run_checks.py SIGKILLs the timed-out command's whole process group so a
backgrounded grandchild cannot outlive the record; nothing proved it.
Add a unix-only test that backgrounds `sleep 30`, records its pid, and
probes `kill -0` after the 1s deadline fires.
TOTAL_DEADLINE_SECS (run_checks.py) and the run_checks node's `timeout:`
(graph.yaml) live in different files and could drift until the node
executor kills the script before its in-script degradation runs. Parse
the script's default and assert it stays strictly below the node
timeout, without hardcoding either value.
Sweep every agent node in the six bundled graphs and assert max_attempts
is exactly 2 (step-runner/implement stays 1) against a pinned node list,
so a dropped `max_attempts:` line cannot silently revert a lane to
one-shot (the serde default is 1). Sweep every llm/agent node for a
declared, existing fallback and pin the specific fault routes in
review-gauntlet, code-reviewer, and adversary.
Pin check_criterion's tool list to fs_read/fs_cat/fs_grep/ast_grep and
its 'judged ONLY against the recorded verification runs' instruction,
so the criterion branch can never grow an execution tool unnoticed.
agent.rs: the retry-after-timeout test ran its second attempt with no
timeout bound, so it passed whether or not the retry owned a fresh
budget. Attempt 2 now runs under the same 1s bounded_attempt and sleeps
900ms under the paused clock; it only succeeds if the deadline is
per-attempt rather than shared with the attempt that already used it.
llm.rs: the `LLM node structured-extraction failed: {e:#}` branch had no
test because `run` cannot succeed without a model. Split the post-run
half of execute into `finish(node, state, ctx, result)` (byte-identical
body, mirrors agent.rs's outcome_from seam) and add tests feeding
Ok("not json") through it, with and without a fallback, asserting the
captured text prefix and the extractor's full context chain.
Node B is the graph's `facts` node (script diff_facts.py), not a node
named diff_facts. criterion_fault has no `next`; it reaches holistic
through the map join, so draw it dashed like the other branch-terminal
edges instead of as a solid successor edge.
Rust test comments/assert messages and deep-research script docstrings
cited numbered requirement labels (R3/R5) and task labels (TASK-016,
TASK-021) that are defined only in an external plan document. Reword
each to say what it means on its own: fail-safe crash guards, the
validator's fallback-capture warning, task-queue anchors.
FIX A: run_checks.py passed no env= to Popen, so verification commands
inherited the live GRAPH_STATE/GRAPH_STATE_FILE. Every suite script's
load_state() prefers GRAPH_STATE_FILE, so when the adversary reviews a repo
whose own tests exec these scripts (this repo's R5 tests) the leaked file
silently overrode the test state -> false failures. Popen now gets an env
with all GRAPH_STATE* keys removed. The five sibling script-test helpers
(review-gauntlet, code-reviewer, finding-verifier, step-runner,
deep-research) gain .env_remove("GRAPH_STATE_FILE") for hermeticity. New
R5 test loads state via GRAPH_STATE_FILE and asserts a shell-neutral
python3 -c probe sees both vars UNSET.
FIX B: the depth check compares the child's absolute depth against the
SPAWNER's own max_agent_depth (root = 0), so under
architect(0)->sisyphus(1)->review-gauntlet(2)->code-reviewer(3) the
code-review lane faulted "Max agent depth exceeded (4/3)". Limits are now
child depth + 1 headroom along the documented chains, with the chain in a
comment next to each key: code-reviewer 3->5, domain-reviewer 2->6,
architecture-reviewer 2->4, step-runner default->4 (explicit),
review-gauntlet stays 4. domain-reviewer's file-reviewer hop is documented
but inert (can_spawn_agents unset) - left unwired by decision; noted in
config and pinned via a DOCUMENTED_BUT_UNWIRED exemption in the new
bundled-config test, which pins every value and asserts per-hop headroom +
reachability along four chains.
