Commit Graph

5 Commits

Author SHA1 Message Date
Paul O'Reilly
d7decc1dec minimax: move to MiniMax-M3.1-Flash-Preview; drop bare minimax/minimax-m2 slugs
- new context minimax-m31-flash/v1 (model pin; no thinking-budget init, Flash
  ignores it); four composites switch from minimax-m3-max/v1 (kept for rollback)
- models + registry for minimax-m31-flash-{max,medium}; removes the dangling
  model-registry/minimax.yaml (endpoint "minimax" never existed)
- tiers, harness-roles, minimax-* task templates and the *-review-loop@1
  workflows use the Flash slugs (MiniMax silently maps unknown names to M3, so
  the provider-id translation lands in agent-runtimes)
2026-10-13 10:55:03 +13:00
Paul O'Reilly
887578f0eb feat(templates): explicit cp_write on every kind: script node + audit test (WF-COMP-31d, item 26754227)
cp_write: true  -> state-tx (test-validate@1, frozen-fixture-emit@1) and, in
                   the archived bug-ancestor-auto-advance@1, tag-set + state-tx.
cp_write: false -> every other script node (verdict-gate, policy-pick,
                   preflight-*, frozen-fixture-emit, parent-link-check).
tests/invariants/test_cp_write_field_set_correctly.py pins the set.

HOLD: do not merge until the CP release that adds WorkflowNode.cp_write.
The current CP schema is extra="forbid" and rejects the new key
(verified: nodes.0.cp_write extra_forbidden), so on the old CP these
template edits are NOT inert.

Claude-Session: https://claude.ai/code/session_01N218bERyNeLhbLmDRDvbWF
2026-10-04 09:36:04 +13:00
Paul O'Reilly
8d7b3af77d fix(templates): add AGENT_UPSTREAM_REPO_URL/BRANCH to all workflow templates using the agent fork
Fresh agent branches were seeded from the stale fork main (AR-39 fell through to fork).
Work item 18efa01f-f941-4f16-bb67-9cafbb6d668a.

Claude-Session: https://claude.ai/code/session_01N218bERyNeLhbLmDRDvbWF
2026-10-02 15:03:34 +13:00
Paul O'Reilly
e31d472ff9 fix: migrate Claude model files to current API IDs (opus-5, sonnet-5, haiku-4.5)
Bug 57d8a047-d26d-47ce-ae6f-bc5cb98fef0e: Opus-tier tasks 404'd because
models/claude-opus-4.yaml pinned default_flags.model to "claude-opus-4-5",
a retired ID. models/claude-sonnet-4.yaml was pinned to a dated snapshot
("claude-sonnet-4-20250514") with the same problem.

Slug strategy: the registry slug (filename / RegistryEntry.name) doubles
as the literal --model argument on the workflow-template pass-through path
(task-templates/workflow/*.yaml `model:` field -> compiler WF-COMP-18 ->
payload.runtime.model -> entrypoint/runners/claude.py `--model`), which has
no translation step through this file's default_flags. So rather than
patch default_flags.model in place (leaving the slug stale and the
pass-through bug latent), rename the slug to match the current API ID:

- models/claude-opus-4.yaml, model-registry/claude-opus-4.yaml
  -> claude-opus-5.yaml (name/endpoint/default_flags.model: claude-opus-5)
- models/claude-sonnet-4.yaml, model-registry/claude-sonnet-4.yaml
  -> claude-sonnet-5.yaml (claude-sonnet-5)
- model-registry/claude-haiku-4.yaml -> claude-haiku-4-5.yaml
  (claude-haiku-4-5); added the previously-missing models/claude-haiku-4-5.yaml
  so the claude runner can actually resolve this endpoint
- model-registry/harness-roles.yaml, model-registry/tiers.yaml,
  workflows/smart-agent.yaml, task-templates/workflow/{spec,plan}-review-loop@1.yaml:
  updated every claude-opus-4 / claude-sonnet-4 / claude-haiku-4 reference
  to the new slugs
- models/openrouter-sonnet.yaml: dated snapshot "claude-sonnet-4-20250514"
  -> "claude-sonnet-5" (third-party router proxying the same retired ID)
- refreshed cost_per_1k_tokens on the three renamed registry entries to
  current published pricing

Claude-Session: https://claude.ai/code/session_015nXvGNNNixJPFwZKZHNyha
2026-09-10 12:05:14 +12:00
Paul O'Reilly
d06a526256 feat(templates): sync 4 workflow templates from agent-runtimes
Add direct-impl-sonnet@1, plan-review-loop@1, spec-review-loop@1,
test-write-review-loop@1 — present in agent-runtimes but missing here.
These are needed before agent-runtimes drops its baked-in copies and the
CP loads workflow templates exclusively from this CRS repo.
2026-07-29 09:09:52 +12:00