peaks-loop 4.0.33 → 4.0.34

package/skills/peaks-code/references/runbook.md

@@ -10,7 +10,9 @@
 
 ## Default runbook — CLI sequence
 
-The end-to-end CLI sequence for the `full-auto` profile. `assisted` and `strict` profiles pause at `[CONFIRM]` markers below. `full-auto` and `swarm` auto-proceed through all gates. See Transition Gates for artifact verification at each stage.
+The end-to-end CLI sequence for the `full-auto` profile. `assisted` and `strict` profiles pause at `[CONFIRM]` markers below. `full-auto` and `24h` auto-proceed through all gates. See Transition Gates for artifact verification at each stage.
+
+> **How to resolve a `[CONFIRM]` marker (never a terminal prompt):** the CLI does not read stdin. Without `--confirm` / `--force-confirm` the transition fails with `CONFIRMATION_REQUIRED` and `nextActions`. Code must ask the user via `AskUserQuestion` whether to proceed; if the user approves, re-run the *same* command with `--confirm`. Never wait for a `y/N` prompt — no TTY exists in an LLM-driven session.
 
 Canonical single-shot sub-agent dispatch (the `--prompt` flag is required):
 
@@ -34,11 +36,11 @@ peaks scan existing-system --project <repo> --json
 # → copy tokens, sources, conventions, inconsistencies into .peaks/_runtime/<session-id>/system/existing-system.md (Peaks-Loop Gate A.5)
 
 # 1. Peaks-Loop Standards preflight + apply
-#    Run dry-run first to inspect deltas, then APPLY. In full-auto and swarm modes,
+#    Run dry-run first to inspect deltas, then APPLY. In full-auto and 24h modes,
 #    --apply is the default — Standards files (CLAUDE.md, .claude/rules/**) live INSIDE
 #    the target project and are required for downstream skill preflight, so producing
 #    them is part of completing the workflow. Assisted/Strict modes pause for [CONFIRM]
-#    between dry-run and apply.
+#    between dry-run and apply (AskUserQuestion → re-run with --confirm; no terminal prompt).
 peaks standards init   --project <repo> --dry-run --json
 # or: peaks standards update --project <repo> --dry-run --json
 peaks standards init   --project <repo> --apply --json
@@ -57,7 +59,8 @@ peaks standards init   --project <repo> --apply --json
 # 若 LLM 看到 peaks-code runbook 里出现老命令(>9 之外的 raw 名字),
 # 先 `peaks --help` 校验当前 surface,再决定改 runbook 还是改命令。
 
-# 2. Peaks-Loop PRD (Assisted/Strict: [CONFIRM] before confirmed-by-user)
+# 2. Peaks-Loop PRD (Assisted/Strict: [CONFIRM] before confirmed-by-user
+#    → AskUserQuestion; on approval re-run the transition with --confirm)
 # Classify the request type from the PRD: feature | bugfix | refactor | docs | config | chore
 # This drives RD/QA gate strictness — see "Mandatory RD QA repair loop" for the matrix.
 peaks request init --role prd --id <rid> --project <repo> --apply --type <type> --json
@@ -139,6 +142,7 @@ ls .peaks/_runtime/<sid>/qa/test-cases/<rid>.md                # QA test-cases (
 ls .peaks/_runtime/<sid>/ui/design-draft.md 2>&1               # non-blocking (Gate B info)
 # Apply the degradation rules in the main SKILL.md if any artefact is missing.
 # → Peaks-Loop Gate B convergence check. Assisted/Strict: [CONFIRM]
+#   → AskUserQuestion; on approval re-run the transition with --confirm
 
 # 4. Peaks-Loop RD planning artifact (the file required by the prerequisite gate)
 #    feature / refactor → write .peaks/_runtime/<id>/rd/tech-doc.md
@@ -163,6 +167,7 @@ peaks request transition <rid> --role qa --state running --project <repo> --json
 #                                 + .peaks/_runtime/<id>/qa/performance-findings.md (feature/refactor only)
 peaks request transition <rid> --role qa --state verdict-issued --project <repo> --json
 # → Peaks-Loop Gate D check. Assisted/Strict: [CONFIRM]
+#   → AskUserQuestion; on approval re-run the transition with --confirm
 
