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).
Hoist the three copies of apply_state_updates (llm, agent, rag) into
graph::state_updates::apply(state, output, has_schema, updates). The
helper computes every state_updates value first, restores the transient
`output` binding, and only then writes the computed updates, so a
`state_updates: { output: "{{output}}" }` entry is no longer clobbered
by the restore step.
The per-file wrappers stay as one-line calls so their existing tests are
unchanged; new direct helper tests live in state_updates.rs, including
the regression test for the clobber.
Design: plans/map-subgraph-branches-design.md §2.6, §3.7 (C5, D3).
Agent nodes marked teammates: true whose sub-agents run concurrently (map fan-out branches or multiple flagged agent nodes in one super-step) now form a team: each member gets a pre-provisioned inbox in a messaging-only PeerRegistry before any branch starts, a teammate roster injected into its prompt, peer resolution in agent__send_message, and a peers section in agent__list_running. Registries are scoped to a single fan-out and carry no lifecycle semantics: outputs still flow exclusively through collect_into/state reducers, finished peers reject new messages, and nothing registers in a supervisor. Also hardens the agent-recursion depth guard to work without a supervisor and adds validator warnings for zero-valued orchestration limits.
Graph agents previously derived can_spawn_agents from the presence of an agent node, so a pure-LLM-node graph could never spawn dynamic sub-agents. The three optional graph-level keys now override the derivation/defaults in AgentConfig::from_graph, enabling orchestrator graphs (can_spawn_agents: true with only llm nodes). Explicit false on a graph with agent nodes still runs those nodes; only dynamic spawning from llm nodes is disabled.
python3 first-start on fresh Windows runners (AV interpreter scans) blew
the 5s/10s/30s script timeouts. Drop the incidental python3 spawns from
the bash fixtures (pure-bash JSON extraction) and give the genuinely
python tests 60s headroom.
A scheduled workflow refreshes models.yaml from live API data, validates
the result (rebuild, full test suite, catalog smoke test), and commits it
back, so every build embeds a recent catalog. Also documents the dynamic
model catalog in the README quick links.
Unknown chat/reranker models resolved through the create-from-name
fallback now inherit their provider's family rules (require_max_tokens,
reasoning defaults, etc.) from the quirks overlay, and the model
completion table marks reasoning-capable models with a brain glyph.
Add a hidden --generate-models flag that rebuilds models.yaml from
models.dev and OpenRouter merged with the hand-owned quirks overlay,
regenerate the committed catalog with it (393 -> 1090 models), and
retire the Python updater. GitHub becomes fully quirks-owned since
upstream only tracks Copilot ids, legacy ids upstream dropped are
preserved as hand-owned quirks entries, and non-chat model families
(image/tts/audio/realtime) are excluded from generation.
A scheduled workflow refreshes models.yaml from live API data, validates
the result (rebuild, full test suite, catalog smoke test), and commits it
back, so every build embeds a recent catalog. Also documents the dynamic
model catalog in the README quick links.
Unknown chat/reranker models resolved through the create-from-name
fallback now inherit their provider's family rules (require_max_tokens,
reasoning defaults, etc.) from the quirks overlay, and the model
completion table marks reasoning-capable models with a brain glyph.
Add a hidden --generate-models flag that rebuilds models.yaml from
models.dev and OpenRouter merged with the hand-owned quirks overlay,
regenerate the committed catalog with it (393 -> 1090 models), and
retire the Python updater. GitHub becomes fully quirks-owned since
upstream only tracks Copilot ids, legacy ids upstream dropped are
preserved as hand-owned quirks entries, and non-chat model families
(image/tts/audio/realtime) are excluded from generation.
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.
- use_session_applies_persisted_mcp_tools_immediately now loads a session
file from disk through the real use_session, proving the post-assignment
filter refresh applies a re-attached session's persisted allowlist.
- New use_rag_does_not_drop_role_filters loads a yaml-driver RAG through
the real use_rag and proves the tool-scope rebuild recomputes the role's
filter layer instead of dropping it.
- Seed the process-wide client/model registries in a pre-main ctor (new
ctor dev-dependency) so model resolution is deterministic across test
orderings; the seed exposes only an embedding model so tests that assert
'no chat model available' keep their premise.
Dark-Alex-17