@mmerterden/multi-agent-pipeline 16.11.0 → 16.12.0

package/CHANGELOG.md

@@ -16,6 +16,35 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ## [Unreleased]
 
+## [16.12.0] - 2026-08-27
+
+### Added
+
+- **`/multi-agent:analysis` reviews the document before publishing it.** It had no review phase: the only pre-dispatch gate was a structural validator, so nothing ever read what was about to reach Confluence, and one real run published a channel it never searched for, an open question about a frame it never opened, and twenty-three unowned `EKLENECEK` markers. Phase 3.2 runs `phase-4-review.md` Step 0 (the analysis branch that already existed and nothing called) on the draft, before the destination is chosen. Reviewers are subagents holding `analysis/review.md`, never the context that wrote the document, because a context cannot notice a search it never thought to run. A blocking finding returns to synthesis with dispatch closed and never becomes an open question. Locked 36.
+- **Phase 3.3 closes gaps instead of writing them down.** Reachable evidence is searched and never asked about, decisions the user owns are asked, and only external gaps enter the document as `AS-NN` rows with an owner. A gap with neither a `searched, not found` nor an `asked, external` stamp fails the dispatch gate. Autopilot runs both phases; only the asking degrades.
+- **A third reviewer on Claude Code.** Opus fills the slot GPT-5.4 occupies on Copilot and Codex, so every host now runs three: Fable + Opus + Sonnet here. A finding two independent readers both miss is one triage has no chance to catch.
+- **`figma-screenshot.sh --discover-sections`.** One `GET ?depth=3` lists every section whose name matches the feature, with a frame count and a channel guess, folding diacritics so `Elite` and `Elit` are the same word. A channel may no longer be called missing until this returns nothing, and the record must cite the scan (Locked 12). Verified against the file that caused the defect: it returns both the Desktop section and the mobileWeb sibling the run had declared absent.
+- **Four validator gates**: `AS-NN` matched in both directions, `EKLENECEK` without an id, JSON inside a service-table cell, and Turkish diagram labels flattened to ASCII inside a mermaid fence, which the punctuation gate skips.
+
+### Changed
+
+- **"All variants drilled" now means read, not counted** (Locked 19). Visible `TEXT` layers inside each frame's own bounds are extracted, hidden layers and overflowing component boilerplate dropped. A frame can be called out of scope only by quoting its own text, and opening an open question about a frame nobody read fails the gate. One run logged a frame named `08 Payment` as ambiguous while its text spelled out the whole payment step.
+- **Every frame-inventory row gets an embedded image** (Locked 18). The gallery is generated from the inventory rather than hand-picked; narrowing to a canonical subset for page weight is not a call the run makes alone. One run uploaded 34 attachments and embedded 14, and was reported as "frames not uploaded" - the files were there and invisible.
+- **Embedded images carry a display width.** `md2confluence-v3.py --image-width` defaults to 720 with a per-image `![](f.png "width=320")` override; the attachment stays full resolution. A 2x phone export is 750x1624 and took two screen heights at natural size.
+- **Service tables put payloads under the table, not in a cell.** `Request` and `Response` carry one of three states; JSON goes in a fenced block below, field notes in their own table. A whole-unknown contract is one line, not six `EKLENECEK` cells.
+
+### Fixed
+
+- **`md2confluence` re-upload logged one warning per attachment and lost nothing.** The already-exists path was keyed off HTTP 400, and this Confluence Server answers 500 for a duplicate filename, so the update path was unreachable. It looks before creating now; 400, 409 and 500 remain handled as the race they should always have been. `attachments_updated` is counted apart from `attachments_uploaded`, because "0 uploaded, 12 warnings" reads as data loss when nothing was lost.
+- **The mermaid fallback lost every edge in any diagram whose nodes carry labels.** The pattern required the node id to sit next to the arrow, so `A[Basla] --> B` matched nothing - not just labelled branches, the whole flow. Both label syntaxes are captured now and the label is kept (`Evet -> Odeme Yap`), and the source ships beside the list so the diagram is recoverable.
+
+### Internal
+
+- **This release sets the `required` dist-tag.** An install older than 16.12.0 does not produce a worse analysis document, it produces one that has to be redone: no review before publishing, gaps recorded instead of closed, a channel called missing without the file ever being scanned, and frame filenames where the pictures belong. That is the criterion in the Supported Version Gate, so the tag is set rather than left off.
+- The analysis ref ceiling moves 148000 -> 154000 across two raises in one session. Everything that could live outside the count already does: the scan in `figma-screenshot.sh`, the reviewer rubric in `analysis/review.md` which a subagent loads and the orchestrator does not, and all four new gates in `validate-analysis-doc.mjs`. The tree was measured for reclaimable duplication first and had none.
+- `smoke-validate-analysis-doc.sh` replaces four section-number pairing assertions with the `AS-NN` contract in both directions.
+
+
 ## [16.11.0] - 2026-08-27
 
