Commit Graph
1206 Commits
Author SHA1 Message Date
sam ff424b70ac refactor: testing from the beginning. a journey in 150k lines of tests to none 2026-10-03 21:16:25 +10:00
sam b7a6401693 fix(controlplane): an absent MCP server field inherits the file value
The layering rebuilds cfg.Tools from the control plane's projection wholesale,
and ParallelToolCalls was a plain bool. A tool-settings resource seeded before
the field existed therefore carried no key for it, the zero value replaced the
operator's file-level parallel_tool_calls = true, and the setting was inert --
on exactly the stores that cannot be re-seeded, which is the case a new field
has to reach.

Make it a *bool: the shape schedulingPolicy.Label documents, and the shape the
mcp headers in this same function already use. Absent now means "leave the
file's value in force", an explicit stored value still outranks the file, and a
server with no file entry has nothing to inherit and keeps the zero value.
2026-10-03 02:20:06 +10:00
sam 1ba38ac32b feat(workflow): add the command.run step type
archie-core-ndm8 accepted the command-step trust decision, so a stored
workflow definition may run operator argv. The workflow engine has exactly one
call site -- agentworker, which is what the container agent serves -- so the
step runs on the container path by construction. A non-zero exit parks the run;
level: warn makes it advisory.

Settings mirror the repository gate's command shape (name, argv,
expect_failure) so a command means the same thing in both places. The settings
type is local rather than agentexec.Command because that struct carries JSON
wire tags only, and YAML decoding silently dropped expect_failure -- a command
declared to fail would have been reported as passing. A reflection test holds
the two shapes together.
2026-10-03 02:07:45 +10:00
sam d5763a4e98 fix(configuration): make bot_user required, defaulted, and named
bot_user names the agent that chat turns and the session curator attribute memory
to. The loader requires it of a single-identity deployment, but nothing covered
the two paths between that requirement and the consumers.

local-ollama-standalone.toml set no bot_user and defined no [[identities]], so a
profile AGENTS.md lists as supported could not load at all (archie-core-cx0d).
Give the profile the field, and make the regression guard enumerate
deployments/*.toml through the production loader instead of naming two files, so
a profile added later is covered the moment it is committed. dev.toml is
excluded because it is a development overlay layered over an installed config
rather than a standalone profile, and the exclusion is itself checked so a
renamed overlay is noticed instead of silently widening the rule.

The root BotUser was validated only when no [[identities]] block was present, so
a config with exactly one identity left it empty: the curator then skipped every
session with "no agent id" while the chat turn path ran with the same empty agent
(archie-core-4slp). applyIdentityDefaults now adopts a sole identity as the root
single-identity values -- which is what those fields mean -- and leaves the root
alone when two or more identities leave no single answer. The skip reason now
names bot_user, so the remaining case reads as configuration rather than as a
data problem.

Both regressions were red-first: the enumerated profile test failed on
local-ollama-standalone.toml before the profile was fixed, and the sole-identity
test failed before applyIdentityDefaults adopted it.
2026-10-03 01:48:28 +10:00
sam 7656311252 fix(webhookguard): verify uppercase-hex HMAC signatures
VerifyHMAC compared the supplied signature against the computed digest as
case-sensitive hex text, so a sender that emits an uppercase digest failed
verification -- and the failure is indistinguishable from a wrong secret. The
helper is shared by all three inbound surfaces (forge intake, the chat webhook
gateway, capture intake), so one such sender breaks whichever surface it
targets.

Decode both sides to raw bytes and compare those. hex.DecodeString accepts
either case, and comparing digests rather than their text keeps the comparison
constant-time -- strings.EqualFold over the encoded text would not be. A
signature that is not valid hex is rejected outright, and a digest of the
wrong length simply does not match.

archie-core-rl04
2026-10-03 01:44:17 +10:00
sam dec36af87f docs: delete the superseded adversarial review document family
The adversarial self-review system was removed in d73e0748, but four pages
describing it survived: the architecture page, its design-decision PRD, and the
two superseded calibration/operator PRDs. The architecture page carried a
hand-written "removed, not shipped" banner and was kept only because live PRDs
linked to it, so every reader paid for a system the tree no longer has.

Delete all four and repoint the live referrers at the authority that replaced
them (docs/prds/pr-review-agent.md): inline-review.md's Builds-on line,
pr-review-remediation.md's isolation-contract citation, pr-review-agent.md's
supersede clause, CLAUDE.md's contributor rule, and three Go comments that cited
the deleted paths. Regenerate docs/data/generated/dev-docs.json.

