0de766122965be57963c9891adddf99e2772889b
4
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Omar SobhandClaude Opus 5
|
76ac3714f1 |
sec(door): closed by default, governor fails closed; self-authoring off by default
Three fail-open paths on the §15 door: no env at all meant allow-all; a
governor that could not be reached approved with a WARNING; and a reply
that never said DENY — empty, truncated, a refusal — approved, because the
rule was !contains("DENY"). On the two days the judge plan emptied every
outbound action was approved by nobody.
Now: governor_allows() needs an explicit ALLOW and no DENY; both judge()
implementations return false when unreachable; with no governor the door
opens only on CLAWMATES_DOOR_POLICY=allow. Open Agent Passport (arXiv
2603.20953): 74.6% social-engineering success under a permissive policy,
0 of 879 under a restrictive one. Local override gains the governor prod
already runs.
skill_self_authoring: default flipped to OFF. No agent-authored skill has
ever been delivered to a mission or scored; prod held zero proposals.
Enable with CLAWMATES_SKILL_SELF_AUTHORING=1 once promoted skills go
through the files arm and get a Skill-Use score.
Co-Authored-By: Claude Opus 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01WZb5A2kfVfjpdwSochkuHz
|
||
|
Omar SobhandClaude Opus 5
|
769e002bb3 |
feat(skills): deliver on every tier, record what agents receive, let them self-author
Three phases of the approved plan, plus a correction to what the last one
claimed.
CORRECTION: skills reached ONE tier, not all of them
The previous commit said "skills can now reach a mission agent". That was
true only for the container/ZeroClaw tier — the fall-through that queues a
topology_runs row for topology_worker, which drives the executor that was
patched. compose_turn_prompt/pinned_skills_text had exactly one production
caller, and phase_runner's three other paths (composed microVM, solo
microVM, direct session) never called it. CAPABILITY-REVIEW.md said the
broad thing too; both are corrected.
Those three tiers share one task string and have no per-turn alias, so
their skills resolve per PHASE from the mission's crew and are appended
there. The container tier deliberately still injects per turn, with the
running node's own role — appending in both places would put every crew
member's skills in every turn twice.
The behavioural tests prove phase_skills_text and compose_turn_prompt work.
They cannot prove the three launch_* calls pass the composed string, and
that substitution is a one-word edit that would silently return all three
tiers to delivering nothing with every test still green. So there is also a
source-level assertion on the call sites, following the precedent in
mission_events::the_cap_is_enforced_in_one_statement. Its negative control
names the exact tier.
PROVENANCE: what an agent received, and what it said it did
Both were unanswerable. The prompt was never stored anywhere on any tier —
re-deriving it later re-runs the skill lookup against a catalogue that has
since changed, and once agents author their own skills it certainly will
have. The reasoning rows were durably write-only: pushed live once, then
never read from the database again by anything except the GC that deletes
them.
- prompt.composed records the exact bytes, on all four tiers
- the session tier writes its checkpoint record and a reasoning row,
instead of eprintln! and nothing — the same defect the solo microVM
path was fixed for, in the last tier that still had it
- narrative_for_mission reads both back
Found while doing it: the 400-event per-phase cap counted EVERY kind, so a
busy phase could push out its own phase.completed and its own provenance.
The cap now counts only the two unbounded kinds it was written for.
Negative control confirms the old behaviour dropped the prompt.
Retention is now a per-mission hold (0080) rather than a raised global —
with a test asserting unheld missions are still reaped, because an
exemption that applies to everything is not an exemption.
SELF-AUTHORING: agents apply their own skill drafts, no human click
By operator decision. level_up has generated complete drafts from a model
since it shipped; only a checkbox stood between propose and apply.
What replaces the gate is not another gate but four properties, each held
by a test:
- workspace-scoped, so a hand-authored skill can never be modified
- a draft cannot take a hand-authored skill's name. Ids are scoped and
bindings resolve by skill_id, so it could not overwrite or shadow one
anyway — but two procedures under one name means nobody reading a
transcript can tell which the agent followed, and that ambiguity is
fatal in a system where the skill is the standard being graded against
- every revision appends a skill_versions row, so it can be reverted and
a past run can be read against the text it was actually judged under
- approved_by = NULL. An agent's decision is never attributed to a person
who did not make it
Only skill_candidate applies autonomously. identity_refinement and
brain_consolidation still wait for a human: they change what an agent IS
rather than adding a procedure it can consult. State is announced at boot,
because a safety gate that changes silently is one nobody notices changed.
CLAWMATES_SKILL_SELF_AUTHORING=0 restores it.
Also: the test Postgres ran out of /dev/shm mid-suite (Docker's 64MB
default) and surfaced it during MIGRATIONS, which reads like a schema fault
and is not one. --shm-size=1g, and a pointer to the `clean` subcommand that
already existed for the 779 leaked test databases.
Full workspace suite green: 106 binaries, no failures.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar Sobh
|
f6c3ddbf81 |
refactor: no feature depends on Gemini any more
Depleted Gemini prepayment credits took out PDF rendering. The same key was the
only thing standing between level-up proposals and the same fate, so both are
off it.
- `pdf_renderer` is DELETED, not disabled. Nothing sets `render_pdf: true` since
markdown became the deliverable (
|
||
|
Omar SobhandClaude Opus 4.7
|
9b5e63cbb7 |
slice 8.5: per-agent + per-team level-up endpoints
Level-up analyzes an agent's brain + recent run outcomes (or a
whole team's aggregate state), calls Gemini 2.5 Flash for structured
JSON proposals, and persists them as pending level_up_proposals
rows. Reviewer approves a subset via /apply; the applier commits
only those items.
Migration 0052 adds level_up_proposals (id, workspace_id, agent_id
XOR team_id via CHECK constraint, status, payload JSONB,
applied_items[], model, created_by, approved_by, created_at,
applied_at) + workspace/pending/agent/team indexes.
Rust surface:
- cm_db::repo::level_up::{insert, get, list_pending, mark_applied,
mark_rejected}
- cm_api::level_up::{propose_agent, propose_team, apply}
Item kinds handled by apply():
identity_refinement → UPDATE agents.system_prompt
skill_add → agent_skills_ext INSERT
skill_candidate → workspace-scoped skills INSERT
(deterministic id per (workspace, name))
brain_consolidation → set_agent_md on the brain (unlike
brain_seed::ingest, this overwrites)
roster_change / mcp_bundle_change — logged as
"not auto-applied, human runs
team-wizard" (structural changes need
human review of side effects).
API:
- POST /api/claws/{id}/level-up → { proposal_id }
- POST /api/teams/{id}/level-up → { proposal_id }
- GET /api/level-up-proposals → pending list
- GET /api/level-up-proposals/{id}
- POST /api/level-up-proposals/{id}/apply { approved_item_ids }
- POST /api/level-up-proposals/{id}/reject
Uses Gemini 2.5 Flash with response_mime_type: "application/json"
so the model returns structured JSON directly (no ```json fence
stripping needed). Configurable via CLAWMATES_LEVEL_UP_MODEL.
Follow-ups:
- Frontend diff-review UI (pick items, approve/reject)
- roster_change / mcp_bundle_change appliers (currently manual)
- Anthropic + OpenAI proposer variants
- Promote workspace-scoped skills to builtin via a curator flow
Co-Authored-By: Claude Opus 4.7 <[email protected]>
|