 ### Changed

package/README.md

@@ -62,11 +62,13 @@ One command runs 8 phases, with a gate between the risky ones:
 - **1 · Analysis** - detect the stack, scan the codebase, map impact (Sonnet).
 - **2 · Plan** - write a task breakdown and **stop for your approval** before touching code.
 - **3 · Dev** - TDD: failing test → code → green, following the repo's style + the active stack skills.
-- **4 · Review** - deterministic gates (build / lint / test / secret-scan) must pass first, then a **CLI-aware parallel review** - Claude Code runs 2 models (Fable + Sonnet), Copilot CLI runs 3 (GPT-5.4 + Opus + Sonnet) - and a **Fable triage** keeps only actionable findings; blockers loop back to Phase 3.
+- **4 · Review** - deterministic gates (build / lint / test / secret-scan) must pass first, then a **CLI-aware parallel review** - Claude Code runs 3 models (Fable + Opus + Sonnet), Copilot CLI runs 3 (GPT-5.4 + Opus + Sonnet) - and a **Fable triage** keeps only actionable findings; blockers loop back to Phase 3.
 - **5 · Test** - build + run the suite; success is required (no faked passes).
 - **6 · Commit/PR** - conventional commit, push (must succeed), open a PR (`Ref: #N`, never auto-close).
 - **7 · Report** - technical summary + a Jira comment with test scenarios, posted through the channels layer.
 
+`/multi-agent:analysis` runs its own shorter chain and, since v16.12.0, reviews what it wrote before publishing it: the draft goes through the same three-reviewer set and triage as a code diff, a blocking finding returns it to synthesis with dispatch closed, and the gaps that survive are either searched, asked about, or recorded with an owner. It used to publish behind a structural validator alone.
+
 Under the hood: each task runs in its own **git worktree** (or the current branch with `:local`), commits use the **git identity routed from the repo's origin URL**, and **multi-repo** tasks get per-repo worktrees plus an integration build. Tokens stay in the OS keychain; nothing is committed or logged. `/multi-agent:review` can also review an existing GitHub/Bitbucket PR - per-finding inline comments anchored to `file:line` + an explicit Approve / Needs-Work state.
 
 The discipline behind all of this - bounded loops, evidence gates, token-budgeted phase docs, immutable tests, fresh-context handoffs - is catalogued in [docs/engineering.md](./docs/engineering.md). The full feature list lives in [docs/features.md](./docs/features.md). How this repo, the `multi-agent-plugins` marketplace, and the `multi-agent-toolkit-mcp` server compose at install time and at run time is diagrammed in [docs/ecosystem.md](./docs/ecosystem.md).
@@ -223,8 +225,8 @@ error. Measured on 0.145: installing one plugin that declares 142 skills surface
 `multi-agent` router and keeps the sub-command specs as reference files that cost
 nothing until read - same commands, same behaviour, a layout the host can actually hold.
 
-Reviewer sets differ because the available models do: Claude Code runs 2 reviewers
-(Fable + Sonnet), Copilot CLI 3 (Opus + GPT-5.4 + Sonnet), Codex CLI 3 (gpt-5.6 at
+Reviewer sets differ because the available models do: Claude Code runs 3 reviewers
+(Fable + Opus + Sonnet), Copilot CLI 3 (Opus + GPT-5.4 + Sonnet), Codex CLI 3 (gpt-5.6 at
 xhigh, gpt-5.4, gpt-5.6 at medium). Codex is single-vendor, so consensus among its three
 is weaker evidence than the same consensus on a two-vendor host, and the triage note
 says so.

