12147a1e015120b03dcd9e006c5f54c7f93015ef
322
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 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 Sobh
|
e31688bac5 |
fix(delivery): keep the TAIL of a push error — git prints its reason last
A failed push recorded two identical auth lines, a URL, and a branch name cut off mid-word. The reject reason was on the next line and the 500-char head clamp ate it, so the artifact preserved the noise and dropped the answer. That is what left #55 unresolvable: the evidence needed to distinguish "no credentials" from "non-fast-forward" had been truncated away. `evaluator_tools::clamp_output` already existed for exactly this — head AND tail with a byte count of what it dropped, on char boundaries so multi-byte output cannot panic. Reused rather than reinvented. Investigation notes recorded on #55. Two hypotheses were disproved by measurement: push credentials are rebuilt per push from GITEA_TOKEN + repos.clone_url and never live on disk (the clone-time scrub guarantees it, and every checkout on the host — including ones that pushed — has an identical credential-free origin), and neither of the two ways `with_ambient_auth` can silently return an unauthenticated URL applies here: the clone_url matches its required prefix and the token is non-empty in a container that predates the failure. 489 tests pass, clippy clean. |
||
|
Omar Sobh
|
d49acaed5e |
fix(missions): exclude build output from COLLECT too, not just inject
The other half of the same bug. The previous commit filtered `mission_fs::pack_dir` (the inject side) and left the guest's `op_get` tarring everything, so the re-run that proved the #54 fix — it survived 480s where it used to die at 210 — still lost its work to `vm_collect ... node timed out`. Two modules written, four subagents used, nothing delivered. `op_get` now takes an `exclude` list, sent by the host from `mission_fs::transport_excludes()` — the same list `mission_delivery` uses for the diff. Policy in one place, applied at both ends of the wire. Matched on directory NAME at any depth, so a workspace's per-crate `target/` dirs are all covered, with a test that plants a nested one and asserts it does not come along. Also proven by that run: the worker no longer kills a live microVM run. It ran 480 seconds straight through the 180s requeue window and the 210s mark where mission 019fd43e died, untouched. And `subagents: 4` — the team addendum did drive real fan-out this time, which is the first evidence the Slice 3 switch does anything. 483 tests pass, clippy clean. Still to prove: a >3-minute mission that actually DELIVERS. The collect fix is tested in isolation but has not yet carried a real mission's work back, and the guest agent needs rebuilding into the rootfs before it can. |
||
|
Omar Sobh
|
4efcde9d4f |
fix(missions): #54 — the worker was killing live microVM runs at 180 seconds
My hypothesis in #54 was WRONG, and it was wrong because I built it on a bad measurement: `grep -c 'microvm phase'` returned 0, so I concluded the completion log never printed and blamed the 15-minute reaper. The line was there all along, at 14:17:45. The real cause is worse. `requeue_stale` has NO TIER FILTER. A microvm run's `updated_at` is written once at insert and never again — it is driven by a `tokio::spawn` that owns it start to finish, and nothing in `microvm_executor` writes `topology_runs`. So at 180s the sweeper declared a perfectly healthy run stale and flipped it to `queued`; `claim_next_queued` (no tier filter either) handed it to the worker; `run_job` tried to parse the microvm graph placeholder, which `TopologyGraph` cannot deserialize; and it failed the run with "missing or invalid graph". Mission 019fd43e: run created 14:11:16, mission failed ~14:14:46. 210 seconds — the 180s window plus a tick. The agent went on working and finished at 14:17:45 with three modules written, by which time the phase was already dead and the VM was orphaned. A firecracker process was still alive 1h37m later. THE UNCOMFORTABLE PART: every microVM mission that appeared to work this session did so only by finishing inside three minutes. The 90-second ones dodged this. The harness scenario dodges it. Nothing about that was visible. `WORKER_DRIVEN_TIERS` (team, company, org, swarm, compare) is now the allowlist for all three sweep paths — claim, requeue, reap. An allowlist rather than a denylist so the next self-driven tier is safe by default instead of exposed until someone remembers the file. `tier='session'` had exactly the same exposure and is covered too. A unit test asserts microvm and session are NOT in it, next to the code that inserts them. Two more fixes from the same wreckage: - `destroy` reported `killed: pgid.is_some()` — true whenever there was a pgid to signal, whether or not anything died. It now sends the signal, polls /proc for the group leader, retries, and reports what it OBSERVED; `signalled` keeps the old meaning so "nothing to kill" is distinguishable from "it would not die". - the run-status update is now guarded with `AND status <> 'cancelled'`. An operator cancelling is a decision; this task reporting an outcome minutes later is an observation, and it must not overwrite one with the other. And the root cause of the collect timeout itself: `mission_fs::pack_dir` shipped `target/` in both directions. `mission_delivery` has excluded build output from the DIFF since day one; the TRANSPORT never knew. The host checkout was 9.4 MB of which 8.9 MB was `target/`, tarred and base64'd over vsock each way. `EXCLUDED_PATHS` is now one list shared by both layers, matched on directory name at any depth so a workspace's per-crate `target/` dirs are all covered. 483 tests pass, clippy clean. |
||
|
Omar Sobh
|
0d25a94a84 |
fix(missions): agent teams do not form in print mode — say so where it is set
MEASURED, against the CLI in our own image (2.1.223): with
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and an explicit request to "spawn two
teammates", `claude -p` did the work with two SUBAGENTS, wrote both files, and
created no ~/.claude/teams/ directory at all. The docs allow for it — "Claude may
sometimes use subagents instead of creating a team" — and headless appears to be
always: the whole feature is described around an interactive agent panel, which a
print-mode session does not have.
So Slice 3's switch, as written yesterday, set a flag with no mechanism behind it.
The first team mission caught it, because the probe was built to look for teammates
rather than to assume them.
Corrected rather than removed:
- `team_env` documents the measurement at the point the flag is set, so the next
reader does not have to rediscover it. The flag stays: harmless, and free if a
later version supports teams non-interactively.
- the prompt addendum now asks for parallel DELEGATION rather than naming
teammates, which is what print mode can actually deliver — and it keeps the two
anti-patterns worth stating (own different files; do not split one change into
stages).
- the "no teammates" warning was blaming the flag and the config path. It now
judges on the SUBAGENT count, which is the mechanism in play, and a zero
teammate count is documented as expected rather than as a fault.
