Apply Sweep Triage

---
name: apply-sweep-triage
description: |-
  Persist the user's triage decisions (apply, decline, discuss) from a SWEEP snapshot into REVIEW_PREFERENCES.md so future sweeps suppress declined findings and track applied fixes. Use after the user has edited the triage values in a SWEEP snapshot file produced by repo-consistency-sweep. Do not use when no sweep snapshot exists or when the user has not yet set triage values.
metadata:
  category: "audit-and-sweep"
  primary-cursor-mode: "Agent"
  multi-repo-aware: "false"
  context-layers-consumed: "memory"
  context-layers-produced: "memory"
  tools: "Read, Write, Edit, Bash, Glob, Grep"
  x-wos-profiles: "core, full"
  provenance: "first-party"
  suggested-model: "claude-sonnet-5-5"
---

Act as a workflow state updater that persists review-sweep triage decisions into project-level preferences.

Goal:
Read a SWEEP snapshot where the user has set `triage:` values (apply, decline, discuss) on each finding, and persist those decisions into `REVIEW_PREFERENCES.md` at the project level so future `repo-consistency-sweep` runs respect them.

Mandatory context bootstrap (before any output):
- Read these sections in `WORKFLOW_OPERATING_SYSTEM.md` first:
  - `## LLM execution contract`
  - `## Editor mode policy` (mode definitions only; the tool mapping table is lazy-loaded in `wos/editor-mode-mappings.md` and needed only for non-Claude-Code tools)
  - `## Global output contract` (including **Adaptive handoff** and **Mode selection rule**)
  - `## Cross-cutting workflow guardrails`
- **Bootstrap tiers:** the light-weight commands (`branch-commit`, `what-next`, `where-we-at`, `slice-closure`, `compact-task-memory`) plus the high-frequency `implement-approved-slice` and `sync-task-state` (v3 wave1 item D) read the four sections above with two subsections of `## Cross-cutting workflow guardrails` skipped: `### External web access (centralized)` and `### Sequencing heuristics (by phase)`. Everything else is read at every tier, including `### Proposal vs approved persistence` and `### Substrate peer ownership (per ADR-0034)`, since all seven write substrate sections and reason about PROPOSED (`state-reconcile` stays on the full tier for cross-artifact judgment). The full tier is measured at 12109 tokens, the four always-read sections combined; the two skipped subsections are 1,034 of those (measured 2026-09-28), so the reduced tier is about 11,074. The leaf-reviewer tier (`verify-against-rubric`, ADR-0226) reads only `## Global output contract`, measured at 5215 tokens, plus its rubric.
- **Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D):** WHEN this conversation already read the bootstrap sections in an earlier turn still VISIBLE in the context window AND `WORKFLOW_OPERATING_SYSTEM.md` has not changed since, the command MAY skip the re-read and cite the earlier one, emitting one Command transcript line: `Bootstrap: reusing turn <N> read, WOS unchanged`. Scoped exception to the context-budget re-fetch rule (`wos/context-budget.md`, "The re-fetch rule"), because these sections are one large, static, byte-identical read repeated every turn; every other tool result still re-fetches. VISIBLE means the section text itself is still present and quotable now, not merely that a record of the earlier read exists: a harness that clears a tool result while the record survives (ADR-0114) has not satisfied VISIBLE, and self-declared memory after a compaction never qualifies. A stateless-per-turn harness is excluded. The transcript line is mandatory; a silent skip is invalid output.
- **Resolving the spec and `wos/<topic>.md`:** canonical repository FIRST. Otherwise use active-adapter docs: `~/.claude/workflow-docs` (`CLAUDE_WORKFLOW_DOCS_DIR`), `~/.cursor/workflow-docs` (`WORKFLOW_DOCS_DIR`; project `.cursor/workflow-docs` on project installs), `~/.codex/workflow-docs` (`CODEX_WORKFLOW_DOCS_DIR`), or `<kimi-home>/workflow-docs` (`KIMI_WORKFLOW_DOCS_DIR`). Nonempty overrides win. Kimi home: `KIMI_CODE_HOME`, else existing `~/.kimi-code`, else existing `~/.kimi`, default `~/.kimi-code`. Use one root for both paths; try other adapters if absent or unknown. Report resolved root, fallback to other adapters, or missing mandatory context in `### Command transcript`. Installed snapshots refresh and prune retired topics only on sync.
- Read additional sections only when relevant to this command's role.
- Align all routing recommendations and next-command suggestions with the current command set.
- **Official next-command names only:** recommendations, including `Run now`, use registered names from `commands/<name>.md` or `commands/<name>/SKILL.md`; installed mode uses the available Fhorja command or skill inventory. No invented aliases. `Run now: none` with `Mode: N/A` ends only if no honest next step exists, defined under `### Official command names (routing integrity)` (ADR-0126).
Required inputs:
- active task folder path
- SWEEP snapshot path (or pointer from TASK_STATE.md under `## Latest sweep`)
- optional: REVIEW_PREFERENCES.md path (if not present, created from template)

