@mmerterden/multi-agent-pipeline 10.9.0 → 10.12.0

package/CHANGELOG.md

@@ -14,6 +14,149 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ---
 
+## [10.12.0] - 2026-07-06
+
+Two trust upgrades: every external channel post now shows a plan-mode-style
+preview + approval gate before anything is written (autopilot posts directly),
+and Phase 0 gains a proactive token expiry pre-flight with silent Figma MCP
+renewal via OAuth refresh grant.
+
+### Added
+
+- **Channels Step 6 body preview + approval gate** (dispatch → Step 7,
+  summary → Step 8) - interactive runs render
+  every selected channel's final body (PR description, Jira comment,
+  Confluence page, Wiki, Board move, GitHub issue comment) and ask
+  Approve & post / Edit (loop) / Skip channels / Cancel before dispatch.
+  Bypassed only by autopilot and `--dry-run`. What is posted is byte-identical
+  to the approved preview; regeneration after approval re-runs the gate.
+  Phase 7 Step 1.5 (issue comment + progress flags) routes through the same
+  gate. Contract: `smoke-channels-approval-gate.sh`.
+- **Phase 0 Step 0.7 token expiry pre-flight** - probes every token the run
+  will need (jira/github/bitbucket/confluence/figma/figma_mcp) with one cheap
+  call each (cached via `serviceStatus`, TTL 300s) and resolves expiry AT INIT
+  instead of on the first mid-run 401. Figma MCP is the critical path: silent
+  renewal first, then an init-time question (Regenerate now via script / Save
+  Flow / Continue degraded). Autopilot never prompts - silent renewal or
+  logged degrade. Contract: `smoke-token-preflight.sh`.
+- **`lib/figma-mcp-refresh.sh`** - silent Figma MCP (`figu_`) renewal via
+  OAuth refresh grant: reads `<key>_Refresh` from the Keychain + client
+  credentials from the `.figma-oauth.json` next to
+  `prefs.global.tokenScripts.figma_mcp`, saves the new access (and rotated
+  refresh) token back. Status lines only - token values never printed.
+  Live-verified end-to-end (renewed + mcp.figma.com probe 200).
+- **`prefs.global.tokenScripts`** (schema + template) - maps service ids to
+  user-owned token generation scripts; personal paths stay in the local
+  preferences file, never in synced command files.
+- **keychain.md Figma MCP lifecycle section** - refresh-entry convention,
+  silent-renewal-first rule, generation-script escalation, init cross-ref.
+
+### Fixed
+
+- Copilot parity catch-ups the 10.11.0 sweep missed: `multi-agent-sync/SKILL.md`
+  inventory 35 -> 37 + list, `multi-agent-help/SKILL.md` generator entries
+  (EN + TR), `multi-agent-channels/SKILL.md` flow now includes the approval
+  gate (steps 6-8). `smoke-generate-issue.sh` now asserts the SKILL-side
+  counts too.
+- `figma-mcp-refresh.sh` form fields sent via `--data-urlencode` (robust to
+  special characters in tokens); re-verified live.
+
+## [10.11.0] - 2026-07-06
+
+Jira issue generators: `/multi-agent:generate-task` and `/multi-agent:generate-bug` create standards-compliant Jira issues by learning the target project's own conventions before drafting, with a hard preview + approval gate before anything is created.
+
+### Added
+
+- **`/multi-agent:generate-task` + `/multi-agent:generate-bug`** - one-shot
+  Jira issue creators (no worktree, no commits, no pipeline chaining). Inputs:
+  optional free-text description + optional Figma URL; both asked
+  interactively when missing.
+- **Convention mining** - samples the project's 30 most recent same-type
+  issues (JQL) and adopts the team's summary prefix pattern, dominant
+  description heading set, top labels/components, and priority norm.
+  createmeta discovery surfaces required custom fields (allowedValues become
+  picker options) and detects Sprint/Epic/Team fields generically by
+  `schema.custom` id.
+- **Active-sprint placement** - Agile REST board + `sprint?state=active`
+  detection; the user chooses active sprint vs backlog. Sprint assignment
+  happens post-create via `POST /rest/agile/1.0/sprint/{id}/issue`
+  (field-id-agnostic). No board / no active sprint degrades to backlog with
+  an explicit note.
+- **Hard approval gate** - a full draft preview (every field + complete
+  description) renders before create; Approve / Edit (loop) / Cancel. The