What the switch buys today is real but smaller than the plan assumed: it changes
the prompt so the lead parallelises across files instead of working through them
alone. Whether that beats solo on our own missions is still unmeasured, and the
plan's prediction — that it will not be faster — stands untested.
482 tests pass, clippy clean.
UNEXPLAINED, filed as #54: that team run's `topology_runs` row is `failed` while
the log line that sits immediately before the UPDATE never printed — zero matches
for 'microvm phase' in the container's whole log. The prime suspect is
`topology_worker`'s stuck-run reaper, which fails runs that are `running` with no
step records and does not filter by tier; a microvm run has no step records by
design. If that is it, any sufficiently long VM phase is failed out from under
itself. The system failed safely here — the empty-delivery guard caught that
nothing was produced, and nothing false was reported — but the cause is not known
and it is not being written up as if it were.
|
||
|
Omar Sobh
|
cb48f7ff3b |
feat(missions): Slice 3 — agent teams behind a per-mission switch, solo by default
`missions.team_engine` (0069): NULL = solo, `'claude_code'` = Claude Code agent teams inside the mission's VM. Solo stays the default deliberately — Anthropic measure multi-agent at 3-10x the tokens with wall-clock often LONGER, since the benefit is thoroughness rather than speed — so a mission that said nothing does not get a team. In-process teammates live in the lead's process, so ONE VM hosts the whole team. That is why this is a prompt-and-env change rather than an orchestration one: no N-VM fan-out, no placement per teammate, no new completion path. The lead decides its own team size and there is no flag that limits it, so the cap (4) is stated in the prompt. The addendum also carries the two anti-patterns from Anthropic's guidance, because they are exactly the shapes our pipeline templates have: teammates must own DIFFERENT FILES (two in one file overwrite each other), and one change must not be split into stages across teammates (a handoff loses context at every step). And: wait for your teammates — a summary written before they report is the lead's own guess. A solo mission's prompt and env are byte-identical to before this change. That is enforced by test, not by intention: the comparison between solo and team is only meaningful if the solo side did not also move. Evidence, because a team mission that forms no team is silently just a solo run that looked fine and spent fewer tokens: a second probe counts members in `~/.claude/teams/*/config.json` (minus the lead), reported separately from the subagent count, and a team mission with zero teammates logs loudly with the two likely causes. The teammate path is DOCUMENTED BUT NOT YET VERIFIED in our image, unlike the subagent transcript path which was measured — so a zero there means "no evidence found", and the first real team mission is what turns it into a fact. `Option<u32>`: None means no team was asked for or the probe could not run. Hooks (`TaskCompleted` / `TeammateIdle` exit 2, which would move `done_when` from post-hoc into the agent's own loop) are the highest-value part of this slice and are deliberately NOT here — they deserve their own pass rather than a rushed tail. 482 tests pass, clippy clean. |
||
|
Omar Sobh
|
c840688adb |
feat(missions): choose the independent validator per mission (#53)
`CLAWMATES_VALIDATOR_MODEL` is deployment-wide, so proving Slice 2 put a second
provider on the critical path of EVERY phase verdict. `cross_provider_judge`
deliberately does not fall back when the independent judge fails — a verdict
quietly produced by a same-family model would claim a property it does not have —
so a z.ai outage makes phases unmeetable rather than merely unverified. That is a
per-mission trade, not a per-deployment one.
`missions.validator_model` (0068), settable at create, with three distinct states
because an empty string and NULL mean opposite things in a nullable text column:
NULL use the deployment default
'' explicitly NO independent validator — judge with the house model.
The default must not quietly reinstate independence a mission was
told to skip.
'glm:glm-4.7' this spec, subject to the same three refusals as before:
same-family rejected, unregistered provider rejected, and a failed
independent judge does not fall back.
Whitespace counts as empty: a column hand-set to " " meant to say nothing.
478 tests pass, clippy clean. Behaviour is unchanged for existing missions — they
have NULL and so keep following the deployment default.
|
||
|
Omar Sobh
|
9aed20b6d0 |
fix(missions): capture a failed phase's work; harness gains a microvm scenario (#51)
A REGRESSION I INTRODUCED ONE COMMIT AGO. `capture_finished_coding_phases`
selects on `mp.status = 'completed'`, so the moment an unmet phase correctly began
reporting `failed`, its diff stopped being captured, committed or pushed — the work
was silently discarded. Found by the new harness scenario, whose phase legitimately
missed its condition and then had no artifact at all.
What was produced, and whether the goal was met, are different facts. The artifact
records the first; `mp.status` records the second. Capture now covers terminal
phases (`completed`, `failed`), so a phase that did real work and missed its goal
still delivers a reviewable diff — which is exactly what the next pass needs.
`scripts/verify-mission-delivery.sh microvm` — the regression net this session was
missing. Everything the microVM track proved by hand was guarded by nothing:
- THE KERNEL LINE is the assertion that cannot pass by accident. Every other
check would also pass if the phase had quietly run in a container on the
gateway; only the kernel says WHERE it ran. Compared against the real gateway
and node kernels read at start-up rather than pinned to a version, so
upgrading vmlinux does not manufacture a failure.
- subagent count > 0, from the server's own count of Claude Code's per-subagent
transcripts. Before `Agent` was in the allowlist this was structurally
impossible and nothing said so. A probe that could not run reports "?" and
FAILS the check rather than reading as zero.
- the verdict's judge and whether it was independent.
- negative control, observed passing: a mission whose backend no node can run is
refused at launch and stays draft. Without it the positive scenario would pass
just as well against a scheduler that ignored `backend` entirely — which is
what it did until the first real microvm mission landed on a node with no such
rootfs.
Also fixed in the harness: `api` now sends the JSON body on STDIN (`curl -d @-`)
instead of interpolating it into a single-quoted argument inside a double-quoted
ssh command. A task description containing "the crate's test suite" ended the
quoting and killed the remote shell; two attempts to escape it were themselves
wrong, because the backslashes must survive bash AND sed AND sh. Removing the
interpolation removes the class, and the next author does not need to know that
apostrophes were forbidden.
