Skills/implement/workflows/implement-loop.js

// implement-loop — the per-task implement loop, as a Workflow script.
//
// This is the Workflow-substrate form of what used to be the
// `implement-orchestrator` agent's inline three-phase role-switch loop.
// The substrate change is the point of issue #7's Part B:
//
//   • Each per-task phase is now a separate `agent()` call — implementer,
//     spec-reviewer, quality-reviewer are dispatched as their existing
//     agent-types (they SURVIVE the migration; the inline-role-switch
//     ORCHESTRATOR is what retires). A single phase is therefore
//     independently invokable, which the inline loop could not offer.
//   • Inter-phase aggregation and the re-loop limit are deterministic
//     code here, not natural-language reasoning between dispatches.
//   • Routing keys on the structured verdict each agent reports (which
//     encodes the project's real build/test outcome), not on a guess.
//
// Discipline preserved verbatim from the old loop:
//   • The script NEVER commits and NEVER moves main HEAD. All code edits,
//     the stats file, and (on PARTIAL/BLOCKED) BLOCKED.md live in the
//     working tree as unstaged changes; the orchestrator that invoked
//     this workflow inspects and commits.
//   • Tasks run SEQUENTIALLY — plan tasks carry implicit ordering
//     dependencies, and the script does not know the graph, so a BLOCKED
//     task stops the loop rather than skipping ahead.
//   • Spec-compliance is gated BEFORE quality, per task.
//   • Re-loop limit: 2 repair retries per failure-mode per task; the 3rd
//     unresolved attempt escalates to BLOCKED.
//   • Quality re-loop hold (issue #10): a quality finding whose only remedy
//     would contradict the ratified plan (a name/signature/structure the
//     task prescribes) is HELD, not chased into a deviation the next review
//     then re-flags. The repair implementer keeps the plan and records the
//     finding in `held`; a no-op backstop holds it anyway when a repair
//     leaves the diff unchanged (or cycles back) yet quality still flags.
//     Either way the finding surfaces as a concern, not a false BLOCKED on a
//     green task — and the orchestrator weighs it on its Step-3 inspection.
//     A finding the implementer judges correctness-breaking (would not
//     build / a test fails / a prescribed caller breaks) escalates to
//     BLOCKED instead of holding. The held/no-op partition is the
//     implementer's call, not enforced in code (the script cannot tell a
//     cosmetic hold from an ignored bug) — hence the neutral concern label
//     and the orchestrator backstop, same trust placed in its other reports.
//   • The script has no filesystem or shell access of its own — every
//     working-tree mutation (code, stats.json, BLOCKED.md) happens inside
//     an agent() call.
//   • Model policy: every agent() call pins an explicit model — never the
//     session-model inherit (which could route to an unintended tier, e.g.
//     fable — banned for all plugin agents and workflows). Mechanical and
//     in-loop steps run sonnet; the quality gate is the one deliberate opus
//     call (last correctness check before a task is marked DONE).
//   • Effort policy mirrors the model policy: every agent() call pins an
//     explicit effort — never the session inherit. Code-writing and review
//     steps run high, the opus quality gate runs xhigh, and schema-bound
//     extraction/check steps (preflight, plan-index, plan-extract, mini-verify,
//     tree-check, finalize) run medium. See docs/agent-template.md § effort.
//
// Carrier — passed as the Workflow `args` object by the orchestrator:
//   mode:          'standard' | 'mini'
//   iter_id:       e.g. 'ct.2.3' (standard) or 'bugfix-<symptom>' / 'feat-<behaviour>' (mini)
//   plan_path:     (standard) path under docs/plans
//   task_range:    (standard, optional) [from, to] inclusive, 1-based
//   red_test_path: (mini) absolute path to the RED test from debug / tdd
//   cause_summary: (mini) 1–2 sentences (debugger cause, or tdd spec_summary)
//   constraint:    (mini) e.g. 'minimal fix, no surrounding cleanup'
// A non-object carrier, an unknown mode, or a missing required field fails
// fast as an infra BLOCKED before any agent is dispatched (issue #24).

export const meta = {
  name: 'implement-loop',
  description:
    'Execute a plan iteration (standard) or a debug/tdd RED->GREEN handoff (mini) task-by-task: implementer -> spec-compliance -> quality, with deterministic re-loop and aggregation. Writes code, tests, stats.json, and (on PARTIAL/BLOCKED) BLOCKED.md to the working tree as unstaged changes; never commits, never moves main HEAD.',
  phases: [
    { title: 'Preflight' },
    { title: 'Per-task loop' },
    { title: 'Verify' },
    { title: 'E2E coverage' },
    { title: 'Report' },
  ],
}

