6 Commits

Author SHA1 Message Date
Hunter B 5106ecfb2d test(fleet): CI-safe multi-worker dogfood smoke with injected failure (#3166)
Adds a verifiable dogfood smoke that drives several concurrent exec-style
workers (three healthy + one injected-failure that emits an error event and
exits non-zero) through the real host adapter, asserting distinct terminal
pass/fail outcomes — no external services, no model calls, no codewhale binary.
Documents the automated CI smoke vs the manual `codewhale fleet run` path in
the dogfood spec, and is honest that the manager run-loop cutover to drive real
FleetExecutor workers is still in progress.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-13 01:30:06 -07:00
Hunter B e8b52ac57a feat(fleet): security/trust + headless-worker foundation; unify recursion depth
Lands the Agent Fleet security/trust boundary and the headless-worker bridge on
the v0.8.60 line, and collapses the sub-agent and fleet recursion model into a
single shared axis (Hunter steer: "not two moving targets").

Security & trust (#3165):
- FleetTrustLevel, FleetSecurityPolicy, FleetSecretRef (redacted), FleetWorkerAuth,
  FleetCapabilityGrant, FleetAlertEndpoint (redacted) in protocol.
- secrets: resolve_direct(key, source_hint) — fleet secret resolution, never logged.
- Host adapters refuse secret-bearing env keys; SSH uses SendEnv (no argv secrets).

Roles & delegation (#3167):
- fleet role -> SubAgentType mapping; reviewer/verifier default read-only.

Headless worker bridge (#3096/#3154, partial — still simulation, real spawn next):
- worker_runtime: FleetTaskSpec -> AgentWorkerSpec, status -> ledger events,
  exec hardening (mirrors #3027), parallel-safe read-only tool set (#2983).
- FleetManager carries an optional SharedSubAgentManager + exec config.

Recursion depth — ONE axis:
- codewhale_config now owns DEFAULT_SPAWN_DEPTH (3) + MAX_SPAWN_DEPTH_CEILING (3).
- sub-agent DEFAULT_MAX_SPAWN_DEPTH and the fleet clamp both source these consts.
- fleet default raised 1 -> 3 to match standalone sub-agents; root runs at depth 0,
  budget gates child delegation. End-to-end test proves a depth-0 fleet worker
  reaches 3 nested levels (afford >= 3).

Dogfood scaffolding (#3166, partial): docs/examples/fleet-dogfood.toml.

Tests green: codewhale-config fleet, codewhale-tui fleet (58), subagent max_depth;
cargo fmt + git diff --check clean; cargo check --workspace ok.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-13 01:10:30 -07:00
Hunter B 2b69f4e041 chore: polish codewhale home defaults 2026-05-31 19:22:12 -07:00
Zhuoran Deng 57625af4f8 docs(docker): tighten toolbox compose defaults 2026-05-30 19:17:55 -07:00
Zhuoran Deng 127f0565dd docs(docker): add toolbox compose template 2026-05-30 19:17:55 -07:00
Hunter Bown 671aa4810e docs: add Docker toolbox/custom-image contract and examples (#2217)
- Document default image contract (non-root, no sudo, conservative)
- Add opt-in toolbox image pattern with passwordless sudo
- Include Dockerfile.toolbox example
- Document multi-project volume pattern
- Add bootstrap script, custom CA certificate, and proxy workflows
- Clarify that bootstrap/CA workflows require the opt-in toolbox image
2026-05-26 16:37:33 -05:00