+  gate has no bypass: no autopilot variant exists for these commands.
+  Genuinely unknown fields (component, epic, priority, labels, assignee,
+  sprint, required customs, missing Bug repro/environment) are asked, never
+  invented.
+- **Figma context (optional)** - the 3-tier chain (MCP -> REST PAT -> user
+  screenshot) resolves frame name + node id for a Design Reference section,
+  a remote link on the created issue, and an opt-in screenshot attachment.
+  Standalone command, so MCP use is allowed (analysis-class); Figma failures
+  never block issue creation.
+- **Language rule** - issue summary + description follow
+  `prefs.global.outputLanguage` (intentional exception to the
+  external-payloads-English default; the issue is authored for the user's
+  team). Documented in both command files and the shared ref.
+- **Shared flow ref** `refs/generate-issue.md` - single 11-step contract
+  consumed by both commands via profile blocks (`ISSUE_TYPE`, default
+  sections, JQL filter); UTF-8 verbatim POST path (`jq --rawfile` +
+  `--data-binary @file`) and humanizer pass reused from the Jira channel
+  adapter.
+- **Smoke gate** `smoke-generate-issue.sh` - 66 assertions: file/frontmatter
+  presence, profile declarations, approval-gate markers, endpoint markers,
+  UTF-8 path, section vocabulary, 37-command count consistency across
+  dispatcher/contract/sync/help, forbidden-string scan.
+
+### Changed
+
+- Command inventory 35 -> 37 across `cross-cli-contract.md`, `sync.md`,
+  dispatcher routing/loading tables, `help.md` (EN + TR), README.
+
+## [10.10.0] - 2026-07-03
+
+Live tracker UX: per-tile cost, a real "currently doing X" line, and tracker continuity across the local-test handover. Shaped by a market sweep of 2026 agent-UX practice (transparency-first live status; per-step cost visibility).
+
+### Added
+
+- **`phase-tracker.sh now <N> "<text>"`** - dedicated live current-action
+  line for the active phase (quiet: writes `meta.Now`, never renders, 60-char
+  cap). The bordered card shows it as `Now: <text>` under the active tile.
+- **`phase-tracker.sh cost <N>|total`** - single pricing implementation
+  (cost-table.json rates, cached tokens at the discounted cacheRead rate,
+  floored to cents; `-` when unpriceable). The completion narration line,
+  the card, and finish's summary all reuse it - no more inline USD math.
+- **Per-tile est. USD + cached footer on the bash card.** Tiles render
+  `<elapsed> · <tok> tok · ~$<usd>` when the phase has a priced model; the
+  footer adds total USD and cached tokens. Render survives a missing cost
+  table. Tiles now sort by numeric phase id so continuation sets stay ordered.
+- **Progress-line mirror rule** (tracker-contract "Active phase" +
+  progress-contract cross-link): every normal-tier `→ verb object` line is
+  mirrored to the active phase - `TaskUpdate activeForm` on Claude Code,
+  `now` elsewhere - so the tracker always answers "what is it doing right
+  now". Throttled: canonical lines only, dedupe, no renders.
+- **Completion tile suffix (Claude Code):** on phase completion the tile
+  subject gains the spend (`Phase 3: Dev · ~35k tok · ~$0.58`); subject edits
+  do not reorder tiles.
+- **Tracker continuity across the local-test handover.** Phase 5 and
+  `/multi-agent:manual-test` mark the waiting state
+  (`now 5 "awaiting local test (user)"`); `/multi-agent:finish` now runs
+  load-or-continue instead of an unconditional `init` - prior phase 0-3
+  history (elapsed, tokens, USD) survives, Phase 5 is closed with a Result
+  meta, the Claude Code TaskList is rebuilt from state, and one line
+  summarizes the inherited history (`Continuing <id>: phases 0-3 finished
+  earlier (12m, 38.4k tok, ~$0.74)`). `add` is idempotent to make this safe.
+- **`/multi-agent:resume` rebuilds the phase tiles** from `tracker-state.json`
+  (the contract documented it; the command now actually does it).
+- **Phase 0 + 7 token forwarding**: the clarifier call and the Phase 7 report
+  compose call forward tokens to the tracker, completing all 8 tiles.
+
+### Fixed
+
+- Tracker doc drift: the `tokens` action's 4th `[cached]` arg and the `model`
+  action are now documented in the contract and the script usage text.
+
+---
+
 ## [10.9.0] - 2026-07-03
 