// Carrier guard (issue #24): a named-workflow invocation can deliver `args`
// as a STRING. `args || {}` alone does not catch that — a non-empty string is
// truthy, so every field would destructure to undefined and the failure
// would surface far downstream (a plan-index dispatch against "Read the plan
// at undefined"), mislabelled as a plan-content problem after burning agent
// calls. Normalize, then reject a malformed carrier HERE, before any agent
// is dispatched — a distinct infra verdict, never a substantive one.
let carrier = args
if (typeof carrier === 'string') {
  // Tolerate a JSON-SERIALIZED object carrier (a stringifying caller or
  // substrate layer still authored the documented object form); free text
  // does not parse to an object and falls through to the rejection below.
  try {
    carrier = JSON.parse(carrier)
  } catch {}
}
if ((carrier !== undefined && carrier !== null && typeof carrier !== 'object') || Array.isArray(carrier)) {
  return {
    status: 'BLOCKED',
    iter_id: null,
    reason:
      `infra: args arrived as ${Array.isArray(carrier) ? 'an array' : `a ${typeof carrier}`}, not the documented ` +
      'object carrier — nothing was dispatched; re-invoke with args: { mode, iter_id, ' +
      'plan_path | red_test_path + cause_summary, ... } (invocation examples in implement/SKILL.md)',
  }
}

const {
  mode = 'standard',
  iter_id,
  plan_path,
  task_range = null,
  red_test_path,
  cause_summary,
  constraint = 'minimal change, no surrounding cleanup',
} = carrier || {}
// Blank-safe echo for the guard verdicts below: never mirror a blank/non-string
// iter_id into the end-report while also naming it missing.
const iterIdEcho = typeof iter_id === 'string' && iter_id.trim() ? iter_id : null

if (mode !== 'standard' && mode !== 'mini') {
  return {
    status: 'BLOCKED',
    iter_id: iterIdEcho,
    reason: `infra: unknown mode '${mode}' — expected 'standard' or 'mini'; nothing was dispatched`,
  }
}
// The required carrier fields per mode (the header comment above is the
// contract). Missing or blank fields fail fast by name — the loop must never
// glob for a plan or brief an implementer with the literal string "undefined".
const requiredByMode = mode === 'mini' ? { iter_id, red_test_path, cause_summary } : { iter_id, plan_path }
const missingFields = Object.entries(requiredByMode)
  .filter(([, v]) => typeof v !== 'string' || !v.trim())
  .map(([k]) => k)
if (missingFields.length) {
  return {
    status: 'BLOCKED',
    iter_id: iterIdEcho,
    reason:
      `infra: missing required carrier field(s) for mode '${mode}': ${missingFields.join(', ')} — ` +
      'nothing was dispatched (carrier contract in the header comment and implement/SKILL.md)',
  }
}

const STANDING =
  "Standing reading first (the plugin convention): read the project's CLAUDE.md " +
  '(its "## Skills plugin: project facts" name the build and test commands and any ' +
  'design ledger) and `git log -10 --format=full`. Resolve the build/test commands ' +
  'from those facts — do not assume a toolchain.'