package/README.tr.md

@@ -62,11 +62,13 @@ Tek komut 8 fazı çalıştırır, riskli olanlar arasında bir kapı ile:
 - **1 · Analysis** - stack'i tespit et, codebase'i tara, etkiyi haritala (Sonnet).
 - **2 · Plan** - bir görev kırılımı yaz ve koda dokunmadan önce **onayın için dur**.
 - **3 · Dev** - TDD: başarısız test → kod → yeşil, repo'nun stiline + aktif stack skill'lerine uyarak.
-- **4 · Review** - önce deterministik kapılar (build / lint / test / secret-scan) geçmeli, sonra bir **CLI-farkında paralel review** - Claude Code 2 model çalıştırır (Fable + Sonnet), Copilot CLI 3 (GPT-5.4 + Opus + Sonnet) - ve bir **Fable triage** sadece aksiyon alınabilir bulguları tutar; blocker'lar Phase 3'e geri döner.
+- **4 · Review** - önce deterministik kapılar (build / lint / test / secret-scan) geçmeli, sonra bir **CLI-farkında paralel review** - Claude Code 3 model çalıştırır (Fable + Opus + Sonnet), Copilot CLI 3 (GPT-5.4 + Opus + Sonnet) - ve bir **Fable triage** sadece aksiyon alınabilir bulguları tutar; blocker'lar Phase 3'e geri döner.
 - **5 · Test** - build + suite'i çalıştır; başarı zorunlu (sahte pass yok).
 - **6 · Commit/PR** - conventional commit, push (başarılı olmalı), bir PR aç (`Ref: #N`, asla otomatik kapatma).
 - **7 · Report** - teknik özet + test senaryolarıyla bir Jira yorumu, channels katmanından gönderilir.
 
+`/multi-agent:analysis` kendi kısa zincirini koşar ve v16.12.0'dan beri yazdığını yayınlamadan önce review ediyor: taslak, bir kod diff'iyle aynı üç-reviewer setinden ve triyajdan geçiyor, bloklayıcı bulgu dokümanı sentez fazına geri gönderip dispatch'i kapatıyor, hayatta kalan boşluklar ya aranıyor ya sana soruluyor ya da sahibiyle birlikte kayda giriyor. Önceden yalnızca yapısal bir validator'ın arkasından yayınlıyordu.
+
 Perde arkasında: her görev kendi **git worktree**'sinde çalışır (ya da `:local` ile mevcut branch'te), commit'ler **repo'nun origin URL'inden yönlendirilen git kimliğini** kullanır, ve **çoklu-repo** görevleri repo başına worktree artı bir integration build alır. Tokenlar OS keychain'de kalır; hiçbir şey commit edilmez ya da loglanmaz. `/multi-agent:review` mevcut bir GitHub/Bitbucket PR'ını da review edebilir - `file:line`'a bağlı bulgu-başına inline yorumlar + açık bir Approve / Needs-Work durumu.
 
 Bunun arkasındaki disiplin - sınırlı loop'lar, kanıt kapıları, token-bütçeli faz dokümanları, değişmez testler, taze-context handoff'lar - [docs/engineering.md](./docs/engineering.md)'de kataloglanmıştır. Tam özellik listesi [docs/features.md](./docs/features.md)'te. Bu repo, `multi-agent-plugins` marketplace'i ve `multi-agent-toolkit-mcp` sunucusunun install zamanında ve run zamanında nasıl bir araya geldiği [docs/ecosystem.md](./docs/ecosystem.md)'de diyagramlanmıştır.
@@ -224,8 +226,8 @@ pipeline tek bir `multi-agent` router gönderir ve alt-komut spec'lerini, okunan
 hiçbir maliyeti olmayan referans dosyaları olarak tutar - aynı komutlar, aynı davranış,
 host'un gerçekten tutabildiği bir düzen.
 
-Reviewer setleri farklı çünkü mevcut modeller farklı: Claude Code 2 reviewer çalıştırır
-(Fable + Sonnet), Copilot CLI 3 (Opus + GPT-5.4 + Sonnet), Codex CLI 3 (xhigh'da
+Reviewer setleri farklı çünkü mevcut modeller farklı: Claude Code 3 reviewer çalıştırır
+(Fable + Opus + Sonnet), Copilot CLI 3 (Opus + GPT-5.4 + Sonnet), Codex CLI 3 (xhigh'da
 gpt-5.6, gpt-5.4, medium'da gpt-5.6). Codex tek-vendor olduğu için üçü arasındaki
 konsensüs, iki-vendor'lu bir host'taki aynı konsensüsten daha zayıf bir kanıttır ve
 triage notu bunu belirtir.

package/docs/adr/0001-three-model-triage.md

@@ -2,6 +2,11 @@
 
 **Status:** Accepted · 2025 · Amended 2026-04 (CLI-aware reviewer set) · Amended 2026-07 (v10.6.0: Fable 5 restored - Reviewer 1 and triage run on Fable on Claude Code; Copilot CLI pins Opus. "Opus" below reads as "the top tier of the day")
 
