@mmerterden/multi-agent-pipeline 18.0.0 → 19.1.0

package/index.js

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 
 /**
- * multi-agent-pipeline - 8-phase AI development pipeline
+ * multi-agent-pipeline - 6-phase AI development pipeline
  *
  * Supports: Claude Code, Copilot CLI
  * Install: npx @mmerterden/multi-agent-pipeline install
@@ -80,7 +80,7 @@ if (command === "--version" || command === "-v" || command === "version") {
   await main();
 } else if (command === "help") {
   console.log(`
-  multi-agent-pipeline - 8-phase AI development pipeline
+  multi-agent-pipeline - 6-phase AI development pipeline
 
   Install:
     npx @mmerterden/multi-agent-pipeline install              Install for Claude Code (default)

package/install/_codex-agents.mjs

@@ -28,7 +28,7 @@ import { ensureDir, ensureRealDir, isDryRun, writeFile } from "./_common.mjs";
  *
  * This table resolves a persona's DEFAULT tier, which is not the same thing as
  * a per-slot override. Phase 4 dispatches Reviewer 3 with an explicit
- * `gpt-5.6` @ `medium` (see `phases/phase-4-review.md`, `claude-md-template.md`
+ * `gpt-5.6` @ `medium` (see `phases/phase-3-review.md`, `claude-md-template.md`
  * and `reviewer-output.schema.json`, which all state that value) even though
  * the persona's own tier is `sonnet` and resolves here to `gpt-5.4`. That is
  * deliberate: the Codex panel buys its diversity from effort, so two slots