// JSON Schemas — force structured verdicts so the script can branch on real outcomes.
const PREFLIGHT_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['clean', 'head_sha', 'branch'],
  properties: {
    clean: { type: 'boolean', description: '`git status --porcelain` produced no output' },
    head_sha: { type: 'string' },
    branch: { type: 'string' },
    dirty_paths: { type: 'array', items: { type: 'string' } },
  },
}
// Plan extraction is a TWO-step, cardinality-guarded operation (issue #22),
// never a single unbounded verbatim dump. TASK_INDEX_SCHEMA carries the cheap
// enumerate pass (ids + one-line titles only — one short line per task, so it
// self-limits far later than a verbatim dump; the `total_tasks` field is a
// self-consistency backstop for the residual). TASK_TEXT_SCHEMA carries one
// task's verbatim body per agent call (per-task extraction removes the
// ACROSS-ALL-TASKS output-budget ceiling that silently truncated big plans to a
// prefix; a single task whose own body overflows one response is bounded only by
// the planner's bite-sized-task invariant — see the block comment below).
const TASK_INDEX_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['total_tasks', 'task_ids'],
  properties: {
    total_tasks: {
      type: 'integer',
      description:
        'the TOTAL number of tasks the ENTIRE plan defines — count all of them directly (e.g. count the task ' +
        'headers), IGNORING any range filter. This is a self-consistency check: the plan text is fully readable ' +
        '(input budget is ample), so this count is authoritative even if the id list below self-limits.',
    },
    task_ids: {
      type: 'array',
      items: {
        type: 'object',
        additionalProperties: false,
        required: ['id', 'title'],
        properties: {
          id: { type: 'integer' },
          title: { type: 'string', description: 'one-line title ONLY — never the task body' },
        },
      },
    },
  },
}
const TASK_TEXT_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['id', 'title', 'text'],
  properties: {
    id: { type: 'integer' },
    title: { type: 'string' },
    text: { type: 'string', description: 'verbatim task block from the plan (this one task only)' },
  },
}
const IMPL_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['status', 'summary', 'applied_changes'],
  properties: {
    status: { type: 'string', enum: ['DONE', 'DONE_WITH_CONCERNS', 'NEEDS_CONTEXT', 'BLOCKED'] },
    summary: { type: 'string', description: 'one line: what changed (paths + functions)' },
    applied_changes: {
      type: 'boolean',
      description:
        'GROUND TRUTH, not intent: did THIS task write to at least one file? true if you called Edit/Write (or ' +
        'equivalent) on any file; false if you made no file change at all — the code was already in the target ' +
        'state, or you skipped/misunderstood the task. Report it honestly even when status is DONE: a DONE that ' +
        'touched nothing is not a contribution, and the loop surfaces it for the orchestrator to weigh.',
    },
    concerns: { type: 'array', items: { type: 'string' } },
    reason: { type: 'string', description: 'on BLOCKED/NEEDS_CONTEXT: the blocker' },
    held: {
      type: 'array',
      description:
        'quality-repair dispatch only: quality findings KEPT against the ratified plan because honouring them ' +
        'would deviate from a plan-prescribed name/signature/structure while the tree stays green. Each is a ' +
        'concern to surface, not a deviation to chase. A finding that would break correctness is NOT held — it ' +
        'is escalated via status BLOCKED.',
      items: {
        type: 'object',
        additionalProperties: false,
        required: ['finding', 'kept', 'why'],
        properties: {
          finding: { type: 'string', description: 'the quality finding being kept (held)' },
          kept: { type: 'string', description: 'the plan-prescribed element preserved (name/signature/structure)' },
          why: { type: 'string', description: 'why honouring the finding would contradict the ratified plan' },
        },
      },
    },
  },
}
const SPEC_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['status'],
  properties: {
    status: { type: 'string', enum: ['compliant', 'non_compliant', 'unclear', 'infra_blocked'] },
    findings: { type: 'array', items: { type: 'string' }, description: 'missing requirements + unrequested extras' },
    ambiguity: { type: 'string' },
  },
}
const QUAL_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['status', 'diff_fingerprint'],
  properties: {
    status: { type: 'string', enum: ['approved', 'changes_requested', 'infra_blocked'] },
    issues: { type: 'array', items: { type: 'string' }, description: 'Important + Minor only (Nits never gate)' },
    diff_fingerprint: {
      type: 'string',
      description:
        'sha256 hex of the FULL `git diff HEAD` (the whole working-tree diff, not a footprint subset) — REQUIRED; ' +
        'the loop compares it across rounds to detect a no-op/cyclic repair and stop oscillating to a false BLOCKED',
    },
  },
}
const E2E_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['status'],
  properties: {
    status: { type: 'string', enum: ['DONE', 'DONE_WITH_CONCERNS', 'NEEDS_CONTEXT', 'BLOCKED'] },
    fixtures: { type: 'array', items: { type: 'string' } },
    note: { type: 'string' },
  },
}
// mini-mode only: independently OBSERVE that the RED test is now GREEN, rather
// than trusting the implementer's self-reported DONE. The whole telos of a
// mini-mode handoff is to drive one specific RED test to GREEN; a no-op leaves
// it RED while the implementer can still report DONE. This is the implement-loop
// analogue of compiler-driven-edit's verify agent (build+suite re-run +
// working_tree_dirty) — observe, do not assert.
const MINI_VERIFY_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['red_test_now_green', 'suite_green', 'working_tree_dirty'],
  properties: {
    red_test_now_green: {
      type: 'boolean',
      description: 'the handed-off RED test, re-run by name, now PASSES (it was red before the fix; confirm it is green now)',
    },
    suite_green: { type: 'boolean', description: 'the full suite passes — the fix introduced no regression' },
    working_tree_dirty: {
      type: 'boolean',
      description: 'GROUND TRUTH from `git status --porcelain` being non-empty (NOT `git diff HEAD`, which omits brand-new untracked files): a fix actually landed (a clean tree means the RED test, if green, was never red, or nothing was done)',
    },
    detail: { type: 'string', description: 'on any false: which test is still red, what regressed, or that the tree is clean' },
  },
}
// Standard-mode no-op gate (issue #12, facets 1+2): the authoritative ground
// truth that the iteration's per-task work actually landed. Runs after the loop
// but BEFORE E2E/finalize, so neither E2E fixtures nor the stats/BLOCKED.md
// artefacts can inflate the count. Uses `git status --porcelain` (counts brand-new
// UNTRACKED files — the implementer leaves edits unstaged, so a new-file deliverable
// is untracked and `git diff HEAD` would miss it). A self-report can never reach
// this verdict; it is git ground truth.
const TREE_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['files_touched'],
  properties: {
    files_touched: {
      type: 'integer',
      description:
        'the line count of `git status --porcelain` (every changed/added/untracked path). Run exactly that — do NOT ' +
        'use `git diff`, which omits untracked new files. Do NOT edit anything. 0 means the iteration is a no-op.',
    },
  },
}
const FINALIZE_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['stats_path', 'wrote_blocked_md'],
  properties: {
    stats_path: { type: 'string' },
    wrote_blocked_md: { type: 'boolean' },
  },
}

// ---- Phase 0 — clean-tree preflight ------------------------------------
phase('Preflight')
const pre = await agent(
  `${STANDING}\n\nYou are the clean-tree preflight for an implement iteration. ` +
    'Run `git status --porcelain`, `git rev-parse HEAD`, and `git rev-parse --abbrev-ref HEAD`. ' +
    'Report whether the tree is clean (no porcelain output), the HEAD sha, the branch, and any dirty paths. ' +
    'Do NOT modify anything, do NOT commit. The HEAD sha is an informational anchor only — never a reset target.',
  { model: 'sonnet', effort: 'medium', label: 'preflight', phase: 'Preflight', schema: PREFLIGHT_SCHEMA },
)
if (!pre) return { status: 'BLOCKED', iter_id, reason: 'infra: preflight agent did not return' }
if (!pre.clean) {
  return {
    status: 'BLOCKED',
    iter_id,
    reason: 'infra: working tree dirty — the orchestrator must clean it before re-invoking',
    dirty_paths: pre.dirty_paths || [],
  }
}
const startSha = pre.head_sha