History stays in git; the tree stops describing a system it does not have.
2026-10-03 00:01:42 +10:00
sam 0cf46cce3d fix(storepkg): mask the tar mode to the permission bits before narrowing
The conversion is now exact rather than a truncation: the low nine bits are the permission bits whatever the tar header's width.
2026-10-02 22:45:07 +10:00
sam 793348b461 fix(forge): refuse a review line number that does not fit an int
Gitea reports a review comment position as a uint64. Past the int range the conversion wrapped negative and would reach a reviewer as a line that cannot exist. Refused instead, with a test that fails when the guard is made inert.
2026-10-02 22:45:06 +10:00
sam 749165787c fix(webhook): set a ReadHeaderTimeout on the forge webhook receivers
Both listen on the network without a header-read bound, the slowloris surface. Matches the timeout the other daemon servers already carry.
2026-10-02 22:45:02 +10:00
sam dabe7c8888 fix(app): assign the temp-file close result on the error path
Each atomic-write helper returned the write error while silently dropping the close result. The success path already checks it.
2026-10-02 22:45:02 +10:00
sam 5757385439 fix(daemon): drop the import and assignment left by the composition cleanup
l45's refactor removed the assigned-but-unread daemon handles and l44 had
already moved the guardrail wiring out of the daemon, so the rebase union
left internal/daemon/daemon.go importing internal/tools with no use and
internal/app/archied/bootstrap.go assigning a Guardrails field that no
longer exists. main did not build.

Caught by building the merged tree rather than trusting the merge; the
merge train merged on a failed gate instead of chaining on it, which is
the mistake this commit repairs.
2026-10-02 13:00:56 +10:00
sam de24485e10 fix(daemon): classify workflow-pin parks by cause, not a blanket transient
pinTaskProfile parked every pinWorkflowDefinition failure as
taskstate.ParkTransient. That class documents that a requeue can succeed,
but the dominant pin failures are durable: a stored definition whose YAML
does not hash to the digest beside it, a definition that does not parse,
and a workflow or playbook binding resolving to an undefined workflow all
recur on every requeue until an operator repairs the row or the
configuration. A future retry pass reading transient as its input would
loop on them forever.

pinFailure now carries the class its cause needs, decided where the cause
is known, and pinParkClass reads it at the park site. A durable pin defect
parks operator-actionable; only a State Store read or persist failure --
the genuinely environmental case -- stays transient. The safe default for
an unclassified cause is ParkNeedsHuman, never a requeue that will fix it.

Red-first: TestDurablePinDefectIsNotParkedTransient failed at its
assertion before the fix (parked "transient"); TestTransientPinFailureStaysTransient
keeps the environmental case transient so the rule is per-cause, not a
blanket flip.
2026-10-02 12:57:53 +10:00
sam f69ce1db56 refactor(daemon): drop assigned-but-unread composition handles
Three exported Daemon fields were wired by the composition root and read
nowhere: CapabilityHost (*plugin.Host), Curators (*curator.Registry) and
ToolRegistry (*tools.Registry). No field access exists anywhere in the
repo, and git history shows no read ever existed.

Each handle has a live owner outside the daemon: the curator
registry/runtime is boot-owned (the curator isolation invariant keeps it
off the agent loop), the capability host is lifecycle-owned by the
composition root and consumed by the control plane, and the tool registry
is consumed by chat, curator and MCP wiring. Keeping the daemon copies was
decorative wiring, so the fields, their composition assignments and the
now-unused plugin/curator imports go together.

The daemon architecture test now refuses the three names, and the plugin
host contract test refuses a CapabilityHost: handle on the daemon alongside
the PluginRegistry: one it already refused.
2026-10-02 12:57:53 +10:00
sam 88fb3c4f03 fix(agentworker): supply the guardrail engine to every task run
TaskContext.Guardrails was never assigned: the engine was built in
archied's composition root and held on Daemon.Guardrails, which no code
read after workflow execution moved to the full-task worker handoff.
archie-agent is a separate process, so a live engine cannot cross that
handoff. Build the engine at the agentworker composition root (the
process that runs agent stages), thread it through the task dependencies,
and set it on TaskContext; drop the now-dead archied-side construction.

Refs: archie-core-jd5v
2026-10-02 12:37:35 +10:00
sam 4785ec1fc6 fix(config): carry max_retries into the worker TaskConfig snapshot
The remediate round cap runs inside archie-agent and reads
TaskContext.Cfg.MaxRetries, but TaskConfig did not carry the global
Config.MaxRetries: ForTask and ToConfig both dropped it, so a default
configuration reached the cap as 0 and a remediation never parked. Carry
the value (a repo-level override still wins via EffectiveMaxRetries) and
pin it with a red-first cap test traced through ForTask/ToConfig.

Refs: archie-core-ad3p
2026-10-02 12:37:35 +10:00
sam b6aed040a7 fix(workflow): bind the remediate worktree before the builder runs
Commit 14c4de77 moved the remediate resume into daemon worktree
preparation and deleted StageResumeWorktree together with the Dir/Resume
pair it called, but nothing in the workflow replaced the binding it did:
TaskContext.Dir and Branch stayed empty for a whole run, so
remediate-build ran the builder with no workspace and
remediate-commit-push called CommitAll/Push with an empty dir and branch.

Extend the workflow-side Trees seam with the prepare target, mirroring
the daemon's mode-aware worktree.Manager.Prepare: PrepareFresh lands on
base, a non-empty target is the branch a resume continues. Remediate now
stages StagePrepareWorktreeOnBranch before any agent stage, binding the
same directory the daemon prepared and the task's PR branch, and failing
closed when the task has no branch rather than preparing base. The
container adapter returns the requested resume target verbatim.