The crash-path assertion checked only "PIPELINE-FAULT:"; verdict.py's died() keys on "PIPELINE-FAULT: criterion ", so a regression there would have passed the test yet stopped the crashed marker from rendering as DIED.
A live code-reviewer run degraded through synthesize's fallback; the
graph already retries once (max_attempts: 2) and falls back to verdict
with synth_failure captured, but nothing pinned that wiring. Add the
wiring test so a future edit cannot silently drop the retry or route.
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.
A live code-reviewer run reported "LLM node failed: Failed to call
chat-completions api" with the root cause invisible, because the
state_updates fault text used `{e}` (top context only). Format with
`{e:#}` so fault scripts and warn! logs see the whole anyhow chain.
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).
The adversary conformance review flagged that the fallback warn! at
outcome_from (src/graph/agent.rs:71) was never asserted — only the retry
warn had captured-text coverage. Adds one test installing the shared warn
collector, filtered by the unique node id 'fallback_warn_capture' for
parallel safety, asserting the warn names both the node and the fallback
target and carries the error chain.
Agent nodes gain an optional fallback target with llm-node parity: on any
failure (retries exhausted, hard error, or structured-extraction failure)
the failure chain is written into state as 'Agent node failed: <chain>'
and the chain routes to the fallback node. Without a fallback the error
propagates unchanged. Validator collects agent fallback edges for
missing-target checks, reachability, and map-branch locality.
Hoist the llm node's transient-error matcher to graph::is_transient_error,
extend it with broken-pipe / connection-error / error-sending-request
signatures, and give AgentNode an opt-in max_attempts retry loop with
llm-parity semantics: contexts applied before the transient check, fresh
wall-clock budget per attempt, peer identity (assignment + registry)
re-armed before each retry, retirement exactly once after the final
attempt, and structured extraction outside the loop.
- agent__spawn accepts an optional variables object (string->string);
values overlay the parent-inherited agent variables per key, with
inheritance preserved as the fallback layer
- unknown variable names, non-string values, and non-object shapes
return self-correcting status:error JSON listing the agent's
declared variables
- spawned children can no longer trigger the interactive variable
prompt: a new interactive gate in Agent::init_agent_variables routes
missing required variables to the existing bail path while leaving
CLI/REPL prompting and --info skip semantics unchanged
- agent__task_create persists variables on the task, agent__task_list
echoes them, and task auto-dispatch threads them into the spawn
- tool schemas and built-in spawn docs updated; unit tests extended
in agents.rs and taskqueue.rs
A task aborted before its first poll never runs its body, so a guard
constructed inside the future did not exist yet and the pre-provisioned
teammate identity stayed messageable. Built outside and moved in, the
guard drops with the unpolled future on both the frontier and map items.
Also rewords the two timeout: 0 validator warnings: the graph-level one
no longer claims max_loop_iterations always applies (it may be 0 too),
and the node-level one names the enclosing bounds that still end the
node instead of saying it runs until it returns.
Semaphore::new panics above tokio's MAX_PERMITS, so a fixed or templated
map cap (or settings.max_concurrency) that large crashed the run instead
of erroring. The validator rejects both at load, resolve_max_concurrency
rejects every arm at run time, and the executor checks the graph setting
before building its own semaphore, so validation mode makes no difference.
Also corrects run_child_agent_with_graph_inputs' contract comment: inputs
for a config-only agent are rejected, not ignored.
On slow runners bash start-up alone can exceed the fixed 300 ms delay, so
the abort landed before the worker tasks (and their retirement guards)
existed and the observer saw nothing. The dispatcher now leaves a marker
and the trigger waits for it.
Comment-only: settings.timeout notes that Ctrl-C ends a run promptly from
anywhere; the map node's as:/output_key: comments state that the two must
differ, and max_concurrency describes the template form as exactly one
{{key}} with nothing around it.