// ---- Phase 1 — assemble the task list ----------------------------------
let tasks
if (mode === 'mini') {
  tasks = [
    {
      id: 1,
      title: 'drive the RED test to GREEN',
      text:
        `Make this RED test pass: ${red_test_path}\n\n` +
        `Context (debugger cause, or tdd spec_summary): ${cause_summary}\n\n` +
        `Constraint: ${constraint}`,
    },
  ]
} else {
  // Plan extraction is split into an enumerate pass + per-task verbatim
  // extraction, guarded by cardinality checks (issue #22). The old design
  // pulled every requested task's VERBATIM block through ONE schema-bound
  // response; on a large plan (many tasks, or a few tasks carrying long code
  // blocks) that response self-limits and the agent returns a well-formed
  // PREFIX of the tasks — commonly just task 1. The short list was non-empty,
  // so the only guard (reject empty) passed, and the loop ran to a clean DONE
  // over the truncated subset. The missing tasks were never attempted, yet the
  // end-report read as a completion. This fix removes the across-all-tasks
  // ceiling AND adds the backstops:
  //   • Enumerate pass (plan-index) — returns ONLY task ids + one-line titles,
  //     one short line per task, so it self-limits far later than a verbatim
  //     dump. It also reports `total_tasks` (the whole plan's task count,
  //     computed from the fully-readable plan text independently of the emitted
  //     list) — the self-consistency oracle the whole-plan path otherwise lacks.
  //   • Per-task extract (plan-extract:<id>) — one agent() per id carries
  //     exactly one task's verbatim block, so no single response has to hold
  //     every task's text. Extraction is read-only and order-independent (unlike
  //     the implement loop, whose tasks carry ordering dependencies), so the
  //     calls fan out via parallel() (which also honours the concurrency cap on
  //     a big plan). The requested id is bound INSIDE each thunk and the results
  //     are re-associated by it — never by array position — so the mapping is
  //     correct regardless of the order parallel() resolves in.
  //   • Cardinality guards — (a) the enumerate must list exactly `total_tasks`
  //     on the whole-plan path; (b) a task_range must be well-formed and covered
  //     exactly by the plan; (c) every expected id must extract non-empty text.
  //     Any breach is a hard BLOCKED, never a silent short run.
  // Residual (bounded, not closed): a SINGLE task whose own verbatim body
  // overflows its dedicated per-task response would return a non-empty prefix
  // that part-(c) accepts — there is no per-task round-trip oracle. This is far
  // narrower than the closed across-tasks vector and rests on the planner's
  // bite-sized-task invariant; it is the one truncation slice left open here.
  const index = await agent(
    `${STANDING}\n\nRead the plan at ${plan_path}. List the task ` +
      (task_range
        ? `ids in the range ${task_range[0]}..${task_range[1]} (inclusive, 1-based)`
        : 'ids of EVERY task') +
      ' that the plan actually defines, each with its one-line title. Return ONLY ids and titles — do NOT include ' +
      'any task body or code block. Do not summarise, invent, reorder, or pad the list. Separately report ' +
      '`total_tasks`: the count of ALL tasks the entire plan defines, ignoring any range filter. Do not edit anything.',
    { model: 'sonnet', effort: 'medium', label: 'plan-index', phase: 'Per-task loop', schema: TASK_INDEX_SCHEMA },
  )
  if (!index || !index.task_ids || index.task_ids.length === 0) {
    return { status: 'NEEDS_CONTEXT', iter_id, reason: `no tasks found in ${plan_path}` }
  }
  // Dedup the enumerated ids (first title wins); they define the enumerate set.
  const titleById = new Map()
  for (const t of index.task_ids) if (!titleById.has(t.id)) titleById.set(t.id, t.title)
  const enumeratedIds = [...titleById.keys()].sort((a, b) => a - b)
  const planTotal = typeof index.total_tasks === 'number' ? index.total_tasks : null

  // Which ids MUST be extracted, and the guard that the enumerate is complete.
  let expectedIds
  if (task_range) {
    // Guard 0 — a well-formed 1-based [from, to]. A degenerate/inverted range
    // (from > to, non-integer, < 1) is a caller error surfaced as its own
    // BLOCKED, not swallowed into an empty task list that later mis-reports as
    // a no-op iteration.
    const [from, to] = task_range
    if (!Number.isInteger(from) || !Number.isInteger(to) || from < 1 || to < from) {
      return {
        status: 'BLOCKED',
        iter_id,
        reason: `invalid task_range [${from}, ${to}]: expected a 1-based [from, to] with 1 <= from <= to`,
      }
    }
    // Guard (b) — the range must be covered EXACTLY by the plan. A range that
    // overshoots (e.g. [1,10] on a 5-task plan) is surfaced, not run short.
    const wanted = []
    for (let i = from; i <= to; i++) wanted.push(i)
    const missing = wanted.filter((i) => !titleById.has(i))
    if (missing.length) {
      return {
        status: 'BLOCKED',
        iter_id,
        reason:
          `plan-extract cardinality mismatch: range ${from}..${to} asked ${wanted.length} task(s) but ` +
          `${plan_path} defines ${planTotal ?? enumeratedIds.length} task(s) (missing in-range id(s): ${missing.join(', ')})`,
      }
    }
    expectedIds = wanted
  } else {
    // Guard (a) — whole-plan path: the enumerate is the sole authority, so
    // cross-check its own count. `total_tasks` is computed from the full plan
    // independently of the emitted list; a listed-vs-counted mismatch is the
    // enumerate self-limiting to a prefix — issue #22's symptom relocated to the
    // (bounded) enumerate pass, and the only backstop this path can have without
    // a caller-supplied range.
    if (planTotal !== null && enumeratedIds.length !== planTotal) {
      return {
        status: 'BLOCKED',
        iter_id,
        reason:
          `plan-index truncated: enumerated ${enumeratedIds.length} task(s) but the plan at ${plan_path} ` +
          `defines ${planTotal} — the enumerate pass self-limited; re-run, do not proceed over a partial index`,
      }
    }
    expectedIds = enumeratedIds
  }