Task repository files to update:
- REVIEW_PREFERENCES.md (create from `templates/REVIEW_PREFERENCES.template.md` if absent; append rows)
- TASK_STATE.md (update last completed step)

Operating rules:
- **Handoff:** end with the adaptive `### Handoff` block per `WORKFLOW_OPERATING_SYSTEM.md` `## Global output contract` (Mode A compact or Mode B full).
- **Step 1: Locate snapshot.** Read the SWEEP snapshot path from inputs or from TASK_STATE.md `## Latest sweep` pointer.
- **Step 2: Parse findings.** Extract each finding block from the snapshot. For each, read: bug_class, file_path, triage value (apply, decline, discuss, or unset).
- **Step 3: Skip unset.** Findings with `triage: unset` are skipped (user has not decided yet). If ALL findings are unset, return no-op.
- **Step 4: Compute file hashes.** For each triaged finding, run `git hash-object <file_path>` to capture the current file hash. This hash anchors the suppression: when the file changes, the declined entry ages out.
- **Step 5: Persist decisions.** Open or create REVIEW_PREFERENCES.md:
  - For `decline`: append a row to the `## Declined findings` table with date, bug_class, file_path, file_hash, and the user's reason (from the `reason:` line in the snapshot, or "no reason given" if absent).
  - For `apply`: append a row to the `## Applied findings` table with date, bug_class, file_path, and action_taken (from the `action:` line in the snapshot, or "acknowledged" if absent).
  - For `discuss`: append a row to the `## Discussed findings` table with date, bug_class, file_path, and the user's note (from the `note:` line in the snapshot, or empty).
- **Step 6: Deduplicate.** Before appending, check whether the target table already contains the same bug_class + file_path. If yes, update its date and the fields Step 5 defines for that table instead of appending a duplicate.
- **Step 7: Update TASK_STATE.** Set last completed step to this command with a summary of how many decisions were persisted (N declined, M applied, K discussed).
- Do not modify the SWEEP snapshot file itself (it is a read-only historical record).
- Do not implement code fixes. Persistence only.

Required output:
1. Summary: how many findings triaged (N declined, M applied, K discussed, J skipped as unset)
2. Rows added or updated in REVIEW_PREFERENCES.md
3. TASK_STATE.md update
4. Recommended next command

### Claim grounding (active epistemic humility)
**Claim grounding (active epistemic humility).** This block governs what you may assert and how you record it. It is keyed to the substrate section you are writing, not to which command is running, and it is INERT on any output that writes none of the claim-bearing sections below. Full contract and rationale: `wos/active-epistemic-humility.md`.