A string max_concurrency passed the load-time check whenever it merely
contained a {{...}} pair, so forms like "n={{k}}" or "{{ key }}" that
can never resolve at runtime were only caught after the map's inputs had
been computed. The check now requires the trimmed string to be exactly
one template reference, matching what interpolate_raw resolves as a pure
reference; padded forms like " {{budget}} " stay valid.
Also: the bash tool build-failure context names the source file instead
of the destination path, and the map-subgraph validator no longer
shadows its member id list with the resolved member nodes.
A map node whose item binding shares its name with output_key would have
the binding collected as the chain's result whenever the chain never
wrote it, while the missing-writer warning stayed silent. The collision
is now a validator error attributed to the map node and, with validation
off, a runtime error in run_map before any item forks.
LlmNodeExecutor::execute now takes the graph's abort signal and threads
it through run -> run_with_retries -> run_chat_loop, replacing the
loop-private signal, so an in-flight model call is interrupted and every
turn starts with an abort check that bails 'llm node aborted' before any
client is created.
run_llm_function gains an optional abort signal: the synchronous tool
wait loop kills the child and returns a 'Tool call ... aborted' error
within one poll interval when it is set. The tool dispatcher passes the
session abort; the agent _instructions runner passes None.
A graph run now observes user interrupts wherever it is: GraphExecutor::run
spawns a run-scoped bridge that maps SIGINT or the enclosing session abort
onto the graph's own abort flag (only when a session signal exists; a
pre-set session trips a synchronous check). The frontier join selects on
the abort and, like the timeout path, cancels every in-flight branch task,
failing the run with 'Graph ... aborted during super-step'.
Branch and map item tasks are cancellation-owned via TaskCancelGuard, so
dropping a map task's future no longer detaches its item chains. Peer
retirement is a Drop guard (PeerRetireGuard) constructed before the
semaphore acquire and dropped explicitly right after step(), so the
success-path ordering is unchanged while task abort, panic, and the
pre-step abort return all still retire the identity.
A child agent spawned from a graph node now carries its parent's session
abort signal, so a user interrupt is observable from every sync wait in
the agent tree. Background agent__spawn children are unchanged.
run_child_agent_with_graph_inputs also guards the child's own supervisor
with a disarmable CancelOnDrop: if the future is dropped mid-flight or
the child fails before its normal cleanup, its spawned subagents are
cancelled instead of running on invisibly.
GraphState.history was pushed to on every node visit and deep-cloned on
every super-step snapshot and map fork, but its only reader is the
cfg(test) current_node accessor. Gate the field, its initializer, and
the push behind cfg(test) so production builds no longer carry an
unbounded Vec<String> that nothing observes.
validate_timeouts now also flags settings.max_loop_iterations: 0, ahead
of the settings.timeout: 0 warning so both opt-outs read top-to-bottom
as they appear in settings. (design §3.14 / C22)
Both enforcement sites (frontier loop and map chain step) skip the
comparison when the cap is 0; visits are still counted and logged.
Adds an executor test that loops past the default cap with 0, a test
pinning the frontier cap message for a non-zero value, and a map-chain
twin at 0. (design §3.14 / C22)
A timeout: 0 on settings.timeout or on an agent/script/llm/rag node is
the author's explicit opt-out of the wall-clock bound. It stays legal;
the validator now emits one warning per zero so the choice is visible in
--validate output. Non-zero and unset values do not warn (unset already
means no bound for settings.timeout and llm nodes, matching the
explicit-zero-only convention of the orchestration-limit warnings).
Design §3.13 / C21.
A zero on any of the five timeout fields (settings.timeout, agent, script,
llm, rag) now disables the bound instead of firing an immediate
"timed out after 0s" or graph bail. Unset values keep their defaults
(agent 300, script 30, rag 120, llm/settings none); non-zero values are
unchanged. One resolution helper, wall_clock(secs) -> Option<Duration>,
feeds all five call sites; the C17 peer-retirement mark and every error
message stay where they were.