 # 7. Peaks-Loop RD↔QA repair loop — if verdict is return-to-rd, re-run 4 through 6 until QA passes or blocked TXT.
 #    Before invoking peaks-rd again, check the cycle count so you don't blow past the cap silently:
@@ -289,7 +294,7 @@ peaks code emit-handoff --project <repo> --job-id <jid> --json
 # job-shape.json says isJob=true, ≥0.85 is MANDATORY auto-compact.
 # Code MUST call this without confirmation under Job mode.
 peaks code context-now --project <repo> --enforce-job-mode --json
-peaks compact auto --execute --project <repo> --json
+peaks code auto-compact --project <repo> --json
 
 # v3.1.2 PreToolUse gate (installed by `peaks workspace init`):
 # every Bash tool call runs `peaks code gate-step-08` automatically.

package/skills/peaks-code/references/session-overload-signal-index.md

@@ -15,8 +15,8 @@ the lookup table the LLM must consult in lieu of intuition.
 
 | # | Signal source | Threshold | File / CLI | LLM action |
 |---|---|---|---|---|
-| 1 | prompt size (main session) | 50% / 75% / 80% / 90% | `src/services/context/threshold.ts`; probe via `peaks code context-now` | soft-warn at 50%; consider compact at 75%; MUST NOT auto-compact mid-batch (D6.e); Job mode ≥ 0.85 ⇒ MANDATORY `peaks compact auto --execute` |
-| 2 | auto-compact zone | 0.85 pre-compact / 0.95 red-line | `src/services/code/auto-compact-orchestrator.ts`; `--enforce-job-mode` flag | Auto-fires `peaks compact auto --execute`; LLM MUST NOT prompt user to compact (zero-pause contract v2.13.0) |
+| 1 | prompt size (main session) | 50% / 75% / 80% / 90% | `src/services/context/threshold.ts`; probe via `peaks code context-now` | soft-warn at 50%; consider compact at 75%; MUST NOT auto-compact mid-batch (D6.e); Job mode ≥ 0.85 ⇒ MANDATORY `peaks code auto-compact` |
+| 2 | auto-compact zone | 0.85 pre-compact / 0.95 red-line | `src/services/code/auto-compact-orchestrator.ts`; `--enforce-job-mode` flag | Auto-fires `peaks code auto-compact`; LLM MUST NOT prompt user to compact (zero-pause contract v2.13.0) |
 | 3 | sub-agent dispatch prompt size | 50% / 75% / 80% | `src/services/context/context-guard.ts`; `peaks sub-agent-dispatch-guard` PreToolUse hook | soft-warn at 50%; CONTEXT_NEAR_LIMIT at 75%; hard-reject at 80% (CLI + hook double-guard) |
 | 4 | statusline compact bar | visual | `src/services/compact-statusline/compact-statusline-service.ts` | ambient UI; surfaces queued/preparing/compacting/verifying/completed/failed/stalled |
 | 5 | in-flight batch deferral | D6.e | `src/services/code/auto-compact-modes.ts` | defer compact until batch lands (NOT "new session") |

package/skills/peaks-code/references/standards-preflight.md

@@ -5,7 +5,7 @@
 - `peaks standards init --project <path> --dry-run`
 - `peaks standards update --project <path> --dry-run`
 
-Use `standards init` for first-time creation and `standards update` for existing `CLAUDE.md` append/review behavior. In `full-auto` and `swarm` profiles, `--apply` runs automatically after `--dry-run` succeeds — these files live inside the target project, are required for downstream skill preflight, and producing them is part of finishing the workflow (Peaks-Loop Gate G enforces this). `assisted` and `strict` profiles pause for explicit user confirmation between dry-run and apply.
+Use `standards init` for first-time creation and `standards update` for existing `CLAUDE.md` append/review behavior. In `full-auto` and `24h` profiles, `--apply` runs automatically after `--dry-run` succeeds — these files live inside the target project, are required for downstream skill preflight, and producing them is part of finishing the workflow (Peaks-Loop Gate G enforces this). `assisted` and `strict` profiles pause for explicit user confirmation between dry-run and apply.
 