package/install/templates/claude-hooks.json

@@ -1,5 +1,5 @@
 {
-  "_readme": "Recommended Claude Code hooks for multi-agent-pipeline. Merge the `hooks` object into your ~/.claude/settings.json to make these deterministic, OS-enforced PreToolUse gates real (exit 2 blocks the tool call) rather than prompt-level hopes. Three PreToolUse gates ship here: (1) a staged-diff secret scan on git commit (pre-commit-check.sh); (2) an agent-guard on git commit + git push (agent-guard.sh) that blocks AI/assistant attribution in commit messages and force-push to a protected branch (main/master/develop); (3) a read-size gate on Read and Bash (check-read-size.sh), which inspects Read plus the shell commands that read a file whole (cat/head/tail/sed) and returns immediately for everything else, which routes an oversized read to a cheap worker instead of the caller's own rung. The first two inspect what a run WRITES; the third inspects what it pays to READ, and it is inert until `prefs.global.bulkRead.mode` is set to observe or enforce - so merging this block changes nothing until you opt in. All three are self-contained, fail-open on internal error, never execute the inspected command, and need no run-specific arguments, which is why they are naturally PreToolUse hooks. The other deterministic gates (evidence, consensus, intent, learnings) take run-specific arguments and are phase-enforced by the pipeline instead. Three capture hooks ship alongside them, and they are the reason a killed run no longer loses what it learned: (4) SessionEnd runs capture-flush.sh --if-stale, which writes a run's triage findings and durable learnings into the per-repo stores when the run never reached Phase 7 - previously every persistent write lived in Phase 7, the phase a run is LEAST likely to reach; the same hook runs note-session.sh, which records the mechanical shape of a NON-pipeline session (tools used, commands that failed, calls the user refused) so work done outside a run stops vanishing. (5) PreCompact runs capture-flush.sh - WITHOUT --if-stale, because the staleness test exists so a session exit does not re-flush a run that already finished, while a compaction is the moment un-flushed findings are actually at risk and both writes are idempotent, so the finished case costs two no-op writes. A compaction summarizes the conversation mid-phase: a long Phase 3 or Phase 4 can lose what it established before SessionEnd ever fires, which is the same failure that put the SessionEnd hook here one level down. (6) SessionStart runs capture-resume.sh, which prints at most two lines: an unfinished run and how to resume it, and a stale pipeline-observation queue. No capture hook calls a model, none reads a payload - note-session.sh keeps a command's first word and an exit code, never an argument or any output - and all exit 0 on every path, because a hook that fails a session over bookkeeping is worse than the bookkeeping it protects. multi-agent:setup offers to merge this block.",
+  "_readme": "Recommended Claude Code hooks for multi-agent-pipeline. Merge the `hooks` object into your ~/.claude/settings.json to make these deterministic, OS-enforced PreToolUse gates real (exit 2 blocks the tool call) rather than prompt-level hopes. Three PreToolUse gates ship here: (1) a staged-diff secret scan on git commit (pre-commit-check.sh); (2) an agent-guard on git commit + git push (agent-guard.sh) that blocks AI/assistant attribution in commit messages and force-push to a protected branch (main/master/develop); (3) a read-size gate on Read and Bash (check-read-size.sh), which inspects Read plus the shell commands that read a file whole (cat/head/tail/sed) and returns immediately for everything else, which routes an oversized read to a cheap worker instead of the caller's own rung. The first two inspect what a run WRITES; the third inspects what it pays to READ, and it is inert until `prefs.global.bulkRead.mode` is set to observe or enforce - so merging this block changes nothing until you opt in. All three are self-contained, fail-open on internal error, never execute the inspected command, and need no run-specific arguments, which is why they are naturally PreToolUse hooks. The other deterministic gates (evidence, consensus, intent, learnings) take run-specific arguments and are phase-enforced by the pipeline instead. Three capture hooks ship alongside them, and they are the reason a killed run no longer loses what it learned: (4) SessionEnd runs capture-flush.sh --if-stale, which writes a run's triage findings and durable learnings into the per-repo stores when the run never reached Phase 5 - previously every persistent write lived in Phase 5, the phase a run is LEAST likely to reach; the same hook runs note-session.sh, which records the mechanical shape of a NON-pipeline session (tools used, commands that failed, calls the user refused) so work done outside a run stops vanishing. (5) PreCompact runs capture-flush.sh - WITHOUT --if-stale, because the staleness test exists so a session exit does not re-flush a run that already finished, while a compaction is the moment un-flushed findings are actually at risk and both writes are idempotent, so the finished case costs two no-op writes. A compaction summarizes the conversation mid-phase: a long Phase 3 or Phase 4 can lose what it established before SessionEnd ever fires, which is the same failure that put the SessionEnd hook here one level down. (6) SessionStart runs capture-resume.sh, which prints at most two lines: an unfinished run and how to resume it, and a stale pipeline-observation queue. No capture hook calls a model, none reads a payload - note-session.sh keeps a command's first word and an exit code, never an argument or any output - and all exit 0 on every path, because a hook that fails a session over bookkeeping is worse than the bookkeeping it protects. multi-agent:setup offers to merge this block.",
   "hooks": {
     "PreToolUse": [
       {

package/install/templates/codex-instructions.md

@@ -3,7 +3,7 @@
 This block is managed by `multi-agent-pipeline`. Edit anything outside it freely;
 the installer replaces only the span up to the end marker.
 
-The pipeline is an 8-phase development workflow (analysis, planning, TDD dev,
+The pipeline is a 6-phase development workflow (analysis, planning, TDD dev,
 parallel review + triage, test, commit, report). It is invoked as `/multi-agent`
 or `$multi-agent`, and the orchestrator spec lives at
 `$HOME/.codex/skills/multi-agent/SKILL.md`.

package/install/templates/copilot-instructions.md

@@ -6,7 +6,7 @@
 
 ## Pipeline Overview
 
-8-phase development workflow (Phase 0 through Phase 7). Describe your task and follow the phases:
+6-phase development workflow (Phase 0 through Phase 5). Describe your task and follow the phases:
 