Refs archie-core-h4tk
2026-10-02 12:29:57 +10:00
sam 6fa1836eca feat(agentworker): answer MCP sampling from the task's model
A task hosts the same configured MCP servers as a chat turn, but the
worker's provider builder passed no sampling handler, so a task-scoped
server's sampling/createMessage request got a JSON-RPC method-not-found
while the identical request succeeded on the chat path. The worker runs
its own model runtime, so it can answer.

Thread a sampling handler built from the task's builder model into the
worker's MCP provider builder, beside the chat path's handler. Build the
task's model runtime once and share it with the stage runners instead of
creating a second client for sampling.

Move the sampling message mapping and max-token bound to agentexec, next
to the runtime both paths call models through, so a server gets the same
bound on either path. Carry the catalog's reasoning flag in
ModelLimits: a reasoning-class builder model must omit the max-token
bound its provider rejects, exactly as the chat path does.
2026-10-02 12:20:31 +10:00
sam b56099f320 refactor(agent): drop the SOUL upgrade branch with no shipped template
ShippedSoul returned an empty SoulDocument.Legacy, so SoulSuperseded,
replaceSoul and SoulUpgraded had no production producer: the only body the
build ships is its current default, which classifies as SoulCurrent, and only
tests constructed a Legacy document. No earlier SOUL ever shipped (the file was
introduced with the starter in a80cca7d), so the upgrade path has nothing to
consume.

Remove the speculative machinery and keep the behaviour that is real: seed the
starter when no file exists, recognise the shipped default as current, and
preserve every other body, including a template-shaped edit. A build that
supersedes the starter reintroduces the upgrade together with the old body it
consumes.
2026-10-02 11:59:54 +10:00
sam 8e88adbf85 fix(webui): pin the dashboard validators to the control plane's
ui/src/settings/validation.ts hand-mirrors three control-plane validators with
no shared source, and the model-role rule had already diverged: the dashboard
required a stricter regex while the server only asks for a slash, so it refused
values the server accepts.

Add a shared fixture (internal/app/controlplane/testdata/dashboard-validators.json)
that both sides run through their real implementations: a Go test over the
server validators and ui/test/control-plane-validator-parity.test.ts over the
dashboard ones. Either side changing a rule alone now fails the other's test.

Fix the diverged rule to mirror the server's predicate exactly (non-blank role,
model containing a slash), so an empty or whitespace-padded model is judged the
same way the control plane judges it. Regenerate ui/dist and the dev-docs
artifact.
2026-10-02 11:59:17 +10:00
sam b468fb8b5c feat(telegram): carry clarify and picker through the text fallback
Telegram had no generic question or choice widget in the agent-turn path,
so the interactive contract could not be carried by the only channel that
ships. telegramInteractor implements ClarifyRequester and PickerRequester
on the shared TextFallback and reports both capabilities honestly: the
capability is about carrying the interaction, not the widget, and the cost
is a typed answer. A reply typed while a prompt is pending is consumed by
the blocked interaction rather than dispatched as a new turn; a command is
never consumed, so /stop still cancels the turn.

The carrier is set on the turn context in the Messaging process. It does
not cross the gRPC boundary into the Gateway process, so in the extracted
messaging deployment the gateway turn has no interactive adapter and
ask_user is not offered -- the same gap that already makes
WithApprovalRequester unreachable there. That transport is a product
decision recorded on the lane, not silently worked around; the in-process
path, the capability report and the tests land here.

Red-first: TestInteractivePickUsesTextFallback and
TestInteractiveClarifyReturnsTypedAnswer (plus the command guard) failed at
the assertion before the interactor was implemented.
2026-10-02 11:52:07 +10:00
sam 7bb62b56a7 feat(gateway): offer ask_user when the turn's channel can carry a question
prepareTurn now registers an ask_user tool only when the turn context
carries an interactive adapter (WithInteractive), so a contract with no
caller has a real one and a channel that cannot ask registers no tool
rather than one that always fails. A channel reporting Picker gets the
native single-choice request; one reporting only Clarify still carries a
choice, rendered as numbered text and matched from the typed reply through
the domain's FormatPickerText/ParsePickerReply rather than erroring.

Red-first: InteractiveTools returned nothing and
TestInteractiveToolsRegisteredWithCarrier / TestAskUserUsesPickerWhenChannelCanPick
/ TestAskUserFallsBackToTextWhenChannelCannotPick failed at the assertion
before the tool was implemented. TestTurnRegistersAskUserOnlyWithCarrier
proves reachability from a real TurnRunner turn.
2026-10-02 11:52:07 +10:00
sam fe62c0ac33 feat(messaging): add a per-turn interactive carrier for clarify and picker
The contract could carry a question but nothing carried the ability to ask
one. Add Interactive, resolved from a channel adapter's own capability
report through InteractiveOf, with WithInteractive / InteractiveFromContext
as the per-turn carrier -- the same shape WithApprovalRequester already uses
for consent. The capability still wins over the method set, so a
mis-reporting adapter contributes nothing instead of being called.

