S00-013: Bound runner prompts with explicit required task input reads

Changes: Keep startup instructions and exact context packets inline while listing supplementary task inputs as mandatory project reads. Preserve root containment, missing-artifact guidance and budget failures. Add S21-006 exact UI context regression and cover claim/review budgets for all tasks; leave stdin delivery unchanged.
Validation: make check passed all 68 tests, including delayed UTF-8 stdin/EOF, timeout and terminal-transition checks. All 556 current prompts fit 80000 characters; largest 77693. git diff --check passed. Foundation checks do not establish application readiness.

Task: S00-013
Agent: auto-ci-cd-5f68f03dd33b
Role: ci-cd
Action: claim
Status: review

Task title: Bound oversized S21-006 runner context without truncating requirements

planning/TASK_MATRIX.md

@@ -1,6 +1,6 @@
 # Матрица задач
 
-Generated; state revision **14**. Canonical status: state/tasks.json.
+Generated; state revision **16**. Canonical status: state/tasks.json.
 
 | ID | Этап | Оператор | Reviewer | Статус | Owner | Зависимости | Задача |
 | --- | --- | --- | --- | --- | --- | --- | --- |
@@ -15,7 +15,7 @@ Generated; state revision **14**. Canonical status: state/tasks.json.
 | [S00-009](tasks/S00-009.md) | S00 | orchestrator | security | todo |  | S00-003, S00-004, S00-005, S00-006, S00-007, S00-008 | Согласовать результаты spikes |
 | [S00-011](tasks/S00-011.md) | S00 | ci-cd | security | done | auto-ci-cd-d105e8027730 | S00-001 | Restore verified npm registry access for the stack spike |
 | [S00-012](tasks/S00-012.md) | S00 | ci-cd | qa | blocked | manual-ci-cd-stdin-20261015b | S00-001, S00-011, S00-013 | Fix runner prompt delivery after partial stdin timeout |
-| [S00-013](tasks/S00-013.md) | S00 | ci-cd | qa | todo |  | S00-001, S00-011 | Bound oversized S21-006 runner context without truncating requirements |
+| [S00-013](tasks/S00-013.md) | S00 | ci-cd | qa | review | auto-ci-cd-5f68f03dd33b | S00-001, S00-011 | Bound oversized S21-006 runner context without truncating requirements |
 | [S00-010](tasks/S00-010.md) | S00 | qa | orchestrator | todo |  | S00-001, S00-002, S00-003, S00-004, S00-005, S00-006, S00-007, S00-008, S00-009 | Gate: Профиль и проверка стека |
 | [S01-001](tasks/S01-001.md) | S01 | orchestrator | security | todo |  | S00-010 | Описать identity/model contracts |
 | [S01-002](tasks/S01-002.md) | S01 | orchestrator | security | todo |  | S00-010, S01-001 | Описать async account context |

planning/stages/S00.md

@@ -17,7 +17,7 @@
 - [S00-009](../tasks/S00-009.md): Согласовать результаты spikes — orchestrator; todo.
 - [S00-011](../tasks/S00-011.md): Restore verified npm registry access for the stack spike — ci-cd; done.
 - [S00-012](../tasks/S00-012.md): Fix runner prompt delivery after partial stdin timeout — ci-cd; blocked.
-- [S00-013](../tasks/S00-013.md): Bound oversized S21-006 runner context without truncating requirements — ci-cd; todo.
+- [S00-013](../tasks/S00-013.md): Bound oversized S21-006 runner context without truncating requirements — ci-cd; review.
 - [S00-010](../tasks/S00-010.md): Gate: Профиль и проверка стека — qa; todo.
 
