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.
The user-scope MCP config historically lived at
<config-dir>/functions/mcp.json, a leftover from when MCP support was
part of the llm-functions tooling. It now resolves through a single
choke point with these semantics:
- Preferred location: <config-dir>/mcp.json (created there on first run)
- Historical <config-dir>/functions/mcp.json still honored when the
preferred file does not exist, so existing installs are unchanged
- If both exist, the preferred location wins
--info/.info now reports the resolved location as mcp_config_file, and
the --scope help text plus config.agent.example.yaml reference the new
default. This also removes the asymmetry with the workspace scope,
which already used .coyote/mcp.json directly.
The supervisor registry went kind-generic (TaskHandle::Agent | Job)
earlier in this branch, but the module holding the agent__* handlers
and two model-facing error strings still carried the old name:
- src/function/supervisor.rs -> src/function/agents.rs (it contains
only agent__* tool handlers, pairing with function/jobs.rs; the
kind-generic src/supervisor/ registry keeps its name)
- 'Supervisor tool failed' -> 'Agent tool failed'
- 'Unknown supervisor action' -> 'Unknown agent action'
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.
Dark-Alex-17