrichment and Phase 4 prior-art lookup can recall them on future tasks. Idempotent  -  re-running on the same task writes 0 rows.
 
 ```bash

package/pipeline/multi-agent-refs/phases.md

@@ -63,6 +63,12 @@ $HOME/.claude/scripts/phase-tracker.sh update <N> failed         # phase failed
 $HOME/.claude/scripts/phase-tracker.sh update <N> skipped        # --dev mode etc.
 ```
 
+After every LLM call (counts are additive; skipping this is why runs end with durations but no cost  -  nothing reconstructs spend afterwards):
+
+```bash
+$HOME/.claude/scripts/phase-tracker.sh tokens <N> <in> <out> [cached]
+```
+
 For sub-phase progress (e.g. Phase 1's parallel Explore agents, Phase 4's reviewer dispatch + triage + validator gate, Phase 6's commit + push + PR sub-steps):
 
 ```bash

package/pipeline/multi-agent-refs/rules.md

@@ -122,6 +122,8 @@ This is the single source of truth. When a contributor or model is unsure where
 
 4. **Terminal output, log lines, and `echo`/`printf` calls** also use real newlines  -  never `\n` literals. For multi-line messages, prefer heredoc.
 
+5. **Markup dialect is a second axis beyond language.** Markdown: PR body, GitHub issue, wiki files. Jira: wiki markup. Confluence: storage format. Wrong dialect renders literally. Table: `payload-contracts.md`.
+
 ## Issue Management
 
 - **NEVER auto-close** GitHub issues or Jira tickets. Closure requires team review (configurable, typically 4 approvals).

package/pipeline/multi-agent-refs/tracker-contract.md

@@ -310,7 +310,7 @@ The `tasklist_id` meta from the previous session is replaced with the new IDs du
 
 ## Continuation runs (finish / manual-test)
 
-A pre-existing `tracker-state.json` for the task is never re-initialized. Rules for any command that continues an earlier run (`/multi-agent:ship`, `/multi-agent:manual-test`, resume):
+A pre-existing `tracker-state.json` for the task is never re-initialized. Rules for any command that continues an earlier run (`/multi-agent:resume-local`, `/multi-agent:manual-test`, resume):
 
 1. `init` runs ONLY when no state file exists for the task. Otherwise the existing file is kept - phase history (elapsed, tokens, model, meta) survives.
 2. The continuing command re-declares its phase set with `add` - `add` is idempotent, so existing phases keep their name, status, and token history; only genuinely new phases are appended. The card renders phases sorted by numeric id, so mixed sets stay in order.

package/pipeline/multi-agent-refs/wiki-capture.md

@@ -77,9 +77,9 @@ Save the answer to `prefs.global.wikiDefault` for next run. Migration script (`m
 
 ## Dispatch
 
-1. Resolve wiki mode from `figmaConfig.wiki.mode`  -  one of `submodule`, `in-repo`, `github-wiki`, `separate-repo`. Each has a dedicated adapter inside the `figma-component-wiki` skill; see the `ai-ios-engineering-toolkit:figma-component-wiki` plugin skill for per-mode path layout and push semantics.
+1. Resolve wiki mode from `figmaConfig.wiki.mode`  -  one of `submodule`, `in-repo`, `github-wiki`, `separate-repo`. Each has a dedicated adapter inside the `figma-component-wiki` skill; see the `ai-ios-toolkit:figma-component-wiki` plugin skill for per-mode path layout and push semantics.
 2. Emit progress line: `→ writing wiki {componentName} (mode: {mode})`.
-3. Dispatch to the plugin skill `ai-ios-engineering-toolkit:figma-component-wiki` (iOS) or `ai-android-engineering-toolkit:figma-component-wiki` (Android), passing `{componentName, componentPath, figmaConfig}`.
+3. Dispatch to the plugin skill `ai-ios-toolkit:figma-component-wiki` (iOS) or `ai-android-toolkit:figma-component-wiki` (Android), passing `{componentName, componentPath, figmaConfig}`.
 4. Skill returns `{ writtenPaths[], committedSha?, pushedRemote? }`. Write `writtenPaths` to Phase 7 summary's "Files written" section and push metadata (if any) to "External publishes".
 5. On adapter failure  -  log the adapter + mode + error, continue Phase 7. Wiki is a non-blocking augmentation; the Jira comment in Step 3 already carries the component summary, so the developer is never left in the dark if wiki misfires.
