Seventh slice of docs/prds/eda-playbook-engine.md (t2db.15), consuming
t2db.14's expr package: the rich trigger+actions playbook document and
the coordinator that dispatches it.
- internal/domain/eda/playbook: Load(dir) reads *.yaml/*.yml playbook
documents (trigger + exactly one workflow-kind action + optional CEL
when), validating the HARD BOUNDARY at load: a playbook with 2+ actions
or a non-workflow action position is a reported load failure --
multi-action and Module/Channel/Forge actions stay blocked on the
unresolved execution-time gaps. Any malformed YAML, invalid trigger,
missing workflow name, or when compile failure fails the WHOLE load
(reject-at-load, same shape as routing collisions); a missing dir is an
empty store. Trigger reuses the existing workintake kind/label
vocabulary (no second label-matching mechanism). Dispatch matches
trigger, evaluates when (CEL, event context with actions: {} -- no
prior actions in single-action playbooks), and returns the named
workflow from the registry via the same lookup Route() uses -- no
duplicated dispatch logic. when eval error follows the resolved doc's
J3: false, skip, caller logs.
- Store.Dispatch(reg, DispatchInput) is the coordinator entrypoint; input
carries Labels/Kind/Event. Production task intake wiring
(daemon.go/pollNATS/publishTask) is explicitly NOT in this ticket -- a
follow-up; proven end to end via direct tests plus the shipped example
(examples/eda-playbooks/bug-tdd.yaml) loaded and dispatched through the
real path.
- Config: EDAPlaybookDir (eda_playbook_dir), documented as DISTINCT from
PlaybookDirs (flat binding files) -- a reader cannot confuse the two.
- Bootstrap: playbook.Load wired in loadWorkflows, log-and-abort on
failure matching every prior slice; nonexistent dir is an empty store.
- workflow.Route(), workflowForLabels, and the t2db.9-.12 binding loaders
are UNTOUCHED (verified: their full test suites pass, zero regressions).
Also carries small lint cleanups on t2db.13/.14 code flagged by the gate
run: expr Eval no longer type-asserts to ref.Val (Eval returns ref.Val
directly in v0.32.0; cel-go's own Eval wraps evaluation in recover --
verified in source); module decodeLogArgs extracted to clear the nestif
finding. golangci-lint: 0 issues.
Tests (10): single-action round trip, when-false skip, 2-action load
failure, non-workflow position load failure, when compile failure drops
playbook, empty trigger load failure, trigger mismatch skip, no-when
match, one-invalid-file fails whole load, missing dir empty store, plus
the shipped example load+dispatch. task check clean (113/113 UI, exit 0).
Fifth slice of docs/prds/eda-playbook-engine.md (t2db.13), implementing
docs/prds/module-position.md's recommended first slice: prove schema ->
go:generate -> Yaegi load -> ModuleRegistry end to end with a
side-effect-free action kind, before any kind with a real external effect
(notify, image-gen, forge writes) -- those stay blocked on the parent
doc's unresolved execution-time gaps (idempotency, mid-run failure).
- internal/domain/eda/module/log: hand-written schema source (Args/Result/
SchemaVersion per module-position.md) + logextract generated symbol
table via go:generate yaegi extract (same tooling as wfextract/
gateextract; scoped to ./internal/domain/eda/module/...).
- internal/domain/eda/module: ModuleRegistry with Register(kind, dir) /
Invoke(ctx, kind, rawArgs). No generic Module interface with an any
payload: each kind is its own tiny package with its own generated
contract; the registry's internal storage is the only place erasure
appears (exactly as inside wfextract). Invoke decodes rawArgs strictly
into the kind's Args before calling the interpreted function -- an
unknown key or wrong type is a reported failure, not a silent
zero-value fill (the 'schema defines the accepted message' rule).
Generalizes gateeval's fixed-signature Yaegi pattern via
yaegiutil.New/Resolve/Safe -- no new interpreter-construction or
panic-recovery mechanism.
- Config: ModuleDir mirroring PluginDir's shape and doc comment
(operator-trusted directory of Yaegi module implementations, one .go
per kind; empty means none loaded). Wired at daemon startup in
bootstrap.go alongside PlaybookDirs loading -- log-and-abort on load
failure (a broken module is a startup failure, not degrade-and-skip).