1. When this applies. This block fires ONLY while you are writing a claim-bearing substrate section: `TASK_STATE.md ## Current known facts`, `## Risks to watch`, `## Observations`, `## Active files in scope`, `## Canonical decisions`; `DECISIONS.md ## Locked decisions`; `IMPLEMENTATION_PLAN.md ## Current gaps`, `## Risks and mitigations`; `IMPACT_ANALYSIS.md`; `EXTERNAL_RESEARCH.md`; `REFERENCES.md`; or any section whose content is a statement a later command or a human decision will act on. WHEN your output writes none of these, this block imposes nothing: skip it and proceed. This is the D-13 inert clause; a fully-grounded or claim-free output pays nothing.

2. The unit is the load-bearing claim. A load-bearing claim is one a downstream command or a human decision consumes. A passing aside is not load-bearing; a statement someone will act on is. Apply the rest of this block per load-bearing claim, not per sentence.

3. Ground it or abstain. Before you assert a load-bearing claim, trace it to the enumerable grounded set: a captured `REFERENCES.md` entry, a file read in this session, command output actually seen, or a passing deterministic gate. A claim supported only by model memory is OUTSIDE the grounded set, including when you are right, because that support is not observable. WHEN a load-bearing claim falls outside the set, do NOT assert it: either investigate until it is grounded, or abstain per rule 6.

4. Status records provenance, never confidence. WHERE you attach an epistemic status to a claim, the status names WHERE THE CLAIM CAME FROM: a `REFERENCES.md` entry title, a file path plus line, or the gate output it came from. It SHALL NOT express a degree of certainty. Do NOT add a confidence field, a numeric threshold, or a self-assessment prompt anywhere; a self-reported confidence signal is not a usable control signal (`wos/active-epistemic-humility.md` Part 1.3). A status whose referent slot is empty is read as UNKNOWN, not as a weak yes.

5. Persisted claims carry the status; chat-only claims carry it when they route. Every load-bearing claim you write into a task-memory artifact carries its provenance referent, and that referent travels with the claim so a later command reads it too; do not drop it at the write boundary. A load-bearing claim that appears only in a chat-turn output carries a status only when it crosses the grounding boundary and triggers a route (an abstention, an escalation).

6. Abstain as a routed continuation, never a bare refusal. WHEN you abstain, name the specific investigation that would settle the question AND route to the command that runs it (`capture-references`, `code-locate`, `incident-triage`, or the fitting one). A withholding that stalls the work is invalid output. Abstention is distinct from `NO_OP`: `NO_OP` means there is no work to do; abstention means there is work and the grounding to do it is missing.

7. An unfired gate is not evidence. The absence of a fired check does not mean grounding existed. Do not read silence here as a pass.
### Standard output layout (required)
Produce the command output using this structure (English only):

### Artifact changes
Follow `## Global output contract` in `WORKFLOW_OPERATING_SYSTEM.md` for `APPLIED` / `PROPOSED` / `SKIP` rules. Every listed file carries one of those three tokens, in Lean output too; a prose verb like "written" is not a label.

### Command transcript
Brief audit trail (max 4 lines; max 3 in no-op runs with `NO_OP_TRACE`).

### Handoff
Use the adaptive ending format of `WORKFLOW_OPERATING_SYSTEM.md` `## Global output contract`. Every Handoff is one fenced `text` block with all four lines, `Run now:`, `Mode:`, `Work complexity:` and `Reason:`, on a stop and on a refusal too; the terminal form is `Run now: none` with `Mode: N/A`. A new `Mode:`, a model or a fresh session is never a stop, an offered choice is one, and `Reason:` names a role, never a model.
### Definition of done (command output)
- All triaged findings (non-unset) are persisted into REVIEW_PREFERENCES.md.
- Declined rows include file_hash for suppression aging.
- No duplicate rows (deduplication by bug_class + file_path).
- TASK_STATE.md updated with triage summary.
- SWEEP snapshot is read-only (not modified).
- Before declaring this output done, confirm it satisfies the shared **Definition of done (command outputs)** and **Gate conditions** in WORKFLOW_OPERATING_SYSTEM.md.

Quality bar:
Accurate persistence. Every triaged finding maps to exactly one row in REVIEW_PREFERENCES.md. No data loss, no silent overwrites.