 ## Граница этапа

planning/task_matrix.csv

@@ -10,7 +10,7 @@ S00-008,S00,ci-cd,qa,todo,,"S00-003, S00-004",Описать WSS/upload/TURN/pus
 S00-009,S00,orchestrator,security,todo,,"S00-003, S00-004, S00-005, S00-006, S00-007, S00-008",Согласовать результаты spikes
 S00-011,S00,ci-cd,security,done,auto-ci-cd-d105e8027730,S00-001,Restore verified npm registry access for the stack spike
 S00-012,S00,ci-cd,qa,blocked,manual-ci-cd-stdin-20261015b,"S00-001, S00-011, S00-013",Fix runner prompt delivery after partial stdin timeout
-S00-013,S00,ci-cd,qa,todo,,"S00-001, S00-011",Bound oversized S21-006 runner context without truncating requirements
+S00-013,S00,ci-cd,qa,review,auto-ci-cd-5f68f03dd33b,"S00-001, S00-011",Bound oversized S21-006 runner context without truncating requirements
 S00-010,S00,qa,orchestrator,todo,,"S00-001, S00-002, S00-003, S00-004, S00-005, S00-006, S00-007, S00-008, S00-009",Gate: Профиль и проверка стека
 S01-001,S01,orchestrator,security,todo,,S00-010,Описать identity/model contracts
 S01-002,S01,orchestrator,security,todo,,"S00-010, S01-001",Описать async account context

scripts/runner.py

@@ -121,17 +121,27 @@ The coordinator commits each transition before launching another agent.
 '''
         paths = ['AGENTS.md', 'README.md', 'master_prompt.md', 'roles/common.md', f'roles/{item["role"]}.md',
                  'docs/WEB_PROFILE.md', 'docs/ARCHITECTURE.md', 'docs/CONTRACTS.md', 'docs/WORKFLOW.md', 'docs/AUTOMATION.md']
-        # Only bounded, concrete referenced upstream artifacts, never the entire repository.
+        # Task-specific inputs are explicit required reads, rather than whole
+        # documents duplicated beside the exact requirements in the packet.
+        # Keep startup instructions inline for every fresh session.
+        required_reads = []
         for raw in task['inputs']:
             candidate = raw.split(' (')[0]
-            if candidate not in paths and (self.root / candidate).is_file():
-                paths.append(candidate)
+            if not (self.root / candidate).resolve().is_relative_to(self.root):
+                raise ValueError('Prompt input escapes project root')
+            if candidate not in paths:
+                required_reads.append(raw)
         row = tracker.state()['tasks'][item['id']]
         if row.get('handoff'):
             paths.append(row['handoff'])
         if item['action'] == 'review' and row.get('evidence'):
             paths.append(row['evidence'])
         chunks = [assigned]
+        if required_reads:
+            chunks.append('\n# Required task input reads (not inlined)\n\n'
+                          'Before implementation or review, read these task inputs from the project. '
+                          'Their contents are not included in this prompt; a missing required artifact is a blocker.\n\n'
+                          + '\n'.join('- ' + raw for raw in required_reads))
         for rel in dict.fromkeys(paths):
             path = (self.root / rel).resolve()
             if not path.is_relative_to(self.root):

state/commit_messages/auto-ci-cd-5f68f03dd33b.txt

@@ -0,0 +1,4 @@
+Bound runner prompts with explicit required task input reads
+
+Changes: Keep startup instructions and exact context packets inline while listing supplementary task inputs as mandatory project reads. Preserve root containment, missing-artifact guidance and budget failures. Add S21-006 exact UI context regression and cover claim/review budgets for all tasks; leave stdin delivery unchanged.
+Validation: make check passed all 68 tests, including delayed UTF-8 stdin/EOF, timeout and terminal-transition checks. All 556 current prompts fit 80000 characters; largest 77693. git diff --check passed. Foundation checks do not establish application readiness.