 

package/pipeline/preferences-template.json

@@ -1,5 +1,5 @@
 {
-  "schemaVersion": "2.5.0",
+  "schemaVersion": "2.6.0",
   "global": {
     "identities": [],
     "keychainMapping": {
@@ -46,7 +46,12 @@
       "autoDiff": false,
       "manualNote": false
     },
-    "wikiScope": ["main", "ios", "screenshots", "index"],
+    "wikiScope": [
+      "main",
+      "ios",
+      "screenshots",
+      "index"
+    ],
     "autopilotReportTimeoutSeconds": 1800,
     "promptLanguage": "en",
     "outputLanguage": "en",
@@ -78,7 +83,7 @@
     "skillConformance": {
       "blockOnCoverageGap": false
     },
-    "ship": {
+    "resumeLocal": {
       "autoFix": false
     }
   },
@@ -164,13 +169,16 @@
     }
   },
   "_derivedSkillSourcesTemplate": {
-    "_comment": "Optional. Populate global.derivedSkillSources[] to let /multi-agent:refactor check whether skills you derived from an upstream marketplace plugin have been updated. Kept in your LOCAL prefs only (never synced), so it may reference private sources. Copy an entry like the one below. Set upstreamLocalClone when you have a working copy: the installed plugin cache is only as fresh as your last marketplace update, and a stale cache makes the drift check answer 'up to date' when it is four releases behind.",
+    "_comment": "Optional. Populate global.derivedSkillSources[] to let /multi-agent:refactor check whether skills you derived from an upstream marketplace plugin have been updated. Kept in your LOCAL prefs only (never synced), so it may reference private sources. Copy an entry like the one below. Set upstreamLocalClone when you have a working copy: the installed plugin cache is only as fresh as your last marketplace update, and a stale cache makes the drift check answer 'up to date' when it is four releases behind. Set driftAcknowledged to the current upstream version to accept a known drift without failing the gate; the gate re-fails when upstream moves past it.",
     "_example": {
       "label": "Component toolkit skills",
       "localPath": "plugins/<my-plugin>/skills/workflow",
       "upstreamMarketplace": "<installed-marketplace-name>",
       "upstreamPlugin": "<upstream-plugin-name>",
-      "upstreamSkills": ["<skill-a>", "<skill-b>"],
+      "upstreamSkills": [
+        "<skill-a>",
+        "<skill-b>"
+      ],
       "derivedFromVersion": "0.0.0",
       "upstreamVersionSource": "marketplace.json",
       "upstreamLocalClone": "$HOME/<upstream-repo-working-copy>",

package/pipeline/rules/figma-pipeline.md

@@ -1,6 +1,6 @@
 ## Figma -> Component Generation
 
-Skill set lives in the marketplace plugins  -  `ai-ios-engineering-toolkit` (iOS/SwiftUI) and `ai-android-engineering-toolkit` (Android/Compose). Activated when the task contains a Figma URL and target files are `.swift` (iOS) or `.kt` (Android).
+Skill set lives in the marketplace plugins  -  `ai-ios-toolkit` (iOS/SwiftUI) and `ai-android-toolkit` (Android/Compose). Activated when the task contains a Figma URL and target files are `.swift` (iOS) or `.kt` (Android).
 
 ### MUST: Figma access - 3-tier fallback chain (BLOCKING, pipeline-wide)
 
@@ -190,7 +190,7 @@ Phase 3.3: figma-iteration-commit     → Batch iteration commit (if iterating)
 | Wiki | enabled/disabled | `wiki.enabled` |
 | Figma API | MCP / REST fallback | `figma.mcpEnabled` |
 
-Provider interfaces are defined inline in the plugin skill sets  -  see the `ai-ios-engineering-toolkit` and `ai-android-engineering-toolkit` marketplace plugins.
+Provider interfaces are defined inline in the plugin skill sets  -  see the `ai-ios-toolkit` and `ai-android-toolkit` marketplace plugins.
 
 ### Optional Features (graceful skip when disabled)
 

package/pipeline/schemas/agent-state.schema.json

@@ -144,7 +144,7 @@
               "skill": {
                 "type": "string",
                 "minLength": 1,
-                "description": "Skill name as invoked, e.g. ios-coding-standard, ai-ios-engineering-toolkit:create-component, or a guide path for a stack guide."
+                "description": "Skill name as invoked, e.g. ios-coding-standard, ai-ios-toolkit:create-component, or a guide path for a stack guide."
