agent-afk 5.247.1 → 5.248.0

package/dist/agent/placeholder-prevent.d.ts

@@ -0,0 +1,2 @@
+import type { HookHandler } from './hooks.js';
+export declare function createPlaceholderPreventHook(): HookHandler;

package/dist/bundled-plugins/awa-bundled/skills/diagnose/SKILL.md

@@ -7,6 +7,11 @@ category: Debug & fix
 
 Gather context: read the failing test or bug description, relevant error output, and recent git changes. If no failing test exists yet, write a minimal reproducer test (or identify a concrete verification command) before proceeding — hypotheses need a pass/fail signal to validate against. Dispatch two sub-agents in parallel — one to search the codebase for code paths involved in the failure (`subagent_type: research-agent`, read-only), and one to check recent commits and diffs that could have introduced the regression (`subagent_type: general-purpose` — requires Bash for `git log`/`git diff`/`git show`). When both return, synthesize findings into 2–4 ranked hypotheses, each with a specific code location and proposed cause.
 
+**TUI label convention.** Set `id_prefix` on each Agent dispatch to a short, descriptive label so the live progress view shows the agent's role:
+- Codebase search agent: `id_prefix: "codebase search"`
+- Git history agent: `id_prefix: "git history"`
+- Each hypothesis-testing agent: `id_prefix: "hypothesis: <one-phrase cause>"` (e.g. `"hypothesis: null deref in parser"`)
+
 For each hypothesis, dispatch a sub-agent with `isolation: "worktree"` to apply a minimal speculative fix, run the test or verification command, and then run the broader related test suite to check for regressions. Run all hypothesis-testing agents in parallel. Collect results: which fixes passed, which didn't, and any regressions surfaced by the broader suite.
 
 Report the validated root cause (the hypothesis whose fix passed), the speculative fix diff, and regression status from the broader test run. If no hypothesis passes, synthesize what was learned and form a second round of hypotheses. If the user approves the fix, apply it to the main worktree.

package/dist/bundled-plugins/awa-bundled/skills/research/SKILL.md

@@ -9,6 +9,10 @@ context: load
 
 Dispatch two sub-agents in parallel using the Agent tool. Prefer `subagent_type: "research-agent"`; fall back to `subagent_type: "Explore"` with thoroughness "very thorough" if the research-agent is not available. One researches the web for external context relevant to the current task. The other inspects the local working directory for domain-relevant artifacts. Return a concise merged research brief highlighting relevant findings, conflicts, risks, and implications for the task.
 
+**TUI label convention.** Set `id_prefix` on each Agent dispatch to a short, descriptive task label so the live progress view shows the agent's job rather than a generic identifier:
+- Web agent: `id_prefix: "web research"`
+- Local inspection agent: `id_prefix: "local inspection"`
+
 **Web research agent** — always the same: search for external context, prior art, patterns, APIs, and comparable approaches relevant to the task. Domain-agnostic.
 
 **Local inspection agent** — adapt to the domain:

package/dist/bundled-plugins/awa-bundled/skills/review/SKILL.md

@@ -74,8 +74,8 @@ When `reviewed_ref` is `unknown` (patch-file input), skip pre-fetch entirely and
 **The post-synthesis tail is the conditional half of that budget.** A review that surfaces a `critical`/`high` finding (or one whose `blocking` value departs from the default table — see **Post-synthesis** below) invokes `/shadow-verify`, which dispatches one verifier per claim in parallel, so the whole-run budget is **peak 2–3 concurrent, 4–6 total (1–3 verifiers)**, and it lands on exactly the high-stakes reviews most likely to hit a rate ceiling. Bound it: **at most 3 claims in a single round, no repeat rounds**, and hand the verifiers Wave 1.5's manifest so each re-derives the *claim* instead of re-locating evidence Wave 1.5 already pinned at the ref. Wave 1.5 verifies that a citation is real; shadow-verify re-derives whether the inference drawn from it holds — never substitute one for the other.
 
 **Wave 1 — Full review (regime=full, 2 parallel agents, `subagent_type: "research-agent"`).** Dispatch:
-- **security · api-compat** — contracts, auth, injection, breaking changes, secret exposure.
-- **correctness · spec-compliance · test-coverage · perf-observability** — logic bugs, regressions, whether the change satisfies its **stated intent** (unmet requirement or unrequested scope creep), missing tests, hot-path perf, logging gaps.
+- **security · api-compat** — contracts, auth, injection, breaking changes, secret exposure. Set `id_prefix: "security & api-compat"` on this Agent dispatch.
+- **correctness · spec-compliance · test-coverage · perf-observability** — logic bugs, regressions, whether the change satisfies its **stated intent** (unmet requirement or unrequested scope creep), missing tests, hot-path perf, logging gaps. Set `id_prefix: "correctness & coverage"` on this Agent dispatch.
 
