A live run died at map_criteria: one heavy criterion exhausted
max_iterations (10) with no fallback and sank the whole 17-criterion
review. check_criterion now has a 30-iteration budget, a tool-budget
instruction, and falls back to criterion_fault, which records a
schema-shaped UNMET verdict with a PIPELINE-FAULT evidence marker for
that one criterion; verdict.py renders it as DIED rather than judged.
R3 guards: parse_request (crash → ask_topic), bootstrap_research,
combine_findings (crash → fault-text findings; also lifts branch-local
PIPELINE-FAULT findings into pipeline_faults, deduped), reflexion_gate
(crash fails forward to synthesize), incorporate_feedback (crash still
loops with a generic feedback note), verify_sources (top-level guard +
pipeline_notes fold).
Fallbacks per the plan's naming pins: plan → plan_fault → end_fault
(fail-closed; gains state_updates plan_failure per the TASK-016 rule);
research_one_question → branch-local question_fault (map collects the
fault finding); vet_sources/critique → degrade-visibly markers that
continue to the stage each node's own next pointed to; synthesize →
synth_fault → end_fault. end_fault renders
'DEEP_RESEARCH FAILED — PIPELINE-FAULT: <fault text>'.
Accepted-path visibility: verify_sources folds pipeline_faults into
pipeline_notes ('' when fault-free), appended to end_accepted's output
and the approval question — happy-path output stays byte-identical.
initial_state seeds questions: [] so a dying plan inside the static
fan-out leaves the sibling knowledge_lookup lane mapping over zero
items while end_fault renders.
R5: 19 python3-guarded regression tests + GraphParser wiring test;
bundled warning baseline unchanged.
- prompts.rs DEFAULT_SPAWN_INSTRUCTIONS: example IDs task_1/task_2 -> "1"/"2"
(real numeric-string IDs; old format silently produced dep_error + unblocked
task), plus task-queue rules: root tasks with agent are never auto-dispatched,
task_complete is what dispatches dependents, auto-dispatched agents must be
collected, failed tasks permanently block dependents.
- architect config: optional task-queue mirroring guidance for parallel mode
(disk task files stay the durable store; queue is in-memory).
- sisyphus config: short note on encoding dependency-shaped bursts as
agent__task_create chains; todos remain the tracking source of truth.
The three fallback-capture keys (orient_failure, sweep_failure,
handoff_failure) were write-only dead state: captured on LLM-node failure
but interpolated nowhere, so end_failure rendered an empty STEP_FAILED
shell and write_handoff carried no trace a dead sweep.
- new crash-proof script node note_llm_fault distills orient/handoff
'LLM node...' failure text into fault_note (prefix-anchored; empty when
neither key holds a fault); orient and write_handoff fallbacks now route
through it before end_failure
- end_failure renders 'Pipeline fault (if any): {{fault_note}}' (sentinel
and all existing fields preserved; fault_note defaulted in initial_state)
- write_handoff prompt interpolates {{sweep_failure}} with a
PIPELINE-FAULT VISIBILITY instruction mirroring the review_report
treatment (fault -> Deviations entry + step_summary; success/empty
ignored)
- tests: note_llm_fault fault/clean/crash/truncation paths via the
GRAPH_STATE harness; wiring test pins the retargeted fallbacks,
note_llm_fault routing, {{fault_note}} in end_failure, and the
sweep-fault prompt/instruction anchors; warning baseline unchanged
finding-verifier: parse gains max_attempts 2 + parse_failure capture +
fallback to a new parse_fault marker that rewrites verdicts to a single
UNVERIFIABLE PIPELINE-FAULT entry and continues to done (sentinel
preserved — the caller's verify lane degrades instead of dying);
verify_one gains a branch-local verify_fault marker normalizing the
engine failure text into a schema-conformant UNVERIFIABLE verdict.
step-runner: implement gains fallback end_failure (no retry — reruns
against a mutated tree are unsafe; STEP_FAILED renders the failure via
coder_result); independent_review gains fallback write_handoff with the
handoff instructions and route_review treating an "Agent node failed:"
review_report as review-did-not-run (fail-visible, guard ahead of the
🔴 grep); orient/edge_case_sweep/write_handoff capture their failure
text via state_updates, shrinking the bundled fallback-capture warning
baseline back to zero.