The one existing test that relied on timeout: 0 firing
(run_item_chain_marks_identity_finished_when_agent_step_times_out) moves
to timeout: 1 with its 5s hold unchanged.
Design §3.13 / C21.
Two offline chain tests materialize an echo-inputs graph agent whose
script reports the width it sees: a parent with inputs.width gets the
parent's value back, a parent without inputs gets the child's YAML
default. Two agents.rs tests pin the exact runtime guard texts for a
config-only target and a reserved initial_prompt key.
Task T5 of plans/map-subgraph-branches-design.md §3.12.
Inside validate_agents: an agent node with inputs whose target has a
config.yaml but no graph.yaml is an error, and an inputs key named
initial_prompt is rejected. primary_templated_fields now includes every
inputs value for agent nodes, so validate_parallel_reads treats them as
cross-branch reads with no new pass.
Design: plans/map-subgraph-branches-design.md §3.12 V10a–V10c, task T5.
Agent nodes gain an optional `inputs:` map of templates resolved against
the parent state and overlaid on the child graph agent's initial_state
before its executor starts. A lone {{key}} keeps the state value's JSON
type; mixed text renders to a string; initial_prompt is still owned by the
dispatcher. run_child_agent and run_active_agent_graph keep their
signatures as wrappers over the new *_with_inputs variants, and
run_agent_for_graph rejects inputs aimed at a config-only agent or
containing initial_prompt.
Design: plans/map-subgraph-branches-design.md §3.12 (C18), task T5.
PR #24 follow-up 10. The identity was only retired by the frontier and
chain-exit safety nets, so a peer stayed messageable during
structured::extract after its agent had already stopped. Mark it
finished the moment the agent future resolves, on success and on both
error paths.
Copilot review on PR #24. The validator already rejects 0 and the
template path errors on it, but a literal 0 loaded with
validate_before_run off was silently clamped to 1. Fail with the same
error shape as the template path; only the absent-cap default clamps.
Copilot review on PR #24. The fields were only ever cleared by
run_agent_for_graph taking them, so a failure between arming and that
take (e.g. prompt interpolation) left them set on the item's ctx.
Reset both unconditionally once the step returns.
PR #24 follow-up 6. The identity used to fall back to YAML declaration
order after the entry, so the name depended on how the author ordered
the nodes map. Walk next/fallback edges from the entry instead.
PR #24 follow-ups 3 and 4. run_chain_steps already wraps every step
error with the map/item/node/step locator, so the inner messages
repeated it. Make them prefix-free and turn the unreachable End arm
into an honest internal-invariant message.
PR #24 follow-up 2. With validate_before_run off, a user-authored
approval/input/end/map node inside a branch reached a message that
called itself an internal error. Name the node type and point at the
validator setting instead.
PR #24 follow-up 1. The bundled-tools test called the writing
generate_bash_declarations on the repo's assets/functions/tools/*.sh,
so cargo test could rewrite tracked files. Split the build+export step
into a pure build_bash_tool so the test never touches the source tree.
Comment-only rewrite of the map/branch and teammates comments: a branch is
the entry of a per-item chain; chain nodes may use next, state_updates,
output_schema, fallback and script _next inside the chain; output_key is
removed from the fork and must be written by the chain; max_concurrency
accepts an integer or a template; a teammate identity spans the item's
whole chain.
Add the motivating map-chain integration test: draft -> check, where check
re-routes to draft via script `_next` until an item-local attempts counter
reaches 2, run with validate_before_run on. A sibling test drives the same
map node against a parent state to pin that only collect_into lands on the
parent and that no chain visit touches the parent's loop counts.
Extend bundled_graph_agents_parse_and_validate: the sorted (node, warning)
set of every bundled graph must equal the set the pre-subgraph validator
produced, and graph.example.yaml must load through GraphParser, validate
without errors, and declare a writer for its map's output_key.