 ### Added

package/README.md

@@ -63,7 +63,7 @@ The discipline behind all of this — bounded loops, evidence gates, token-budge
 | Local | `/multi-agent:local "task"` | Full pipeline, current branch (no worktree) |
 | Finish | `/multi-agent:finish` | Run the review→test→commit→report tail over local work |
 
-Helpers: `setup`, `status`, `resume #N`, `review`, `test`, `channels`, `stack`, `update`, `sync`, `jira`, `issue`, `analysis`. Full list: `/multi-agent:help`.
+Helpers: `setup`, `status`, `resume #N`, `review`, `test`, `channels`, `stack`, `update`, `sync`, `jira`, `issue`, `analysis`, `generate-task`, `generate-bug`. Full list: `/multi-agent:help`.
 
 ## Stacks
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "10.9.0",
+  "version": "10.12.0",
   "description": "8-phase AI development pipeline with full orchestration on Claude Code and Copilot 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/commands/multi-agent/channels.md

@@ -34,7 +34,7 @@ Target resolution is identical to the pre-existing enrich flow  -  any of the 6
 
 ## Flow
 
-`resolve target → fetch context → menu (or flags) → generator → humanizer → dispatch → summary`. Channels: Jira comment, Confluence page, Wiki pages, PR description, Board status (GitHub Projects v2).
+`resolve target → fetch context → menu (or flags) → generator → humanizer → approval → dispatch → summary`. Channels: Jira comment, Confluence page, Wiki pages, PR description, Board status (GitHub Projects v2).
 
 ### Step 1  -  Target resolution
 
@@ -49,7 +49,7 @@ Target resolution is identical to the pre-existing enrich flow  -  any of the 6
 
 **Multi-repo:** when `agent-state.json` `projects[].length > 1`, Step 1 builds **one target per project**. Each project's PR is resolved via `pr` field in its projects[] entry; if missing, the Jira/Issue link query returns multiple PRs (one per repo)  -  all are added to `targets[]`. The project at `projects[0]` (or whose name matches `state.project`) is marked `isPrimary: true`; others are `isPrimary: false`.
 
-For single-repo tasks, `targets` has exactly one entry. The rest of the flow is target-aware: Step 5 generates one body, Step 6 dispatches to each target, with cross-links (see below).
+For single-repo tasks, `targets` has exactly one entry. The rest of the flow is target-aware: Step 5 generates one body, Step 7 dispatches to each target, with cross-links (see below).
 
 ### Step 2  -  Context source detection
 
@@ -298,9 +298,44 @@ Generated by `pipeline/scripts/render-cost-summary.sh <task-id>` using prices fr
 
 **Target length rule:** full body fits one screen on a typical laptop (< 80 lines). Auto-diff summary capped at 5 lines per section. No framework-theory paragraphs, no numbered "why this approach" lists.
 
-### Step 6  -  Channel dispatch
+### Step 6  -  Body preview + approval gate (interactive modes)
 