- examples/modules/log.go: operator-facing example (//go:build ignore,
mirroring examples/secret-engines/) proving the shipped contract.
Tests: registry (register/invoke, unknown kind, missing file, strict
arg-decode shape failures, malformed file, panic recovery), logextract
smoke test, and an example-load test that runs the shipped
examples/modules/log.go through the real registry (not a test fixture).
task check clean (113/113 UI, exit 0).
Playbook YAML action dispatch is deliberately out of this slice: a
minimal 'run this one module action, no chaining' dispatch still requires
naming how args values reach the action (parent doc open question 1 --
data-flow/interpolation syntax) and what the result feeds, both
unresolved by design. Dispatch is a follow-up ticket that consumes this
registry as-is; recorded in module-position.md.
Fourth slice of docs/prds/eda-playbook-engine.md (t2db.12): the design
doc's pre-merge collision layer, as a gopls-shaped standalone binary
(cmd/archie-playbooks) rather than a Taskfile wrapper -- one binary, one
schema source, mode-based entrypoints.
- cmd/archie-playbooks: subcommand dispatch table from day one (lint now;
an lsp/serve mode later slots in without restructuring), flag parsing
only per organisation.md's cmd/ rule.
- internal/app/archieplaybooks: the lint mode's composition -- collects
directories, calls workflow.LoadPlaybookDirs (the daemon's own loader),
reports findings. No second validation path: the linter agrees with
runtime startup validation by construction.
- Reuses LoadKindWorkflowsYAML/LoadLabelWorkflowsYAML/LoadPlaybookDirs
directly; collision/malformed/invalid bindings exit non-zero.
- Known limitation recorded: findings are file-granular, not
line-granular (yaml.Unmarshal into map discards line numbers; a
file:line diagnostic needs a yaml.Node upgrade, out of scope here).
- Taskfile lint:playbooks target; PRD records the shipped shape and the
file-granular caveat.
Third slice of docs/prds/eda-playbook-engine.md (t2db.11), completing open
question 2: instead of a single playbook dir, the config gains a LIST of
directories (playbook_dirs) of *.yaml/*.yml binding files, loaded at
startup as an additional input to workflow_routing_file and
workflow_labels_file, which remain supported unchanged.
- LoadPlaybookDirs(dirs []string) reads every yaml file across the
configured directories and merges kind + arbitrary-label bindings.
- This is what finally exercises the design doc's drop-and-report
collision rule: a single file cannot collide with itself, so the
cross-source path (two files in one dir, two dirs, or a dir plus a
single-file field) had never run in production. A binding key declared
by more than one source is a reported load failure, not a silent
pick-one by source order or version.
- Router-level collision handling: MergeKindWorkflows/MergeLabelWorkflows
fail on a key bound by both the single-file fields and the playbook
dirs, applied at boot.
- Config: PlaybookDirs []string, empty by default (no behavior change for
existing configs). Repo-scoping (typing dirs to Config.Repos owner/name)
is explicitly deferred to a separate later decision per ticket;
org/tenant keying is out of scope.
- PRD: records the list shape per Sam's correction (single dir would
contradict multiple independently-maintained playbook sources).
Second slice of docs/prds/eda-playbook-engine.md, complementing the
kind->workflow layer (WorkflowRoutingFile): the label vocabulary itself
becomes playbook data. A label outside the closed bug/feature/bootstrap
kind set (e.g. security) now dispatches to a registered workflow from an
optional WorkflowLabelsFile, instead of falling through to triage.
- LabelWorkflows + LoadLabelWorkflowsYAML/SetLabelWorkflows in
internal/domain/workflow/routing.go, mirroring the kind layer's
once-at-startup lifecycle. The closed Kind/NATS-subject set is
untouched; the map only extends binding authority for labels the kind
layer does not own.
- Collision rule per design doc: a label owned by the kind set, an empty
label, an empty workflow name, or a duplicate binding is a reported
load failure (dropped, logged, error returned to the caller) -- the
schema defines what is accepted; nothing is silently arbitrated by
schema/version.