R5 tests: fault-marker normalization + crash paths (raw non-JSON
GRAPH_STATE), route_review.sh fault/critical/clean routing via bash+jq,
and structural wiring tests pinning fallbacks, sentinels, and
end_failure's initial_state-backed template keys.
render.py's empty-diff stub bypass is anchored on the 'PIPELINE-FAULT:'
prefix in reason/attention, but verdict.py's crash guard emitted
'verdict computation error: …' / 'verdict script error: …' without it —
on an empty diff a crashed verdict gate collapsed into the
'No changes to review.' stub and the fail-closed NEEDS-HUMAN verdict
never reached the final report.
- prefix the crash-guard reason and attention entry with PIPELINE-FAULT:
- strengthen the existing crash test to assert the prefix on both fields
- add R5 chained test: empty diff + crash-inducing state piped
verdict.py -> render.py must render the fault, never the stub
- add crash-guard symmetry tests for parse_fault.py / aux_fault.py
(raw non-JSON GRAPH_STATE keeps the fault marker) and a test that a
fault survives the attention[:5] cap alongside 6 user flags
Every llm/agent stage that can die persistently now falls back to a
machine-readable PIPELINE-FAULT sentinel instead of killing the graph:
- review_domain -> branch-local domain_fault marker (banner-prefixed
domain_report the map collects; completeness_gate precedent)
- verify -> verdict (verifier fault renders findings unverified + a
PIPELINE-FAULT attention line)
- parse -> parse_fault -> render (complete NEEDS-HUMAN verdict_out;
render's no-changes stub is bypassed for fault verdicts)
- refine_groups -> cover_gate (deterministic-proposal fallback absorbs
the failure; degradation noted in groups_note)
- aux_lanes -> aux_fault -> synthesize (aux_note fault marker; visible,
never blocking - aux is enrichment)
- synthesize -> verdict (synth_failure marker; keyed off the failure
prefix + non-empty diff, never findings==[], so clean zero-finding
reviews stay MERGE-READY)
verdict.py gains unified fault accounting (R2): any PIPELINE-FAULT in
domain_reports / verifier_output / state fault keys forces NEEDS-HUMAN,
prefix-anchored so a report merely quoting the marker mid-text never
trips it; old 'PIPELINE FAULT' spelling migrated. Faults are prepended
to attention so the [:5] cap can never hide one. Dedicated *_failure
state keys capture engine failure text on every fallback+output_schema
node, keeping the bundled warning baseline at zero.
15 python3-guarded R5 tests: fault paths, quoted-marker precedence,
happy-path byte-compat regression, marker normalization, crash-path
fail-closed (verdict/cover_gate/domain_fault), verifier-fault-on-empty-
diff render, and the no-changes stub regression.
Adversary finding 1: verdict_gate treated any lane report CONTAINING
'PIPELINE-FAULT:' as a lane fault, so a real review quoting the marker
silently bypassed red-finding counting and sentinel parsing. Lane-fault
detection is now precise — only a report that IS the lane_fault.py
marker (starts with it) routes to the fault rule. Adds the missing
regression tests: reds block despite MERGE-READY, NEEDS-HUMAN without
reds passes with attention, probe INCONCLUSIVE blocks with the
environment note, a gate crash fails closed, and a quoting report is
routed to the red rule, not the fault rule.
Adversary finding 2: default_lanes overwrote caller-forced lanes and
dropped the security lane the deterministic signals guaranteed. The
fallback now unions its defaults with caller-forced lanes (canonicalized
via the same aliases build_items uses) and forces security on
auth/deps/exec signals or hardened posture — selection degrades wider,
never narrower, and stays deterministic via a fixed lane order. Tests
cover forced-lane survival, alias canonicalization, unknown-name
tolerance, each security signal, and determinism.
- lane_fault.py + fallback on all four run_* lane nodes: an agent-node
failure is normalized into a PIPELINE-FAULT lane result instead of
killing the graph
- verdict_gate.py: PIPELINE-FAULT lane results block distinctly from
SKIPPED and missing-sentinel; a PIPELINE-FAULT in signals_error blocks
at the gauntlet level
- build_items.py: restructured into main() + fail-closed guard (crash
emits empty lanes + PIPELINE-FAULT) and folds lanes_degraded into
lanes_summary
- parse: state_updates/fallback -> parse_fault.py, which records the
fault in signals_error and jumps to the verdict gate
- select_lanes: state_updates/fallback -> default_lanes.py, a
deterministic wider-never-narrower lane fallback
- verification_commands threaded through parse into run_adversary's
prompt (declared-only, never invented)
- run_probe prompt gains the aborted-attempt reconcile line
- 8 gauntlet_* R5 tests in src/config/request_context.rs (script harness
+ graph interpolation)
Adversary conformance-review fixes for the TASK-017 exec-evidence stage:
- run_checks.py: total-runtime deadline (3300s = node timeout minus margin);
each command gets min(900s, remaining budget), commands past the deadline
are recorded as {cmd, skipped: deadline} entries so in-script handling
stays authoritative instead of the node timeout killing the script from
outside. POSIX hardening: per-command process group (start_new_session)
+ killpg on timeout so hung grandchildren cannot linger; non-POSIX
limitation documented in the docstring.