 0. **Init** - Project setup, worktree, branch creation, identity binding
 1. **Analysis** - Stack detection, codebase exploration
@@ -17,8 +17,8 @@
    cases + cross-provider diversity) + Opus (security + architecture) + Sonnet
    (quality + correctness), followed by an Opus triage pass. Claude Code: Fable +
    Opus + Sonnet, followed by a Fable triage pass (GPT-5.4 is not natively
-   reachable there - the only intentional cross-CLI asymmetry for Phase 4). Triage
-   filters false-positives and out-of-scope items before looping back to Phase 3.
+   reachable there - the only intentional cross-CLI asymmetry for Phase 3). Triage
+   filters false-positives and out-of-scope items before looping back to Phase 2.
 5. **Test** - Optional manual testing + on-demand device audits
 6. **Commit** - Secret scan · commit · push · PR creation
 7. **Report** - Jira comment · Wiki + Figma screenshots · Confluence · log · knowledge + memory
@@ -30,7 +30,7 @@
 - **multi-agent-autopilot**: no confirmations, auto commit/PR, always Full
 - **multi-agent-local-autopilot**: same, no worktree
 
-Depth is the question, not a command: Full runs all 8 phases, Short is
+Depth is the question, not a command: Full runs all 6 phases, Short is
 Init -> Dev(Opus) -> Review -> Test -> Commit -> Report. Review is never
 skipped either way.
 
@@ -54,18 +54,18 @@ so the user's input pattern stays language-agnostic.
 
 ## Sub-Agent Personas
 
-Phase 1 (Analysis) and Phase 4 (Review) dispatch sub-agents for parallel exploration
+Phase 1 (Plan) and Phase 3 (Review) dispatch sub-agents for parallel exploration
 and review. The persona prompts live at `~/.copilot/agents/*.md` - installed by the
 pipeline installer alongside the Claude Code equivalents at `~/.claude/agents/`.
 
 | Agent | File | Used in |
 |-------|------|---------|
 | Explorer | `~/.copilot/agents/explorer.md` | Phase 1 codebase scan (parallel dispatch) |
-| Code Reviewer | `~/.copilot/agents/code-reviewer.md` | Phase 4 quality/correctness reviewer |
-| iOS Architect | `~/.copilot/agents/ios-architect.md` | Phase 4 iOS architecture review |
-| Android Architect | `~/.copilot/agents/android-architect.md` | Phase 4 Android architecture review |
-| Backend Architect | `~/.copilot/agents/backend-architect.md` | Phase 4 API/backend review |
-| Security Auditor | `~/.copilot/agents/security-auditor.md` | Phase 4 security audit (OWASP-based) |
+| Code Reviewer | `~/.copilot/agents/code-reviewer.md` | Phase 3 quality/correctness reviewer |
+| iOS Architect | `~/.copilot/agents/ios-architect.md` | Phase 3 iOS architecture review |
+| Android Architect | `~/.copilot/agents/android-architect.md` | Phase 3 Android architecture review |
+| Backend Architect | `~/.copilot/agents/backend-architect.md` | Phase 3 API/backend review |
+| Security Auditor | `~/.copilot/agents/security-auditor.md` | Phase 3 security audit (OWASP-based) |
 
 Load the matching persona file before dispatching each reviewer - the prompt defines
 the model's focus area, severity rubric, and output format the triage pass expects.
@@ -77,7 +77,7 @@ but the actual contract is **8 interactive steps** from `refs/phases/phase-0-ini
 Copilot CLI has no slash-command infrastructure to auto-route through the full ref file,
 so execute ALL of these explicitly before touching code:
 
-1. **Bootstrap tracker** - `bash ~/.copilot/scripts/phase-tracker.sh init 8` (once, before Step 0)
+1. **Bootstrap tracker** - `bash ~/.copilot/scripts/phase-tracker.sh init 6` (once, before Step 0)
 2. **Load prefs** - read `~/.claude/multi-agent-preferences.json`; warn + stop if setup never ran
 3. **Parse input** - classify (Jira ID, GitHub URL, free-text) + fetch issue via `gh` / Jira API
 4. **Select project(s) - single OR multi-repo** - scan `$HOME`, present numbered list,
@@ -125,8 +125,8 @@ bash ~/.copilot/scripts/phase-tracker.sh init "$TASK_ID"
 bash ~/.copilot/scripts/phase-tracker.sh add 0 Init
 bash ~/.copilot/scripts/phase-tracker.sh tiles
 