 Each agent receives: full diff + file tree + triage header + **reviewed ref (SHA)** + the **stated intent** (what the change is meant to accomplish, or `(none supplied)`), the **`prior-reviewer-feedback`** block (when available), the severity rubric, **the `blocking` default table plus its overrides and assignment-order invariant**, and the finding schema. The blocking rules are not optional context: the finding schema mandates a `blocking` value per finding, so an agent that receives the schema without the table is being told to emit a field whose assignment rules it was never given.
 
@@ -106,7 +106,7 @@ If the `Grep` tool is unavailable, tag the finding `[UNVERIFIED: reachability no
 
 This is the agent's first-line self-check; **Wave 1.5 Check B** independently re-verifies any surviving absence claims against the reviewed ref as a backstop.
 
-**Wave 1 — Light review (regime=light, 1 agent, `subagent_type: "research-agent"`).** Single agent covers all dimensions (including spec-compliance). Same `stated-intent` input, `prior-reviewer-feedback` block, rubric, schema, and citation requirement. Through synthesis, the light regime peaks at **1 concurrent sub-agent session** and dispatches **2 in total** (Wave 1 ×1, then Wave 2 ×1, sequential). Its conditional post-synthesis `/shadow-verify` tail dispatches 1–3 verifiers in parallel when qualifying findings surface, making the whole-run budget **peak 1–3 concurrent, 3–5 total (1–3 verifiers)**; the same bound of at most 3 claims in one round with no repeat rounds applies.
+**Wave 1 — Light review (regime=light, 1 agent, `subagent_type: "research-agent"`).** Set `id_prefix: "full review"` on this Agent dispatch. Single agent covers all dimensions (including spec-compliance). Same `stated-intent` input, `prior-reviewer-feedback` block, rubric, schema, and citation requirement. Through synthesis, the light regime peaks at **1 concurrent sub-agent session** and dispatches **2 in total** (Wave 1 ×1, then Wave 2 ×1, sequential). Its conditional post-synthesis `/shadow-verify` tail dispatches 1–3 verifiers in parallel when qualifying findings surface, making the whole-run budget **peak 1–3 concurrent, 3–5 total (1–3 verifiers)**; the same bound of at most 3 claims in one round with no repeat rounds applies.
 
 **Wave 1.5 — Citation + absence-claim verification (INLINE — run by the orchestrator, dispatches nothing).** Run after Wave 1 returns, before Wave 2 synthesis. The orchestrator already holds exactly the read-only shell this verification needs (`git show` / `git diff` / `gh pr diff` / `grep` / `rg` — see the shell grant above), so running it inline costs **zero** additional sessions and zero nesting. A shell-less sub-agent here would have to nest a `git-investigator` to run the very commands the orchestrator can already run. Two independent checks:
 
@@ -122,7 +122,7 @@ This is the agent's first-line self-check; **Wave 1.5 Check B** independently re
 
 Returns a combined verification manifest: `[{type: citation|absence, claim, status, finding_id, evidence?}]`. Findings classified `fabricated` (citation) or `false-absent` (absence) are excluded from Wave 2 input. `diff-only` citations are passed to Wave 2 with a `⚠ diff-only citation — line absent at the reviewed ref` annotation and auto-downgraded one severity tier. `grep-unavailable` absence claims are passed through with their `[UNVERIFIED]` tag intact.
 
-**Wave 2 — Synthesis (1 agent, `subagent_type: "research-agent"`).** Receives: Wave 1 findings **after** citation-verification filtering + manifest of dropped/downgraded citations + **the `prior-reviewer-feedback` block** (when available) + **the merge-decision rule and its counts format below**. Wave 2 emits the verdict, so it needs that rule for exactly the reason Wave 1 needs the blocking table: an agent told to produce an output whose format and threshold it was never given will improvise both. Dedup by `(file, line_range, dimension)` — keep highest severity on exact match. Flag cross-agent conflicts as `CONFLICT` blocks (surface both rationales; do not auto-resolve).
+**Wave 2 — Synthesis (1 agent, `subagent_type: "research-agent"`).** Set `id_prefix: "synthesis"` on this Agent dispatch. Receives: Wave 1 findings **after** citation-verification filtering + manifest of dropped/downgraded citations + **the `prior-reviewer-feedback` block** (when available) + **the merge-decision rule and its counts format below**. Wave 2 emits the verdict, so it needs that rule for exactly the reason Wave 1 needs the blocking table: an agent told to produce an output whose format and threshold it was never given will improvise both. Dedup by `(file, line_range, dimension)` — keep highest severity on exact match. Flag cross-agent conflicts as `CONFLICT` blocks (surface both rationales; do not auto-resolve).
 
