@mmerterden/multi-agent-pipeline 16.2.0 → 16.2.1

package/CHANGELOG.md

@@ -16,6 +16,12 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ## [Unreleased]
 
+## [16.2.1] - 2026-08-24
+
+### Fixed
+
+- **Both READMEs credited Phase 1 to Opus.** The explorer persona has run on `sonnet` since it was retuned, with a rationale in its own frontmatter saying sonnet matches opus on file inventory and dependency graphs at a fraction of the cost. The phase doc carried the same leftover in an `explorer/Opus` reference. A model name in a README is the kind of claim nobody re-derives, so it stays wrong until someone reads the persona file.
+
 ## [16.2.0] - 2026-08-23
 
 The analysis subsystem said things its gate did not enforce. `locked.md` carries 31 decisions; four of them ended with the sentence "fails the dispatch gate", and the dispatch gate implemented none of the four. This release makes three of them true and pulls the fourth back to what actually happens.

package/README.md

@@ -53,7 +53,7 @@ Update later with `/multi-agent:update`. Uninstall (tokens preserved) with `npx
 One command runs 8 phases, with a gate between the risky ones:
 
 - **0 · Init** - parse the input (Jira id / GitHub URL / free text), pick account + repo(s), fetch the issue, run a maturity check.
-- **1 · Analysis** - detect the stack, scan the codebase, map impact (Opus).
+- **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.

package/README.tr.md

@@ -53,7 +53,7 @@ Sonra `/multi-agent:update` ile güncelle. Kaldırmak için (tokenlar korunur) `
 Tek komut 8 fazı çalıştırır, riskli olanlar arasında bir kapı ile:
 
 - **0 · Init** - girdiyi ayrıştır (Jira id / GitHub URL / serbest metin), hesap + repo(lar) seç, issue'yu çek, maturity kontrolü yap.
-- **1 · Analysis** - stack'i tespit et, codebase'i tara, etkiyi haritala (Opus).
+- **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.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "16.2.0",
+  "version": "16.2.1",
   "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/multi-agent-refs/phases/phase-1-analysis.md

@@ -208,7 +208,7 @@ Log: "Phase 1: Analysis  -  stack:{detectedStack} | {N} files identified, {summa
 
 #### Telemetry  -  token forwarding
 
-Forward the explorer/Opus call's token totals into the tracker so Phase 7's Cost Breakdown captures Phase 1:
+Forward the explorer call's token totals into the tracker so Phase 7's Cost Breakdown captures Phase 1:
 
 ```bash
 LOG_METRIC_FORWARD_TO_TRACKER=1 $HOME/.claude/scripts/log-metric.sh "$TASK_ID" 1 analysis.completed \