-For each selected **channel**, call the corresponding adapter. Adapters run **in parallel**  -  one failure does not block others.
+Plan-mode-style gate: the user sees exactly what will be posted BEFORE any external write. Runs after the generator + humanizer, before Step 7 dispatch, in every interactive invocation  -  menu mode AND `--channels`/`--content` flag mode alike (flags pick the targets, they do not waive the content approval).
+
+Skipped in exactly two cases:
+
+| Case | Why |
+|---|---|
+| Autopilot (`state.autopilot === true` or `MULTI_AGENT_AUTOPILOT=1`) | Explicit consent for side-effect creation  -  posts directly with prefs/flag selections, zero interaction |
+| `--dry-run` | Already prints without posting; a question would be redundant |
+
+**Preview render** (one block per selected channel, final body after humanizer  -  shown in readable Markdown, channel-specific markup conversion happens after approval):
+
+```
+── PR description  ({repoName} #{prNumber}, replace) ─────────
+{body}
+── Jira comment  ({jiraId}) ──────────────────────────────────
+{body}
+── Confluence page  ("{title}" under {parentUrl}) ────────────
+{body}
+```
+
+Secondary artifacts ride along as one-line intents at the bottom of the preview: Wiki page list, wiki → Jira triad comment (when Wiki is selected and the triad is active per `refs/issue-jira-triad.md`), Board status move (`{from} → {to}`), GitHub issue comment + Progress-flag sync (Phase 7 Step 1.5  -  same gate, see `refs/phases/phase-7-report.md`).
+
+**Then a single AskUserQuestion** (`question`/`description` in `outputLanguage`; `label`/`header` English):
+
+| Option | Behavior |
+|---|---|
+| `Approve & post` | Step 7 dispatches every previewed body verbatim |
+| `Edit` | Free-text "which channel, what should change" → apply → re-render the FULL preview → re-ask (loop, no cap) |
+| `Skip channels` | multiSelect which channels to drop this run → re-render remaining → re-ask |
+| `Cancel` | Abort dispatch entirely  -  nothing posted anywhere. Internal capture (agent-log, knowledge) is unaffected |
+
+**Hard rule:** what is posted is byte-identical to the approved preview (markup conversion excepted). Any body regeneration after approval invalidates the approval and re-runs the gate. Persisting channel prefs (Step 8) still happens on `Cancel`  -  selection memory and content approval are independent.
+
+### Step 7  -  Channel dispatch
+
+For each selected **channel**, call the corresponding adapter. Adapters run **in parallel**  -  one failure does not block others. Dispatch NEVER starts before the Step 6 gate resolves (`Approve & post`), except in the two documented skip cases (autopilot, `--dry-run`).
 
 **Multi-repo dispatch:** When `state.projects[].length > 1`, the dispatcher delegates per-channel rendering to `~/.claude/lib/channels-multi-repo.sh`:
 
@@ -358,7 +393,7 @@ Full contract: [`refs/channels/confluence.md`](refs/channels/confluence.md)  -
 
 Full contract: [`refs/channels/wiki.md`](refs/channels/wiki.md)  -  all four `figma-config.wiki.mode` adapters (submodule / in-repo / github-wiki / separate-repo), full Case A scope menu, screenshot quadrant gate.
 
-### Step 7  -  Summary
+### Step 8  -  Summary
 
 After all adapters complete (or fail non-blocking):
 
@@ -397,6 +432,7 @@ Persist selections to `prefs.global.reportChannels` + `prefs.global.reportConten
 - **No markers**  -  channels does a full replace each run; no `<!-- channels:start -->` bookmarks.
 - **Every body item references a symbol/file/line** from diff or pipeline log. No generic "tested the feature" sentences.
 - **Adapter failures are non-blocking**  -  one channel failing does not abort others. Final summary shows per-adapter status.
+- **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
 
@@ -423,7 +459,7 @@ Phase 7 invokes this command internally instead of running its own inline Jira/C
 
 Phase 7 passes a runtime state bundle: `{jiraId, prUrl, remoteType, taskType, figmaConfig, agentState, pipelineLogPath}`. `channels` reads these directly, skips target-resolution Step 1.
 
-**Autopilot contract:** Phase 7 ALWAYS pauses at the channels menu (breaks generic autopilot zero-interaction). 30-min timeout → session ends cleanly, task resumable via `/multi-agent:resume`. See `refs/phases/modes.md` for full contract.
+**Autopilot contract:** Phase 7 ALWAYS pauses at the channels menu (breaks generic autopilot zero-interaction). 30-min timeout → session ends cleanly, task resumable via `/multi-agent:resume`. See `refs/phases/modes.md` for full contract. The Step 6 body preview + approval gate follows the same split: interactive runs approve the composed bodies before dispatch; autopilot posts directly after the menu resolves.
 