  // Per-task verbatim extraction — read-only and order-independent, so fan out
  // via parallel(). The requested id is captured in the closure and returned
  // alongside the result, so association is by id, never by resolution order.
  // parallel() yields null for a thunk that threw / whose agent died; agent()
  // itself returns null on a terminal error — both surface as a missing id below.
  const extractedTasks = await parallel(
    expectedIds.map((id) => () =>
      agent(
        `${STANDING}\n\nRead the plan at ${plan_path}. Extract EXACTLY task ${id} (1-based) as its VERBATIM block — ` +
          'the full task text as written, including any code blocks. Do not summarise, truncate, reorder, or merge in ' +
          'any other task. Return that one task only. Do not edit anything.',
        { model: 'sonnet', effort: 'medium', label: `plan-extract:${id}`, phase: 'Per-task loop', schema: TASK_TEXT_SCHEMA },
      ).then((t) => ({ reqId: id, t })),
    ),
  )

  // Guard (c) — every expected id must have produced non-empty verbatim text.
  // A null result (thunk threw, or agent died) or empty text is the truncation
  // this issue is about; fail loudly with "got N of M". Keyed by the REQUESTED
  // id carried in the closure (never the agent's self-reported id, so a
  // mislabelled response cannot masquerade as coverage, and never array
  // position, so parallel()'s resolution order is irrelevant).
  const tasksById = new Map()
  for (const slot of extractedTasks) {
    if (!slot) continue // parallel() null: the thunk threw
    const { reqId, t } = slot
    if (t && typeof t.text === 'string' && t.text.trim()) {
      const title = (t.title && t.title.trim()) || titleById.get(reqId) || `task ${reqId}`
      tasksById.set(reqId, { id: reqId, title, text: t.text })
    }
  }
  const missingText = expectedIds.filter((id) => !tasksById.has(id))
  if (missingText.length) {
    return {
      status: 'BLOCKED',
      iter_id,
      reason:
        `plan-extract truncated: got ${expectedIds.length - missingText.length} of ${expectedIds.length} task(s) ` +
        `from ${plan_path} (missing id(s): ${missingText.join(', ')}) — re-run; do not proceed over a partial plan`,
    }
  }
  // Restore plan order — expectedIds is already sorted ascending.
  tasks = expectedIds.map((id) => tasksById.get(id))
}

// ---- Phase 2 — per-task loop (sequential) ------------------------------
phase('Per-task loop')

async function runTask(task) {
  // 2.1 — implementer phase
  const impl = await agent(
    `${STANDING}\n\nImplement this task exactly, RED-first if it adds behaviour (TDD is an independent ` +
      'inner-loop discipline — add the failing test inline even if the task text forgot to script it). ' +
      'Build and test must be green before you report DONE. Leave all edits UNSTAGED; never commit.\n\n' +
      `mode: ${mode}\niter_id: ${iter_id}\n\nTASK ${task.id} — ${task.title}\n${task.text}`,
    { agentType: 'implementer', model: 'sonnet', effort: 'high', label: `impl:${task.id}`, phase: 'Per-task loop', schema: IMPL_SCHEMA },
  )
  if (!impl) return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: 'implementer agent did not return' }
  if (impl.status === 'BLOCKED') return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: impl.reason || 'worker-blocked' }
  if (impl.status === 'NEEDS_CONTEXT') return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: `context-exhausted: ${impl.reason || ''}` }
  const concerns = impl.concerns || []
  // Did THIS task write a file, across the initial dispatch AND any repair? The
  // initial implementer may legitimately no-op (the code was already in shape)
  // while a spec/quality repair does the real writing — so OR the self-reports
  // across every dispatch. This feeds a concern and the E2E gate; it is NOT the
  // no-op verdict (the git file count is — see the iteration guard).
  let wroteAnyFile = impl.applied_changes === true

  // 2.2 — spec-compliance check (gated before quality), with repair re-loop
  for (let round = 0; ; round++) {
    const spec = await agent(
      `${STANDING}\n\nSpec-compliance review of task ${task.id}. Compare \`git diff HEAD\` against the task ` +
        'text ONLY — list missing requirements and unrequested extras. No quality opinions, no fix proposals. ' +
        `Focus on the files this task claims to touch.\n\nTASK ${task.id} — ${task.title}\n${task.text}`,
      { agentType: 'spec-reviewer', model: 'sonnet', effort: 'high', label: `spec:${task.id}`, phase: 'Per-task loop', schema: SPEC_SCHEMA },
    )
    if (spec && spec.status === 'compliant') break
    if (spec && spec.status === 'unclear') return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: 'spec-ambiguous', detail: spec.ambiguity }
    if (round >= 2) return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: 'review-loop-exhausted (spec-compliance)' }
    // repair: re-dispatch the implementer with the review findings as the repair brief
    const specFix = await agent(
      `${STANDING}\n\nRepair task ${task.id} to satisfy the spec-compliance review. Address EACH finding; ` +
        'do not widen scope. Keep build + tests green; leave edits unstaged.\n\n' +
        `TASK ${task.id} — ${task.title}\n${task.text}\n\nFINDINGS:\n- ${(spec?.findings || ['(none reported)']).join('\n- ')}`,
      { agentType: 'implementer', model: 'sonnet', effort: 'high', label: `impl-fix-spec:${task.id}`, phase: 'Per-task loop', schema: IMPL_SCHEMA },
    )
    if (specFix && specFix.applied_changes === true) wroteAnyFile = true
  }

