// 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. // • 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. // // Carrier — passed as the Workflow `args` object by the orchestrator: // mode: 'standard' | 'mini' // iter_id: e.g. 'ct.2.3' (standard) or 'bugfix-' / 'feat-' (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' 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: 'E2E coverage' }, { title: 'Report' }, ], } const { mode = 'standard', iter_id, plan_path, task_range = null, red_test_path, cause_summary, constraint = 'minimal change, no surrounding cleanup', } = args || {} 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' } }, }, } const TASKS_SCHEMA = { type: 'object', additionalProperties: false, required: ['tasks'], properties: { tasks: { type: 'array', items: { 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' }, }, }, }, }, } const IMPL_SCHEMA = { type: 'object', additionalProperties: false, required: ['status', 'summary'], properties: { status: { type: 'string', enum: ['DONE', 'DONE_WITH_CONCERNS', 'NEEDS_CONTEXT', 'BLOCKED'] }, summary: { type: 'string', description: 'one line: what changed (paths + functions)' }, concerns: { type: 'array', items: { type: 'string' } }, reason: { type: 'string', description: 'on BLOCKED/NEEDS_CONTEXT: the blocker' }, }, } 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'], properties: { status: { type: 'string', enum: ['approved', 'changes_requested', 'infra_blocked'] }, issues: { type: 'array', items: { type: 'string' }, description: 'Important + Minor only (Nits never gate)' }, }, } 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' }, }, } const FINALIZE_SCHEMA = { type: 'object', additionalProperties: false, required: ['stats_path', 'wrote_blocked_md'], properties: { stats_path: { type: 'string' }, wrote_blocked_md: { type: 'boolean' }, files_touched: { type: 'integer' }, }, } // ---- 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.', { 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: ${constraint}`, }, ] } else { const extracted = await agent( `${STANDING}\n\nRead the plan at ${plan_path}. Extract ` + (task_range ? `tasks ${task_range[0]}..${task_range[1]} (inclusive, 1-based)` : 'every task') + ', each as its VERBATIM block with the task id and a one-line title. Do not summarise or reorder. Do not edit anything.', { label: 'plan-extract', phase: 'Per-task loop', schema: TASKS_SCHEMA }, ) if (!extracted || !extracted.tasks || extracted.tasks.length === 0) { return { status: 'NEEDS_CONTEXT', iter_id, reason: `no tasks extracted from ${plan_path}` } } tasks = extracted.tasks } // ---- Phase 2 — per-task loop (sequential) ------------------------------ phase('Per-task loop') async function runTask(task) { // 2.1 — implementer phase const impl = await agent( `${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', 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: ${impl.reason || ''}` } const concerns = impl.concerns || [] // 2.2 — spec-compliance check (gated before quality), with repair re-loop for (let round = 0; ; round++) { const spec = await agent( `${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', label: `spec:${task.id}`, phase: 'Per-task loop', schema: SPEC_SCHEMA }, ) if (spec && spec.status === 'compliant') break if (spec && spec.status === 'unclear') return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: 'spec-ambiguous', detail: spec.ambiguity } if (round >= 2) return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: 'review-loop-exhausted (spec-compliance)' } // repair: re-dispatch the implementer with the review findings as the repair brief await agent( `${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- ${(spec?.findings || ['(none reported)']).join('\n- ')}`, { agentType: 'implementer', label: `impl-fix-spec:${task.id}`, phase: 'Per-task loop', schema: IMPL_SCHEMA }, ) } // 2.3 — quality check, with repair re-loop for (let round = 0; ; round++) { const qual = await agent( `${STANDING}\n\nQuality review of task ${task.id} (spec-compliance is already green — do not re-check it). ` + 'Read every chunk of `git diff HEAD` in this task\'s footprint. Report only Important and Minor issues; ' + 'Nits never gate.', { agentType: 'quality-reviewer', label: `qual:${task.id}`, phase: 'Per-task loop', schema: QUAL_SCHEMA }, ) if (qual && qual.status === 'approved') break if (round >= 2) return { id: task.id, title: task.title, outcome: 'BLOCKED', reason: 'review-loop-exhausted (quality)' } await agent( `${STANDING}\n\nFix the quality issues on task ${task.id}. Address EACH Important/Minor issue; do not widen ` + 'scope. Keep build + tests green; leave edits unstaged.\n\nISSUES:\n- ' + (qual?.issues || ['(none reported)']).join('\n- '), { agentType: 'implementer', label: `impl-fix-qual:${task.id}`, phase: 'Per-task loop', schema: IMPL_SCHEMA }, ) } return { id: task.id, title: task.title, outcome: 'DONE', concerns } } 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' // ---- Phase 3 — E2E coverage (standard mode, only on a full clean run) -- 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} ${c.title}`).join('; ')}`, { agentType: 'tester', label: 'e2e', phase: 'E2E coverage', schema: E2E_SCHEMA }, ) } // ---- Phase 4/5 — finalize: stats.json always, BLOCKED.md on non-DONE ---- phase('Report') const aggregate = { iter_id, mode, started_from: startSha, outcome, tasks_total: tasks.length, tasks_completed: completed.length, task_summaries: results.map((r) => ({ id: r.id, title: r.title, outcome: r.outcome })), concerns: results.flatMap((r) => r.concerns || []), blocked_detail: blocked ? { task: blocked.id, reason: blocked.reason, detail: blocked.detail || null } : null, } const fin = await agent( `${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' + (outcome === 'DONE' ? '2. Do NOT write BLOCKED.md — this run is DONE.\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 diff --name-only HEAD`).\n') + 'Report the stats path, whether you wrote BLOCKED.md, and the count from `git diff --name-only HEAD | wc -l`. ' + 'Do NOT commit anything.\n\nAGGREGATE:\n' + JSON.stringify(aggregate, null, 2), { label: 'finalize', phase: 'Report', schema: FINALIZE_SCHEMA }, ) // ---- 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: fin ? fin.files_touched : null, blocked_detail: aggregate.blocked_detail, }