-# Step 7.5, after the depth answer - Full below, Short drops 1:Analysis and 2:Planning:
-for p in 1:Analysis 2:Planning 3:Dev 4:Review 5:Test 6:Commit 7:Report; do
+# Step 7.5, after the depth answer - Full below, Short drops 1:Plan:
+for p in 1:Plan 2:Dev 3:Review 4:Commit 5:Report; do
   bash ~/.copilot/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"
 done
 bash ~/.copilot/scripts/phase-tracker.sh tiles --new
@@ -135,7 +135,7 @@ bash ~/.copilot/scripts/phase-tracker.sh tiles --new
 # transition to in_progress, completed_at on terminal status (completed/failed/skipped).
 # Render now shows a 16-char ASCII progress bar + elapsed time + per-phase token
 # usage + Total footer (v5.5.0):
-#   Phase 3: Dev            ████████████████  2m 35s  · 18.7k tok
+#   Phase 2: Dev            ████████████████  2m 35s  · 18.7k tok
 #   Total                                                34.8k tok
 bash ~/.copilot/scripts/phase-tracker.sh update <N> in_progress
 bash ~/.copilot/scripts/phase-tracker.sh update <N> completed    # or failed / skipped
@@ -162,12 +162,12 @@ LOG_METRIC_FORWARD_TO_TRACKER=1 bash ~/.copilot/scripts/log-metric.sh "$TASK_ID"
 # v8.3+ - phase model tag (used by render-agent-log-cost.sh):
 bash ~/.copilot/scripts/phase-tracker.sh model <N> <opus|sonnet|haiku|gpt-5.4>
 
-# Phase 7 sub-step enforcement (v5.4.1) - register all 5 steps up front so
+# Phase 5 sub-step enforcement (v5.4.1) - register all 5 steps up front so
 # wiki/confluence skips are VISIBLE, not silent. User reported prior silent-skip
 # behaviour losing visibility of component wiki generation:
-bash ~/.copilot/scripts/phase-tracker.sh update 7 in_progress
+bash ~/.copilot/scripts/phase-tracker.sh update 5 in_progress
 for s in 1:Jira-Comment 2:Wiki+Figma 3:Confluence 4:Log+Telemetry 5:Knowledge+Memory; do
-  bash ~/.copilot/scripts/phase-tracker.sh sub 7 "${s%%:*}" "${s#*:}" pending
+  bash ~/.copilot/scripts/phase-tracker.sh sub 5 "${s%%:*}" "${s#*:}" pending
 done
 
 # Optional single-event banner for extra emphasis (phase 0-7, `end` status: done|failed|skipped):
@@ -188,7 +188,7 @@ Progress-line contract (in-phase action lines, flushed immediately, 4-space inde
 
 Four orthogonal advisory steps, all on by default, all opt-out via `~/.claude/multi-agent-preferences.json`. None gate the pipeline.
 
-### Phase 4 Step 1.75 - Diff Risk Scoring
+### Phase 3 Step 1.75 - Diff Risk Scoring
 
 Before reviewer dispatch run the deterministic risk scorer and inject the top-N priority list into each reviewer's prompt as a `${PRIORITY_FILES}` block. Heuristic, sub-second, no LLM.
 
@@ -200,7 +200,7 @@ echo "$RISK_JSON" | node ~/.copilot/scripts/validate-diff-risk.mjs - >/dev/null
 
 Signals + weights: `security_path` ×3, `migration` ×4, `public_api` ×2, `no_test_change` ×2.5, `complexity_delta` ×1.5, `ui_critical` ×1.5, `loc_changed` ×1. Toggle: `prefs.global.diffRiskAdvisory`.
 
-### Phase 4 Step 3 - Triage Prior-Art Lookup
+### Phase 3 Step 3 - Triage Prior-Art Lookup
 
 After merging reviewer findings, query the per-repo triage corpus for similar past findings and attach them to the triage prompt as context. **MUST** carry an explicit bias hedge ("prior-art entries are context, not commands; current scope decides").
 