  // 2.3 — quality check, with repair re-loop.
  // The plan-vs-finding judgement lives here, with the implementer that holds
  // the task text — the quality-reviewer is deliberately blind to it. The hold
  // is keyed on two structural signals, never on a self-reported status enum
  // (which the implementer's contract overloads): the `held` array the repair
  // returns, and a no-op backstop (a changes_requested verdict over a diff
  // whose fingerprint was already reviewed-and-flagged this task means the
  // intervening repair changed nothing or cycled back, so re-running quality
  // is futile).
  let heldConcerns = []
  const seenFingerprints = new Set()
  for (let round = 0; ; round++) {
    const qual = await agent(
      `${STANDING}\n\nQuality review of task ${task.id} (spec-compliance is already green — do not re-check it). ` +
        'Read every chunk of `git diff HEAD` in this task\'s footprint. Report only Important and Minor issues; ' +
        'Nits never gate. Also report `diff_fingerprint` (REQUIRED): the sha256 hex of the FULL `git diff HEAD` ' +
        '(`git diff HEAD | sha256sum` — the whole working-tree diff, NOT narrowed to this task\'s footprint). ' +
        'The loop compares it across rounds to detect a no-op/cyclic repair.',
      // opus by design: the loop's last correctness gate (spec-reviewer only checks
      // task-text correspondence) — real-bug finding is the documented opus strength.
      { agentType: 'quality-reviewer', model: 'opus', effort: 'xhigh', label: `qual:${task.id}`, phase: 'Per-task loop', schema: QUAL_SCHEMA },
    )
    if (qual && qual.status === 'approved') break
    // No-op / cyclic-repair backstop: a changes_requested verdict over a diff-state already reviewed-and-flagged
    // this task means the intervening repair changed nothing (or cycled back to an earlier state) — the
    // implementer kept the plan, or rejected the finding. Re-running quality would only re-flag identical code,
    // so stop here rather than burning the retry budget down to a false BLOCKED. A byte-identical diff cannot
    // distinguish a principled plan-hold from an ignored finding, so the concern is labelled neutrally and left
    // for the orchestrator to adjudicate on its Step-3 inspection.
    if (qual && qual.status === 'changes_requested' && qual.diff_fingerprint && seenFingerprints.has(qual.diff_fingerprint)) {
      heldConcerns = (qual.issues && qual.issues.length ? qual.issues : ['(finding not reported)']).map(
        (i) =>
          'unresolved quality finding — the repair left the diff unchanged (a kept plan-prescribed element, or a ' +
          `finding the implementer rejected); verify by hand on inspection: ${i}`,
      )
      break
    }
    if (round >= 2) return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: 'review-loop-exhausted (quality)' }
    if (qual && qual.diff_fingerprint) seenFingerprints.add(qual.diff_fingerprint)
    const fix = await agent(
      `${STANDING}\n\nThe quality review of task ${task.id} requested changes. Address EACH Important/Minor issue; ` +
        'do not widen scope; keep build + tests green; leave edits unstaged. The task text below is the ratified plan.\n\n' +
        'HOLD CLAUSE — most issues you simply fix. But if honouring an issue would force you to deviate from a ' +
        'name, signature, or structure THIS TASK prescribes (or to break the downstream callers the plan ' +
        'prescribes), do NOT deviate. Two cases:\n' +
        '  • The finding is cosmetic — keeping the plan leaves the build and tests GREEN (e.g. a name reads ' +
        'slightly off but everything compiles and passes). KEEP the plan, fix every other issue, and record each ' +
        'kept finding in `held` (finding / kept / why). Do not rename or restructure to chase it.\n' +
        '  • Honouring the plan would make the code WRONG — it would not build, a test would fail, or a ' +
        'prescribed caller would break. That is a real plan-vs-correctness conflict, not a cosmetic hold: report ' +
        'status BLOCKED with the conflict in `reason`. Never bury a correctness defect in `held`.\n' +
        'A finding whose only remedy is to diverge from the ratified plan must be held or escalated, never chased ' +
        'into a deviation the next review flags.\n\n' +
        `TASK ${task.id} — ${task.title}\n${task.text}\n\nISSUES:\n- ` + (qual?.issues || ['(none reported)']).join('\n- '),
      { agentType: 'implementer', model: 'sonnet', effort: 'high', label: `impl-fix-qual:${task.id}`, phase: 'Per-task loop', schema: IMPL_SCHEMA },
    )
    if (fix && fix.applied_changes === true) wroteAnyFile = true
    if (fix && (fix.status === 'BLOCKED' || fix.status === 'NEEDS_CONTEXT')) {
      // The implementer judged a finding a real plan-vs-correctness conflict. Escalate loudly so it is
      // adjudicated, rather than letting that judgement ride a green commit as a quiet concern.
      return {
        id: task.id,
        title: task.title,
        outcome: 'BLOCKED',
        reason: `quality/plan conflict: ${fix.reason || 'honouring a quality finding would break the ratified plan'}`,
      }
    }
    if (fix && fix.held && fix.held.length) {
      // The implementer kept plan-prescribed elements against cosmetic findings. Stop chasing — re-running
      // quality would only re-flag the unchanged code. Surface the held findings as concerns to weigh.
      heldConcerns = fix.held.map(
        (h) => `quality finding held against the ratified plan: ${h.finding} — kept ${h.kept}; honouring it would ${h.why}`,
      )
      break
    }
  }