 ## Cross-CLI parity
 

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

@@ -65,25 +65,34 @@ Phases 1-3 (Analysis / Planning / Dev) are skipped by design  -  `finish` treats
 
 ## Required: Phase Tracker Contract
 
-**The phase tracker is mandatory.** Full spec: [`refs/tracker-contract.md`](./refs/tracker-contract.md). `finish` registers only its active phase set  -  `0:Init 4:Review 5:Build+Test 6:Commit 7:Report` (phases 1-3 are not part of the finish set; do not register tiles for them).
+**The phase tracker is required.** Full spec: [`refs/tracker-contract.md`](./refs/tracker-contract.md). `finish` registers its active phase set  -  `0:Init 4:Review 5:Build+Test 6:Commit 7:Report`  -  but NEVER resets a tracker that an earlier run already built (load-or-continue; contract section "Continuation runs"):
 
 ```bash
-# Phase 0, first shell call (every CLI):
-bash $HOME/.claude/scripts/phase-tracker.sh init "$TASK_ID"
+# Phase 0, first shell call (every CLI). init ONLY when no prior state exists -
+# a task handed off from Phase 5 ("awaiting local test") keeps its full
+# phase 0-3 history (elapsed, tokens, USD).
+STATE="$HOME/.claude/logs/multi-agent/${TASK_ID}/tracker-state.json"
+if [ ! -f "$STATE" ]; then
+  bash $HOME/.claude/scripts/phase-tracker.sh init "$TASK_ID"
+fi
 for p in "0:Init" "4:Review" "5:Build+Test" "6:Commit" "7:Report"; do
-  bash $HOME/.claude/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"
+  bash $HOME/.claude/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"   # idempotent: existing phases keep their history
 done
 bash $HOME/.claude/scripts/phase-tracker.sh update 0 in_progress
 
 # Every phase boundary (every CLI):
 bash $HOME/.claude/scripts/phase-tracker.sh update <N> in_progress|completed|failed|skipped
 # After every LLM call (every CLI):
-bash $HOME/.claude/scripts/phase-tracker.sh tokens <N> <in> <out>
+bash $HOME/.claude/scripts/phase-tracker.sh tokens <N> <in> <out> [cached]
 ```
 
+**Continuation path (prior state existed):** (1) if Phase 5 was left `in_progress` with `Now: awaiting local test (user)`, mark it `update 5 completed` + `meta 5 Result "local test done (user)"` before finish's own work (finish re-opens it with `update 5 in_progress` when its Build+Test gate runs; elapsed keeps the original `started_at`, which is expected); (2) print ONE line in `outputLanguage` summarizing the inherited history, e.g. `Continuing PROJ-12345: phases 0-3 finished earlier (12m, 38.4k tok, ~$0.74)` (USD via `phase-tracker.sh cost total`); (3) `render`.
+
 ### Visual channel  -  Claude Code (native TaskList widget, required)
 
-Register one tile per phase in **strict creation order** (`0 → 4 → 5 → 6 → 7`) BEFORE any TaskUpdate, capture each `taskId`, persist via `phase-tracker.sh meta <N> tasklist_id "<taskId>"`, then flip status with `TaskUpdate` at each boundary. Out-of-order TaskCreate scrambles the tile stack. Full contract: `refs/tracker-contract.md` "TaskCreate ordering (strict)".
+Fresh state: register one tile per phase in strict phase-number order (`0 → 4 → 5 → 6 → 7`) BEFORE any TaskUpdate, capture each `taskId`, persist via `phase-tracker.sh meta <N> tasklist_id "<taskId>"`, then flip status with `TaskUpdate` at each boundary. Out-of-order TaskCreate scrambles the tile stack. Full contract: `refs/tracker-contract.md` "TaskCreate ordering (strict)".
+
+Continuation: rebuild the FULL TaskList from the state file (completed 0-3 tiles included) in phase order before any `TaskUpdate`, refreshing every `tasklist_id` meta  -  same as the contract's "Resume behaviour".
 
