@flumecode/runner 0.11.0 → 0.12.0

package/dist/cli.js

@@ -738,7 +738,7 @@ var planInputSchema = {
   assumptions: z2.array(z2.string()).describe("Anything decided during planning, including unanswered defaults."),
   steps: z2.array(stepSchema).min(1).describe("Ordered list of changes. Each step says what and why, with file references."),
   acceptanceCriteria: z2.array(z2.string().min(1)).min(2).describe(
-    "Observable conditions that together define done. Each must be checkable \u2014 a behavior, test, or state you could verify \u2014 not a restatement of a step. At least 2 required."
+    "Concrete, deterministically-checkable conditions that together define done. Each names a trigger/precondition and the exact observable result (run X -> output Y; file Z contains W; f(a) returns b) \u2014 no vague adjectives, not a restatement of a step. The set must collectively cover every step's change. At least 2 required."
   ),
   risks: z2.array(z2.string()).describe("Anything that could change the approach."),
   outOfScope: z2.array(z2.string()).describe("What is deliberately not being done.")
@@ -858,13 +858,13 @@ var acVerdictSchema = z3.object({
   status: z3.enum(["met", "not_met", "unclear"]).describe("Verdict for this criterion, verified against the actual diff."),
   rationale: z3.string().min(1).describe("One or two sentences on why the verdict holds."),
   evidence: z3.array(evidenceSchema).describe(
-    "Diff hunks proving the verdict. Include the relevant hunk(s) for a met criterion; may be empty for not_met / unclear."
+    "Diff hunks proving the verdict, copied verbatim from git --no-pager diff. Across ALL criteria the evidence must collectively cover every hunk in the diff \u2014 each changed hunk appears under at least one criterion. Cite the relevant hunk(s) for a met criterion; may be empty for not_met / unclear."
   )
 });
 var reportInputSchema = {
   summary: z3.string().min(1).describe("One or two sentences on what was implemented."),
   prose: z3.string().min(1).describe(
-    "Markdown for the remaining report sections \u2014 What changed, Files changed, Build / tests, and Caveats / follow-ups. Use ## headings. Do NOT include the acceptance-criteria section here (that goes in acceptanceCriteria) and do NOT include the PR link (the runner appends it)."
+    "Markdown for the remaining report sections \u2014 Files changed, Build / tests, and Caveats / follow-ups. Use ## headings. Do NOT include the acceptance-criteria section here (that goes in acceptanceCriteria) and do NOT include the PR link (the runner appends it)."
   ),
   acceptanceCriteria: z3.array(acVerdictSchema).min(1).describe(
     "One entry per acceptance criterion from the plan, in plan order, each with a verdict and the diff evidence behind it."

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@flumecode/runner",
-  "version": "0.11.0",
+  "version": "0.12.0",
   "type": "module",
   "description": "FlumeCode local runner — claims jobs and drives your local Claude Code against a real checkout.",
   "bin": {

package/skills-plugin/skills/implement-plan/SKILL.md

@@ -96,8 +96,9 @@ the next step.
    useful). For **each** AC it must return: the criterion text verbatim, a verdict
    (**met / not met / unclear**), a one-or-two-sentence rationale, and — this is the
    evidence the report needs — the **exact diff hunk(s)** that prove it, each tagged
-   with its file path (the minimal lines that matter, copied verbatim from
-   `git --no-pager diff`; not the whole file). A _met_ AC should cite at least one
+   with its file path (the hunks that prove it, copied verbatim from
+   `git --no-pager diff`, such that the union of every AC's evidence covers the
+   entire diff — each changed hunk cited under at least one criterion). A _met_ AC should cite at least one
    hunk; _not met_ / _unclear_ may cite none. **Ground every verdict in the actual
    diff:** a criterion may be marked _met_ only if `git --no-pager diff` really
    contains the change that satisfies it, and each cited hunk must be copied verbatim
@@ -105,7 +106,7 @@ the next step.
    implement subagent claimed. If `git --no-pager diff` is empty, the implementation
    produced no changes: no criterion may be _met_, and the review must say so. Tell it
    to return this as a clean, structured list so you can hand it straight to the
-   report step.
+   report step. In addition to per-AC verdicts, cross-check that every hunk in `git --no-pager diff` is cited by at least one AC's evidence; report any uncovered hunk as a coverage gap (signalling a missing AC or an out-of-scope change).
 