 **Prior-feedback dedup (cross-run).** After intra-run dedup, compare each surviving finding against the `prior-reviewer-feedback` block. Decision rubric:
 - The **diff contains evidence** that the concern was addressed (removed line, added guard, new test) → downgrade finding to `low` severity with `blocking: false` and annotation `[addressed since prior review]`. This is an explicit override of the assignment-order invariant: the pre-downgrade `blocking` value does **not** carry through, because the concern is resolved and surfacing it as blocking defeats the purpose of recognizing the fix. Do not suppress entirely — the reviewer sees the resolution.

package/dist/bundled-plugins/awa-bundled/skills/shadow-verify/SKILL.md

@@ -30,6 +30,7 @@ Select 2–3 of the highest-stakes normalized claims to send to the verifier wav
 2. Dispatch one shadow sub-agent per claim, in parallel. Each receives the normalized claim text + the user's original goal + **the search surface** — the inventory of files, directories, or URLs the original investigation touched. It must NOT receive the original agent's reasoning, verdict, confidence language, or the specific line/region it concluded from. **Withhold the conclusion, not the map.** Withholding the map too does not buy extra independence — the verifier still has to reach the same evidence, it just spends its budget guessing paths to get there. Measured: one verifier denied the inventory spent 70 `grep` + 18 `read_file` calls re-locating files the parent already had paths for, guessed 5 nonexistent paths on the way, and hit its tool-loop ceiling before finishing. The independence that matters is epistemic (re-deriving the verdict), not navigational.
    - The inventory is a **starting surface, not a boundary**: it does not satisfy the composition-axis guard below, and a verifier that reads only inside it still returns `evidence_base: artifact-internal`. At least one primary source outside that surface is still required for `independent-rederivation`.
    - **Default to `subagent_type: "research-agent"` (mechanically locked to Read/Grep/Glob/WebFetch/WebSearch — cannot Edit/commit/push).** If the claim requires Bash to verify (running a failing test, `gh pr view`, `git log origin/...`), fall back to a Bash-capable subagent type with `isolation: "worktree"` and prepend this prefix to the prompt: *"Verifier sub-agent — do not Edit, Write, commit, push, `gh pr create`, or `curl`. Return findings only."*
+   - **Set `id_prefix`** to a short label identifying the claim being verified, e.g. `"verify: unused export"` or `"verify: missing null check"`, so the live TUI shows which claim each verifier is checking.
    - **Every verifier dispatch carries an explicit budget** — `max_tool_use_iterations` (a wave of 2–3 claim checks needs ~15–25 rounds each, not 50) plus the cheapest sufficient model. An unbudgeted verifier does not fail loudly: it exhausts the default tool-round ceiling, terminates `stopReason: "tool_use_loop_capped"`, and emits its verdict from a tools-stripped wind-down round built on partial evidence. A `CONFIRMED` produced that way is indistinguishable from a real one and silently defeats the entire point of the wave. Check each returned verifier's stop reason before merging its verdict; treat a capped or wind-down verifier as `UNVERIFIABLE`, not as a verdict.
 3. Each verifier re-derives the verdict independently using tool calls only — never re-reading the original report's reasoning. Returns `{claim_id, verifier_verdict, evidence_pointer, evidence_base}`, where `verifier_verdict` is one of `CONFIRMED`, `REFUTED`, `STALE`, or `UNVERIFIABLE`, and `evidence_base` is `independent-rederivation` (read primary sources *outside* the cited artifact's boundary) or `artifact-internal` (re-read only the cited file/region). On `REFUTED` or `STALE`, the verifier also emits a corrected or updated finding.
 

package/dist/cli/commands/interactive/tool-lane-format.d.ts

@@ -16,5 +16,6 @@ export declare function batchBadge(chunk: ToolResultChunk | undefined): string;
 export declare function activeToolBadge(toolUseId: string, activeTools: {
     activeCount: number;
     toolUseIds: Set<string>;
+    toolIndex?: Map<string, number>;
 } | null): string;
 export declare function formatToolResultLine(chunk: ToolResultChunk, toolPrefix?: string, homeDir?: string, toolName?: string): string;

package/dist/cli/commands/interactive/tool-lane-overlay.d.ts

@@ -3,4 +3,5 @@ import type { ToolLaneFlash } from './tool-lane-flash.js';
 export declare function renderToolLaneOverlay(entries: Map<string, Entry>, order: string[], activeTools: {
     activeCount: number;
     toolUseIds: Set<string>;
+    toolIndex?: Map<string, number>;
 } | null, flash: ToolLaneFlash | null, maxOverlayRoots: number): string;