 **CRITICAL — Standards must reflect the project scan.** When generating or updating `CLAUDE.md`, the content must reference concrete findings from `.peaks/project-scan/project-scan.md`: the detected component library (e.g. "This project uses antd 5.x"), CSS solution (e.g. "Uses Less via Umi"), build tool, state management, and routing. Never emit a generic template that says "read .claude/rules/..." without naming the actual project stack. If the project-scan has not been run yet, run it before standards init/update.
 

package/skills/peaks-code/references/startup-sequence.md

@@ -31,7 +31,7 @@ After autonomous work (RD, QA, security, perf), invoke peaks-final-review for 4-
 
 ### Peaks-Loop Step N+2: Main-session context monitor (D6 + slice 2026-07-02)
 
-After every 4th tool call, probe via `peaks code context-now --project <repo> --json`. Thresholds: 50% / **0.85 pre-compact / 0.95 red-line** (v2.13.0). **In Job mode ≥ 0.85 is MANDATORY auto-compact** (`peaks compact auto --execute`). Pass `--enforce-job-mode` for single-rid. **≥ 0.95** red line: next Bash/Task fires `peaks compact auto`. **Karpathy §4 exception**: compact red line keeps runner alive — zero-intervention wins; LLM MUST NOT ask user to run `/compact`. Honor `--in-flight-batch` (D6.e).
+After every 4th tool call, probe via `peaks code context-now --project <repo> --json`. Thresholds: 50% / **0.85 pre-compact / 0.95 red-line** (v2.13.0). **In Job mode ≥ 0.85 is MANDATORY auto-compact** (`peaks code auto-compact`). Pass `--enforce-job-mode` for single-rid. **≥ 0.95** red line: next Bash/Task fires `peaks code auto-compact`. **Karpathy §4 exception**: compact red line keeps runner alive — zero-intervention wins; LLM MUST NOT ask user to run `/compact`. Honor `--in-flight-batch` (D6.e).
 
 ### Peaks-Loop Step 0: Anchor the workflow (MANDATORY FIRST ACTIONS — no bail-out)
 

package/skills/peaks-code/references/step-0-8-gate.md

@@ -45,7 +45,7 @@ Refuses to emit a final handoff while `remaining > 0` under Job mode. Pass `--fo
 
 ### 3. Forced auto-compact — `--enforce-job-mode`
 
-`peaks code context-now --enforce-job-mode` (auto-enabled when `job-shape.json` says `isJob=true`) returns `action: 'auto-compact-now'` at ≥ 0.85; Code MUST call `peaks compact auto --execute` without confirmation.
+`peaks code context-now --enforce-job-mode` (auto-enabled when `job-shape.json` says `isJob=true`) returns `action: 'auto-compact-now'` at ≥ 0.85; Code MUST call `peaks code auto-compact` without confirmation.
 
 ### 4. On-disk slice progress — `progress.json`
 

package/skills/peaks-code/references/swarm-dispatch-contract.md

@@ -48,7 +48,7 @@ Return a compact JSON envelope — do not write prose.
 - session-id: <sid>          (from .peaks/.active-skill.json or .peaks/.session.json)
 - request-id: <rid>          (PRD id)
 - type: <type>               (feature | bugfix | refactor | config | docs | chore)
-- mode: <mode>               (full-auto | swarm | assisted | strict)
+- mode: <mode>               (full-auto | assisted | strict | 24h)
 - project-scan-path: <path>  (read this for component library / CSS / build tool)
 - existing-system-path: <path>  (legacy projects only)
 - frontendOnly: <bool>       (from project-scan)
@@ -209,7 +209,7 @@ Sub-agent presence in this list = Code launched a Task for it. Absence = the rol
 | Mode | How the swarm plan is decided | What Code does |
 |---|---|---|
 | `full-auto` | Compute plan from signals above, no question to user | Auto-launch all sub-agents in the plan in parallel |
-| `swarm` | Same as `full-auto` | Same as `full-auto` (this profile name is historical — behavior is identical) |
+| `24h` | Same as `full-auto` | Same as `full-auto` (long-run profile; the fan-out shape is identical, only the auto-compact cadence differs) |
 | `assisted` | `AskUserQuestion` with three options: (a) Full — UI + RD(planning) + QA(test-cases); (b) Backend-only — RD(planning) + QA(test-cases); (c) Sequential — run RD first, then QA, skip UI | Use the user's choice as the plan |
 | `strict` | Same as `assisted` (the question is informational; strict still enforces confirmation gates later) | Same as `assisted` |
 

package/skills/peaks-code/references/workflow-gates-and-types.md

@@ -182,5 +182,5 @@ ls <repo>/.claude/rules/common/coding-style.md \
 # standards init/update with --apply and re-verify.
 # Skipping Peaks-Loop Gate G (e.g. because the user did not explicitly authorize writes) is
 # only acceptable in `assisted`/`strict` modes where the user actively declined; in
-# `full-auto`/`swarm` the absence of these files is a workflow violation.
+# `full-auto`/`24h` the absence of these files is a workflow violation.
 ```