475 tests pass, clippy clean.
|
||
|
Omar Sobh
|
bb807c2f3a |
fix(missions): an unmet goal condition is no longer reported as success
Found by the Goodhart test for the independent judge, which is exactly what it was built to find. The test: a phase whose `done_when` demanded a passing suite, and a task that deliberately left a failing test. glm-4.7 judged it, ran `cargo test` itself, saw `parity_is_wrong_on_purpose ... FAILED` (exit 101), and returned met=false quoting the assertion — while the agent's own summary said "All three steps are implemented exactly as specified and independently verified". The verdict and the agent's account diverged, which is the whole point of an independent judge. And then the mission closed `completed`. `if verdict.met || last_pass` marked BOTH outcomes completed, so a phase that ran out of passes without ever meeting its condition reported success — and through `close_finished_missions`, so did the mission. The verdict said met=false in a column nobody reads before believing a green status. Anything consuming mission status rather than digging into the verdict saw a goal that was never reached as a goal achieved. Exhausted-and-unmet is now `failed`, and the log names the judge and whether it was independent. This changes observable behaviour: missions that would previously have finished green with an unmet condition now finish failed. That is the correction, not a regression — but it is worth knowing before the next scheduled run. Also: `Verdict.independent` had no column. The field existed in the struct and in the logs, so the audit question the mechanism exists to answer — was this checked by something other than the model that wrote it? — could not be asked of the database. Migration 0067 adds it, defaulting to false, which is the truth about every row written before now. Verified in production before the fix: glm-4.7, 4 checks all executed, the real cargo failure quoted, met=false. 475 tests pass, clippy clean. Note for whoever rebases: `sqlx::migrate!` embeds migrations at COMPILE time, so a new migration needs cm-db rebuilt (`touch crates/cm-db/src/lib.rs`) or the integration tests fail on a column that exists in the file and not in the binary. |
||
|
Omar Sobh
|
8796fbbcbb |
feat(evaluator): Slice 2 — an independent judge, from a different provider, with the same teeth
Claude writes the code and Claude judges it. That is a correlated failure: the
model that talked itself into a shortcut is the one disposed to accept it, and it
is the structural cause of the "early victory" failure Anthropic documents and of
our own Goodhart incident.
`glm` and `kimi` are both already registered in production, so the fix needed no
new credential path.
THE UNLOCK: `judge_with_tools` took `&AnthropicProvider`, but `LlmProvider` is a
single method — `stream(ChatRequest)` — and the loop only ever used that. The
concrete type was incidental. Widening it to `&dyn LlmProvider` means a
cross-provider judge runs the SAME allow-listed command loop. Before, independence
and real verification were mutually exclusive: the tool loop existed only on the
subscription path and every other route "judged claims only", so choosing an
independent judge meant giving up the checks that make a verdict evidence. GLM is
registered in anthropic format, so tool calling reaches it unchanged.
`CLAWMATES_VALIDATOR_MODEL` (e.g. `glm:glm-4.7`) selects it. Three refusals, each
protecting the claim the field makes:
- a spec in the implementer's own family is rejected, not used — `opus` judging
`sonnet` is not independence, they share a lineage and most failure modes
- a spec naming a provider this deployment never registered is rejected.
`Runtime::resolve_provider` silently falls back to the DEFAULT provider when
the registry has no such name, which would hand back Claude while the caller
believed it had GLM. Detectable because the returned model keeps its `name:`
prefix, so it is checked rather than trusted.
- an independent judge that FAILS does not fall through to the house judge. A
verdict quietly produced by a same-family model would claim a property it does
not have. The pass stays unmet, says why, and the next sweep retries.
`Verdict.independent` records it, `#[serde(default)]` so verdicts stored before
this field read back as not independent — which is what they were. An unrecognised
model family resolves to "unknown", never to ours: guessing would report
independence nobody established.
474 tests pass, clippy clean. Not yet enabled in production — the env var is unset,
so behaviour is identical until it is set deliberately.
|
||
|
Omar Sobh
|
11b274edc6 |
chore(images): Claude Code 2.1.223, and make the verifier foreground
Reviewed the changelog rather than bumping on principle. 2.1.220 → 2.1.223 for one
reason that bears on how we use subagents:
2.1.222 — "Fixed PreToolUse auto-allow hooks bypassing tool restrictions in
background agent tasks."
Subagents run in the background by default since 2.1.198, and the `verifier`
role's entire guarantee is a TOOL restriction — no Edit, no Write. So on 2.1.220
the one property we rely on was the one that bug could undo. 2.1.221 also fixes
`--mcp-config` servers not connecting before the first turn in print mode, which
is the mode we run and will matter when the MCP door reaches a VM.
Two findings from the changelog that we already had at 2.1.220, both worth knowing:
- 2.1.219: subagents can nest to depth 3 (was 1), so our roles can delegate
further than assumed.
- 2.1.212: a subagent inherits the parent's permission mode, which confirms the
verifier's read-only property must come from `tools` and not from permissions.
That is how it was written; now the reasoning is recorded next to it.
And a correctness fix that follows from the background default: the verifier is now
`background: false`. A background verifier lets the lead carry on and write its
report before the check has finished — the finding would arrive after the
conclusion it was supposed to inform.
Verified on tank: image reports 2.1.223, rootfs rebuilt, `--vm-selftest` all green
including a real agent turn on subscription auth, egress allow and deny both firing.
|
||
|
Omar Sobh
|
2dee941080 |
feat(missions): Slice 1 — a microVM agent can delegate, and we can see that it did
`microvm_executor` passed `--allowedTools Read Edit Write Bash`, which omits the
`Agent` tool, so Claude Code could not spawn a single subagent in any of our VMs.
The tool existed, the model knew how to use it, and the allowlist quietly removed
the ability. Nothing in any output said so.
Now: `Agent` in the allowlist, two roles supplied as `--agents` JSON, and a probe
that counts what actually ran.
Roles are JSON on the command line, not files, because `/mission/repo` is
collected and diffed — a role definition written into the checkout would arrive in
the delivered patch as if the agent had authored it.
Two roles only, and the choice is the research talking:
- `verifier` — the one multi-agent pattern Anthropic endorses for coding work.
It gets Read/Grep/Glob/Bash and deliberately NOT Edit or Write: an agent that
can fix what it is checking will fix it and report success, and the report is
then about a tree nobody reviewed. Its prompt demands the COMPLETE suite,
which is the counter to the "early victory problem" — the same failure as our
own Goodhart incident.