               },
               "phase": {
                 "type": "integer",

package/pipeline/schemas/complaint-analysis-spec.schema.json

@@ -0,0 +1,216 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://github.com/{owner}/multi-agent-pipeline/pipeline/schemas/complaint-analysis-spec.schema.json",
+  "version": "1.0.0",
+  "title": "Multi-Agent Pipeline - /multi-agent:complaint-analysis run state",
+  "description": "Contract for state.complaintSpec, the run state of the customer-complaint triage command. Complaints arrive redacted (parse-complaints.sh strips PII before anything lands here), each one carries its Graylog evidence status, repo evidence rows, and a triage verdict: client / bff (our responsibility, root-cause analysis) or core (routing recommendation only) or insufficient-evidence.",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["runName", "language", "repos", "complaints"],
+  "properties": {
+    "runName": {
+      "type": "string",
+      "minLength": 1,
+      "description": "Run name supplied by the user or defaulted to complaints-<YYYYMMDD>."
+    },
+    "phase": {
+      "type": "string",
+      "enum": [
+        "intake",
+        "fetching_graylog",
+        "correlating_repos",
+        "triaging",
+        "drafting",
+        "awaiting_output_decision",
+        "dispatching",
+        "reporting",
+        "done"
+      ],
+      "description": "Resume marker. Set after each phase boundary."
+    },
+    "language": {
+      "type": "string",
+      "enum": ["tr", "en"],
+      "description": "Report body language, resolved from prefs.global.outputLanguage."
+    },
+    "account": {
+      "type": ["string", "null"],
+      "description": "Account id resolved by the account picker; null for local-only flows."
+    },
+    "repos": {
+      "type": "array",
+      "minItems": 1,
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["name", "layer"],
+        "properties": {
+          "name": { "type": "string", "minLength": 1 },
+          "layer": {
+            "type": "string",
+            "enum": ["ios", "android", "web", "mobile-bff", "web-bff", "other"],
+            "description": "User-confirmed layer tag (Phase 0 Step 3b). core is NOT a layer here - it is the residual verdict, not a repo."
+          },
+          "localPath": { "type": ["string", "null"] },
+          "provider": { "type": ["string", "null"] }
+        }
+      },
+      "description": "Repos selected in the multi-select picker, each tagged with the layer it implements."
+    },
+    "input": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["sources", "complaintCount", "redacted"],
+      "properties": {
+        "sources": {
+          "type": "array",
+          "minItems": 1,
+          "items": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": ["type"],
+            "properties": {
+              "type": { "type": "string", "enum": ["file", "paste", "jira", "confluence"] },
+              "ref": {
+                "type": ["string", "null"],
+                "description": "File path, Jira issue key, or Confluence URL. null for paste."
+              },
+              "format": {
+                "type": ["string", "null"],
+                "enum": ["csv", "xlsx", "txt", "json", "text", null]
+              }
+            }
+          }
+        },
+        "complaintCount": { "type": "integer", "minimum": 0 },
+        "redacted": {
+          "type": "boolean",
+          "description": "Must be true for any run that dispatches output; only --no-redact debug runs of parse-complaints.sh produce false."
+        }
+      }
+    },
+    "complaints": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["id", "textRedacted"],
+        "properties": {
+          "id": { "type": "string", "pattern": "^C-[0-9]{2,}$" },
+          "textRedacted": { "type": "string", "minLength": 1 },
+          "trxId": { "type": ["string", "null"] },
+          "convId": { "type": ["string", "null"] },
+          "date": { "type": ["string", "null"] },
+          "platformHint": { "type": ["string", "null"] },
+          "skipGraylog": {
+            "type": "boolean",
+            "default": false,
+            "description": "True when the user explicitly marked the complaint skip-graylog at the Phase 0 Step 5 id-confirmation loop."
+          },
+          "graylog": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": ["status"],
+            "properties": {
+              "status": { "type": "string", "enum": ["pending", "ok", "degraded", "skipped"] },
+              "totalResults": { "type": "integer", "minimum": 0 },
+              "degradeReason": { "type": ["string", "null"] }
+            }
+          },
+          "repoEvidence": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "required": ["repo", "layer", "file", "signal", "matchKind"],
+              "properties": {
+                "repo": { "type": "string" },
+                "layer": {
+                  "type": "string",
+                  "enum": ["ios", "android", "web", "mobile-bff", "web-bff", "other"]
+                },
+                "file": { "type": "string" },
+                "line": { "type": ["integer", "null"] },
+                "signal": {
+                  "type": "string",
+                  "description": "The Graylog-derived signal that matched: endpoint path, error code, exception name, message template, or source service name."
+                },
+                "matchKind": { "type": "string", "enum": ["direct", "partial"] }
+              }
+            }
+          },
+          "verdict": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": ["category", "confidence", "rationale"],
+            "properties": {
+              "category": {
+                "type": "string",
+                "enum": ["client", "bff", "core", "insufficient-evidence"]
+              },
+              "layer": {
+                "type": ["string", "null"],
+                "enum": ["ios", "android", "web", "mobile-bff", "web-bff", null],
+                "description": "Set for client/bff verdicts; null for core and insufficient-evidence."