 ### Visual channel  -  Copilot CLI / plain shell
 

package/pipeline/commands/multi-agent/generate-bug.md

@@ -0,0 +1,33 @@
+---
+description: "Create a standards-compliant Jira Bug: mines project conventions, drafts in outputLanguage, full preview + explicit approval before create."
+argument-hint: "[\"<free-text description>\"] [figma-url]  -  both optional; pasted logs/screens in the text land in Steps to Reproduce / Environment"
+---
+
+# multi-agent generate-bug  -  Standards-Compliant Jira Bug Creator
+
+**Input**: $ARGUMENTS
+
+Creates exactly one Jira **Bug**, and only after explicit approval. No branches, no commits, no worktrees, no pipeline chaining. The draft learns the target project's conventions from its recent Bugs (summary format, description template, labels, components, priority norms) and offers active-sprint placement when a sprint is running.
+
+> **Language**: instruction prose here is English. AskUserQuestion `question`/`description` and the issue content (summary + description) follow `prefs.global.outputLanguage`  -  an intentional exception to the "external payloads stay English" default, because the issue is authored for the user's team. `label`/`header` stay English.
+
+## Profile
+
+| Key | Value |
+|---|---|
+| `ISSUE_TYPE` | `Bug` |
+| Default description sections | Steps to Reproduce, Expected Result, Actual Result, Environment, Design Reference (only when a Figma URL is given), Notes |
+| JQL sample filter | `issuetype = Bug` |
+| Priority default | mined norm from sampled Bugs (bug priorities often skew higher  -  respect the project's own norm) |
+
+## Flow
+
+Read `$HOME/.claude/commands/multi-agent/refs/generate-issue.md` and execute the 11-step shared flow with the profile above. Non-negotiables restated:
+
+- Free-text parsing maps logs, stack traces, and device/OS mentions into Steps to Reproduce and Environment; anything underivable is asked in step [7/11], never invented.
+- Ask the user (AskUserQuestion) about every genuinely unknown field  -  component, epic, priority, labels, assignee, sprint vs backlog, required custom fields, missing Steps to Reproduce / Environment.
+- Step [8/11] full preview + approval gate always runs. `Approve` / `Edit` (loop) / `Cancel`. No bypass exists.
+
+## Error paths
+
+See `refs/generate-issue.md` Error paths. No command-specific additions.

package/pipeline/commands/multi-agent/generate-task.md

@@ -0,0 +1,33 @@
+---
+description: "Create a standards-compliant Jira Task: mines project conventions, drafts in outputLanguage, full preview + explicit approval before create."
+argument-hint: "[\"<free-text description>\"] [figma-url]  -  both optional, asked interactively when missing"
+---
+
+# multi-agent generate-task  -  Standards-Compliant Jira Task Creator
+
+**Input**: $ARGUMENTS
+
+Creates exactly one Jira **Task**, and only after explicit approval. No branches, no commits, no worktrees, no pipeline chaining. The draft learns the target project's conventions from its recent Tasks (summary format, description template, labels, components, priority norms) and offers active-sprint placement when a sprint is running.
+
+> **Language**: instruction prose here is English. AskUserQuestion `question`/`description` and the issue content (summary + description) follow `prefs.global.outputLanguage`  -  an intentional exception to the "external payloads stay English" default, because the issue is authored for the user's team. `label`/`header` stay English.
+
+## Profile
+
+| Key | Value |
+|---|---|
+| `ISSUE_TYPE` | `Task` |
+| Default description sections | Goal, Scope, Acceptance Criteria, Design Reference (only when a Figma URL is given), Notes |
+| JQL sample filter | `issuetype = Task` |
+| Priority default | mined norm from sampled Tasks |
+
+## Flow
+
+Read `$HOME/.claude/commands/multi-agent/refs/generate-issue.md` and execute the 11-step shared flow with the profile above. Non-negotiables restated:
+
+- Ask the user (AskUserQuestion) about every genuinely unknown field  -  component, epic, priority, labels, assignee, sprint vs backlog, required custom fields.
+- Step [8/11] full preview + approval gate always runs. `Approve` / `Edit` (loop) / `Cancel`. No bypass exists.
+- Never invent Goal, Scope, or Acceptance Criteria content the user did not supply.
+
+## Error paths
+
+See `refs/generate-issue.md` Error paths. No command-specific additions.