+> **Superseded in part, v16.12.0.** The reviewer count is now 3 on every host: Opus
+> fills the slot GPT-5.4 occupies on Copilot and Codex, so Claude Code runs
+> Fable + Opus + Sonnet. The reasoning below about a 2-reviewer set on Claude Code
+> is kept as the record of what was decided then, not as current behaviour.
+
 ## Context
 
 Code review is the phase where the pipeline most commonly ships wrong work. A

package/docs/features.md

@@ -12,7 +12,7 @@ Phase 1: Analysis  Stack detection, codebase exploration (parallel Explore agent
 Phase 2: Planning  Task decomposition, architecture review, user approval
 Phase 3: Dev       TDD cycle: test → code → build (Sonnet)
 Phase 4: Review    Deterministic gates + parallel AI review + Fable triage
-                   (Claude Code: Fable + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
+                   (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
 Phase 5: Test      Optional manual testing + on-demand device audits
 Phase 6: Commit    Git commit, push, PR with default reviewers + draft/ready prompt
 Phase 7: Report   External: Jira comment · Wiki + Figma screenshots · Confluence
@@ -134,6 +134,22 @@ Cheap, objective checks run BEFORE any AI token is spent:
 
 If any gate fails, fix first. Don't waste AI tokens reviewing broken code.
 
+### Analysis Document Review (Phase 3.2 + 3.3)
+
+`/multi-agent:analysis` published behind a structural validator alone until v16.12.0: nothing read the
+document before it reached Confluence. Phase 3.2 now runs the same reviewer set and triage a code diff
+gets, on the draft, before the destination is even chosen. Its first question is what the run skipped -
+an input declared missing that nothing searched for, an open question about evidence nobody read, a gap
+with no owner, a scope call made without asking. A blocking finding returns to synthesis with dispatch
+closed; it never becomes an open question, because "the document is wrong" is not something to ask the
+reader.
+
+Phase 3.3 then sorts what is left: reachable evidence is searched (never asked about), decisions the
+user owns are asked with `AskUserQuestion`, and only genuinely external gaps enter the document as
+`AS-NN` rows with an owner. A gap carrying neither a `searched, not found` nor an `asked, external`
+stamp fails the dispatch gate. Autopilot runs both phases; only the asking degrades, into rows stamped
+`autopilot: could not ask`.
+
 ### CLI-Aware Parallel Review + Fable Triage (Phase 4 Steps 2-3)
 
 | Reviewer   | Model               | Focus                             | Where it runs        |
@@ -142,7 +158,7 @@ If any gate fails, fix first. Don't waste AI tokens reviewing broken code.
 | Reviewer 2 | `gpt-5.4`           | Edge cases, different perspective | **Copilot CLI only** |
 | Reviewer 3 | `claude-sonnet-4-6` | Quality + correctness + naming    | Both CLIs            |
 
-The reviewer set is **CLI-aware**: Claude Code dispatches 2 reviewers in parallel (Fable + Sonnet - GPT-5.4 is not available there); Copilot CLI dispatches all 3. Each returns structured JSON for deterministic aggregation. Cross-model diversity catches blind spots that any single model family would miss.
+The reviewer set is **CLI-aware**: Claude Code dispatches 3 reviewers in parallel (Fable + Opus + Sonnet - Opus fills the slot GPT-5.4 takes elsewhere); Copilot CLI dispatches all 3. Each returns structured JSON for deterministic aggregation. Cross-model diversity catches blind spots that any single model family would miss.
 
 **Fable Triage** (Phase 4 Step 3, Opus on Copilot CLI): Evaluates merged raw findings against task scope. Classifies each as `accepted` (fix now), `deferred` (out of scope, log for later), or `rejected` (false positive / noise). Only triage-accepted blocking items loop back to Phase 3.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "16.11.0",
+  "version": "16.12.0",
   "description": "8-phase AI development pipeline with full orchestration on Claude Code, Copilot CLI and Codex CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase cost ledger, persistent learnings memory, wiki generation, commit automation. Token-preserving uninstall.",
   "type": "module",
   "main": "index.js",

