1758 Commits
Author SHA1 Message Date
sam 4242d94676 chore(release): v1.42.0
deploy / gate (push) Failing after 5m36s
deploy / build-and-push (push) Skipped
deploy / dist-zip (push) Skipped
v1.42.0
2026-09-26 10:32:39 +10:00
sam 1358c3d759 feat(prreview): benchmark harness scoring findings on the Martian problems
Scores a reviewer's findings on the 38 runnable Martian Code-Review-Bench
PRs: the deterministic core turns findings into posted comments, an
independent judge model matches them to the goldens, and the run reports
golden micro-recall and golden-only precision. The reviewer is a findings
fixture directory until the pr-review workflow lands.

Run with: task bench:prreview -- -findings DIR
2026-09-26 10:30:12 +10:00
sam 585df0f81e feat(agentexec): output adapters for Codex, Pi, OMP and Copilot CLI 2026-09-26 10:28:40 +10:00
sam a8c8dfbd7d feat(daemon): run a Kit profile's task in its Kit container on the egress path 2026-09-26 10:14:33 +10:00
sam bc215e8daa feat(config): Kit profiles pin a workload Kit and mixins by digest 2026-09-26 09:21:57 +10:00
sam 0d042b72d9 feat(agentexec): run a Kit task's stages on its harness through a named output adapter 2026-09-26 09:20:30 +10:00
sam 5507ded2d5 feat(storepkg): package descriptor with strict decoding and validation 2026-09-26 09:13:39 +10:00
sam 7a54db0cc6 fix(agentexec): count Claude cache tokens as prompt tokens, as the built-in loop does
Claude's input_tokens excludes cache reads and writes; the built-in
loop's Anthropic provider folds them into PromptTokens so budgets count
total prompt size. The harness adapter now does the same, so one budget
means the same on either runner.
2026-09-26 09:11:57 +10:00
sam 4067949ce8 feat(agentexec): parse Claude Code's stream-json output for the harness runner
Pairs tool_use and tool_result blocks by ID into tool-call reports, keeps
the latest session_id, takes the run's usage from the result event and
falls back to per-message usage, counted once per message ID, for a run
killed before its result. Tested on streams recorded from Claude Code
2.1.282 and scrubbed of host detail.
2026-09-26 09:11:57 +10:00
sam 92a9eca12c docs(architecture): state the shipped execution transition rules
The lifecycle block still showed `running -> merged` and never mentioned
`completed`. `running -> merged` is now illegal (taskstate transition table)
and `merged` is reachable only from `pr_open`; a workflow that opens no pull
request ends in the terminal `completed`.

Rewrite the block to the current rules and fold the crash-recovery requeue
into the `running` row it belongs to. Regenerate the committed docs artifact
carried by `task docs:artifact:check`.
2026-09-26 04:01:08 +10:00
sam 30211478c2 test(taskstate): seed fixture task states along the transition table
The execution transition table refuses most of the pairs shipped fixtures
wrote to build a finished task -- running -> merged, queued -> parked,
queued -> waiting_human, queued -> merged -- so those fixtures fail the
moment the store enforces it.

internal/taskstate/taskstatetest seeds a status by walking the table's
legal edges (shortest route, computed from taskstate.CanTransition), so a
fixture cannot write an illegal pair and fails loudly when no route
exists. The fixtures in internal/daemon, internal/app/archied,
internal/webui and internal/infrastructure/postgres go through it, and
the table's own test names running -> merged as refused.
2026-09-26 04:01:08 +10:00
sam 4e9b30d712 fix(daemon): keep a terminal worktree that holds uncommitted work
The cleanup added for no-change runs removed a `completed` task's
worktree whenever it had no PR. agent.run also ends its workflow
`StatusCompleted`, and it works in a real clone whose uncommitted edits
are the deliverable, so the status alone was enough to delete the work:
no commit, no push, no other copy of those edits anywhere.

Cleanup now reads the worktree first and skips a dirty one. A worktree
whose status cannot be read is kept too -- a wrong keep costs disk, a
wrong delete costs the work -- while one that is not on disk has nothing
to keep. The lifecycle fixtures prepare a real clone now, which is the
only shape the daemon ever cleans up, and the cancelled-context test
still cancels only the cleanup call.
2026-09-26 04:01:08 +10:00
sam f7bfd78d5f fix(ui): count completed runs as delivered on the workflows surfaces
The workflows page's per-workflow bar and its 'N of M' text, and the
workflow picker's percent on the new-task form, counted `merged` alone.
A workflow whose runs now end `completed` (a no-change build, a triage
that needed no code) therefore rendered zero delivery beside three
sibling surfaces that already counted both.