Tests: TestInteractiveOfTrustsCapabilityReport and
TestInteractiveCarrierRoundTrip pin the resolution and the round trip.
2026-10-02 11:52:06 +10:00
sam e6c69a1f48 feat(tools): reconcile MCP servers and tool settings live
Flip tool-settings to ApplyMode live (archie-core-zfb0.3): the daemon now
watches the kind, diffs the stored MCP server set against the running
providers -- connecting added servers, disconnecting removed ones and
reconnecting changed ones while an unchanged server keeps running -- and
rebuilds the web_fetch and minimax entries, whose config is captured at
construction. A changed server whose replacement fails to start is rolled
back to the one running, and the refusal is reported through apply status.

toolprovider.Registry grows running-state Add/Remove/Replace beside
Register, Start and Stop, isolating a provider's failure the way the plugin
host's Add/Replace do. The chat turn model resolves its tool-output policy
per turn instead of capturing it at construction, and the boot registration
reads the running holder so a stored update that lands during boot is not
lost.
2026-10-02 11:46:37 +10:00
sam 04fa1b74fb feat(container): apply container-runtime-policies live
The container runtime policies kind was restart-required because the pool
captured image, pull policy, network, max uptime and max concurrency at
construction and the dispatcher fixed its slot count at the start of a drain
pass. Both consumers now re-read the published config:

- the pool's settings come from a live source read per acquire, with the
  boot-resolved registry credential and Docker construction values preserved;
  a live default-image change is pulled rather than assumed present;
- the daemon owns one long-lived dispatcher that accepts a new limit: running
  tasks keep their slots, a raise admits queued work immediately, and a lower
  limit is applied as tasks finish;
- the control-plane descriptor is live, the kind joins runtimeResourceKinds,
  and the apply/reload paths resize the dispatcher after publishing. The
  ContainerConfig fields whose consumers now re-read are added to the reload
  allowlist; registry_auth stays restart-required.

Regenerate the docs artifacts. contracts.json also carries the voice
media-type description a prior commit left stale.
2026-10-02 11:39:46 +10:00
sam a8843c52b7 revert(tools): drop the checkpoint writer with no restore caller
The pre-mutation file checkpoint added in dcc97afd wrote a full copy of
every write/edit target into .git/archie-checkpoints, but nothing could
restore it: CheckpointStore.RestoreLatest (and its latest/restore
helpers) had no production caller, no rollback surface reaches the
workspace, and the store was never pruned, so it grew without bound in
every workspace.

A writer whose only reader is unreachable is dead weight and an
unbounded disk cost, so the write half goes with the read half: write
and edit no longer snapshot, and CheckpointStore is deleted. The
regression test pins the decision by asserting a write and an edit
leave no .git/archie-checkpoints behind.
2026-10-02 11:36:10 +10:00
sam db7f919c21 feat(messaging): restart only the channel whose settings changed
archie-core-zfb0.4. Channel settings were restart-required as a whole: a
change to one channel needed a process restart that restarted every channel.

The Messaging Service now reconciles the stored channel-settings resource on
the apply-status restamp interval (docs/prds/plugin-settings-live.md), re-layers
it over the file document exactly as boot does, and restarts only the channel
whose transport settings changed. Every other channel keeps serving.

A restart is stop-and-start, not an in-place reload: each channel gets its own
supervisor and a rebuild factory, so email and webhook -- which have no reload
seam -- are restarted too. Telegram's Start still calls dropPendingUpdates
before it long-polls, so the rule holds on the reconcile path as on /restart. A
replacement is built before the running channel is touched, so a configuration
this build cannot run leaves the running channel serving.

The composed set and the bound listen addresses are process bindings: enabling
or disabling a channel, or changing chat.webhook_addr / chat.email.listen_addr,
is refused and reported for a restart rather than applied. A channel rebuild
that fails is not recorded as applied, so it is retried on the next tick. The
applied version reaches apply status, and ChannelSettingsKind flips to live.

Files: internal/app/archiemessaging/{compose,reconcile,supervise,run}.go,
controlplane ApplyMode, archied runtime watch, configuration.md, the config
skill matrix and the regenerated dev-docs artifact.

Verified: go test ./internal/app/archiemessaging/... (race clean); go test
./cmd/archie-messaging/... ./internal/app/controlplane/... ./internal/app/archied/...
./internal/config/...; go vet and golangci-lint run on those packages (0 issues);
go fix ./... and golangci-lint fmt produced no diff; task docs:artifact:check.
2026-10-02 11:31:05 +10:00
sam 52bbb74bf2 fix(messaging): transcribe voice notes on the model-owning side of the boundary
The Messaging Service built the voice-transcription client in-process
from [models].transcription and [providers.*], which the messaging
boundary PRD reserves to the process that owns the model runtime and its
provider credentials. The deletion gate only measured linked packages,
so the PRD violation shipped green: config reads are not imports.