state/evidence/S00-013-auto-ci-cd-5f68f03dd33b.md

@@ -0,0 +1,27 @@
+# S00-013 executor evidence
+
+Agent: auto-ci-cd-5f68f03dd33b; role: ci-cd; date: 2026-10-15.
+Result: bounded context preparation; pending independent QA review.
+
+Input: assigned task/card/context, NFR-007, workflow/role instructions, S00-012/013 blocker reports, accepted scope ADR and S00-001/S00-011 dependency evidence/reviews/handoffs. Output: one runner context correction and focused regressions. No contracts or stack decisions changed.
+
+## Actual change and reasoning
+
+S21-006 packet is 41660 characters and includes all 26 exact UI Kit sections. The old runner additionally embedded entire input documents, including the 11760-character stack ADR. Startup documents plus this packet and task inputs exceeded the 80000-character budget.
+
+Runner now keeps assignment/startup instructions, exact packet, previous handoff and review evidence inline. Other task inputs are listed explicitly as required project reads before implementation/review, preserving their path annotations and missing-artifact blocker instruction. This also makes missing upstream inputs visible instead of silently omitting them. Project-root path checking remains enforced for referenced inputs. No text is sliced, no spec/packet is edited, and both packet and prompt budget guards remain active. The stdin transport implementation is untouched.
+
+The S21-006 regression checks both executor and reviewer prompts, the whole exact packet, every verbatim UI Kit section, required input references and fresh-session/exit instructions. The all-current-prompts check now covers both actions for every task.
+
+## Actual commands and results
+
+- `python3 scripts/tasks.py resume --agent auto-ci-cd-5f68f03dd33b` and `show S00-013`: exit 0; already assigned in_progress, no repeat claim.
+- `python3 scripts/tasks.py packet S00-013 --agent auto-ci-cd-5f68f03dd33b > /private/tmp/luma-S00-013-packet.md`: exit 0.
+- Initial automation run of the first draft: exit 1, 23/24 tests passed; review prompt still exceeded budget when only upstream-annotated artifacts were deferred. Corrected by consistently referencing all supplementary task inputs, keeping startup instructions inline.
+- Read-only Python enumeration using Runner with default config: exit 0; all 556 claim/review prompts for 278 tasks fit; largest S21-006 review 77693 characters, claim 77669 (agent auto-preview).
+- `make check`: exit 0, 68 tests passed. Final rerun after project-root guard: exit 0, 68 tests in 16.124s; validated 278 tasks, 22 stages, 221 requirements, 211 allocated Web requirements, revision 15. Includes delayed large UTF-8 stdin/EOF delivery, timeout, terminal-transition, orchestration, snapshot and CLI checks. Log: temporary /private/tmp/luma-S00-013-check.log.
+- `git diff --check`: exit 0; source diff inspected, limited to scripts/runner.py and tests/tooling/test_automation.py. Initial state/tasks.json change was coordinator claim metadata.
+
+## Limits
+
+These are foundation/harness checks, not app readiness or S00-002 acceptance. Agents must actually read the explicitly listed project inputs; references do not claim those artifacts were read automatically. Budget coverage describes current task/state artifacts; future larger evidence/handoffs still fail explicitly rather than truncate. No dependencies, credentials, production transports or immutable spec snapshots changed. Coordinator owns commit and the next fresh reviewer process.

state/handoffs/S00-013.md

@@ -0,0 +1,8 @@
+# S00-013 handoff
+
+Executor: auto-ci-cd-5f68f03dd33b (ci-cd).
+Result: runner references supplementary task inputs as explicit required project reads, retaining startup instructions, exact context packet, handoff and review evidence inline. No truncation or budget increase; stdin transport unchanged.
+
+Ready for QA review. Inspect scripts/runner.py and tests/tooling/test_automation.py, compare commit message/evidence, run `make check`. Focus on S21-006 executor/reviewer preserving all exact requirements and 26 UI Kit sections, explicit read-before-work/missing-artifact instructions, and all-current-prompts budget check (now both actions). All 556 current prompts fit 80000; maximum 77693. Final make check: 68 tests passed, exit 0, including delayed UTF-8 stdin, timeout and terminal-transition checks.
+
+Evidence: state/evidence/S00-013-auto-ci-cd-5f68f03dd33b.md. Task-specific documents remain mandatory reads from disk. Future larger handoffs/evidence remain subject to fail-fast budgets. No app readiness or parent-task acceptance claimed. Reviewer must independently approve/reject; coordinator commits transition and launches next fresh session. Executor does not set done or continue S00-012.