 5. **Code-quality review** — Task, `model: "opus"`, read-only. Give the subagent
    the coding guidelines (verbatim) and tell it to review the changes for
@@ -131,7 +132,7 @@ the next step.
    copied verbatim from that live diff — it must drop or correct any hunk carried
    over from step 4 that no longer appears in the actual diff, and the **Files
    changed** list must come from `git --no-pager diff --stat`, not from what an
-   earlier subagent claimed. **If `git --no-pager diff` is empty, the
+   earlier subagent claimed. Tell it to enumerate all hunks from `git --no-pager diff` and ensure each is attached to ≥1 AC's `evidence`; any hunk mapping to no plan AC goes under `## Caveats / follow-ups` as an explicit unattributed change. **If `git --no-pager diff` is empty, the
    implementation changed nothing:** the report must say so plainly — an honest
    `summary`, no AC marked `met` with evidence — and must never describe edits
    that aren't in the diff. Tell it to submit the user-facing report by calling
@@ -149,13 +150,13 @@ The report subagent calls `submit_report` with these fields:
 
 - **`summary`** — one or two sentences on what was implemented.
 - **`prose`** — markdown for the remaining sections, using `##` headings:
-  **What changed** (the plan steps, each mapped to the concrete changes that satisfy
-  it), **Code quality** (the quality-review outcome and anything left as
+  **Code quality** (the quality-review outcome and anything left as
   nice-to-have), **Files changed** (the list from the diff), **Build / tests** (lists
   each verification command and its final pass/fail result, or explains that no
   build/test setup was found), and **Caveats / follow-ups** (anything deferred,
-  unmet, or worth a human's eyes). Do **not** put the acceptance-criteria section in
-  `prose`, and do **not** include a PR link — the runner adds it.
+  unmet, or worth a human's eyes — including any diff hunks that map to no plan AC,
+  listed explicitly as unattributed changes). Do **not** put the acceptance-criteria
+  section in `prose`, and do **not** include a PR link — the runner adds it.
 - **`acceptanceCriteria`** — one entry per AC from the plan, in plan order, each:
   - `criterion` — the AC text verbatim.
   - `status` — `"met"` / `"not_met"` / `"unclear"`, mirroring the AC review.
@@ -177,3 +178,4 @@ The report subagent calls `submit_report` with these fields:
   once — not as prose for you to echo. Each acceptance criterion carries the diff
   hunk(s) that prove its verdict, copied verbatim from the live `git --no-pager diff`
   — never fabricated. An empty diff means an honest "nothing changed" report.
+- The report exists so the human reviewer can verify each acceptance criterion is satisfied — the ACs and their diff evidence are the primary review surface.

package/skills-plugin/skills/request-to-plan/SKILL.md

@@ -71,11 +71,19 @@ Field-by-field guidance:
   - **`description`** — what changes and why: the concrete change being made and the rationale for it. Use concrete file references (`path/to/file.ts`) and name the functions/symbols involved.
   - **`pseudoCode`** — an array of `{ file, pseudoCode }` entries. Provide an entry for every file the step touches **except** documentation files (SKILL.md, README.md, wiki pages, etc.). `pseudoCode` is optional in the schema but expected for all non-documentation files. Each entry names the file path and contains pseudo code that precisely describes the changes to make in that file.
 - **`acceptanceCriteria`** — **required; at least 2 items.** Each criterion must
-  be an observable condition you could check after the work is done: a behavior,
-  a test result, or a verifiable state. Together they must fully define "done" —
-  satisfying all of them resolves the request, no more and no less. Do **not**
-  restate a step as a criterion ("the function is updated" is a step; "calling
-  the function with X returns Y" is a criterion).
+  be a concrete, deterministically-checkable condition that a third party can verify
+  without knowing the author's intent. Write each as a trigger/precondition and the
+  exact observable result: `run X → output Y`, `file Z contains W`, `calling f(a) returns b`.
+  No vague adjectives (`robust`, `clean`, `properly`, `works correctly`). The set
+  must be **collectively exhaustive** — every step's intended change is covered by
+  at least one AC. Do **not** restate a step as a criterion.
+
+  **Good vs bad examples:**
+  - ✅ `grep -rn "What changed" apps/runner/src/report.ts` produces no matches.
+  - ❌ The report is cleaner and no longer mentions 'What changed'. _(vague, not checkable)_
+  - ✅ `pnpm test` in the repo root exits 0 and report.test.ts output contains no failures.
+  - ❌ Tests pass correctly. _(no trigger, no observable result)_
+
 - **`risks`** — anything that could change the approach or surface a problem.
 - **`outOfScope`** — what you are deliberately not doing.