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

@@ -111,6 +111,8 @@ Post-Hoc & Side-Channel:
   /multi-agent:analysis ["analysis-name"]  Feature-spec analysis (Figma + Swagger + Confluence + repos) → per-platform v3 doc (23-section Full / 7-section Lite)
   /multi-agent:analysis-resolve [doc]      Resolve Section 20 open questions of an analysis doc, one at a time with source-labeled candidates
   /multi-agent:build-optimize iOS-only Xcode build perf wrapper → benchmark + analyze + recommend-first .build-benchmark/optimization-plan.md
+  /multi-agent:generate-task ["desc"] [figma-url]  Create a Jira Task matching team conventions (mining + active sprint + preview & approval)
+  /multi-agent:generate-bug ["desc"] [figma-url]   Create a Jira Bug matching team conventions (mining + active sprint + preview & approval)
   /multi-agent:diff-explain   Map a Phase 4 triage finding back to specific diff lines
   /multi-agent:search         Cross-task log search with smart ranking; --semantic queries triage corpus
   /multi-agent:scan           Skill security scan against tiered pattern catalog
@@ -220,6 +222,10 @@ Examples:
   # Review current diff only
   /multi-agent:review
 
+  # Create a Jira issue that matches team conventions (preview + approval before create)
+  /multi-agent:generate-task "Profile screen empty state" https://figma.com/design/abc?node-id=1-2
+  /multi-agent:generate-bug "Login crash on iOS 17, see attached log"
+
 ------------------------------------------------------------
 
 Logs: $HOME/.claude/logs/multi-agent/{project}/{task-id}/
@@ -318,6 +324,8 @@ Post-Hoc & Side-Channel:
   /multi-agent:analysis ["analysis-name"]  Feature-spec analizi (Figma + Swagger + Confluence + repolar) → platform başına v3 doküman (23 bölüm Full / 7 bölüm Lite)
   /multi-agent:analysis-resolve [doc]      Analiz dokümanının Bölüm 20 açık sorularını kaynak etiketli adaylarla teker teker çözer
   /multi-agent:build-optimize iOS-only Xcode build performance wrapper → benchmark + analiz + recommend-first .build-benchmark/optimization-plan.md
+  /multi-agent:generate-task ["açıklama"] [figma-url]  Takım standartlarına uygun Jira Task oluştur (convention mining + aktif sprint + önizleme & onay)
+  /multi-agent:generate-bug ["açıklama"] [figma-url]   Takım standartlarına uygun Jira Bug oluştur (convention mining + aktif sprint + önizleme & onay)
   /multi-agent:diff-explain   Phase 4 triage bulgusunu diff satırlarına eşle
   /multi-agent:search         Task log'larında akıllı arama; --semantic triage corpus'unu sorgular
   /multi-agent:scan           Skill güvenlik taraması (tiered pattern catalog)
@@ -427,6 +435,10 @@ Quality & Telemetry (advisory, default açık  -  prefs.global.* ile kapatılabi
   # Sadece mevcut diff'i review et
   /multi-agent:review
 
+  # Takım standartlarına uygun Jira issue oluştur (oluşturmadan önce önizleme + onay)
+  /multi-agent:generate-task "Profil ekranı empty state" https://figma.com/design/abc?node-id=1-2
+  /multi-agent:generate-bug "iOS 17'de login crash, log ekte"
+
 ------------------------------------------------------------
 
 Log'lar: $HOME/.claude/logs/multi-agent/{project}/{task-id}/

package/pipeline/commands/multi-agent/manual-test.md

@@ -22,6 +22,13 @@ Lets you switch to the task branch for manual testing in Xcode before the PR is
    git checkout {branch-name}
    ```
 
+   Then mark the tracker as waiting (this CONTINUES the task's existing `tracker-state.json`; never `init` here - see `refs/tracker-contract.md` "Continuation runs"). On Claude Code in a fresh session, first rebuild the TaskList from state per the same contract:
+   ```bash
+   bash $HOME/.claude/scripts/phase-tracker.sh update 5 in_progress
+   bash $HOME/.claude/scripts/phase-tracker.sh now 5 "awaiting local test (user)"
+   bash $HOME/.claude/scripts/phase-tracker.sh render
+   ```
+
 4. **Tell the user how to test**:
    ```
    🧪 Switched to branch: {branch-name}
@@ -39,5 +46,5 @@ Lets you switch to the task branch for manual testing in Xcode before the PR is
 5. **Wait for the user's reply**
 