- graph.yaml: run_checks gains fallback: pipeline_fault; check_criterion
treats SKIPPED records as at-best PARTIAL (unproven, never failed).
- pipeline_fault.py: run_checks-stage attribution grounded in real engine
behavior (script-node fallback writes nothing into state, executor.rs
script arm) — nonempty diff_text proves facts completed, so the fault is
the verification runner; emits 'PIPELINE-FAULT: verification runner
killed'. Empty diff_text still attributes to diff resolution.
- verdict.py: renders skipped records as [SKIPPED] instead of a bogus
[FAIL] exit-? line; non-degraded verdict semantics untouched.
- tests: outer-except ENVIRONMENT degradation, deadline timeout+skip (env
seam ADVERSARY_RUN_CHECKS_DEADLINE_SECS), pipeline_fault stage
attribution (parse / facts / run_checks), check_criterion prompt cites
{{exec_results}}, verdict SKIPPED rendering; run_adversary_script_env
helper for env-carrying invocations.
- cargo fmt violations in 3d7dea9 test code fixed (fmt --check exit 0).
An llm node never persists its completion under `output` (the binding
is transient), so a map branch without state_updates collected the
stale inherited value: deep-research produced `None` findings and
finding-verifier errored on its first item because `output` was absent.
Both maps now declare an explicit output_key and their branch nodes
write it via state_updates. graph.example.yaml's research_subject gets
the same named-key pattern and its branch comment describes it.
Design: plans/map-subgraph-branches-design.md §2.6, §3.7 (C9).
sisyphus: Quality bar line in the code-reviewer spawn prompt (omitted when
the task prompt carried none); rigor-aware WARNING handling with
(deferred by quality bar) FOLLOW-UPS tagging; evidence-cited rejection
protocol for [convention] findings (repo convention at file:line or a
recorded plan decision; never for CRITICAL/[correctness]; escalate on
re-raise); rigor-to-posture default map for security-reviewer spawns.
architect: Phase B quality-bar round + other:<label> librarian lane;
Phase E Sisyphus CONTEXT and adversary prompts carry rigor/surfaces and
the plan's Quality bar excerpt; task-close logs rejected-finding lines;
Phase F PR body gains the Quality bar line and Review decisions section;
two new anti-patterns (bare rejections, rigor suppressing CRITICAL).
Three new read-only review skills under assets/skills/, mirroring the
transactional-integrity canon: frontmatter load triggers, read-only
enabled_tools, production-bar severity checklists with
[convention]/[correctness] markers, marker-semantics and
orchestrator-linter paragraphs, and aspect-boundary lists.
rest-api-review includes gRPC and GraphQL sections.
Two long-standing agent-facing defects:
1. bash -e aborted the model's script at the first intermediate
non-zero status (grep with no matches exits 1, inspecting a failing
test run, a probing subshell), so trailing guards like '; exit 0'
never executed and output was partially or entirely lost. Dropped
-e: the last statement now decides the exit code, matching the
interactive-shell semantics models expect. pipefail is kept so a
failing pipeline stage still surfaces in the exit code.
2. Only stdout was redirected into $LLM_OUTPUT, and the harness
returns just $LLM_OUTPUT on success, so commands whose useful
output goes to stderr (git push, cargo progress, curl -v) returned
empty on success. Added 2>&1.
- Extend the injected Background Jobs prompt guidance: system_notifications
push on completion, collect-only-when-idle wait protocol, and the graph
LLM-node collect-before-final-turn rule
- Mention the system_notifications push in the agent spawning guidance and
in the sisyphus/architect wait-protocol text (agent completions push
notifications too)
- config.example.yaml: max_concurrent_jobs (default 5, 0 = disabled)
- README: features-list entry pointing at the Background-Jobs wiki page
Dark-Alex-17
github-actions[bot]