- Route() precedence: explicit t.Workflow -> arbitrary-label binding ->
kind binding -> triage -> implement -> default.
- Config: WorkflowLabelsFile (workflow_labels_file), wired at boot
alongside WorkflowRoutingFile; documented in config.example.toml.
- PRD: records this slice's decisions (single-file shape, collision rule,
precedence) so later slices stay anchored.
First slice of docs/prds/eda-playbook-engine.md: which registered
workflow an intake Kind (bug/feature/bootstrap) prefers is now data,
loaded from an optional WorkflowRoutingFile, instead of a Go literal.
labelKinds and the NATS-subject-per-kind set are unchanged -- expanding
the label vocabulary itself is a separate, larger decision (subject
allocation) deferred per the design doc's open questions.
An unrecognised kind in the file is a reported load failure (schema
defines what's accepted, per the design doc's collision-handling rule),
not a silently-dropped binding. No file configured falls back to
today's hardcoded defaults unchanged.
binding.Binding.Secret was persisted as plaintext in the bindings.secret
column, so anyone with the SQLite file saw sender-side HMAC secrets. Seal
it with AES-256-GCM transparently inside the store: encrypt-on-write,
decrypt-on-read.
- cipher: AES-256-GCM, 12-byte random nonce, SHA-256-normalised 32-byte
key resolved through the secret registry ([bindings].encryption_key).
- envelope 'arcie-binding:v1:<fingerprint>:<b64(nonce||ct||tag)>' so a
future cipher/KDF change is a version bump and old rows stay readable.
- rotation via previous_encryption_keys; key identity is the material's
SHA-256 fingerprint embedded in each row.
- legacy plaintext rows written before a key was configured stay readable;
encryption is not retroactive.
- nil cipher (no key configured) preserves the pre-t2db.7 plaintext path.
Deferred: captured_events.body redaction upgrade (separate concern, see
docs/prds/binding-secret-encryption.md).
Refs archie-core-t2db.7
Implements archie-core-t2db.4: the runtime-editable binding entity that
turns a captured webhook into an archie task, plus the per-source HMAC
verification at handleCapture that makes t2db.5's 'unauthenticated event
cannot trigger a binding' invariant structurally enforceable.
Captures, mappings and bindings are now separate concerns on the same
single *store.Store; the new BindingStore / BindingDispatcher /
BindingTaskCreator split keeps each interface under the interfacebloat
limit (8 methods).
State machine: draft -> pending_approval -> armed; any edit on an armed
binding drops it back to pending_approval, enforced in SQL via
status='pending_approval' on UPDATE so the rule cannot be bypassed by a
direct status field in the request body. Approve is the only sanctioned
transition into armed (WHERE status='pending_approval' guard).
Overlap: two bindings may not share a source in any status; enforced at
InsertBinding and UpdateBinding (transaction-local SELECT). Approve has
a separate TOCTOU guard so a race between Insert and Approve cannot
// bypass the check.
HMAC at handleCapture: reads X-Hub-Signature-256 (then X-Signature-256)
// fallback, verifies via webhookguard.VerifyHMAC against the binding's
// per-source secret, marks CapturedEvent.Authenticated=true on match.
// Captures with no armed binding, missing signature, or wrong signature
all persist as authenticated=false -- the dispatch loop's
binding.Matcher.Matches gate (requires authenticated) is what stops
them from spawning a task. Two armed bindings for one source returns
409 at capture time as a belt-and-braces TOCTOU guard.
Dispatch loop: added Daemon.dispatchBindings, called from both Cycle
and maintainAndDrain between poll and drain. Walks
captured_events where authenticated=1 AND source IN armed bindings
AND id NOT IN binding_dispatches, runs the binding's matcher, resolves
the mapping, enqueues a chat-style task with binding_id /
// binding_version provenance stamped in the same transaction as the
// row insert. The binding_dispatches ledger (composite PK on
(binding_id, capture_id)) is the at-most-once guarantee across cycles
// and daemon restarts.
Tasks schema migration: binding_id INTEGER NOT NULL DEFAULT 0 +
binding_version INTEGER NOT NULL DEFAULT 0 (taskSchemaVersion bumped
1 -> 2). Existing tasks keep 0 / 0.