 6. **Branch on the answer**:
-   - **OK** → recreate the worktree, continue to Phase 6
-   - **Fix needed** → recreate the worktree, apply the fix
+   - **OK** → `phase-tracker.sh update 5 completed` + `phase-tracker.sh meta 5 Result "local test passed (user)"`, recreate the worktree, continue to Phase 6
+   - **Fix needed** → `phase-tracker.sh now 5 "applying fix: <summary>"`, recreate the worktree, apply the fix

package/pipeline/commands/multi-agent/refs/channels/pr.md

@@ -120,7 +120,7 @@ Single-repo tasks return one entry from `channels-multi-repo.sh targets ...` wit
 The Bitbucket REST API returns `409 Conflict` if `version` is stale. Adapter behaviour:
 
 1. Refetch PR JSON, retry the PUT once with the new `version`.
-2. Second mismatch → fail this adapter, log reason, return `{status: "failed", reason: "version conflict"}`. Other adapters keep running  -  non-blocking by Step 6 contract.
+2. Second mismatch → fail this adapter, log reason, return `{status: "failed", reason: "version conflict"}`. Other adapters keep running  -  non-blocking by Step 7 contract.
 
 ## Flags that affect this adapter
 

package/pipeline/commands/multi-agent/refs/cross-cli-contract.md

@@ -6,19 +6,20 @@
 
 ---
 
-## 1. Command Inventory (35 commands)
+## 1. Command Inventory (37 commands)
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels, delete, dev,
 dev-autopilot, dev-local, dev-local-autopilot, diff-explain, finish, garbage-collect,
-help, issue, jira, kill, language, local, local-autopilot, log, manual-test,
-prune-logs, purge, refactor, resume, review, scan, search, setup, stack, status,
-sync, test, update
+generate-bug, generate-task, help, issue, jira, kill, language, local,
+local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review,
+scan, search, setup, stack, status, sync, test, update
 ```
 
 Categories:
 
 - **Interactive pickers** (single-purpose, not modes): `jira`, `issue`
+- **Issue generators** (one-shot, no worktree, hard approval gate before create): `generate-task`, `generate-bug`
 - **Full 8-phase modes**: `autopilot`, `local`, `local-autopilot`
 - **Fast modes** (Init -> Dev(Opus) -> Commit -> Report): `dev`, `dev-autopilot`, `dev-local`, `dev-local-autopilot`
 - **Tail modes** (run the pipeline tail over already-done local work): `finish`
@@ -29,7 +30,7 @@ Categories:
 
 ### 1.1 Figma component subphase skills
 
-In addition to the 35 top-level multi-agent commands, the figma-to-component pipeline ships platform-specific skills that multi-agent dispatches from Phase 3 (see `refs/component-dispatch.md`). The structure is **platform-parallel iOS + Android with a shared common pool**:
+In addition to the 37 top-level multi-agent commands, the figma-to-component pipeline ships platform-specific skills that multi-agent dispatches from Phase 3 (see `refs/component-dispatch.md`). The structure is **platform-parallel iOS + Android with a shared common pool**:
 
 | Location | Skill count | Purpose |
 |---|---|---|
@@ -311,7 +312,7 @@ For clipboard ops, callers still gate with `if command -v pbpaste >/dev/null; th
 
 This contract is validated by:
 
-- `smoke-cross-cli-behavior.sh`  -  asserts all 35 commands behave identically, pulls from Section 2 (placeholder vocab), Section 5 (argument parsing), Section 6 (output formats); also regression-locks the 6-persona agent deployment
+- `smoke-cross-cli-behavior.sh`  -  asserts all 37 commands behave identically, pulls from Section 2 (placeholder vocab), Section 5 (argument parsing), Section 6 (output formats); also regression-locks the 6-persona agent deployment
 - `smoke-commands-skills-parity.sh` (50 assertions)  -  enforces colon-form command ↔ dash-form skill directory parity
 - `smoke-compliance-skills.sh` (45 assertions)  -  enforces store-compliance skill catalog + 4 consumer wiring
 - `smoke-personal-data.sh`  -  extended in 0.5.5 to treat deprecated placeholders (`{github-username}`, `{your-website}`, `{website-repo}`) as leaks; adds `mmerterden` to public-handle blocklist for generic docs