package/pipeline/claude-md-template.md

@@ -17,7 +17,7 @@
 2. Planning (Opus) -> spec, task breakdown
 3. Development (Sonnet) -> TDD, code, build
 4. Review -> deterministic gates + parallel review + Fable triage
-   - Claude Code: Opus + Sonnet (2 paralel)
+   - Claude Code: Fable + Opus + Sonnet (3 paralel)
    - Copilot CLI: GPT-5.4 + Opus + Sonnet (3 paralel)
    - Codex CLI: gpt-5.6 (xhigh) + gpt-5.4 + gpt-5.6 (medium) (3 paralel)
 

package/pipeline/commands/multi-agent/SKILL.md

@@ -1,6 +1,6 @@
 ---
 description: "Task orchestrator  -  full pipeline via Jira ID + branch or GitHub Issue URL: analysis, plan, TDD development, parallel review + Fable triage (CLI-aware: 2-model on Claude Code, 3-model on Copilot CLI), commit, log. Use when given a Jira ID, a GitHub issue or a free-text task and the whole pipeline should run."
-description-tr: "Görev orkestratörü - Jira ID + branch veya GitHub Issue URL ile tam pipeline: analiz, plan, TDD geliştirme, paralel review + Fable triyajı (CLI'ya göre: Claude Code'da 2, Copilot CLI'da 3 model), commit, log"
+description-tr: "Görev orkestratörü - Jira ID + branch veya GitHub Issue URL ile tam pipeline: analiz, plan, TDD geliştirme, paralel review + Fable triyajı (CLI'ya göre: Claude Code'da 3, Copilot CLI'da 3 model), commit, log"
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, NotebookEdit, Skill
 ---
 

package/pipeline/commands/multi-agent/analysis/SKILL.md

@@ -61,7 +61,7 @@ Full contract: `$HOME/.claude/multi-agent-refs/analysis/evidence.md`. Fetches ev
 
 Full contract: `$HOME/.claude/multi-agent-refs/analysis/synthesis.md`. Pass A builds the platform-agnostic concept layer; Phase 2a previews the resolved conventions for approval (Locked 26); Pass B projects each concept onto the selected platform with a footnote per filled cell (Locked 24).
 
-### Phases 3, 3.5, 4, 5 - Render, publish, report
+### Phases 3, 3.2, 3.3, 3.5, 4, 5 - Render, review, publish, report
 
 Full contract: `$HOME/.claude/multi-agent-refs/analysis/render.md`. Renders one markdown file per platform, runs the **required** `ai-common-toolkit:humanizer` pass, gates on `validate-analysis-doc.mjs` and on the `build-references.mjs --check` references coverage gate (Locked 34), asks for the output destination, dispatches to Local / Confluence / Jira (a Jira issue receives a comment unless the user explicitly asks for the description, which is never overwritten without a backup and a confirmation), then reports and stops. The humanizer pass and the validator are required in every mode; a document that skipped either is not shippable.
 

package/pipeline/commands/multi-agent/help/SKILL.md

@@ -59,7 +59,7 @@ Pipeline (after Phase 0)  -  shown as visual cards in terminal:
                            only; a Short run has no plan, autopilot may not ask)
   Phase 3:   Dev        -> TDD: test -> code -> build (Sonnet) + build queue
   Phase 4:   Review     -> Deterministic gates + parallel AI review + Fable triage
-                          (Claude Code: Fable + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
+                          (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
   Phase 5:   Test       -> Optional: switch to branch, test in Xcode
                           (only /multi-agent has it; every autopilot and local entry drops it)
   Phase 6:   Commit     -> Commit -> push -> PR + issue body update (never auto-closes)
@@ -334,7 +334,7 @@ Pipeline (Phase 0'dan sonra)  -  terminalde görsel kart olarak görünür:
                            etkileşimli; Kısa'da plan yok, autopilot soru soramaz)
   Phase 3:   Dev        -> TDD: test -> kod -> build (Sonnet) + build queue
   Phase 4:   Review     -> Deterministik kapılar + paralel AI review + Fable triage
-                          (Claude Code: Fable + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
+                          (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
   Phase 5:   Test       -> Opsiyonel: branch'e geç, Xcode'da test
                           (yalnız /multi-agent'ta var; her autopilot ve local girişi düşürür)
   Phase 6:   Commit     -> Commit -> push -> PR + issue body güncelleme (hiç auto-close yok)

