@mmerterden/multi-agent-pipeline 16.8.0 → 16.9.0

package/CHANGELOG.md

@@ -26,6 +26,25 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 - **`smoke-website-deploy-identity.sh` (20 assertions).** It runs the script against throwaway repos with real remotes rather than grepping the doc: the happy path lands and pushes, an exported `GIT_AUTHOR_EMAIL` halts with the commit still local, an unchanged tree makes no empty commit, a matching config is preserved while a wrong name is corrected, and missing or non-repository arguments exit 2. Wiring is asserted separately, since a correct script nothing calls is its own failure mode.
 
+## [16.9.0] - 2026-08-25
+
+### Added
+
+- **`/multi-agent:analysis` emits a run record.** It is a pipeline of its own now - its own phases, its own gates, its own report - but telemetry was only wired into the dev pipeline's Phase 7, so analysis runs were invisible. The panel showed dev work only, and the command people reach for *before* writing any code did not exist in the usage data. Phase 5 now writes its own `agent-state.json` through `write-state.mjs` (atomic, lock-guarded, so concurrent runs cannot wipe each other) and calls the reporter. `mode` carries the profile, which is what tells one analysis run from another: a `global` run and a `corporate` run are different work. `project` is `null` on a stack-optional run - there is no repository to name - and is digested before it leaves the machine either way. The reporter stays best-effort: a failure there never touches the run, whose summary is already printed.
+
+### Fixed
+
+- The Phase 7 telemetry block still called reporting "optional, opt-in" after 16.8.0 made it on by default. It now states the default, both ways to silence it, and what is actually sent - command, duration, tokens, outcome - along with what is not: no repository name, path, prompt or diff. Same class of staleness as 16.7.1 and 16.8.1: the behaviour moved and the sentence describing it did not.
+
+## [16.8.1] - 2026-08-25
+
+### Fixed
+
+- **`/multi-agent:help` still described the analysis command as it behaved before 16.6.0.** The entry read "per-platform v3 doc (23-section Full / 7-section Lite)" and said nothing about the standard being asked at intake, the corporate profile, stack being optional, or References being built from the evidence record - the word "profile" appeared nowhere in the file. Two releases had added the behaviour and neither had updated the sentence a user reads to learn what the command does.
+- **The Copilot and Codex help never listed the analysis family at all.** `multi-agent-analysis` and `multi-agent-analysis-resolve` were absent in both the colon and the dash form, so a user on those hosts could not discover them from help. This predates the recent work; it surfaced while auditing the entry above.
+
+Both fixes fit under the file's grandfathered token ceiling rather than raising it: the new text was trimmed where it carried the least, which is the same rule the 16.7.1 entry followed.
+
 ## [16.8.0] - 2026-08-25
 
 Usage reporting answers the question it was built for, and stops carrying what it never should have.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "16.8.0",
+  "version": "16.9.0",
   "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/commands/multi-agent/help/SKILL.md

@@ -120,7 +120,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:review         Parallel review of a PR or branch diff; no URL -> pick open GitHub/Bitbucket PRs
   /multi-agent:review-jira    Grade a Jira issue's pipeline-readiness -> comment the gaps on it
   /multi-agent:review-issue   Grade a GitHub issue's pipeline-readiness -> comment the gaps on it
-  /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 ["analysis-name"]  Feature-spec analysis (Figma + Swagger + Confluence + repos). Asks the standard first: global (23-section dev handoff) or corporate (IG→UC→FG requirements doc). Stack optional; References built from the evidence record
   /multi-agent:analysis-resolve [doc]      Resolve Section 20 open questions of an analysis doc, one at a time with source-labeled candidates
   /multi-agent:review-analysis [doc]  Review a written analysis; findings cite the rule they break
   /multi-agent:complaint-analysis ["run-name"] [--file path]  Customer-complaint triage: Graylog evidence per trx/conv id + read-only repo correlation → client/bff root cause + fix plan + dev prompt, or core routing recommendation
@@ -394,7 +394,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:review         PR veya branch diff'ini paralel review et; URL yoksa -> açık GitHub/Bitbucket PR'larını seçtir
   /multi-agent:review-jira    Jira maddesinin pipeline'a hazırlığını değerlendir -> eksikleri yorum olarak ekle
   /multi-agent:review-issue   GitHub issue'nun pipeline'a hazırlığını değerlendir -> eksikleri yorum olarak ekle
-  /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 ["analysis-name"]  Feature-spec analizi (Figma + Swagger + Confluence + repolar). Önce standardı sorar: global (23 bölümlük geliştirme dokümanı) veya kurumsal (IG→UC→FG gereksinim dokümanı). Stack opsiyonel; Referanslar kanıt kaydından üretilir
   /multi-agent:analysis-resolve [doc]      Analiz dokümanının Bölüm 20 açık sorularını kaynak etiketli adaylarla teker teker çözer
   /multi-agent:review-analysis [doc]  Yazılmış analizi review eder; bulgular ihlal edilen kuralı gösterir
   /multi-agent:complaint-analysis ["run-adı"] [--file yol]  Müşteri şikayeti triyajı: trx/conv id ile Graylog kanıtı + salt-okunur repo eşleştirme → client/bff kök neden + fix planı + dev prompt'u, veya core'a yönlendirme önerisi