Out of scope (documented follow-ups):
- secret encryption at rest (plaintext today)
- full dashboard HTML for the binding editor (CRUD API only this bead)
- per-binding rate limits (existing per-remote-address limit applies)
- binding.Owner / binding.Repo fields (dispatch falls back to the
single configured repo; multi-repo deployments log and skip)
Adds PATCH /api/config/repos/{owner}/{name}, a dedicated seam distinct
from the generic dotted-key PATCH /api/config path: a repository is
one element of []config.Repo, not a flat key. Traced the mechanism
before adding any new plumbing -- overlay.Nest/ApplyOverlayValues
already handle "repos" as a single whole-slice key with no dot, so
the fix is a webui handler plus a bootstrap seam that reads the
daemon's live, untrimmed Repos (never webui.RepoView, which omits
Preflight/TestGlob), mutates the one matched field via the pure
applyRepoFieldUpdate helper, and republishes through the existing
UpdateConfig(ctx, {"repos": repos}) path unchanged.
config-row.js's row() gains an opts.save override so an edit can be
redirected to a different persistence call. The repositories table
renders an autosaving checkbox for the two booleans and a
save-on-blur/Enter input for max_retries, via api.configRepoUpdate.
Closes archie-core-b6ew.6, and with it archie-core-b6ew.
channels.Manager.MarkRunning was never called for telegram, email, or
webhook -- every start path only called MarkStarting then MarkFailed
on error, so the dashboard showed a working channel stuck on
"Starting" forever (confirmed live: Telegram polling and delivering
messages while /api/channels still reported "starting").
Adds gateway.Lifecycle{Starting, Running func()}, threaded through
Gateway.Start(ctx, router, lifecycle). Email and webhook report
Running once their listener actually binds -- webhook moves off
http.Server.ListenAndServe's internal bind to an explicit
net.ListenConfig.Listen so binding is observable before Serve.
Telegram reports Running after StartWebhook launches in webhook mode,
or after the first successful getUpdates response in long-poll mode,
observed via a pollReadinessClient http.Client wrapper since the
go-telegram/bot library keeps polling errors inside its own worker
goroutine. Restart re-reports Starting/Running each cycle.
Closes archie-core-1786637499114 (persistent session-memory curator),
the last open item in the curator engine epic.
docs/prds/session-memory-curator.md records the decisions this needed
before coding, most notably: Observation.Identity is the session ID,
not a user or cross-session identity. migration-decisions.md#5's
memory-scope mapping (global/agent-wide/user-wide/agent-user
relationship) is still explicitly open, and this issue has no business
deciding it unilaterally -- session-as-identity is the narrowest
unambiguous scope available today and is forward-compatible with a
later, properly-decided identity resolution.
curator gains ConversationSource (RecentSessions/Messages), gated in
Registry.validateDeclared/filter exactly like Skills/MemoryEngines, plus
Manifest.Conversations. internal/infrastructure/sessioncurator/adapter.go
adapts gateway.SessionStore's full CRUD/branch/search surface down to
those two read-only methods -- curator must not import gateway.Message,
so role derivation (message.From == botUser -> assistant) is copied from
gateway.compressTurnHistory's existing logic, not shared.
sessioncurator.go: Check is a cheap RecentSessions bool. Pass takes each
session's last 40 messages, asks the model for a JSON array of durable
facts (capped at 5/session), and writes each through
Registrar.MemoryEngines.Get(name) -- resolved by name at call time, the
same trust model every other curator capability already uses. A
response that fails to parse degrades to "nothing extracted" for that
session (not a Pass error); a real model-call failure propagates as one
(these were originally conflated into the same swallowed-error path --
caught by TestPassPropagatesALLMFailure, fixed by splitting the model
call from the parse step). PassInput.Since zero resolves to a 24h
lookback, not the beginning of time, so a cold-start first pass can't
read a session's entire history.
Manifest.OnInput = true wakes it via the existing WakeOnPrimaryInput
wiring (events.KindTurnCompleted), which already excludes every
curator-derived event kind from the forwarded set -- the trigger-
accounting invariant (archie-core-1786637489768) needed no new code to
hold here.