The count moves into ui/src/lib/delivered.ts, which GatePulseCard,
ThroughputTiles and TasksSummary now read too instead of keeping their
own copies of the arithmetic. The picker's label says delivered, not
merged: a run that ends completed is not merged.
2026-09-26 04:01:08 +10:00
sam 4f62ce5dfc chore(ui): rebuild the dashboard for the completed count 2026-09-26 04:01:08 +10:00
sam 845b192a89 feat(taskstate): count completed runs in the per-workflow stats
The transition table moved the no-change outcomes to StatusCompleted, so a
run that opens no pull request now ends in a status the per-workflow stats
did not count at all: it was not merged, not in review, not parked, and the
workflows page would have shown it as a run that went nowhere. The count
travels the whole State Store path, since every dashboard consumer reads it
through the gRPC client rather than the local store.

- WorkflowStats filters `completed` beside merged and pr_open; the SQL is
  the count, so a wrong filter reads as zero rather than failing, and
  TestWorkflowStatsCountsCompletedRuns holds it against a real store.
- storecontract.WorkflowStat gains Completed (json "completed"), the proto
  message gains field 9, and workflowStatProto/workflowStatValue carry it;
  TestWorkflowStatProtoCarriesEveryField round-trips every field by name.
- The gateway's chat task report names the status.
- The dashboard counts a completed run as delivered in GatePulseCard's
  totals and badge numerator, and the WorkflowStat/WorkflowStats/WorkflowRow
  interfaces carry the field.
- TestOutcomeSitesAreTransitionsFromRunning is the guard that keeps the
  producer and the table agreeing: it re-reads this package's tc.Outcome
  assignment sites from source and requires each status to be one
  internal/taskstate allows from running, so a new or moved site has to be
  adjudicated against the table instead of discovered on a live run.
2026-09-26 04:01:08 +10:00
sam 8ba0b90861 feat(taskstate): end no-change runs as completed and clean their worktrees 2026-09-26 04:01:08 +10:00
sam 7b86dd6cfe feat(taskstate): transition tables for executions and steps 2026-09-26 04:01:08 +10:00
sam 419334dfa2 fix(archied): resolve stored provider credentials at boot 2026-09-26 03:50:07 +10:00
sam 093e677ad8 fix(controlplane): reject stored boot-derived provider keys 2026-09-26 03:44:40 +10:00
sam 235b9c1a87 refactor(agentexec): own the capture file format in agentexec, not the app layer 2026-09-26 03:30:19 +10:00
sam 37d913c5fd feat(agentexec): serve capture tools to harnesses over MCP
archie-agent mcp is a stdio MCP server, on the official go-sdk, serving a
stage's capture tools and appending accepted calls to a captures file.
The harness runner writes the tool spec and a standard mcpServers config,
registers it through HarnessSpec.MCPConfig, and reads the captures back
into the stage result. The captures file is writable by the harness user,
so the worker validates every record again with the same acceptCapture
the built-in loop now shares, and forged, undeclared or over-cap records
are dropped. A stage with capture tools on a harness without MCP is
refused before it runs.
2026-09-26 03:28:58 +10:00
sam 8274ecbc53 fix(prreview): cluster duplicate findings and read every diff shape
The duplicate merge compared each finding against the ones already kept, so
overlap was transitive only through the survivors: a chain of findings 1-2,
2-3, 3-4 collapsed to one finding or to two depending on the order they were
handed in, and the two readings tied on score. It is a clustering now -- a
canonical sort, then a union of each run of overlapping ranges -- so the
surviving set is a property of the findings and not of the permutation they
arrived in, and a cluster's member is chosen by score and then by the
finding itself rather than by arrival order.

Two things the merge got wrong besides order. The PRD keys duplicates on
(file, overlapping lines, category), not on severity, so Finding carries a
Category and the merge reads it, while the severity now only decides which
duplicate speaks for the cluster. And a cluster is blocking when any member
is, so an advisory duplicate can no longer swallow the merge gate's verdict
and turn REQUEST_CHANGES into COMMENT.

diff.go read only the shape git writes. A plain unified diff -- sections
opened by a --- / +++ header pair with no "diff --git" line -- belonged to no
file and contributed no added lines, a silent narrowing of the diff-rules
gate's input; a file section opens from either now. git's C-quoted paths are
decoded from the diff --git line, the --- / +++ headers and the rename pair,
octal escapes to bytes, because a quoted path is not a path the snapshot has.
FileStatus is derived from every statement the section makes -- new file
mode, deleted file mode, old mode / new mode, rename from / rename to, and
the /dev/null side -- so a binary or empty file, whose patch has no headers
and no hunks, is reported as what it was rather than as a modification, and a
change of object type is the typechange the change capture already persists.
2026-09-26 03:24:40 +10:00
sam 2657b18be7 fix(prreview): order the confidence floor before dedup and merge overlapping findings
Score recorded a finding's duplicate identity before dropping it under its
severity's confidence floor, so a below-floor finding shadowed a later
above-floor duplicate of the same defect. The floor now runs first, and the
merge keeps the higher-scoring of two duplicates, so the result depends on
which findings were given and not on the order they were given in.