- `explorer` — context protection, read-only.
Roles like "tester" or "committer" are absent on purpose: splitting sequential
phases of the same work is a named anti-pattern, and it is the shape our pipeline
templates already have.
THREE THINGS THE IMAGE CORRECTED, none of which review would have caught:
1. `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS=1` (in the plan) removes EVERY agent
type, including the ones `--agents` defines. Measured: the lead reported "an
empty available-agents list" after trying four role names and — to its credit —
refused to fabricate a subagent result. Worse, the unit test asserting
"builtins off is paired with our own roles" PASSED throughout, because the
pairing holds in our code and not in the CLI. Dropped, and the test rewritten
to assert only what a unit test can speak to.
2. `--forward-subagent-text` refuses to run without `--output-format=stream-json`,
which would change how this module reads output. Dropped.
3. `--append-subagent-system-prompt` does not exist in 2.1.220 despite being
documented. The anti-shortcut rule is inlined per role instead — better anyway,
since a verifier and an explorer need different wording.
Evidence instead of assumption: Claude Code writes a per-subagent transcript at
`<session>/subagents/agent-*.jsonl`, so the guest is asked to count them before
collection (they live in /root, outside the collected tree). `VmOutcome.subagents`
is `Option<u32>` and the phase log prints it: `None`/"?" means the probe could not
run, which is a different fact from "delegated to nobody" and only one of those is
about the agent.
Verified in a container against the real CLI on tank before any of this shipped:
`FANOUT-OK`, a subagent transcript on disk, and zero errored Agent calls.
469 tests pass, clippy clean.
|
||
|
Omar Sobh
|
7696009b25 |
fix(fleet): name the BACKEND in a placement refusal, not just "microvm capability"
Observed on the negative control: a mission with backend='kimi' was correctly refused, but the message read "no online node reports microvm capability" — and both nodes do report it. What one lacked was the image. That first clause would have sent an operator to reinstall firecracker on a node that already had it. The refusal now names the backend, and the remedy still names both halves. |
||
|
Omar Sobh
|
d9f53a3f96 |
fix(fleet): placement requires the backend's rootfs image, not just KVM
The first real microVM mission was placed on morpheus because it reports
{"microvm": true}, while only tank had rootfs-claude.ext4. It failed by name
rather than booting the wrong image — but whether a mission ran came down to
which capable node was listed first, which is a coin flip dressed as scheduling.
`missions.backend` was invisible to the scheduler.
The node now enumerates the images on its disk and reports them as a `rootfs`
ARRAY. `microvm::available_backends` lives beside `rootfs_for`, its inverse,
because the two must agree on what a backend name means; split apart, one drifts
and the scheduler starts promising images the booter cannot find. It only
advertises names `rootfs_for` would accept, and reports an empty array rather than
omitting the key — set_capabilities REPLACES, so a deleted image stops being
advertised instead of leaving a stale claim.
`nodes::online_for_backend` requires microvm AND that the node's list contains the
mission's backend. A node on an older daemon has no `rootfs` key and matches
nothing: unknown is not permission, the same treatment every other capability
gets. `backend_key` maps the three spellings of "the default image" to the one
name the node advertises, and is tested — a mismatch there would reject every node
for an ordinary mission with no backend set.
The launch error now names both halves of the fix, since "no capable node" was
true but unhelpful when the node was capable and merely lacked the image.
Mission gains `backend` on the domain struct; it was a column the executor read
from the phase query while the struct that placement uses could not see it.
464 tests pass, clippy clean.
|
||
|
Omar Sobh
|
1cd81a8b2a |
fix(missions): place a microvm mission before returning from on_launch
Self-inflicted, one commit old, and found by running a real mission: the early return I added for "a microvm mission materialises no team" sat ABOVE the microVM placement block in the same function, so on_launch returned before ever choosing a node. The mission then failed with the executor's own guard — "mission has no target_node_id ... a microvm mission cannot run on the gateway, which has no /dev/kvm" — which is the guard working exactly as designed, on a cause one layer further up. Placement now runs first. Worth noting the shape: adding an early return to a long function silently skipped everything below it that the same runtime_kind depends on. 461 tests pass, clippy clean. |
||
|
Omar Sobh
|
521b8dea10 |
fix(missions): the third team gate, and a container a microvm mission never uses
on_launch demanded a team template too — "pick teams in the wizard" — so a microvm mission still could not launch after the first two gates were exempted. Three separate places required a claw graph for a path that runs one `claude -p` inside a VM: routes::missions (draft→running), phase_runner::launch_phase (no matching teams → stay pending), and here. Returning before team materialisation rather than filtering its picks: claws that never run are not a cheaper version of the same thing, they are a runtime binding and a pairing code describing something nothing speaks to. Also stops provisioning the per-mission ZeroClaw container for a microvm mission. The first real run was observed starting one and leaving it holding a pairing code and ~3 GB of image for the life of a mission that never contacts it. 461 tests pass, clippy clean. |
||
|
Omar Sobh
|
0a9747091f |
fix(missions): a microvm mission needs no team, and two checks required one
Found by running one: the mission was created with runtime_kind='microvm' and then refused to launch with a bare 400, because draft→running requires a materializable team. Past that, `launch_phase` returns early when a phase has no matching teams — so even with the launch allowed, the phase would have sat `pending` forever while the log said only "no matching teams", and the executor would never have been reached. Neither check applies to this path: microvm_executor runs the agent CLI directly in the VM, so there is no claw graph to materialise. Satisfying the checks by attaching a team template would have provisioned claws that never run. The repo checkout still happens — the VM needs the repository. 461 tests pass, clippy clean. |
||
|
Omar SobhandClaude Opus 5
|
c9b7d8b6ca |
fix(missions): a microvm mission could not be created at all
`runtime_kind='microvm'` passes the DB CHECK, is honoured by placement, and now has an executor — but `POST /api/missions` rejected the value with 400, so the only interface that creates missions could not produce one. And `backend`, which selects the per-CLI rootfs, was not in the create payload at all: it existed as a column and as a parameter to `vm_create`, with nothing able to set it. microvm needs no target_node_id at create time, unlike local_herdr: placement resolves a KVM-capable node at launch and fails the launch when there is none, so an explicit target is a request rather than a requirement. 461 tests pass, clippy clean. 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
|
2edafdaf0d |
fix(fleet): a microVM authenticates by subscription only — never with an API key
B4.4 had the microVM path share `forwarded_provider_env(auth)` with the
container path, on the reasoning that the two must not diverge. That was wrong
in the one direction that costs money: gw-04 has CLAWMATES_RUNTIME_AUTH unset,
so the container path forwards ANTHROPIC_API_KEY today — and a VM would have
received it. Claude Code ranks the API key ABOVE the subscription's OAuth token,
so the VM would have worked perfectly while billing per-token against a plan we
already pay for. No error, no symptom but the invoice.