Wired into bootstrap.go:setupCurators via a new curatorLLMRunner adapter
(main.go) over the shared ai-sdk runtime, and sessioncurator.NewAdapter
over b.chatSessionStore/b.cfg.BotUser. Model resolves from
b.chatModels.ActiveModel() -- not b.defaultChatIdentity, which names a
task-routing identity, not a model reference (the same source
telegram_setup.go's sendChatTurn already uses for a real chat turn).
task check is green (full Go suite + dashboard tests).
Part of archie-core-1786637499206 (skill curator reference
implementation), under the curator engine epic.
docs/prds/skill-curator.md records the design decision this needed
before coding (no settled design existed for what "review, prune, and
improve skill definitions" means as concrete Pass() behavior): v1 is
mechanical validation and safe whitespace normalization only. No
LLM-authored rewrites of skill content, no automatic deletion -- an
autonomous process editing or deleting a user's skill has no undo path
today, and the epic's actual purpose for this issue is proving the
curator contract holds for a second, structurally different consumer
(files-as-skills vs. observations-as-memory), not solving "what makes a
skill good."
internal/infrastructure/skillcurator/store.go: a curator.SkillStore
implementation over one root's .agents/skills/*/SKILL.md files. Not
internal/skill.Discover directly -- Discover parses every skill up front
and fails the WHOLE call if any one of them doesn't parse (correct for
"load the catalog to boot the daemon", wrong for "review each skill and
report what's wrong with it individually"). This store lists/reads raw
bytes per skill; the curator itself parses each one so one bad skill's
parse failure becomes one Action, not an aborted pass.
internal/infrastructure/skillcurator/skillcurator.go: the CuratorEngine.
Check is a cheap directory-listing bool. Pass classifies each skill into
exactly one of: skill.invalid (frontmatter parse failure, left
untouched), skill.incomplete (missing required name/description,
untouched), skill.normalized (trailing whitespace / missing final
newline, written back), or nothing (already clean). Manifest declares
only Skills -- no Tools, no MemoryEngine -- since nothing here needs
either.
Wired into internal/app/archied/bootstrap.go:setupCurators, rooted the
same way loadWorkflows already resolves skillsBase (cfg.SkillsDir falling
back to cfg.WorkDir) -- one local root, not the full multi-root catalog a
chat turn reads. Skills is now a shared registrar-level service
(alongside Events/MemoryEngines), narrowed out of a curator's view by
registry.filter when undeclared, same as every other capability.
task check is green (full Go suite + dashboard tests); go test ./...
is green.
Closes archie-core-1786637499161-356-e424e40d.1.
setupMemory's own doc comment claimed external providers are added via
RegisterExternal when cfg.Memory.Provider is set -- no such call
existed. Investigated wiring it for real: there is no external
MemoryProvider implementation anywhere in the repo to construct and
register (only internal/memory/builtin.Provider exists), so there is
nothing to route memory.provider's value to yet. Wiring the call would
be dead plumbing to nothing, not a fix.
The actual defect is that setting memory.provider has always silently
done nothing -- an operator who set it reasonably believed they
configured something. validateMemory now rejects it outright with a
clear reason, turning a silent no-op into a loud one at config load,
same failure-loudly posture as every other unimplemented-value check in
this file. Drop the rejection once a real external provider (or the new
domain/memory engine family's Honcho proof, archie-core-1786637492031)
gives the field an effect again.
Updated setupMemory's doc comment and config.example.toml to match --
the provider_config example is removed too, since it has nothing left
to configure.
Closes archie-core-1786637499636 (bind curators to memory engines).
curator.Registrar gets MemoryEngines, a MemoryEngineSource
(Get(name) (domainmemory.MemoryEngine, bool)) mirroring
domain/memory.Registry.Get's exact signature so the real registry
satisfies it with no adapter. Registration enforces presence the same
way Tools/Skills already do: a curator declaring Manifest.MemoryEngine
with no MemoryEngineSource on the host is rejected at Register, and
filter() clears MemoryEngines from a curator's view when it declared no
engine. A curator with a declared name that turns out not to exist in
the registry is not this layer's problem -- Get(name) at call time
returns false, same as ToolBuilder.Build with an undeclared tool.
