3 Commits

Author SHA1 Message Date
e9038182a1 fix(tests): hermetic ORCH-41 model/effort tests vs host env (unblock merge-gate)
Some checks failed
CI / test (push) Has been cancelled
CI / test (pull_request) Successful in 55s
Merge-gate re-test runs under the orchestrator's prod env, where the
operator legitimately set ORCH_AGENT_FALLBACK_MODEL and changed
ORCH_AGENT_MODEL_DEFAULT / ORCH_AGENT_EFFORT_*. Two ORCH-41-era tests
asserted SHIPPED defaults through the env-backed settings singleton and
failed 3/3 there, while Gitea CI (clean env) stayed green. Branch
ORCH-009 touches neither src/ nor these tests - latent non-hermetic
landmine on main, detonated by the prod env change.

- test_resolve_agent_effort.py: autouse fixture now mirrors the sibling
  model-file baseline (pins shipped model/fallback fields) so the
  flag-assembly tests are env-independent.
- test_resolve_agent_model.py: fixture also resets agent_fallback_model;
  test_fallback_model_disabled_by_default now asserts the CLASS field
  default (the actual ORCH-074 ADR-001 G4 invariant: shipped default
  is ""), never-break is_valid_model asserts unchanged byte-for-byte.

Clean-env behaviour is byte-equivalent (fixtures pin exactly what an
empty env yields). Full suite: 1713 passed (was 2 failed / 1711).

Refs: ORCH-009

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-10 16:17:54 +03:00
0873803faa feat(launcher): drop dead frontmatter model + validate model name (never-break)
G1: remove the dead `model:` line from all 6 .openclaw/agents/*.md prompts —
launcher never read it; config (agent_model_*) is the single source of truth.

G2: add is_valid_model helper (format check ^claude-…$) applied inside
resolve_agent_model's resolution cascade and at the inline --fallback-model
read in _spawn. An invalid name is logged and skipped to the next valid level
(in the limit: no --model flag), never passed to the CLI, never raises. Format
check chosen over an allowlist for forward-compatibility (ADR-001).

G3 (routing) and G4 (fallback) intentionally NOT enabled — all agents stay on
claude-opus-4-8; agent_fallback_model stays "".

Docs (golden source) updated in the same change: README model/effort table +
validation, CLAUDE.md, .env.example (ORCH_AGENT_MODEL_*/EFFORT_*/FALLBACK_MODEL),
CHANGELOG. Tests: test_agent_frontmatter_no_model.py (G1), extended
test_resolve_agent_model.py (G2 never-break).

Refs: ORCH-074
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-08 22:00:54 +03:00
401bf66fe0 feat(agents): configurable LLM model + effort per-agent and per-project (ORCH-41) (#36)
Some checks failed
CI / test (push) Has been cancelled
2026-06-05 19:45:19 +03:00