package/pipeline/commands/multi-agent/resume-local/SKILL.md

@@ -34,7 +34,7 @@ You already did the work locally  -  wrote code on the current branch and maybe
 
 ```
 Phase 0: Init          → project/branch detect, resolve base + diff (work-already-done), Jira id, state (NO worktree)
-Phase 4: Review        → deterministic gates + parallel review (Fable + Sonnet) + Fable triage
+Phase 4: Review        → deterministic gates + parallel review (Fable + Opus + Sonnet) + Fable triage
 Phase 5: Build+Test    → stack-aware build gate + run existing tests; SUCCESS required (automated, not the interactive user-test)
 Phase 6: Commit        → commit remaining local changes + push + open PR if none exists
 Phase 7: Report        → technical analysis + Jira comment with test scenarios (channels: Jira / PR / Confluence / Wiki)
@@ -52,7 +52,7 @@ Phases 1-3 (Analysis / Planning / Dev) are skipped by design  -  `ship` treats t
 
 ## Phase execution (reuse the existing phase contracts)
 
-- **Phase 4 Review** - run per `$HOME/.claude/multi-agent-refs/phases/phase-4-review.md` against the resolved diff: deterministic gates (Step 1.x), stack-specific parallel reviewers (Fable + Sonnet on Claude Code; GPT + Opus + Sonnet on Copilot CLI), Fable triage → `triage.accepted`. Blocking/important accepted findings:
+- **Phase 4 Review** - run per `$HOME/.claude/multi-agent-refs/phases/phase-4-review.md` against the resolved diff: deterministic gates (Step 1.x), stack-specific parallel reviewers (Fable + Opus + Sonnet on Claude Code; GPT + Opus + Sonnet on Copilot CLI), Fable triage → `triage.accepted`. Blocking/important accepted findings:
   - interactive: present them and ask (`AskUserQuestion`) whether to fix now (loop back through a minimal Phase-3-style TDD fix) or proceed;
   - `autopilot` (or `prefs.global.resumeLocal.autoFix == true`): auto-fix accepted blocking/important findings, then re-review the fix, before advancing.
 - **Phase 5 Build+Test** - the **automated success gate** (this is what "build+test success" means here; the interactive device user-test is `/multi-agent:manual-test`). Stack-aware: build via `figma-config.build` (iOS scheme / Android gradle / detected backend/web build) and run the existing test suite if present (`swift test` / `xcodebuild test` / `./gradlew test` / `pytest` / `npm test` / `vitest`). Require success to advance; on failure, surface logs and (interactive) stop or (autopilot) attempt a bounded fix loop. **If the repo has no tests, report "no tests present" - never fabricate test results.**

package/pipeline/commands/multi-agent/review/SKILL.md

@@ -1,6 +1,6 @@
 ---
-description: "Run parallel review on a branch's diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments and sets approve/needs-work review state. Use when a branch diff or a pull request needs reviewing before it merges."
-description-tr: "Bir branch diff'i veya Pull Request üzerinde paralel review koşar: Claude Code'da 2 model (Fable + Sonnet), Copilot CLI'da 3 model (GPT + Opus + Sonnet). PR girdisinde bulgu başına inline yorum atar ve approve/needs-work durumunu işaretler."
+description: "Run parallel review on a branch's diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments and sets approve/needs-work review state. Use when a branch diff or a pull request needs reviewing before it merges."
+description-tr: "Bir branch diff'i veya Pull Request üzerinde paralel review koşar: Claude Code'da 3 model (Fable + Opus + Sonnet), Copilot CLI'da 3 model (GPT + Opus + Sonnet). PR girdisinde bulgu başına inline yorum atar ve approve/needs-work durumunu işaretler."
 argument-hint: "[#N | repo#N | PR-URL | branch]  -  optional: PR by number/URL, repo+number, or local branch. Supports GitHub and Bitbucket Server URLs. If omitted (interactive), open GitHub + Bitbucket PRs are listed for multi-select; autopilot falls back to the current branch."
 ---
 
@@ -175,7 +175,7 @@ Scope note: a guide governs only files under its own directory  -  a guide found
 
 ### 3. Launch parallel reviewers  -  host-CLI dependent
 
-**Claude Code (2 in parallel):**