The duplicate rule was byte-identical line ranges. The PRD's rule is
overlapping lines: two same-file, same-severity findings whose ranges share a
line are now one finding.

FileStatus said "removed" for a deleted file, a second vocabulary for the
status the repository persists as "deleted". The value says "deleted" now.
2026-09-26 03:24:40 +10:00
sam 8c7ee60270 style(prreview): adopt go fix rewrites in diff stats and snapshot 2026-09-26 03:24:40 +10:00
sam 54ade9713a feat(prreview): deterministic core of the PR review pipeline
Every phase of docs/prds/pr-review-agent.md that can be computed is computed
here, in a package that imports the standard library only: diff parsing with
renames, deletions, multi-hunk files and no-newline markers; directory
clustering; per-language blast radius; evidence packages; scoring,
deduplication, line mapping to diff coordinates and the review event.

The review event is REQUEST_CHANGES when a finding is blocking and COMMENT
otherwise; there is no approving value, because archie does not own the merge
decision.

internal/domain/workflow/prreview is now the one diff parser in this
repository: the diff-rules step's addedDiffLines delegates to it and the
private hunk-header and path helpers it used to carry are deleted, so a
repository rule and a review comment cannot disagree about which line a change
introduced. diff_rules_test.go is unchanged.

Blast radius resolves Go imports through the module path in go.mod, Python
module names, and JavaScript/TypeScript relative specifiers, all against files
inside the snapshot; an import that resolves to nothing there contributes no
edge. Evidence extraction reads through an fs.FS rooted at the snapshot, so
both are tested against fstest.MapFS fixtures.