package/pipeline/multi-agent-refs/analysis/render.md

@@ -106,6 +106,18 @@ Iterate `state.analysisSpec.outputs.requested`. For each target:
 
 After dispatch, print a summary to the user (in `outputLanguage`). Example shape:
 
+**Operational reporting.** Analysis is a pipeline of its own now - its own phases, its own gates, its own report - so it emits a run record like any other run. Without this the panel shows dev runs only, and the command people reach for before writing code is invisible in the usage data.
+
+```bash
+STATE="$HOME/.claude/logs/multi-agent/$TASK_ID/agent-state.json"
+mkdir -p "$(dirname "$STATE")"
+printf '%s' "{\"taskId\":\"$TASK_ID\",\"command\":\"/multi-agent:analysis\",\"mode\":\"$PROFILE\",\"project\":${PROJECT_JSON:-null},\"status\":\"$STATUS\",\"finishedAt\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" \
+  | node "$HOME/.claude/scripts/write-state.mjs" "$STATE" >/dev/null 2>&1 || true
+node "$HOME/.claude/scripts/usage-report.mjs" --state "$STATE" >/dev/null 2>&1 || true
+```
+
+`mode` carries the profile (`global` / `corporate`), which is what distinguishes one analysis run from another. `project` is digested by the reporter before it leaves the machine, and is `null` on a stack-optional run - there is no repository to name. A failure here never affects the run: the reporter is best-effort and the summary above is already printed.
+
 ```
 Feature: <featureName>
 Language: <tr|en>

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

@@ -196,7 +196,7 @@ $HOME/.claude/scripts/log-metric.sh "$TASK_ID" 7 task.completed \
   duration_ms=$TOTAL_DURATION
 ```
 
-**Operational reporting (optional, opt-in).** When `prefs.global.usageLog.enabled` is true, emit one end-of-run run record to the configured endpoint. One POST per run, fire-and-forget, coarse run metadata only  -  no prompts, code, diffs, or absolute paths. The script no-ops when `usageLog.enabled` is not true or no token resolves, so the call is unconditional and never blocks the run.
+**Operational reporting.** On by default since v16.8.0; `enabled: false` or `optOut: true` silences it. Sends command, duration, tokens, outcome - never a repo name or path. One POST per run, fire-and-forget, coarse run metadata only  -  no prompts, code, diffs, or absolute paths. The script no-ops when `usageLog.enabled` is not true or no token resolves, so the call is unconditional and never blocks the run.
 
 ```bash
 node $HOME/.claude/scripts/usage-report.mjs --state "$STATE_FILE" >/dev/null 2>&1 || true

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

@@ -106,6 +106,8 @@ Utility Commands (dash form on Copilot, colon form on Claude Code):
   /multi-agent:review         Review a PR or branch diff; no URL -> pick open GitHub/Bitbucket PRs
   /multi-agent:review-jira    Grade a Jira issue's pipeline-readiness -> comment the gaps
   /multi-agent:review-issue   Grade a GitHub issue's pipeline-readiness -> comment the gaps
+  /multi-agent:analysis ["name"]  Feature-spec analysis. Asks the standard first: global (23-section dev handoff) or corporate (IG→UC→FG requirements doc). Stack optional
+  /multi-agent:analysis-resolve [doc]  Resolve an analysis doc's open questions one at a time, with source-labeled candidates
   /multi-agent:review-analysis [doc | page | KEY]  Review a written analysis: gates first, then parallel model review; findings cite the rule
   /multi-agent:feedback "msg" Tell the maintainer something broke; only your text is sent, shown before it goes
   /multi-agent:create-jira ["desc"] [figma-url] [swagger-url]  Create a Jira Task/Bug/Story matching team conventions (asks type + preview + approval)