+**Claude Code (3 in parallel):**
 - Agent 1: `claude-fable-5` → security + architecture
 - Agent 2: `claude-sonnet-5` → general quality
 

package/pipeline/commands/multi-agent/review-analysis/SKILL.md

@@ -16,7 +16,7 @@ Read `$HOME/.claude/multi-agent-refs/analysis/review.md` and execute it:
 
 1. **Resolve** the document from a local path, a Confluence URL or `pageId`, or a Jira key. With no argument, offer the recent analyses from `~/Desktop/multiAgentAnalysis/` and from each selected repo's `analysis/`, newest first.
 2. **Deterministic gates first**: `validate-analysis-doc.mjs` on the document, and `build-references.mjs --check` when the run's state JSON is available (`--state`, or a fresh analysis). Their output is reported verbatim, before any model reads the document. A finding a script already proves does not need an opinion.
-3. **Parallel model review** against the rubric (buildability, evidence, spine, altitude, admitted gaps, contradiction), CLI-aware: 2 models on Claude Code, 3 on Copilot CLI.
+3. **Parallel model review** against the rubric (buildability, evidence, spine, altitude, admitted gaps, contradiction), CLI-aware: 3 models on Claude Code, 3 on Copilot CLI.
 4. **Fable triage** into Blocker / Important / Suggestion, dropping duplicates and anything the document answers elsewhere.
 5. **Report**, naming the profile it judged against and, explicitly, what was NOT checked.
 6. **Output** on request only: chat (default), Confluence comment, Jira comment, or a `-review.md` beside the document.

package/pipeline/lib/figma-screenshot.sh

@@ -88,6 +88,8 @@ MAX_IDS_PER_CALL=50
 FILE_KEY=""
 NODE_ID=""
 SECTION_URL=""
+DISCOVER=0
+FEATURE_SLUG=""
 OUTPUT_DIR=""
 SCALE="2"
 FORMAT="png"
@@ -118,6 +120,12 @@ Options:
   --file-key       Figma file key (or branchKey for branch URLs).
   --node-id        Node id; may use either "-" or ":" separator.
   --section        Section URL; child FRAMEs are auto-discovered.
+  --discover-sections  With --file-key and --feature-slug: list every SECTION or
+                   FRAME in the file whose name matches the feature, with a
+                   channel guess. One GET ?depth=2. Answers "does this file also
+                   hold the other channel's design" before a run may write that a
+                   channel has none. Emits JSON, downloads nothing.
+  --feature-slug   Feature name to match against, for --discover-sections.
   --output-dir     Output directory. Default: /tmp/figma-screenshots-<ts>.
   --scale          Render scale (1-4). Default: 2.
   --format         Image format. Default: png.
@@ -387,6 +395,8 @@ while [ "$#" -gt 0 ]; do
     --file-key) FILE_KEY="${2:-}"; shift 2 ;;
     --node-id)  NODE_ID="${2:-}"; shift 2 ;;
     --section)  SECTION_URL="${2:-}"; shift 2 ;;
+    --discover-sections) DISCOVER=1; shift ;;
+    --feature-slug) FEATURE_SLUG="${2:-}"; shift 2 ;;
     --output-dir) OUTPUT_DIR="${2:-}"; shift 2 ;;
     --scale)    SCALE="${2:-2}"; shift 2 ;;
     --format)   FORMAT="${2:-png}"; shift 2 ;;
@@ -394,12 +404,16 @@ while [ "$#" -gt 0 ]; do
   esac
 done
 
-if [ -n "$SECTION_URL" ] && { [ -n "$FILE_KEY" ] || [ -n "$NODE_ID" ]; }; then
-  die 1 "--section is mutually exclusive with --file-key/--node-id"
-fi
-
-if [ -z "$SECTION_URL" ] && { [ -z "$FILE_KEY" ] || [ -z "$NODE_ID" ]; }; then
-  die 1 "either --section <url> or both --file-key and --node-id are required"
+if [ "$DISCOVER" -eq 1 ]; then
+  [ -n "$FILE_KEY" ] || die 1 "--discover-sections requires --file-key"
+  [ -n "$FEATURE_SLUG" ] || die 1 "--discover-sections requires --feature-slug"
+else
+  if [ -n "$SECTION_URL" ] && { [ -n "$FILE_KEY" ] || [ -n "$NODE_ID" ]; }; then
+    die 1 "--section is mutually exclusive with --file-key/--node-id"
+  fi
+  if [ -z "$SECTION_URL" ] && { [ -z "$FILE_KEY" ] || [ -z "$NODE_ID" ]; }; then
+    die 1 "either --section <url> or both --file-key and --node-id are required"
+  fi
 fi
 
 require_cmd curl
@@ -421,6 +435,90 @@ if [ -z "$OUTPUT_DIR" ]; then