NOTICE records the derivation from PR-AF (Apache-2.0).
2026-09-26 03:24:40 +10:00
sam e307efe77d feat(container): end the install phase between install and startup hooks
StartKit calls InstallDone after the install hooks, before files and
startup hooks, so the caller moves the egress session to its runtime
policy exactly where the Kit spec ends the install phase.
2026-09-26 03:17:49 +10:00
sam 6143d17caf feat(container): start a Kit container with the worker and harness separated by user
StartKit creates the Kit container with archie's worker as its root
entrypoint and credentials, the Kit's volumes keyed by execution, then
runs install hooks as their users, writes the Kit's files as the harness
user, and runs startup hooks. A failing hook removes the container and
reports the hook's output. The Docker test proves on a real container
that the harness user cannot read the worker's environment, and fails if
the worker shares the harness uid.
2026-09-26 03:17:06 +10:00
sam b54aa00a24 feat(kit): assemble a Kit container's launch from its plan and image
Assemble turns an admitted Kit composition and the workload image's
config into the harness spec (the image's user, never root; the image
env plus the workspace, egress and credential sentinels; the launch
argv and agent-sessions verbs), lifecycle hooks with their declared users
and restricted environments (the image-derived baseline, egress settings,
and only the runtime variables each hook declares), the Kit's files, and
volume names stable per execution.
2026-09-26 03:14:55 +10:00
sam 08d5df9b11 feat(egress): relay forwards the proxy, NATS and the State Store
A Kit task's worker shares the sandbox network with its harness, so it
reaches NATS and the State Store through the relay like the harness
reaches the proxy. archie-agent relay takes repeated -forward
listen=target pairs, binds them all before serving so a port conflict
fails at start, and stops every forward when one fails. RelayArgs builds
the command from the fixed relay ports.
2026-09-26 03:10:11 +10:00
sam 5b6572bcea feat(agentexec): run harness invocations as the Kit's user with no inherited environment
A Kit task runs worker and harness in one container, separated by user:
the worker keeps its credentials as root, and every harness invocation
runs as the Kit's user with only its declared environment. A nil env
would inherit the worker's, so the runner always passes an explicit one;
root is refused as a harness user, and a root worker refuses to start a
harness with no user. The PRD's container layout now says one container
per run, with the relay forwarding the proxy, NATS and the State Store.
2026-09-26 03:08:34 +10:00
sam 606e87d11c docs(skills): lane gates miss the tools module and contract schema 2026-09-26 02:57:14 +10:00
sam 0b24dc8ff0 fix(build): carry the harness runner into the tools module and contract schema
The harness runner made internal/agentexec import go-git, which the tools
module reaches through docsgen, so tools/go.sum needed its entries; tidy
also dropped the stale modernc sqlite requirements. Request gained the
Harness field, so contracts.json is regenerated with the HarnessSpec
schema.
2026-09-26 02:56:56 +10:00
sam e7611903a8 feat(agentexec): harness runner driving a Kit's agent headlessly
A stage whose request carries a HarnessSpec runs the Kit's CLI as a
subprocess in its own process group, with the mission and archie's rules
as the prompt. After every invocation the runner compares HEAD, every ref
and the git configuration, and the worktree against a pre-run baseline:
any ref or config change, a protected-path edit, or a write in a
read-only stage parks the step whatever the CLI claimed. The runner runs
the gate itself and resumes the same session with the gate's output, up
to the gate's failure cap. The wall clock and cancellation kill the whole
process group, so the CLI's children cannot outlive the step.
2026-09-26 02:54:03 +10:00
sam 19e110e68c style(egress): adopt go fix's promoted-field literal 2026-09-26 02:47:15 +10:00
sam f747ff87d0 feat(egress): inject Kit API-key credentials at the proxy
A session carries its run and its Kit's credential@1 requests. The proxy
applies apiKey inject rules only in the credential's phase and only to
hosts its rule names, after the network policy has admitted the request,
so a key never reaches a host its Kit did not declare. The real value
comes from a Resolver that returns only secrets the run credential
carries: a required credential that is unbound or unresolvable stops the
request before anything is sent, and an optional one passes only when it
is genuinely unbound. Named keys appear in the sandbox as a sentinel;
inject-only keys have no presence.
2026-09-26 02:46:40 +10:00
sam 486d5574b3 docs(prds): fit harnesses, steps and the store inside the org boundary and profile model
A harness is an agent profile whose environment is a Kit composition, so
image profiles and existing workflows are unchanged and only Kit runs take
the egress path; the relay replaces the claim that containers reach the
proxy directly. Credentials, step records, store installs and reviews are
org-scoped under the run credential and the Authorizer, and workflow calls
are linked across executions rather than nested.
2026-09-26 02:41:02 +10:00
sam 71435c2bb6 style(egress): adopt go fix's WaitGroup.Go 2026-09-26 02:38:59 +10:00
sam 9b16c0fd64 feat(egress): sandbox networks that reach only the relay
Each sandbox gets an internal bridge on which the host holds no address,
so host services listening on every interface are unreachable; the relay
is attached under a fixed alias and is the one way out. ProxyEnv gives a
sandbox container its proxy URL and CA trust. The Docker integration test
proves allowed egress works and that the proxy listener, host services and
the internet are unreachable directly; it fails if the host-address
inhibition is removed.
2026-09-26 02:38:12 +10:00
sam 4fc06b5d7d feat(egress): relay forwarding a sandbox network to the egress proxy
archie-agent relay listens on the sandbox's isolated network and joins
every connection to one fixed target, the proxy. The relay holds no
secrets and can reach nothing else, so the host needs no address on a
sandbox network at all.
2026-09-26 02:33:41 +10:00
sam 78dd50d60b feat(egress): session-authenticated proxy terminating TLS under the Kit network policy
CONNECT tunnels and absolute-form http requests authenticate to a
per-container session, are checked against the session's phase policy,
and are forwarded with verified upstream TLS. A tunnel serves only its
admitted host: mismatched SNI and Host headers are refused. Upstream dials
refuse loopback, and refuse internal addresses unless the policy names the
exact IP, so an allowed name cannot resolve back into the host.
2026-09-26 02:31:00 +10:00
sam 77a479e99a feat(egress): persistent per-daemon CA issuing cached leaf certificates 2026-09-26 02:27:58 +10:00
sam 6bc7a85404 feat(egress): network-policy@1 matcher 2026-09-26 02:27:25 +10:00
sam a7edc0a5cd feat(kit): admit Kit v3 descriptors against archie's capability support
Decodes published descriptors from the manifest annotation, composes one
workload with its mixins through the Kit spec package, and applies the
runtime's support table: unsupported required capabilities refuse the
launch, optional ones are skipped and recorded, and forge or passthrough
credentials are refused. A composition must carry a headless prompt verb.
2026-09-26 02:23:11 +10:00
sam 1cf2742f54 docs(prds): approve PR review agent and store PRDs 2026-09-26 02:08:13 +10:00
sam 0f6cb5b8a6 docs(prds): store 2026-09-26 02:06:50 +10:00
sam fca30d6445 docs(prds): PR review agent 2026-09-26 02:05:52 +10:00
sam a98ca2c8e9 docs(prds): approve execution-tree and external-harness PRDs 2026-09-26 01:58:29 +10:00
sam 22d36fef75 docs(prds): harnesses run as Kit v3 images behind a credential-injecting egress proxy 2026-09-26 01:54:35 +10:00
sam f74827795d docs(prds): fold review findings into execution-tree and harness PRDs 2026-09-26 01:45:10 +10:00
sam ca8d189f96 docs(prds): agents reach a harness only through a workflow stage 2026-09-26 01:41:12 +10:00