Resolution is by name at call time, not a value pre-fetched at Bind: a
curator calls MemoryEngines.Get(its own Manifest().MemoryEngine) itself,
the identical trust model ToolBuilder.Build(ctx, declared) already
uses -- the curator is trusted to pass its own declared identifier, not
handed something pre-scoped to it. Swapping the configured engine (a
different name resolving through the same registry) changes where a
curator's memories land with no change to the curator itself, since
nothing about the curator's own code names a concrete engine.
setupCurators wires b.memEngines (*domainmemory.Registry, set by
setupMemoryAll which Run() calls first) straight in -- it already
satisfies MemoryEngineSource.
A curator declaring no memory engine remains valid (existing behavior,
now also covered by the "nothing declared" and "no source" table
cases) and is only ever affected by a memory operation it never has the
means to attempt, since MemoryEngines is nil in its view.
Completes archie-core-1786637499480 (ship the file-writing store as
the default memory engine): cfg.Memory.Engine now actually selects and
starts an engine, closing the gap the previous commit's message called
out as remaining.
setupMemoryEngine builds a domain/memory.Registry, registers
infraMemory.BuiltinEngine for "builtin" (and the empty/unconfigured
case, matching applyMemoryDefaults' resolution) rooted at
workDir/memory-engine -- separate from the legacy provider's
workDir/memory, so the two can never collide on the same files while
both exist -- starts the registry, and stops it on daemon shutdown.
cfg.Memory.Engine is already validated against the same set at config
load (configuration.validateMemory), so the switch's default case only
guards the two lists drifting apart, not live operator input.
setupMemory and setupMemoryEngine are both called through a new
setupMemoryAll from Run(), which was already at its cyclomatic
complexity budget -- a genuine grouping (both are memory-subsystem
startup), not two unrelated steps merged just to hit a number.
setupMemoryEngine deliberately does not thread Run()'s ctx through to
registry.Start, matching setupMemory's own existing choice for the same
reason (Start is a synchronous startup step, not a subscription that
needs the daemon's lifetime the way setupCurators' WakeOnPrimaryInput
does) -- also what avoids a contextcheck trip that threading ctx through
setupMemoryAll produced during development.
Not yet done: internal/memory.Manager (the live system-prompt/tool-call
path) does not read through this registry -- the two memory systems run
in parallel, per archie-core-1786637490069-11-e245c170's explicit "do
not extend the legacy system in place" scoping. That convergence is
future work, not part of this issue.
Implements archie-core-h019.3 (reviewer isolation) and h019.4 (wiring),
per docs/prds/adversarial-self-review.md.
- internal/domain/workflow: new Reviewer interface and StageReview,
inserted between StageDiffCap and StageOpenPR in the implement
workflow. Fail-closed: a review that didn't run, or a confirmed
error-level finding, parks the task (store.StatusParked) with
findings in Detail; warn/plausible findings never block. Inert
unless Repo.ReviewEnabled.
- internal/worktree: Manager.Snapshot exports HEAD's tracked files into
a fresh directory with no .git, for the reviewer's isolated
workspace. Trees interface gains Snapshot; hybridTrees delegates to
it.
- internal/app/agentworker: subagentReviewer implements Reviewer using
ai-sdk's agent.Subagent (nested, in-process, non-streaming
generation) -- conversation isolation is structural (Subagent.Run
never carries message history), workspace isolation is the snapshot
above. The reviewer's toolset is read-only (read/grep/find) rooted
at the snapshot, never the worker's own toolset, so it cannot reach
the worktreerpc publication grant. Findings are captured via a typed
record_finding tool appending to a slice the stage owns, read even
when Subagent.Run errors (a truncated run's captured findings
survive).
- internal/config: Repo.ReviewEnabled (default false) and
Models["reviewer"] (falls back to Models["builder"], no schema
change).
Judgment calls: Reviewer.Review never returns a Go error -- every
failure folds into ReviewReport per the PRD's fail-closed contract,
which the stage can act on uniformly. A Subagent.Run error with zero
captured findings resolves to ReviewStatusNotRun (park); a
Subagent.Run error with >=1 captured findings resolves to
ReviewStatusCompleted with those findings, since the PRD's own example
("three defects survive a step-limit truncation") requires them to
still be evaluated for blocking rather than discarded.
