fix(runtime_provision): use team-template risk_profile, not hardcoded toolfree
ci / gates (push) Successful in 6s
ci / frontend (push) Successful in 38s
ci / rust (push) Successful in 3m48s
ci / e2e (push) Skipped
ci / publish (push) Successful in 4m4s

The provisioner was hardcoding risk_profile=toolfree for every claw,
which the ZeroClaw config explicitly configures to EXCLUDE every
usable tool (shell, file_read, file_write, http_request, browser).
Result: coder/tester/committer claws had zero tools and produced text
in the context window with no ability to actually write files or run
tests — exactly what the last mission summary showed.

Fixes:
- provision_claw now takes risk_profile: &str, passed through from
  the team template (development teams already had coding_readwrite,
  which now actually gets applied).
- Research team templates updated from toolfree → research_readonly
  (file_read) and papers_research → research_web_readonly
  (file_read + web_search + web_fetch). Applied to both the on-disk
  TOML files and the live DB rows.
- Added RuntimeProvisioner::default_risk_profile_for_role for
  auto-provision code paths that lack a template context — picks
  coding_readwrite for coder-like roles, research_readonly otherwise.
- Split rebind_model out of provision_claw so the model-change UI
  path doesnt inadvertently clobber the existing risk_profile.

Templates DB fixup for missions launched pre-deploy is already
applied via manual UPDATE.
This commit is contained in:
Omar Sobh
2026-07-23 19:44:27 -07:00
parent 9a23c851e0
commit 84572186e9
9 changed files with 68 additions and 13 deletions
+2 -1
View File
@@ -129,8 +129,9 @@ pub(crate) async fn build_team_with_lifecycle(
)
.await?;
let claw_id = agent.id.as_uuid();
let risk = RuntimeProvisioner::default_risk_profile_for_role(&m.role);
provisioner
.provision_claw(claw_id, &m.model)
.provision_claw(claw_id, &m.model, risk)
.await
.map_err(|e| {
eprintln!("teams: provision claw {claw_id} failed: {e}");