Move the capability across the boundary:

- archiemessaging no longer reads [models] or [providers], builds no
  transcription client, and drops the ResolvedConfig.Transcriber field.
- telegram classifies a voice note as messaging.MediaTypeVoice and stops
  transcribing; it carries the attachment bytes and its note to the turn,
  which is all a frontend without the credential can do.
- archied builds the transcriber beside the chat runtime from its own
  model-role configuration (setupTranscriber) and gives it to every
  gateway TurnRunner.
- the turn runner transcribes a speech attachment before recording the
  inbound message, so stored history and the model context carry the
  transcript; a nil/failed/empty transcription keeps the frontend note.
- messaging.TranscribedMessageText renders the transcript into the text a
  frontend built from its media note, preserving the sender's caption.

Red first: TestTurnRunnerTranscribesSpeechOnTheModelOwningSide failed at
'Transcribe calls = 0, want 1' with the transcription call disabled.
2026-10-02 11:12:59 +10:00
sam 8eab196b8d feat(controlplane): add the writable review-settings resource
review.precision_gate and review.approve_before_post were file-only, so the
dashboard had no way to write them: no control-plane resource carried them.
Add the review-settings kind (docs/prds/review-settings-resource.md), seed it
from the file's [review] section, layer it field-by-field into cfg.Review,
watch it live, and publish it through ConfigView.Review. The dashboard gets a
Review settings page bound to the kind through PAGE_RESOURCES, showing each
dial beside the value in force.
2026-10-02 11:08:44 +10:00
sam a80cca7d5c feat(agent): seed a starter SOUL and upgrade only untouched templates 2026-10-02 11:06:40 +10:00
sam 0aa0277ee9 docs(prds): name the registered step type and hold the vocabulary PRD to the provider set
docs/prds/workflow-step-vocabulary.md named the repository-rules step type
`workflow.diff-rules` while the vocabulary a deployment resolves carries
`gate.diff-rules` (workflow.DiffRulesStepName), so a definition written to
the document's word is refused at save and at run. The same decision's
sibling, docs/prds/runtime-control-plane.md, still claimed "Plugins can add
step types", which this document's closed-set rule contradicts: an
interpreted plugin contributes none, and a step type arrives as a provider
in the compiled-in set.

Correct both documents, and hold the vocabulary PRD to the provider set with
a guard test: every step-type-shaped name the document identifies must
resolve in workflowsteps.Providers(). The test fails on the pre-fix document
("workflow.diff-rules" is contributed by no provider) and passes after.

Refs: archie-core-vwqc, split from archie-core-gcoj (closed as invalidated by
re-verification: the provider set exists and cross-side agreement is already
pinned).
2026-10-02 11:05:08 +10:00
sam 13b03dad5c feat(webui): let the operator choose the retry worktree mode
A retry now carries the operator's worktree choice (refresh onto the base
branch or continue the work already pushed on the task branch) from the
dashboard through the task action to the daemon dispatch, and persists it
on the task row so it survives a reload. The daemon resolves the mode from
the task, never from the workflow; BeginRemediation records continue
explicitly so a remediation still resumes its pull request branch.
2026-10-02 10:53:21 +10:00
sam 148791d5c8 fix(control-plane): unify validation for the domain-managed kinds
The control-plane catalog advertises identities, capture-events,
capture-mappings and capture-bindings as domain-managed: the domain API
validates their writes, not the generic resource store. Two of those
paths did not hold.

Identities: the file loader judged an identity name with its own
`name == ""` test, while the store derives the same string through
identity.New, whose rule rejects an empty-after-trim name. A
whitespace-only name passed the file and then failed State Store boot
(or was silently skipped by BootstrapIdentities). The loader now calls
identity.ValidDisplayName, the feature's own rule, and
BootstrapIdentities derives legacy names through
identity.FromLegacyName rather than dropping one it cannot build.

Capture mappings and bindings: mapping.Validate and binding.Validate
ran only in the archie-ui handlers, so any other client of the RPCs the
catalog names could store a mapping or binding the feature refuses.
The staterpc write handlers now apply the feature's rule before the
store, per runtime-control-plane.md ("the server validates the change,
then writes it"). The rule stays in the domain package; the handlers
only translate its refusal.

Capture-events has no file-side copy and no feature rule for a captured
event's content, so there is nothing to unify there.

Tests: identity_agreement_test.go ties the file loader's name rule to
the store constructor; domain_validation_test.go proves the mapping and
binding RPCs refuse an invalid value before it reaches the store.
2026-10-02 10:50:52 +10:00
sam cb923cc0d9 fix(logging): file a task log record under its own event time
A remotely-shipped task log entry was re-emitted through the sink with
slog.Logger.LogAttrs, which stamps time.Now(): the entry's own event time
was discarded and replaced with the daemon's receipt time. Because a
container's records arrive in bursts, a multi-minute run collapsed onto a
few milliseconds of receipt timestamps and its timing became
unrecoverable -- which stage ran when, how long an iteration took, whether
a stage stalled.