`microvm_provider_env` is subscription-only BY CONSTRUCTION: it does not take
the auth mode as an argument and does not read CLAWMATES_RUNTIME_AUTH at all.
Taking the mode as a parameter would mean one unset variable on a new host
silently turns the API key back on. The container path is unchanged and still
honours the operator's mode — the divergence is now deliberate, with the reason
at the definition.
Two other fail-closed rules fall out of it:
- A missing or blank subscription token REFUSES the launch rather than
returning an empty environment. A VM with no credential does not error;
`claude -p` hangs, which reads as a phase stuck at `running` with nothing in
the logs. The refusal names the variable.
- An unrecognised backend is refused rather than handed the Anthropic token.
GLM and Kimi reach their own endpoints via ANTHROPIC_BASE_URL and that
contract is not settled yet; guessing it would send a subscription
credential to z.ai.
Measured on tank, and this is the end-to-end proof B4.4 could not give:
`claude -p` in the agent-claude image with the real subscription token replies
"OK". Injecting the token in a VM moves the failure from "Not logged in" to a
network error, so the credential channel is accepted by the CLI — the VM's
remaining problem is egress (#49), not auth.
447 tests pass, clippy clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
c3297b86cf |
feat(fleet): B4.4 — credentials reach the microVM guest as exec env, and a bad entry refuses the exec
`claude -p` in the VM failed with "Not logged in". The credential now travels on
the exec op: `env` on `vm_exec` → fcagent → the command's environment. An env var
rather than a file because the per-VM rootfs dies with the VM but an env var
never touches the guest disk at all.
**Every problem in an env entry fails the exec.** The tempting alternative —
skip the entry we cannot use and run anyway — produces a `claude -p` with no
credential, and that does not error, it HANGS. A phase stuck at `running` for
ten minutes with nothing in the logs is exactly what a missing token looked like
on the container path. Names are validated ('=' or NUL would define a different
variable than the one asked for via putenv semantics), values must be strings,
and errors name the key and never the value — an error string travels back over
the wire and into logs.
One list of which credentials travel: `forwarded_provider_env` reuses
`forwarded_provider_keys`, and the container path now reads it too. If the two
execution paths diverged, a mission would behave differently depending on where
it landed — including the expensive way, where one path forwards
ANTHROPIC_API_KEY and bills it while the other uses the subscription. A blank
value is omitted rather than forwarded empty, so `claude` reports having no
credential instead of failing authentication with one.
Verified on tank (`--vm-selftest` backend=claude, 13/13, create 1532 ms): an
injected var reaches the guest command over the real vsock wire, and an
unusable entry comes back ok:false with no rc.
FINDING — the CLI leg remains UNPROVEN, and deliberately so. The guest has no
network interface: `create` writes boot-source, drives, machine-config and vsock
and no `network-interfaces` key, and a booted guest has no routes, no
resolv.conf, no DNS and no TCP. So `claude -p` cannot reach the API whatever
credential it holds. Injecting the real token would have proven nothing, because
the failure would have been network and not auth. Filed as B4.6 (task #49) with
the TAP-vs-vsock-proxy trade-off; B4.5 is now blocked on it.
444 tests pass, clippy clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
6687f8b808 |
feat(fleet): B4.3 — per-mission rootfs selection (missions.backend)
`vm_create` takes a backend name and boots `rootfs-<backend>.ext4`; NULL or "default" boots the golden image. Makes the per-CLI images from B4.1 actually reachable (one image per CLI, per A6). A missing image is an ERROR naming the file and how to build it, never a quiet fall back to the default. That fallback is the tempting version and the wrong one: it would run a claude mission in a kimi VM, or in a rootfs with no CLI at all, and report success for whatever came out. Verified on real hardware, not just in a unit test — the selftest asks for an image that does not exist and FAILS if it boots. `create` now reports the rootfs that actually booted, not the one that was requested, so a mission artifact can show the wrong VM ran. The migration adds no CHECK constraint listing the CLIs. Which images exist is a property of the NODES, not the schema; a constraint would need migrating for every new image while still not guaranteeing the image exists anywhere. The node validates and names what is missing. Backend names are `[A-Za-z0-9_-]` and rejected rather than sanitised, since they become filenames. Verified on tank: default backend 8/8; `CLAWMATES_FC_BACKEND=agent-terminal` 9/9 including the absent-image check, create in 910ms on a rootfs built from a real Docker image. 435 tests green, no leaked processes or VM dirs. 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
|
0f7fa31f86 |
feat(fleet): B1 — microvm runtime kind and KVM placement predicate
Phase B step 1, on top of the B0 spike that proved microVMs boot here.
KVM is a HARD predicate, not a preference. gw-04 — where every mission
runs today — is itself a VM without nested virtualisation and has no
/dev/kvm, so a microvm mission landing there cannot start at all. The
scheduler therefore has to be able to tell nodes apart, which means the
node has to report what it can host.
Nodes gain a `capabilities` jsonb, populated from a probe on the node
rather than from configuration: /dev/kvm either exists there or it does
not, and nothing on the server can make it appear. The probe OPENS the
device rather than stat-ing it, because it can exist while being
unopenable (wrong group, or a container without the device passed
through) — which is precisely how firecracker will fail.
`microvm` requires BOTH kvm and a firecracker binary. A node with KVM
but no binary looks capable by the obvious test and fails at launch; a
node with the binary but no KVM is gw-04.
Placement fails the launch when no capable node exists, rather than
letting a mission sit in 'running' with nowhere to run. An explicit
target_node_id is treated as a request, not a guarantee — it is honoured
only if that node actually reports the capability.