  // Per-task no-op surfacing (issue #12, facet 1): a task that reports DONE yet
  // wrote no file across any dispatch is suspicious — it was either genuinely
  // already satisfied, or skipped/misunderstood. The script cannot tell those
  // apart (same trust placed in the held/no-op partition above), so it does NOT
  // gate on it — it surfaces a neutral concern for the orchestrator's Step-3
  // inspection. The iteration-level git file count is the gate, never this
  // self-report (issue #12 review: the self-report must not be able to fail a
  // run that actually did the work).
  const noopConcern = !wroteAnyFile
    ? [
        `task #${task.id} reported ${impl.status} but wrote no file — confirm it was genuinely already ` +
          'satisfied by the baseline (or earlier tasks), not skipped or misunderstood',
      ]
    : []
  return {
    id: task.id,
    title: task.title,
    outcome: 'DONE',
    concerns: [...concerns, ...heldConcerns, ...noopConcern],
  }
}

const results = []
for (const task of tasks) {
  const r = await runTask(task)
  results.push(r)
  if (r.outcome === 'BLOCKED') break // do not skip ahead — task ordering dependencies are unknown
}

const completed = results.filter((r) => r.outcome === 'DONE')
const blocked = results.find((r) => r.outcome === 'BLOCKED')
let outcome
if (!blocked) outcome = 'DONE'
else if (completed.length > 0) outcome = 'PARTIAL'
else outcome = 'BLOCKED'

// An iteration-level guard (issue #12) may downgrade a DONE outcome to BLOCKED on
// positive-evidence grounds. It runs BEFORE finalize so the persisted stats.json
// records the final outcome (not a stale DONE), and so E2E does not run over a
// no-op. The verdict is git ground truth, never a per-task self-report — a
// self-report must never be able to FAIL a run that actually did the work. It
// carries its own blocked_detail (no single offending task) and a `noopClean`
// flag: a clean-tree no-op needs no BLOCKED.md (nothing to explain).
let synthBlock = null
let noopClean = false

// ---- Phase 2.5 — verify (issue #12, facets 1+2+4) ----------------------
// mini mode: independently OBSERVE the handed-off RED test is now GREEN (a no-op
// leaves it RED while the implementer can still report DONE). standard mode: the
// git file count is the authoritative no-op gate. Both are git ground truth, the
// implement-loop analogue of compiler-driven-edit's verify agent.
let miniVerify = null
let treeState = null
if (mode === 'mini' && outcome === 'DONE') {
  phase('Verify')
  miniVerify = await agent(
    `${STANDING}\n\nVerify a bug/feature fix WITHOUT changing any code or test. The fix was meant to drive this ` +
      `RED test to GREEN: ${red_test_path}\n\nRun that test by name and confirm it now PASSES (it was RED before the ` +
      'fix). Then run the full suite and confirm it is green (no regression). Also report working_tree_dirty — ' +
      'whether `git status --porcelain` (NOT `git diff HEAD`, which misses new untracked files) shows any change at ' +
      'all (a clean tree means no fix landed). Do NOT edit anything; do NOT commit.',
    { model: 'sonnet', effort: 'medium', label: 'mini-verify', phase: 'Verify', schema: MINI_VERIFY_SCHEMA },
  )
  if (!miniVerify || !miniVerify.red_test_now_green || !miniVerify.suite_green || !miniVerify.working_tree_dirty) {
    outcome = 'BLOCKED'
    synthBlock = {
      task: null,
      reason: !miniVerify
        ? 'mini-verify agent did not return'
        : !miniVerify.working_tree_dirty
          ? 'no-op fix: the working tree is clean — the RED->GREEN handoff produced no change'
          : !miniVerify.red_test_now_green
            ? 'the handed-off RED test is still red — the fix did not land; route back to debug (RED-first)'
            : 'the fix regressed the suite — not behaviour-correct; route back to debug (RED-first)',
      detail: miniVerify ? miniVerify.detail || null : null,
    }
    // a verified-clean tree is a clean no-op (no BLOCKED.md); a still-red/regression
    // tree is genuinely dirty (BLOCKED.md explains it). A null agent is infra, not a
    // known-clean tree — leave noopClean false so a BLOCKED.md is written if dirty.
    if (miniVerify && !miniVerify.working_tree_dirty) noopClean = true
  }
} else if (mode === 'standard' && outcome === 'DONE') {
  phase('Verify')
  treeState = await agent(
    `${STANDING}\n\nReport the working-tree footprint of an implement iteration WITHOUT changing anything. Run ` +
      '`git status --porcelain` and report files_touched = its line count (every changed, added, or untracked ' +
      'path). Use `git status --porcelain`, NOT `git diff`, so brand-new untracked files are counted. Do NOT edit, ' +
      'do NOT commit.',
    { model: 'sonnet', effort: 'medium', label: 'tree-check', phase: 'Verify', schema: TREE_SCHEMA },
  )
  if (!treeState || treeState.files_touched === 0) {
    outcome = 'BLOCKED'
    synthBlock = {
      task: null,
      reason: !treeState
        ? 'infra: tree-check agent did not return — cannot confirm the iteration landed; treat as not-done'
        : 'no-op iteration: `git status --porcelain` is empty — every task reported DONE but nothing landed in the working tree',
      detail: null,
    }
    // a confirmed-empty tree is a clean no-op (no BLOCKED.md); a null agent is infra
    // (tree state unknown — possibly dirty), so leave noopClean false.
    if (treeState && treeState.files_touched === 0) noopClean = true
  }
}