Write now builds the record from entry.Time (falling back to receipt time
only for an entry that carries none) and dispatches it through the same
handler, preserving the sink's level gate. Receipt time stays available
separately in the record's received_at field, so event time and arrival
time cannot be confused. The agent-side producer already carried the
record's own time; a test now pins that half too.
2026-10-02 10:33:24 +10:00
sam 148c81af36 fix(archied): omit the max-token bound on reasoning-class models
The OpenAI chat-completions provider in the pinned ai-sdk serialises a
non-zero output-token bound as `max_tokens`, which reasoning-class models
reject with HTTP 400 ("Use 'max_completion_tokens' instead"). Send no bound
at all for a model the catalog marks reasoning; classic models keep their
bound. Covers the chat turn path and MCP sampling, the two call sites that
set one today.

The reasoning flag rides TurnPrepareContext from the catalog details the
gateway already resolves, so archie-core keeps one notion of "reasoning
model": messaging.ModelDetails.Reasoning. A max_completion_tokens path in
ai-sdk is still needed to ever bound these models; that is filed separately.
2026-10-02 10:25:39 +10:00
sam 14c4de77f4 fix(daemon): resume a retry whose worktree is gone
prepareWorkspace chose between Manager.Prepare (refresh onto base) and a
separate Manager.Resume, and Manager.Resume only opened an
already-prepared clone. A remediation whose local worktree the terminal
cleanup removed, an expired volume dropped, or a different host never had
could therefore never be resumed, and the retry path had no way to select
the mode that continues pushed work.

Unify the two matched methods into Prepare(..., Target): Fresh resets onto
origin/<base>, a non-empty Target resets onto origin/<that branch>, and
either target clones a missing worktree. The daemon's retry path selects
the target from the task row and passes the persisted branch, so a resume
lands on the branch the open PR lives on and fails closed when it is not
on the remote.

Delete the container-mode no-op resume (hybridTrees.Resume and the
resumableTrees capability) now that the daemon owns it. The remediate
workflow no longer stages a resume, and the retired remediate.resume step
word stays resolvable as an inert stage: a stored definition is validated
as a whole collection, so a removed word would fail every workflow to
decode, not just its own.
2026-10-02 10:24:52 +10:00
sam a0b5059f2e fix(messaging): carry an inbound attachment's bytes to the gateway turn
A Telegram photo or document was dropped between the process that receives
it and the one that runs the turn. Telegram runs in archie-messaging, which
downloads the attachment; the turn runs in archie-gateway/archied, which
never holds the bot token. gatewayrpc stripped MediaAttachment.Data on the
inbound request, so by the time the Gateway's model seam ran, the
attachment had no bytes and no URL, and mediaParts dropped it -- the model
read only the "[photo]" placeholder.

- proto/gateway/v1: Media gains a `data` field, populated only on the
  inbound request. Stored-history and outbound-event directions keep it
  empty: a persisted record still strips the bytes, and a streamed media
  event still carries metadata only.
- gatewayrpc: the inbound conversion maps Data; the stored and outbound
  conversions deliberately do not.
- archied: the Gateway server raises its gRPC receive limit from the 4 MB
  default to the messaging contract's inbound attachment ceiling plus
  framing headroom, so a maximal (20 MB) attachment is accepted rather than
  failing the RPC.
- messaging: MaxInboundAttachmentBytes is the single ceiling the Telegram
  download gate and the Gateway receive limit both derive from.

Red first: a new TestInboundMediaBytesReachTheTurn asserted the bytes crossed
the wire and failed at that assertion before the mapping changed; it was then
consolidated into TestInboundMediaRoundTrip, which now pins metadata plus bytes.
2026-10-02 10:18:01 +10:00
sam b3ea333564 fix(messaging): report the daemon version this process was built from
The Telegram update-report relay verified every pending report against a
nil running-version map, so a successful update always ended with "I still
can't confirm which version is actually running" and read as a failure.

The 2026-09-19 extraction decision left RunningVersions nil because the
Messaging Service could obtain only another binary's stamp. ec0f17a7
(archie-core-k94o) then gave every host binary, archie-messaging included,
a buildinfo.Version self-report stamped with the archied release tag, so
the process now has a truthful source for its own running version: report
daemon = buildinfo.Version and leave the agent Unverified, since every
archie-agent process is task-scoped and observed only through
daemon.AgentStatus. A relaying process that the update did not replace
still reports its old build, which Verify reads as drift.
2026-10-02 10:16:22 +10:00
sam 1e42342693 fix(workflow): deliver the feasibility PRD to the forge issue
The deliver stage's notify() returned early when [notify].webhook was
unset, so a parked feasibility PRD left the process nowhere while both
its doc comments promised an issue comment that was never posted. A
default deployment sets no webhook: the PRD reached only the operator
who went looking.

notify now posts a one-way delivery notice on the task's forge issue
before the webhook, for a forge-backed task. The issue is the channel a
default deployment always has; the webhook remains an additional push.
Neither is a reply channel -- the decision surfaces stay chat and the
Web UI, so the notice carries the PRD and names where to decide rather
than inviting a reply, and no reply cursor is recorded (WatchCommentID
stays 0).

Both stale doc comments now describe what the code does.
2026-10-02 10:10:04 +10:00
sam c835aabb1e feat(plugins): load plugin and secret-engine files without a restart
docs/prds/plugin-settings-live.md: a `plugin-settings` change now applies
live for plugin_dir, module_dir and secret_engine_dir, and a file dropped
into any of those directories loads on the reconciliation tick.