`capabilities` defaults to '{}' NOT NULL so a node that has never
reported fails every predicate: an unqueried node and an incapable node
must be indistinguishable to the scheduler, because scheduling onto a
node whose abilities are unknown is how you get a mission that cannot
start and does not say why. The report replaces rather than merges, so a
capability the node has LOST disappears instead of leaving a stale true.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
da3731d753 |
fix(missions): a coding phase that delivers nothing is a failure
The last open item in the silent-success class: a coding phase that changed no files reported `completed` — the same status a phase gets for delivering tested, reviewed, pushed work. Mission `019fcf62` completed that way with its agents silently unpinned from the repo, and nothing in the platform disagreed; it was found by a script diffing the forge. The verdict is applied at capture rather than at completion, because capture selects on `status = 'completed'` — the platform does not know whether a phase produced anything until after it has already finished. Three conditions must hold before failing a phase, because a false positive here fails honest work: the phase is a coding phase (research phases legitimately write nothing to the tree), the diff was actually computed (an uncomputable diff also reports zero files — blaming the agent for a platform fault is the same defect wearing different clothes), and `allow_empty` is not set. Only an explicit `true` opts out, so a typo leaves the check armed. Registered in phase_config with its reader named, per the seam-2 rule. Also closes an ordering hazard this exposed: capture is batched and runs after a phase completes, so a backlogged mission could close as 'completed' and only then have capture discover an empty phase — leaving a 'completed' mission holding a 'failed' phase, unfixable because the mission-close CASE only touches 'running' rows. A repo-bearing mission now waits for its work to be captured before closing. Adds a `noop` scenario to the harness: a phase told to change nothing, which PASSES only when the phase comes back `failed`. Same discipline as the uid self-test — a check that has never been seen to fire has not been shown to work. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
4f6719c80e |
feat(missions): make copy-in/copy-out the default filesystem model
Copy mode shipped opt-in so that changing how every mission receives its
code required someone to type it. Four production missions and a
fail-closed harness later, opt-in is the riskier setting: the bind path
is the one with four documented work-loss incidents, and leaving it as
the default means the untested path runs whenever nobody sets the
variable. `CLAWMATES_MISSION_FS=bind` still selects it; anything else —
unset, empty, misspelt — gets copy mode, so a typo lands on the safer
path rather than the one being retired.
Also fixes a real leak found while scoping the deletion below: the git
helper built its `safe.directory` argument with `Box::leak`, justified as
"the process is short-lived". That is true of a CLI and false of cm-api,
which is a long-running server — so it leaked one allocation per git
call, growing with every phase of every mission.
The A5 deletion is NOT done here, and two of its items should never be
done:
- `scrub_remote_credentials` is a security control, not a uid
workaround. Copy mode uploads the whole `.git` into a container the
agent controls as root, which makes stripping the token from
`.git/config` more necessary, not less.
- `has_local_work` / `checkout_in_use` guard `fetch_and_reset` at every
phase launch and have nothing to do with who writes the checkout.
The host checkout still persists across phases under copy mode —
mission `019fcf62` shows the marker firing there. Deleting them
reintroduces PRIOR-PHASE-WORK-WAS-LOST.
The rest (`share_repository_across_uids`, `clear_stale_commit_editmsg`,
`-c safe.directory`) are genuinely obsolete under copy mode but stay
while `bind` remains selectable: a workaround may only be deleted once
the situation it works around can no longer be chosen.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
1253595ba7 |
fix(missions): stop three launch failures from passing as success
A verification run against the deployed stack found a chain mission whose phase 0 reported `completed` with zero files, no commit error and no push error — indistinguishable from a phase that correctly had nothing to do. Three separate defects had to line up, each of them the same shape: a failure sharing its representation with a legitimate negative result. 1. `pin_agent_workspaces` embedded the whole config in one `sh -c` argv. That works until the file grows — config gains a block per provisioned claw — then fails with `argument list too long`. Now written through the tar upload API, which has no argv limit, so the failure mode is gone rather than merely further away. 2. A failed pin was logged "(continuing)". Without the pin, agents write to their sandboxes and the committer finds nothing in /mission/repo — the mission cannot deliver, so the launch now fails where someone is still looking. The restart that applies the pin is fatal for the same reason. 3. `capture_phase_diff_at` swallowed `git diff` failures with `unwrap_or_default`, so an unreadable base landed `empty: true, files_changed: 0` — byte-identical to an honest no-op. The error is now recorded as `diff_error`, and an empty patch that came from a failed diff is no longer trusted to mean an unchanged tree. Adds scripts/verify-mission-delivery.sh, which found #1 and #2 on its first real run. Its probes are fail-closed: no placeholder values, a self-test that proves the uid probe can detect the split it looks for, and FAIL-NORUN for a scenario that never executed. Its own first version had this bug too — a `die` inside `$(...)` exited the subshell, so a run that could not authenticate printed "all checks passed" and exited 0. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
7e07c389c6 |
feat(missions): wire copy-in/copy-out behind CLAWMATES_MISSION_FS=copy
With the flag set, ensure_container omits the /mission bind, the checkout is pushed into the container at phase launch, and the agent's work is pulled back before capture. The simplification that makes this small: sync_out unpacks over the SAME host path the checkout came from. The host directory stays a server-owned staging area with exactly one writer, and capture_phase_diff_at needs no change at all — it still finds a normal checkout exactly where it always has. Delivery, gating, commit and push are untouched. Two failures are deliberately loud rather than silent: - copy-IN failure fails the phase launch. Continuing would start a phase against an empty directory, and the agent would cheerfully report having done work on a repo that was not there. - copy-OUT failure SKIPS capture. Capturing anyway would diff a stale host tree and record "no changes" for work that exists — success reported for nothing, which is the exact failure mode this codebase keeps paying for. Opt-in: the bind path is what production has run since the beginning, and the test asserts a near-miss value leaves it there rather than silently switching every mission. 414 tests, clippy clean. 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
|
0d9498ec6e |
fix(missions): copy an allow-list, not the whole 1.7GB seed dir
Checking before deploying caught a mistake in the previous commit. The seed dir on gw-04 is 1.7 GB and the first version copied all of it per mission — tens of seconds each, and ~17 GB across ten concurrent missions. 1.5 GB of that is .rustup: a Rust toolchain that installed itself into the data dir back when HOME=/zeroclaw-data and the image had no toolchain. The image now ships Rust at /usr/local/cargo, which is what the container's PATH actually resolves — verified live. The data-dir copy is dead weight and is not even reachable. SEEDED_PATHS now copies only what carries per-mission identity or secrets: .zeroclaw (config.toml with the door token, sessions.db, devices.db), clawmates-mcp.json, .claude + .claude.json, .kimi-code, glm-home, agents. Roughly 46 MB instead of 1.7 GB — about 37x smaller. Caches and toolchains are deliberately excluded: .rustup, .npm, .cargo, .cache, .local. They hold no secrets and a mission reads the image's. Absent paths are tolerated: a fresh deployment has no .kimi-code until Kimi is first used, and that must not fail container creation. The test asserts both directions — the token-bearing paths ARE copied and the caches are NOT — because either mistake is silent: copying everything just makes missions slow, and copying nothing quietly restores the credential sharing. 409 tests, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
15e7608e4a |
fix(missions): give each mission its own runtime data
Every per-mission container bind-mounted the SAME host seed dir as
/zeroclaw-data — shared with each other AND with the singleton runtime.