// ---- Phase 3 — E2E coverage (standard mode, only on a full clean run) --
// outcome is DONE only past the no-op gate above, so E2E never runs over a no-op
// and cannot inflate the (already-taken) file count.
let e2e = null
if (mode === 'standard' && outcome === 'DONE') {
  phase('E2E coverage')
  e2e = await agent(
    `${STANDING}\n\nThe iteration completed. Identify 1–3 invariants worth protecting and write the smallest ` +
      'E2E fixtures for them in the project\'s canonical fixture form; each test\'s doc comment names the property ' +
      'it protects. Run the project\'s test command — all green. Leave edits unstaged; never commit.\n\n' +
      `iter_id: ${iter_id}\nshipped: ${completed.map((c) => `#${c.id} ${c.title}`).join('; ')}`,
    { agentType: 'tester', model: 'sonnet', effort: 'high', label: 'e2e', phase: 'E2E coverage', schema: E2E_SCHEMA },
  )
}

// E2E status is load-bearing (issue #12, facet 3): the phase was previously
// dispatched but only its `fixtures` were read, so a tester that returned a
// non-DONE status or wrote zero fixtures silently left the iteration reading
// DONE with no protecting test. Surface it as a concern (never a gate — the
// coverage gap is the orchestrator's call, not a reason to fail a green run).
const e2eConcerns = []
if (e2e) {
  if (e2e.status && e2e.status !== 'DONE') {
    e2eConcerns.push(
      `E2E coverage did not complete cleanly (status ${e2e.status})` +
        (e2e.note ? `: ${e2e.note}` : '') +
        " — verify the iteration's invariants are actually protected",
    )
  } else if (!(e2e.fixtures && e2e.fixtures.length)) {
    e2eConcerns.push('E2E coverage reported DONE but added no fixtures — the iteration shipped without a protecting test')
  }
}

// ---- Phase 4/5 — finalize: stats.json always, BLOCKED.md on non-DONE ----
phase('Report')
// A clean-tree no-op (mini or standard) gets NO BLOCKED.md (issue #12 /
// consistency): there is no dirty tree to explain, so the status + reason ride
// the end-report. `noopClean` was set by whichever no-op gate fired above.
const writeBlockedMd = outcome !== 'DONE' && !noopClean
const aggregate = {
  iter_id,
  mode,
  started_from: startSha,
  outcome,
  tasks_total: tasks.length,
  tasks_completed: completed.length,
  task_summaries: results.map((r) => ({ id: r.id, title: r.title, outcome: r.outcome })),
  concerns: [...results.flatMap((r) => r.concerns || []), ...e2eConcerns],
  blocked_detail: blocked
    ? { task: blocked.id, reason: blocked.reason, detail: blocked.detail || null }
    : synthBlock,
}

const fin = await agent(
  `${STANDING}\n\nFinalize an implement iteration. Using the aggregate below:\n` +
    '1. Write a stats file at `/tmp/iter-' + iter_id + '/stats.json` (or under the project stats dir if its facts ' +
    'declare one) containing: iter_id, date (from `date +%F`), mode, outcome, tasks_total, tasks_completed, and ' +
    'blocked_reason (or null).\n' +
    (!writeBlockedMd
      ? '2. Do NOT write BLOCKED.md — ' +
        (outcome === 'DONE' ? 'this run is DONE.\n' : 'this is a clean-tree no-op; there is nothing to explain.\n')
      : '2. Write `BLOCKED.md` at the repo ROOT (uncommitted by convention; never staged). Sections: a `# BLOCKED — ' +
        'iter ' + iter_id + '` header with Date/Started-from/Status/Tasks-completed, `## What ran` (one line per DONE ' +
        'task), `## What did not` (the blocked task, its reason, and a one-line suggested next step), `## Concerns`, ' +
        'and `## Files touched` (from `git status --porcelain`).\n') +
    'Report the stats path and whether you wrote BLOCKED.md. Do NOT commit anything.\n\nAGGREGATE:\n' +
    JSON.stringify(aggregate, null, 2),
  { model: 'sonnet', effort: 'medium', label: 'finalize', phase: 'Report', schema: FINALIZE_SCHEMA },
)

// The no-op verdict was already taken before finalize (the tree-check / mini-verify
// gates set outcome + synthBlock + aggregate.blocked_detail), so the end-report
// just relays the final outcome. files_touched comes from the standard-mode
// tree-check (git status --porcelain, untracked-aware); it is null for mini /
// PARTIAL / BLOCKED, where the orchestrator reads BLOCKED.md and inspects the tree.

// ---- End-report — the orchestrator reads this, inspects the tree, commits.
return {
  status: outcome,
  iter_id,
  mode,
  started_from: startSha,
  tasks_total: tasks.length,
  tasks_completed: completed.length,
  task_summaries: aggregate.task_summaries,
  concerns: aggregate.concerns,
  e2e_fixtures: e2e ? e2e.fixtures || [] : [],
  stats_path: fin ? fin.stats_path : null,
  blocked_md: fin && fin.wrote_blocked_md ? 'BLOCKED.md (uncommitted)' : null,
  files_touched: treeState ? treeState.files_touched : null,
  blocked_detail: aggregate.blocked_detail,
}