Same two-script chain as `map_chain_two_script_steps_route_via_next`,
with `validate_before_run: true`, proving the validator admits the
chains the runtime executes.
`validate_map_branches` checked only the entry node and forbade `next`,
non-`output_key` `state_updates` and `output_schema` on it. The runtime
now executes the whole subgraph reachable from `branch`, so the validator
follows suit as `validate_map_subgraphs`, at the same position in
`validate()`:
- approval/input/end/map nodes are rejected anywhere in the subgraph,
attributed to the map node; when the offending node is a `fallback`
target the message says why a previously accepted `fallback` now fails
- a fan-out `next` inside the subgraph is rejected
- a subgraph that shares nodes with the main flow (reachable from
`start` without entering any map branch, via the new
`main_flow_reachable`) is rejected, naming the shared nodes
- a new warning fires when no subgraph node declares a write to
`output_key` via `state_updates` or `output_schema`; any script in the
subgraph suppresses it, since scripts may write any key
- the `next`, `state_updates` and `output_schema` restrictions are gone:
intra-branch writes are fork-local scratch
Two maps may share a subgraph. `find_reachable_nodes` and
`compute_parallel_groups` are unchanged.
Tests: the three rules that inverted are renamed to say what they now
assert (`map_branch_with_in_subgraph_next_passes`,
`map_branch_state_updates_scratch_key_passes`,
`map_branch_with_output_schema_passes`); the four
`map_branch_cannot_be_*` tests pass unmodified. Thirteen new tests cover
each rule, the fallback hint, the missing-writer warning and its three
suppressions, a three-node chain, and `main_flow_reachable`.
A map item no longer runs a single branch node; it walks the subgraph
reachable from `branch` over `next`/`fallback` edges (branch_subgraph),
one chain per item, holding one semaphore permit for the whole chain.
Chain steps go through the shared `step()` so llm retries, fallbacks,
script `_next` and agent timeouts keep their existing semantics. A node
without `next` ends the chain (StepContext.branch_mode), a route outside
the subgraph, a fan-out, an end node or a loop past
max_loop_iterations fails the item, and every item error carries
`map node 'X': sub-branch [i] failed at node 'Y' (step n)`.
`output_key` is removed from each item's fork before the chain runs, so
the collected value must be written by the chain rather than inherited
from the parent.
Teammate identities are now per item for the whole chain: provisioned
when any flagged agent is in the subgraph, armed only before
`teammates: true` agent steps, and retired at chain exit. mark_finished
moves out of run_agent_for_graph to the two provisioning sites (frontier
task and chain exit), so timed-out and early-failing agents are also
marked finished.
`MapNode.max_concurrency` becomes `Option<ConcurrencyCap>`, where
`ConcurrencyCap` is `Fixed(usize) | Template(String)`. Integers parse
exactly as before (`4` -> `Fixed(4)`, `0` -> `Fixed(0)`, absent -> `None`);
a string parses as a template that the map executor resolves against the
parent state right before the fan-out via `StateManager::interpolate_raw`,
mirroring `over:`. A template must resolve to an integer >= 1 or a numeric
string (scripts often emit numbers as strings); anything else, including 0,
is an error naming the map node, the template, and the resolved value/type.
The fixed path keeps its `.max(1)` clamp for byte-compatibility.
`Deserialize` is hand-written so a malformed value (`-1`, `4.5`, `true`,
a list, a map) reports the offending value and the accepted forms rather
than serde's opaque untagged-enum "did not match any variant".
Validator: a string cap that contains no `{{ ... }}` pair is a load-time
error (catches `"4"` typed for `4`); a templated cap joins the map node's
read set so `validate_parallel_reads` flags a read of a sibling branch's
write. The existing `Fixed(0)` rule and every other rule keep their order.
Design: plans/map-subgraph-branches-design.md §3.5, §3.11 (C3, I3).
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).
Dark-Alex-17