state/tasks.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "revision": 14,
+  "revision": 16,
   "tasks": {
     "S00-001": {
       "status": "done",
@@ -1150,10 +1150,14 @@
       "handoff": "state/handoffs/S00-012.md"
     },
     "S00-013": {
-      "status": "todo",
-      "owner": null,
+      "status": "review",
+      "owner": "auto-ci-cd-5f68f03dd33b",
       "external_wait": false,
-      "reason": null
+      "reason": null,
+      "started_at": "2026-10-14T18:37:37+00:00",
+      "updated_at": "2026-10-14T18:40:32+00:00",
+      "evidence": "state/evidence/S00-013-auto-ci-cd-5f68f03dd33b.md",
+      "handoff": "state/handoffs/S00-013.md"
     }
   },
   "events": [
@@ -1324,6 +1328,29 @@
       "from": "in_progress",
       "to": "blocked",
       "reason": "Required automation suite fails in existing all-prompts budget test: S21-006 exceeds even a diagnostic 90000-character prompt limit. This blocks verification of the stdin remediation; production limit remains 80000."
+    },
+    {
+      "revision": 15,
+      "at": "2026-10-14T18:37:37+00:00",
+      "action": "claim",
+      "task": "S00-013",
+      "agent": "auto-ci-cd-5f68f03dd33b",
+      "role": "ci-cd",
+      "from": "todo",
+      "to": "in_progress",
+      "reason": null
+    },
+    {
+      "revision": 16,
+      "at": "2026-10-14T18:40:32+00:00",
+      "action": "submit",
+      "task": "S00-013",
+      "agent": "auto-ci-cd-5f68f03dd33b",
+      "role": null,
+      "from": "in_progress",
+      "to": "review",
+      "reason": null,
+      "evidence": "state/evidence/S00-013-auto-ci-cd-5f68f03dd33b.md"
     }
   ],
   "retired_agents": [

tests/tooling/test_automation.py

@@ -281,11 +281,37 @@ else:
 
 
 class FoundationRunnerTests(unittest.TestCase):
+    def test_ui_acceptance_prompt_keeps_exact_context_and_explicit_upstream_reads(self):
+        runner = RUN_MODULE.Runner(ROOT, {})
+        task = runner.tracker.task('S21-006')
+        for action, role in [('claim', task['role']), ('review', task['reviewer_role'])]:
+            with self.subTest(action=action):
+                prompt = runner.prompt({'id': task['id'], 'role': role, 'action': action}, 'auto-preview')
+                self.assertLessEqual(len(prompt), 80000)
+                self.assertIn(runner.tracker.packet(task['id'], 'auto-preview'), prompt)
+                self.assertIn('Required task input reads (not inlined)', prompt)
+                self.assertIn('Before implementation or review, read these task inputs', prompt)
+                self.assertIn('a missing required artifact is a blocker', prompt)
+                for raw in task['inputs']:
+                    self.assertIn(raw, prompt)
+                    if ' (upstream artifact' in raw:
+                        self.assertIn('- ' + raw, prompt)
+                        self.assertNotIn('# File: ' + raw.split(' (')[0] + '\n', prompt)
+                # Every UI Kit section stays verbatim, including tables and
+                # unnumbered details beyond the short requirement registry.
+                spec = (ROOT / 'specs/uikit_clear.md').read_text(encoding='utf-8')
+                for section in task['ui_sections']:
+                    self.assertIn(runner.tracker.section(spec, section), prompt)
+                self.assertIn('This is a fresh session.', prompt)
+                self.assertIn('After submit/approve/reject EXIT.', prompt)
+
     def test_all_current_fresh_agent_prompts_fit_configured_budget(self):
         runner = RUN_MODULE.Runner(ROOT, {})
         lengths = []
         for task in runner.tracker.definitions()['tasks']:
-            lengths.append(len(runner.prompt({'id': task['id'], 'role': task['role'], 'action': 'claim'}, 'auto-preview')))
+            for action, role in [('claim', task['role']), ('review', task['reviewer_role'])]:
+                with self.subTest(task=task['id'], action=action):
+                    lengths.append(len(runner.prompt({'id': task['id'], 'role': role, 'action': action}, 'auto-preview')))
         self.assertLessEqual(max(lengths), 80000)
 
     def test_unconfigured_runner_does_not_claim_product_work(self):