That directory holds config.toml, which carries the §15 door bearer
token, plus sessions.db and devices.db.
So one mission could read another mission's credential, and anything it
wrote there was inherited by every later mission. teardown_container
only removes /var/lib/clawmates-missions/{id}, so the shared directory
was never cleaned — the contamination was permanent.
The code already knew. The comment on DEFAULT_SEED_DIR names the sqlite
race and calls copy-on-write per mission the long-term fix. This is that
fix: seed_runtime_data copies the seed into
<missions_root>/<mission>/runtime-data at container create, and the
mount points there. Cleanup is free — teardown already removes that tree.
The copy runs in a throwaway container because cm-api cannot see the seed
dir: it hands that host path to Docker but never mounts it itself. The
runtime image is reused so nothing extra is pulled, and `cp -a /seed/.`
copies dotfiles — `/seed/*` would silently skip .zeroclaw/ and produce a
runtime with no config at all.
A copy failure is fatal to container creation on purpose. Falling back to
the shared mount would silently restore the credential sharing this
removes, and silent fallback to a weaker posture is the failure mode this
codebase keeps paying for.
The test asserts path shape rather than behaviour: an edit that points
the mount back at the seed dir restores credential sharing with no other
visible symptom, so the path IS the invariant.
408 tests, clippy clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
5d98fcf44a |
feat(missions): forward ZAI/KIMI keys so one binary serves three backends
All three providers run through the SAME `claude` binary, verified live: Anthropic CLAUDE_CODE_OAUTH_TOKEN -> ANTHROPIC-OK GLM ANTHROPIC_BASE_URL=https://api.z.ai/api/anthropic -> GLM-OK Kimi ANTHROPIC_BASE_URL=https://api.kimi.com/coding/ -> KIMI-OK That is a stronger multi-provider story than a provider-per-implementation: skills, subagents, MCP, hooks and tool policy are identical across all three because it is literally the same harness. The `kimi` CLI (0.31.1, shipped in the image) 401s on this key and is not needed -- the claude binary reaches Kimi's Anthropic-compatible endpoint directly. Worth knowing before someone debugs the CLI. forwarded_provider_keys now ships ZAI_API_KEY and KIMI_API_KEY into mission containers in BOTH auth modes: they are unrelated to the Anthropic credential, so the api_key/subscription split does not apply to them. A mission that selects a backend without its key present would otherwise fail at the first turn. Keys persisted in /opt/clawmates/.env and passed through compose. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
4ff4e6f7ee |
fix(missions): a root-owned COMMIT_EDITMSG must not block delivery
Mission 019fcd0c produced correct work — a reviewed, tested function plus a REVIEW.md quoting a real cargo test summary — and delivered none of it: git commit → exit 128: could not open '.git/COMMIT_EDITMSG': Permission denied The agent ran `git commit` itself inside the mission container (as root), leaving that file owned by root at 0644. core.sharedRepository covers objects and refs — .git/index lands at 0666, which is why commits work at all — but not COMMIT_EDITMSG, which git writes with the default umask. Unlinking works where overwriting does not: removing a file needs write permission on the DIRECTORY, and .git/ is owned by the server. Silent on failure by design, so the commit reports the real error rather than this speculative cleanup. Third distinct instance of the same uid-split class (objects, then the capture base, now this). The pattern holds: the checkout is one directory written by two users, and each new file git touches is a new opportunity. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
758b2dbd96 |
feat(missions): run a phase as one direct session, behind a flag
CLAWMATES_MISSION_EXECUTOR=session makes launch_phase run the whole phase as a single `claude -p` against /mission/repo instead of driving turns through ZeroClaw. Opt-in, because silently changing how every mission executes is exactly the sort of change that should require someone to have typed it. It still writes ONE topology_runs row. The entire downstream lifecycle -- close_finished_phases, evaluation, capture, commit, gate, publish -- keys off those rows, and inventing a second completion path would mean two ways for a phase to finish with one of them untested. The session is simply a run with tier='session' and an empty graph. Spawned rather than awaited: launch_phase runs inside the sweep loop, and blocking it for the length of a coding session would stall every other mission. The session's own summary is logged as diagnostics only. Whether the phase actually did anything is still decided downstream by capture and delivery against the repository -- a 0-exit session that pushed nothing was measured at ~5%, so the agent's account can never be the verdict. 406 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
|
5232175c88 |
fix(missions): forward the subscription token into mission containers
Switching agents to claude_cli left missions hanging: the per-mission container had claude_cli configured but no credential, so `claude -p` waited forever. A phase sat at `running` for ten minutes with nothing in the logs — no error, because there is nothing to error on. The original subscription design assumed a persisted `claude /login` under a bind-mounted $HOME. That holds for the shared runtime and NOT for a mission container, which gets its own data dir and therefore no login. So subscription mode now forwards CLAUDE_CODE_OAUTH_TOKEN. The two Anthropic credentials remain mutually exclusive, and there is now a test asserting it in both directions: Claude Code ranks ANTHROPIC_API_KEY above the OAuth token, so shipping both bills the API while the deployment believes it is on the subscription — visible only on the invoice. Deployment: CLAWMATES_RUNTIME_AUTH=subscription and CLAUDE_CODE_OAUTH_TOKEN added to compose + .env on gw-04. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
ac47dcbe94 |
feat(runtime): run agents on the subscription via the real claude binary
provider_alias_for now resolves Claude models to `claude_cli.default`,
which spawns the actual `claude` binary, instead of `anthropic.default`,
which posts to the raw API with Claude Code identity headers. Agent work
is ~99% of tokens, so this moves essentially all of it onto the Max
subscription and onto the supported client.