+              },
+              "confidence": { "type": "string", "enum": ["high", "medium", "low"] },
+              "rationale": { "type": "string", "minLength": 1 }
+            }
+          },
+          "handoff": {
+            "type": ["object", "null"],
+            "additionalProperties": false,
+            "description": "Present only for client/bff verdicts: development handoff grounded in the existing architecture (repoEvidence files as reference).",
+            "properties": {
+              "fixPlan": {
+                "type": "array",
+                "items": { "type": "string" },
+                "description": "2-5 numbered steps, each referencing a cited file:line or component, reuse-first."
+              },
+              "devPrompt": {
+                "type": ["string", "null"],
+                "description": "English prompt block ready for /multi-agent:dev or a Jira description; includes the [C-NN] id."
+              }
+            }
+          },
+          "routing": {
+            "type": ["object", "null"],
+            "additionalProperties": false,
+            "description": "Present only for core verdicts: the routing recommendation to the backend core team. Never contains fix analysis.",
+            "properties": {
+              "suspectedService": {
+                "type": ["string", "null"],
+                "description": "Graylog message source field of the failing upstream service."
+              },
+              "endpoint": { "type": ["string", "null"] },
+              "errorCode": { "type": ["string", "null"] },
+              "evidenceExcerpt": {
+                "type": ["string", "null"],
+                "description": "Short redacted English excerpt from the Graylog message."
+              },
+              "suggestedQueue": {
+                "type": ["string", "null"],
+                "description": "Optional team/queue label from prefs.projects[*].routing.coreTeamLabel; null when unset."
+              },
+              "confidence": { "type": ["string", "null"], "enum": ["high", "medium", "low", null] }
+            }
+          }
+        }
+      }
+    },
+    "outputs": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "draftDir": { "type": ["string", "null"] },
+        "files": { "type": "array", "items": { "type": "string" } },
+        "destinations": {
+          "type": "array",
+          "items": { "type": "string", "enum": ["local", "confluence", "jira"] }
+        },
+        "confluencePageUrl": { "type": ["string", "null"] },
+        "jiraIssueKey": { "type": ["string", "null"] }
+      }
+    }
+  }
+}

package/pipeline/schemas/migrations/prefs-2.5.0-to-2.6.0.mjs

@@ -0,0 +1,46 @@
+/**
+ * prefs-2.5.0-to-2.6.0.mjs  -  preference schema upgrade 2.5.0 -> 2.6.0
+ *
+ * v15.0.0 renamed the pipeline-tail command a second time: /multi-agent:finish
+ * (pre-2.5.0) became :ship (2.5.0) and is now :resume-local, because the command
+ * continues locally-done work through review/commit/report - it opens the PR but
+ * merges nothing, so "ship" oversold it. One preference key follows:
+ *
+ *   - global.resumeLocal.autoFix  (default FALSE)
+ *       Carried across from global.ship.autoFix (itself carried from
+ *       global.finish.autoFix): a user who opted into auto-fix did so
+ *       deliberately, so the value survives every hop of the rename chain.
+ *
+ * Idempotent: safe on already-2.6.0 input. Non-destructive: an existing explicit
+ * value is preserved; the legacy `ship`/`finish` blocks are removed because they
+ * are no longer declared properties and would fail a closed `global`.
+ *
+ * @param {object} data  -  parsed JSON content of the preferences file
+ * @returns {object}     -  same data with schemaVersion = "2.6.0"
+ */
+export default function migrate(data) {
+  const out = JSON.parse(JSON.stringify(data));
+
+  out.schemaVersion = "2.6.0";
+
+  if (!out.global) out.global = {};
+
+  if (typeof out.global.resumeLocal !== "object" || out.global.resumeLocal === null) {
+    out.global.resumeLocal = {};
+  }
+  if (typeof out.global.resumeLocal.autoFix !== "boolean") {
+    const legacy =
+      typeof out.global.ship?.autoFix === "boolean"
+        ? out.global.ship.autoFix
+        : out.global.finish?.autoFix;
+    out.global.resumeLocal.autoFix = typeof legacy === "boolean" ? legacy : false;
+  }
+  for (const key of ["ship", "finish"]) {
+    if (out.global[key] && typeof out.global[key] === "object") {
+      delete out.global[key].autoFix;
+      if (Object.keys(out.global[key]).length === 0) delete out.global[key];
+    }
+  }
+
+  return out;
+}