@mmerterden/multi-agent-pipeline 16.7.1 → 16.8.1

package/CHANGELOG.md

@@ -26,6 +26,28 @@ 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.
 
+## [16.8.1] - 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.
+
+### Changed
+
+- **`usageLog.enabled` now defaults to `true`.** Reporting was opt-in and nothing opted in, so the panel showed three runs across eight days and could not distinguish "nobody uses this" from "the pipe is broken" - the sender swallows every error by design. On-by-default is defensible only because of the change below: the payload carries no repository name, no path, no prompt, no diff and no secret. `usageLog.optOut: true` remains the hard escape hatch, and `enabled: false` still silences the emitter completely.
+- **The event carries the command that ran.** `commandOf()` returned `state.mode`, so every row read `full` or `local` and the one question the panel exists to answer - which commands people actually run - had no answer in the data. It now sends the invoked command; `mode` continues to ship separately.
+
+### Fixed
+
+- **The repository name is no longer sent.** `rp` carried the raw project name, which put a corporate repository into the maintainer's database - the exact disclosure this telemetry must not make. It now sends a one-way digest: stable, so runs still group per project, and unreadable back into a name. The panel never needed the name, only the ability to tell one project's runs from another's. The row already stored was redacted in place.
+
 ## [16.7.1] - 2026-08-25
 
 ### Fixed

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "16.7.1",
+  "version": "16.8.1",
   "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/schemas/prefs.schema.json

@@ -1061,8 +1061,8 @@
           "properties": {
             "enabled": {
               "type": "boolean",
-              "default": false,
-              "description": "Master switch. When false the emitter exits silently and nothing leaves the machine."
+              "default": true,
+              "description": "Master switch, on by default. The payload carries no repository name, path, prompt, diff or secret - only which command ran, how long, how many tokens, and whether it failed - which is what makes on-by-default defensible. Set false, or optOut true, and the emitter exits silently with nothing leaving the machine."
             },
             "optOut": {
               "type": "boolean",

package/pipeline/scripts/usage-report.mjs

@@ -26,6 +26,7 @@ import { homedir, platform } from "os";
 import { dirname, join } from "path";
 import { fileURLToPath, pathToFileURL } from "url";
 import { execFileSync } from "child_process";
+import { createHash } from "crypto";
 import { costUsd } from "./_cost.mjs";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
@@ -272,13 +273,28 @@ function inputType(state) {
   return "free-text";
 }
 
+// The command that was actually invoked (`/multi-agent:analysis`, `:review`,
+// ...). This used to return `state.mode`, so every row read "full" or "local"
+// and the one question the panel exists to answer - which command did people
+// run - had no answer in the data. `mode` still ships separately as `m`.
 function commandOf(state) {
+  const c = state.command;
+  if (typeof c === "string" && c.trim()) return c.trim().slice(0, 60);
   if (state.mode) return state.mode;
   if (state.onlyDevelop) return "dev";
   if (state.localMode) return "local";
   return "full";
 }
 
+// A repository name is the user's, not ours. It put a corporate project into
+// the maintainer's database, which is the disclosure this telemetry must not
+// make - and the panel never needed the name, only the ability to tell one
+// project's runs from another's. A digest does that and cannot be read back.
+function projectDigest(name) {
+  if (typeof name !== "string" || !name.trim()) return null;
+  return `p${createHash("sha256").update(name.trim()).digest("hex").slice(0, 8)}`;
+}
+
 function resolveTracker(state) {
   const id = state.taskId || state.shortId;
   if (id == null) return null;
@@ -490,7 +506,7 @@ function buildEvent(state) {
     lo: Boolean(state.localMode),
     dev: Boolean(state.onlyDevelop),
     in: inputType(state),
-    rp: state.project || null,
+    rp: projectDigest(state.project),
     ph: typeof state.currentPhase === "number" ? state.currentPhase : null,
     st: state.status || null,
     hr: state.haltReason || null,

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)