S00-012: Record blocked task and remediation handoff

Changes: Preserve incomplete work and blocker metadata for S00-012. This checkpoint does not mark implementation accepted.
Validation: Session ended with status blocked.
Blocker: 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.

Task: S00-012
Agent: manual-ci-cd-stdin-20261015b
Role: ci-cd
Action: escalate
Status: blocked

Task title: Fix runner prompt delivery after partial stdin timeout

state/issues/S00-002-manual-security-stdin-20261015a.json

@@ -0,0 +1,30 @@
+{
+  "title": "Fix runner prompt delivery after partial stdin timeout",
+  "reason": "Reviewer startup hangs waiting for stdin EOF: runner retries communicate(None) after a .2s partial-write timeout. Reproduced with delayed stdin reader and 80000-byte payload on Python 3.9.6; no S00-002 acceptance review was performed.",
+  "reproduction": "state/evidence/S00-002-manual-security-stdin-20261015a.md",
+  "role": "ci-cd",
+  "reviewer_role": "qa",
+  "scope": [
+    "scripts/runner.py",
+    "tests/tooling/test_automation.py"
+  ],
+  "outcome": "Reliable complete prompt delivery under startup delay and pipe backpressure, preserving runner lifecycle guarantees.",
+  "steps": [
+    "Read diagnostic evidence and reproduce delayed-reader partial-write timeout without launching a model.",
+    "Fix only runner stdin delivery; retain fresh sessions, prompt budget, terminal-transition monitoring, timeout and process-tree cleanup.",
+    "Add a deterministic delayed-reader large-prompt regression check and run focused runner tests plus make check.",
+    "Record evidence/handoff/commit message and submit for independent review."
+  ],
+  "acceptance": [
+    "A delayed stdin reader receives the complete large UTF-8 prompt and EOF without hanging.",
+    "Timeout and terminal-transition process cleanup still work; no background source-writing descendants remain.",
+    "Existing runner/tooling checks pass; no task scope, spec snapshots or product implementation is changed."
+  ],
+  "checks": [
+    "Delayed-reader large UTF-8 prompt regression.",
+    "Existing runner timeout, transition, scope and fresh-session tests.",
+    "make check"
+  ],
+  "depends_on": [],
+  "requires_user_input": false
+}

state/issues/S00-012-manual-ci-cd-stdin-20261015b.json

@@ -0,0 +1,30 @@
+{
+  "title": "Bound oversized S21-006 runner context without truncating requirements",
+  "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.",
+  "reproduction": "python3 -m unittest discover -s tests/tooling -p test_automation.py -v: 22 pass, one prompt-budget error. Read-only Runner(max_prompt_chars=90000).prompt for S21-006 also errors. Evidence: state/evidence/S00-012-manual-ci-cd-stdin-20261015b.md",
+  "role": "ci-cd",
+  "reviewer_role": "qa",
+  "scope": [
+    "scripts/runner.py",
+    "tests/tooling/test_automation.py"
+  ],
+  "outcome": "All task prompts fit the existing configured budget with exact relevant requirements retained and no silent truncation.",
+  "steps": [
+    "Inspect S21-006 prompt inputs and identify unnecessary duplication or overly broad context loading.",
+    "Implement one bounded context-preparation correction while preserving assignment instructions and exact relevant requirements; retain stdin transport changes.",
+    "Add focused regression for the real oversized context and run existing prompt-budget checks and make check.",
+    "Record evidence/handoff/message and submit for independent review."
+  ],
+  "acceptance": [
+    "S21-006 and all current task prompts fit the existing 80000-character limit.",
+    "Exact required context is retained; no spec snapshot edits, silent truncation or validation suppression.",
+    "stdin delivery, timeout and terminal-transition regression checks remain passing; make check passes."
+  ],
+  "checks": [
+    "Existing FoundationRunnerTests all-current-prompts budget check.",
+    "Delayed UTF-8 stdin delivery and runner lifecycle tests.",
+    "make check"
+  ],
+  "depends_on": [],
+  "requires_user_input": false
+}