- PluginSettingsKind moves to ApplyMode "live" and joins
  runtimeResourceKinds, so a stored directory change re-layers immediately.
- A reconciler re-runs the directory loads and the layering on the
  apply-status restamp interval. Files are content-hashed, so only new and
  changed files load.
- plugin.Host grows Add and Replace for the running state (Register keeps
  its pre-Start rule), and plugin.LoadFile / secret.Registry.LoadFile are
  the single-file load paths the boot loader and the reconciler share.
- Yaegi cannot unload, so a removed file keeps running and the removal is
  reported through apply status against the live version until restart; a
  clean pass clears it.
- A plugin-settings document that changes skills_dir is refused before the
  layering, since skills_dir has no live consumer.
- applystatus.Reporter.AppliedVersion lets the reconciliation report an
  outcome without resetting the version to zero.
2026-10-02 10:01:35 +10:00
sam 8f27cfe8c1 feat(gateway): gate admin slash commands by sender policy
Add SlashAccessPolicy, a deny-by-default role policy (admin allowlist plus
per-user delegated commands), and enforce it in Router.route before any
local command dispatches. A refusal executes none of the handler, is
visible to the sender, logged, and recorded through an optional
SlashDenials sink.

No config field yet: the gatewayrpc wire drops Message.SenderID (only the
display Sender crosses), so a per-sender allowlist cannot match a Telegram
sender at the daemon Router until the layered auth mixin carries identity
(archie-core-263). Nil policy preserves today's behaviour.
2026-10-02 10:00:37 +10:00
sam 5221926753 feat(messaging): adapter-facing clarify, picker and approval contract
The optional-capability pattern had media and delete but no interactive
UX: a channel could ask a human to approve an action through
ApprovalRequester, but there was no domain contract for posing a
clarifying question or presenting a single-choice picker, and no
capability flag a caller could read before attempting one.

Add ClarifyRequester and PickerRequester to internal/domain/messaging
alongside ApprovalRequester, with Clarify/Picker/Approval flags on
AdapterCapabilities and ClarifierOf/PickerOf/ApproverOf lookups that
treat the capability as the contract rather than the method set, so a
mis-reporting adapter degrades instead of panicking.

TextFallback is the shared text degrade: a channel with no native
question or selection UI still carries the interaction (numbered
prompt, parsed reply) instead of failing or silently dropping it.
FormatClarifyText/FormatPickerText/ParsePickerReply hold the rendering
and matching logic once.

The approval half reuses the existing decision model: Telegram's
telegramApprover already renders a native prompt, so it now reports the
Approval capability and deliberately does not claim Clarify/Picker it
has no native UI for. Gateway re-exports the contract.

Red-first: internal/domain/messaging/interactive_test.go drives the
test double adapters (native, degrade, mis-reporting, over-claiming)
and the text rendering/parsing; telegram/approval_test.go pins the
honest capability report.
2026-10-02 09:57:44 +10:00
sam e9a79ec3ed fix(workflow): park environment gate failures without dispatching a builder
The baseline stage treated every red gate as a pre-existing code defect and
dispatched a TDD repair agent. A failure the environment caused -- no Docker
daemon for the test harness, or a gate command that is not installed -- cannot
be fixed from the worktree, so the run spent a full agent budget and then
parked. A provider error during that repair run (observed: HTTP 402) replaced
the gate cause in the park reason entirely.

Classify at the producer: gateEnvironmentCause names a failure whose command
could not start (*exec.Error) or whose output names unavailable host
infrastructure (the Docker shapes from archie-core-71mq). That failure parks
with the cause and the gate output and starts no builder. A real code failure
still dispatches exactly one repair run, and every post-dispatch failure now
carries the gate output alongside the agent/provider error instead of masking
it.

Refs archie-core-rwy6.
2026-10-02 09:57:15 +10:00
sam af450d3ea0 feat(gateway): list the harness page in the dashboard page registry
internal/gateway/dashboard_tools.go mirrors the dashboard's route table so
the agent can navigate to every page. The new /settings/harness route needs
its entry or page_index would not offer it (archie-core-egkf.7).
2026-10-02 09:38:09 +10:00
sam 70fc0143ab feat(webui): the dashboard reads harness bindings and opens the setup terminal
The harness page lists each credential binding with its captured OAuth
state (expiry, scopes, capture time; never the tokens), and the setup
terminal route upgrades to a WebSocket and bridges it to a harness
session. The session is a narrow webui-owned HarnessTerminal seam: the
container, sandbox network and egress path belong to the daemon, so the
dashboard process cannot implement it and answers 503 until a transport
is wired (archie-core-egkf.7). Opening the terminal authorizes as the
update action on the secret, per the PRD.
2026-10-02 09:38:09 +10:00
sam 2e1ab386fb fix(egress): take a run's credential kind from its binding, not the Kit
The sandbox kit spec lets one credential@1 declare apiKey and oauth
together, meaning "whichever the host has bound": the published
docker/claude-code-kit does exactly that for anthropic, and codex for
openai. archie decided the kind from the Kit's declaration instead
(egress.IsOAuthManaged), so a dual-declared service always came out
OAuth-bound however the org had bound it:

  - kitrun.resolveCredentials granted an API-key binding's service the
    empty string, so the proxy had no key to inject and every request to
    a domain the Kit named carried an empty credential. The reference
    Claude Code Kit could not authenticate with an API key at all.
  - an API-key-only service whose binding named no secret resolved to ""
    through the zero SecretRef, presenting an empty credential rather than
    staying unbound.
  - the proxy fired an apiKey inject rule for an OAuth-bound service,
    putting "Bearer " on the wire, and intercepted the token endpoint of
    an API-key-bound one, whose only outcomes were a 502 on the missing
    token set, a capture the org never bound, or -- for a required
    dual-declared credential -- a refused launch when no token store was
    configured.
  - the container's SBX_CRED_*_MODE said "apikey" for an OAuth-bound
    dual-declared service, and kitrun demanded a captured OAuth token for
    an API-key-bound one whose Kit renders a credential file.

One root cause, fixed once: the org's binding decides the kind. It is
now a first-class fact (egress.CredentialKind: apikey or oauth, absent
meaning unbound), computed from the binding in resolveCredentials and
carried to every consumer of it -- the resolver grant, the container's
credential state (mode variable and credential file), and the proxy
session, whose rule sets are built from it so a rule can only fire for a
service the run carries as that same kind. A service the run does not
carry at all keeps both rule sets, so resolving it still refuses a
required credential and skips an optional one.

Declared and bound stay two independent facts, as the reported
declared-and-granted intersection requires: neither widens the other.
No secret value crosses into kit (Bound carries kinds only) and none is
logged or written to a task row.
2026-10-02 09:37:20 +10:00
sam 2c5dfe51a7 feat(messaging): transcribe Telegram voice notes
A Telegram voice note was stored as the placeholder "[voice message]" and
nothing turned its audio into text, so the agent could not read it. Add a
channel-neutral Transcriber capability to the messaging media layer
(internal/domain/messaging), an ai-sdk Whisper implementation behind it
(internal/infrastructure/transcription), and wire it for Telegram.

The capability is config-driven like the other model roles:
models.transcription names a provider/model, the matching [providers.*]
entry carries the credential (api_key_env or an api_key secret ref), and
a missing role, provider, class or credential degrades to today's
behaviour with a log -- never an error that fails the turn.

A transcribed note replaces its placeholder with "[voice transcription]"
followed by the transcript, preserving any caption, so stored history
shows the agent it is reading a machine transcript.
2026-10-02 09:36:48 +10:00
sam 962678113a feat(messaging): retract ephemeral replies after their TTL
An EphemeralReply is a status notice a channel delivers and then removes
once its TTL elapses, so a transient placeholder does not linger in the
chat history after it is superseded. The TTL lives on the reply, the
Delete capability joins AdapterCapabilities alongside Media, and
channels.EphemeralSender does the send-then-retract with an injected
clock. A sender that cannot delete still delivers the reply and logs the
missed retraction instead of failing the turn.

Telegram implements MessageDeleter through deleteMessage and honours the
mechanism for the "Archie reloaded." status notice; the pre-restart
"Reloading…" message remains the durable acknowledgement.
2026-10-02 09:36:16 +10:00
sam d240f4979a feat(container): send registry auth on image pull
ImagePull was called with empty options, so a private registry answered 401
on every pull regardless of containers.pull_policy. docker login did not help
either: it writes ~/.docker/config.json, which only the CLI reads.

Add containers.registry_auth, a SecretRef reusing the credential shape the
rest of the file uses, whose resolved value is a Docker registry.AuthConfig
JSON document. archied resolves it at boot and the pool base64url-encodes it
into the X-Registry-Auth header ImagePullOptions carries.

A missing or unresolvable credential degrades to the anonymous pull that
existed before the field (with a warning), so a deployment with no private
registry is unaffected; a half-named reference is refused by
configuration.Validate. The field is file-owned and json:"-", so the
container-runtime-policies layering has to preserve it explicitly, the way it
preserves Profiles.
2026-10-02 09:35:28 +10:00
sam 2aef002988 style(mcp): apply go fix to the sampling transport 2026-10-02 09:35:21 +10:00
sam c3faf30b12 feat(mcp): answer server-initiated sampling from the chat model
MCP servers could not ask the client for a completion: the transports
routed only responses by id and dropped every server-initiated request,
so a server calling sampling/createMessage hung waiting for a reply.

Route server->client requests through the transport readers to a handler
on the client. The client answers sampling/createMessage from a
configured SamplingHandler and maps a missing handler, malformed params
and handler failure to JSON-RPC errors for that request alone -- never a
silent drop or a failed session. stdio and SSE implement the routing;
the stateless HTTP transport cannot receive the request at all and says
so in its doc.

The daemon wires the handler to its own chat runtime and active model
role, so a sample is answered by the model a chat turn uses, capped by
the request's maxTokens and the model's output ceiling, and recorded on
/status like every other model call. No model configured is a refused
request with a clear error.
2026-10-02 09:33:32 +10:00