The judge deliberately stays on the API key. If both rode one credential,
a single subscription limit would blind the verifier at exactly the
moment there is most to verify; this way a throttle degrades missions but
verification keeps working.
Runtime config (applied on gw-04, reloaded via loopback — remote admin
reload is disabled by design):
- [providers.models.claude_cli.default] with mcp_config pointing at the
§15 door, so a subscription agent can ACT and not merely reason
- disallowed_tools denies Claude Code's own Bash/Write/Edit/WebFetch so
the gated door is the ONLY actuator and nothing bypasses the audit log
- env CLAUDE_CODE_OAUTH_TOKEN = "$CLAUDE_CODE_OAUTH_TOKEN" — the $NAME
form reads the daemon env, keeping the token out of config.toml
- anthropic.judge swapped to the API key (0 oat01 left in config)
Verified before changing anything: the real binary returned SUBSCRIPTION-OK
through the token, then ENV-OK once the daemon carried it in env.
Note for future readers: /api/config/prop reflects what is CONFIGURED, not
what the binary supports — `openai` 404s there too. An earlier note that
the image "has no claude_cli in its schema" was true of the old :sync
image and is not true of the rebuilt one.
400 tests, clippy clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
ad89ef94cd |
feat(library): attribute a run to a mission, and prove what it contributed
`corpus_items.mission_id` has existed since the table landed and nothing could populate it. `POST /api/library/runs` now accepts `missionId`, which is the seam the wizard needs: a mission-driven run is the same run, tagged. `corpus::contributed()` answers the question a continuous mission has to be able to answer — did THIS run add anything new. Because `record` never reassigns mission_id on conflict, the mission that first found a source keeps the credit, so a rerun cannot inflate its own count by re-recording what an earlier run already held. The test asserts exactly that: two missions see the same paper, the finder reports 1 and the rerun reports 0. This is the check the 0030-0044 generation of continuous research did not have. It could run weekly forever and every run looked like success. The test also earned its FK: the first version attributed to a bare UUID and the database refused it. Attribution to a mission that does not exist is not attribution, so the test now seeds real mission rows. 400 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
|
9bdc3cd89b |
fix(missions): stop titling commits "phase phase work"
Mission 019fc4e0 pushed "clawmates: phase phase work" — the iteration
marker was interpolated into a slot whose default already said "phase".
A rerun read correctly ("pass 2 phase work"), so only the common case was
wrong. Cosmetic, but it lands in the operator's git history under their
own name now that delivery commits as them.
Subject is now "clawmates: phase work" and "clawmates: phase work
(pass 2)". The test covers both, since the bug lived only in the branch
the previous shape did not exercise.
Co-Authored-By: Claude Opus 5 <[email protected]>
|
||
|
Omar SobhandClaude Opus 5
|
ddab8e35f5 |
feat(missions): commit as the operator, overridable per deployment
Delivery commits now carry "Omar Sobh <[email protected]>" by default, so pushed branches associate with the operator's forge account the way their own commits do. CLAWMATES_COMMIT_NAME / CLAWMATES_COMMIT_EMAIL override it — a shared instance wants a bot identity, not a person's. This is attribution, not the fix. What made 019fc450's phase fail was the *absence* of any identity: the server container has none of its own, so git commit exits 128 regardless of which name would have been used. That was fixed in 25d9805; this only changes the value. The push credential is GITEA_TOKEN throughout and is untouched by any of it. Since the author line now names a person, the commit body says plainly that agents authored the work — otherwise autonomous commits would be indistinguishable from hand-written ones in git log. Also fixes 13 stray spaces that a string continuation had baked into every message body. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
1a979f500f |
fix(missions): judge local work against the remote tip, not the capture base
Mission 019fc476 lost phase 0's work again, and this time the cause was the interaction between two fixes I had just shipped. has_local_work compared HEAD against .git/clawmates-base to decide whether a checkout held mission work. advance_base_commit moves that marker to each phase's committed head. So the moment a phase committed successfully, base == HEAD, has_local_work reported "pristine", and the next phase's launch reset the work away. Phase 1 wrote CHAIN_MISSING.md. The preceding mission survived only because its phase 0 FAILED to commit and left a dirty tree. Fixing that failure is what exposed this one. One marker was carrying two meanings: "where should the next diff start" (rolling, per phase) and "is this checkout untouched" (fixed for the mission). Only the first belongs to clawmates-base. The second is now `origin/<branch>`, which does not move for the life of the mission, so a HEAD that differs from it means a phase committed — one commit ago or five. An unresolvable remote ref preserves, since wrongly skipping a refresh costs staleness while wrongly resetting destroys a phase. The existing test passed throughout because it never advanced the base. It now does, which makes it a reproduction rather than a restatement, and it needs a real bare origin to resolve origin/main the way a clone does. Co-Authored-By: Claude Opus 5 <[email protected]> |
||
|
Omar SobhandClaude Opus 5
|
25d9805806 |
fix(missions): commit under the pipeline's own git identity
Mission 019fc450 lost its first phase to: git commit → exit 128: Author identity unknown The server container has no git identity — `git config --global user.email` exits 1 — so any commit fails unless one is supplied. This is the third consecutive failure whose trigger was agent behaviour rather than our code. Earlier missions committed only because an agent had happened to run `git config user.email` in the checkout, leaving a local identity the server inherited. Alongside the object-permission split and the reset, the pattern is the same: delivery depended on incidental side effects of what an agent chose to do, so identical missions succeeded or failed for reasons invisible in our code. Supplied via GIT_AUTHOR_*/GIT_COMMITTER_* env on every git call, which overrides config without a leaked string per invocation and names the committer as the pipeline. Agents' own commits keep the identity they set. The test asserts the identity *overrides* an existing local config rather than trying to unset the developer's global — an override necessarily also applies when config is absent, and it does not race parallel tests. Co-Authored-By: Claude Opus 5 <[email protected]> |