 fi
 mkdir -p "$OUTPUT_DIR"
 
+# --- Discovery mode ---------------------------------------------------------
+# One GET /v1/files/{key}?depth=3 lists every page, its sections and their frames,
+# which is what makes frameCount real rather than always zero.
+# That is enough to answer "does this file also hold the other channel's design",
+# which a run has to ask before it may write that a channel has no design at all.
+# Matching is diacritic- and case-insensitive because the same feature is spelled
+# "Elite Kart" on one section and "Elit Kart" on its sibling.
+
+run_discover_mode() {
+  local body
+  # Same as fetch_with_retry: the token goes through a curl config on a process
+  # substitution, never argv, because argv is readable from ps.
+  body=$(curl -sS --max-time "$HTTP_TIMEOUT" --connect-timeout 5 \
+    -K <(printf 'header = "X-Figma-Token: %s"\n' "$FIGMA_TOKEN") \
+    "https://api.figma.com/v1/files/${FILE_KEY}?depth=3") || die 3 "file tree fetch failed"
+
+  printf '%s' "$body" | FEATURE_SLUG="$FEATURE_SLUG" FILE_KEY="$FILE_KEY" python3 -c '
+import json, os, re, sys, unicodedata
+
+def fold(t):
+    t = unicodedata.normalize("NFKD", t)
+    t = "".join(c for c in t if not unicodedata.combining(c))
+    # Turkish dotless i and the rest survive NFKD, so map them explicitly.
+    t = t.translate(str.maketrans("ıİşŞğĞçÇöÖüÜ", "iIsSgGcCoOuU"))
+    return re.sub(r"[^a-z0-9]+", " ", t.lower()).strip()
+
+CHANNELS = [
+    ("mobileweb", ["mobileweb", "mobile web", "mobil web", "responsive"]),
+    ("mobile",    ["mobile app", "mobil uygulama", "app", "ios", "android", "mobil", "mobile"]),
+    ("desktop",   ["desktop", "masaustu", "web"]),
+]
+
+def channel_of(name):
+    f = fold(name)
+    for label, tokens in CHANNELS:
+        for tok in tokens:
+            if re.search(r"\b" + re.escape(fold(tok)) + r"\b", f):
+                return label
+    return None
+
+raw = sys.stdin.read()
+try:
+    doc = json.loads(raw).get("document", {})
+except Exception:
+    print(json.dumps({"error": "unparseable file response"})); sys.exit(3)
+
+slug_words = [w for w in fold(os.environ["FEATURE_SLUG"]).split() if len(w) > 2]
+out, weak, pages = [], [], 0
+for page in doc.get("children", []) or []:
+    pages += 1
+    for node in page.get("children", []) or []:
+        if node.get("type") not in ("SECTION", "FRAME"):
+            continue
+        name = node.get("name", "")
+        f = fold(name)
+        hits = [w for w in slug_words if w in f]
+        if not hits:
+            continue
+        # A single shared word is not a match: "Mil Hediye Et" shares "hediye" with
+        # "Elite Kart Hediye Et" and is a different feature. Require half the slug,
+        # at least two words. Weak hits are reported separately, never dropped in
+        # silence, because a run has to be able to say what it looked at.
+        need = max(2, (len(slug_words) + 1) // 2) if len(slug_words) > 1 else 1
+        row = {
+            "id": node.get("id"),
+            "name": name,
+            "type": node.get("type"),
+            "page": page.get("name"),
+            "frameCount": len(node.get("children", []) or []),
+            "channelGuess": channel_of(name),
+            "matchedWords": hits,
+        }
+        (out if len(hits) >= need else weak).append(row)
+print(json.dumps({
+    "fileKey": os.environ["FILE_KEY"],
+    "featureSlug": os.environ["FEATURE_SLUG"],
+    "pagesScanned": pages,
+    "tokensTried": slug_words,
+    "candidates": sorted(out, key=lambda c: (c["channelGuess"] or "zz", c["id"])),
+    "weakMatches": sorted(weak, key=lambda c: c["id"]),
+}, ensure_ascii=False, indent=2))
+'
+}
+
 # --- Section mode -----------------------------------------------------------
 
 run_section_mode() {
@@ -548,7 +646,9 @@ PY
 
 # --- Dispatch ---------------------------------------------------------------
 
-if [ -n "$SECTION_URL" ]; then
+if [ "$DISCOVER" -eq 1 ]; then
+  run_discover_mode
+elif [ -n "$SECTION_URL" ]; then
   run_section_mode
 else
   run_single_mode