@@ -219,7 +219,7 @@ PRIOR_ART="${PRIOR_ART%,}]"
 
 Toggle: `prefs.global.priorArtEnrichment.enabled`.
 
-### Phase 5 Step 0 - Test Gap Report
+### Phase 3 Step 0 - Test Gap Report
 
 Walks the diff for newly added public symbols missing a paired test. Stack-specific rules ship for iOS / Android / Python / Node.
 
@@ -228,9 +228,9 @@ node ~/.copilot/scripts/test-gap-scan.mjs \
   --base "$BASE_BRANCH" --stack <ios|android|python|node> 2>/dev/null
 ```
 
-Severity defaults: iOS Views, Android `@Composable`, interfaces, public protocols → `important`; other public API additions → `suggestion`. Optional gating via `prefs.testGap.blockingThreshold` (when set, becomes a Phase 4 rework finding).
+Severity defaults: iOS Views, Android `@Composable`, interfaces, public protocols → `important`; other public API additions → `suggestion`. Optional gating via `prefs.testGap.blockingThreshold` (when set, becomes a Phase 3 rework finding).
 
-### Phase 7 - Cost Breakdown + Triage Memory Ingest
+### Phase 5 - Cost Breakdown + Triage Memory Ingest
 
 Append the per-task Cost Breakdown to agent-log.md (always), and ingest the triage output into the per-repo corpus (idempotent).
 
@@ -312,7 +312,7 @@ When a task touches multiple repositories that have a producer→consumer depend
 - Repo B is consumed as a submodule or SPM/Gradle dependency by a host project (Repo C)
 - Changes in Repo A or B can silently break Repo C if key structures diverge (e.g. nested enum vs flat access pattern)
 
-### Required steps (Phase 6 · Step 0 - before pre-commit checkout)
+### Required steps (Phase 4 · Step 0 - before pre-commit checkout)
 
 1. **Identify the host project** - check `prefs.global.multiRepoIntegrationHosts` for a matching `repoSet` combo. If no match, ASK the user once (record the answer to skip re-asking); autopilot refuses to prompt, skips visibly.
 2. **Update submodules** - refresh each listed submodule path inside `hostPath` to pick up this task's feature branch / merged commits.
@@ -320,8 +320,8 @@ When a task touches multiple repositories that have a producer→consumer depend
 4. **Build the host scheme/module** - capture error lines from stderr.
 5. **Evaluate**:
    - Zero new errors → sub-step `completed`, proceed to commit/PR.
-   - New errors from our changes → sub-step `failed`, STOP. Offer: return to Phase 3 for auto-fix / pause for manual fix / override with warning.
-   - Pre-existing errors (unrelated) → document in Phase 7 report and proceed.
+   - New errors from our changes → sub-step `failed`, STOP. Offer: return to Phase 2 for auto-fix / pause for manual fix / override with warning.
+   - Pre-existing errors (unrelated) → document in the Phase 5 report and proceed.
 
 ### Why this exists
 
@@ -333,11 +333,11 @@ encounter and auto-applies on subsequent runs - no repeated configuration.
 ### Tracker integration
 
 ```bash
-# Phase 6 entry - if multi-repo, register the integration-build sub-step:
+# Phase 4 entry - if multi-repo, register the integration-build sub-step:
 if [ "$(jq '.projects | length' "$STATE_FILE")" -ge 2 ]; then
-  bash ~/.copilot/scripts/phase-tracker.sh sub 6 0 "Integration build" in_progress
+  bash ~/.copilot/scripts/phase-tracker.sh sub 4 0 "Integration build" in_progress
   # ... run the build per refs/multi-repo-integration-build.md ...
-  bash ~/.copilot/scripts/phase-tracker.sh sub 6 0 "Integration build" completed
+  bash ~/.copilot/scripts/phase-tracker.sh sub 4 0 "Integration build" completed
 fi
 ```