Test TestPluginEngineRuleIsCanonicalAndSharedByAgentInstructions was
missing entirely, letting CLAUDE.md drift out of sync with
ARCHITECTURE.md#plugin-engine-rule-strict. Added the test and the
missing reference.
Task runs now preserve real model context limits, provider usage, baseline-repair spend, commit identity, durable agent-finish telemetry, and useful timeline details without imposing a token cap. Dashboard forge links are canonical per owning GitHub or Gitea identity. Chat turn claims acquire SQLite writer intent before reading, eliminating the concurrent SQLITE_BUSY snapshot race.
Autonomous workflows now have exactly one production boundary: a task-scoped archie-agent receives a full-task core-NATS request and runs the worker-local stage loop. The legacy [agent] section remains decode-only for migration; it no longer selects runtime behavior.
archied's own build has carried a compiled-in gatewayVersion and an
internal/installtype stamp since archie-core-522/2873cbb, but
archie-agent's build had neither -- its Taskfile.yml and Dockerfile
build steps passed no -ldflags at all, so even a daemon that wanted to
verify what agent build is actually in service had nothing to check
against. daemonRunningVersions said as much explicitly: the agent was
left out of every verification on purpose, because nothing self-reported
a real value.
Every archie-agent process is task-scoped and ephemeral (spawned per
task, dies after), not a long-lived process the daemon can poll on
demand the way it polls Telegram's gateway. So there's no "ask the
agent its version" request -- the only channel back is whatever a
worker includes in the taskrun.Response it already sends on every
completed task.
Stamp archie-agent's build the same way archied's is (installtype,
plus a new agentworker.Version()), have executeTaskRequest report both
in its Response, and have the daemon record the latest observation in
a new mutex-guarded AgentStatus, fed from runViaAgent on every
successful response only -- never off a request that never reached an
agent, or one describing a failed/parked task. daemonRunningVersions
now includes the agent component once (and only once) something has
actually been observed, so Report.Verify gets a real value to check
future update claims against instead of omitting the component
entirely.
Part 1/3 of archie-core-1786751948782-3-837a8fd0 point 4. Closes
archie-core-1786751948782-3-837a8fd0.1.
TestApplicationOwnsNoTransportWireMechanics was failing on main since
d82b232: persistent_runner.go imported encoding/json to decode its
own project-memory JSONL log, which the architecture test treats as
a transport-wire-mechanics violation. That ban exists to keep NATS
message encoding out of the app layer -- this was local disk I/O, not
wire traffic, but the test can't tell the difference from an import
alone, and it shouldn't have to: the fix is to not decode JSON in
agentworker at all.
storage.ReadJSONLines is AppendJSONLine's read-side counterpart,
added to the package that already owns this format (see
organisation.md, "a package owns its own format end to end").
persistent_runner.go now calls it instead of scanning and decoding
itself, and no longer imports encoding/json or bufio.
This was blocking every deploy.yml run on main, independent of and
found while shipping the video-generation PR (#561).
Worktree RPC used to accept repository coordinates from the sandbox. It now accepts only an opaque per-dispatch grant, and the daemon derives the repository path and branch from grant-owned state.
Repository worktree paths also move from an ambiguous flattened key to encoded owner/repo components. Origin-matched legacy clones migrate safely; mismatched legacy paths are preserved.
Ephemeral task containers re-resolve and re-download npx-launched MCP
server packages from the npm registry on every task, since each task
gets a fresh container with no persistent cache -- a worse amplifier
of a registry outage than the daemon-restart case d4bb914b already
fixed.
Extract the daemon's npm-cache env logic into mcp.NpmCacheEnv, shared
by both the daemon's own long-lived npx MCP servers and archie-agent's
per-task ones. Mount a new archie-cache-mcp-npm Docker volume at
/data/cache/mcp-npm on every task container regardless of ecosystem
(MCP servers are daemon-wide config, not tied to the task repo's
language), and point npx-launched per-task stdio transports at it.
Closes archie-core-qk8m.
Agent containers run as root (no USER in the Dockerfile, no
userns-remap), so a commit the agent writes to the bind-mounted
worktree lands owned by UID 0 on the host. The daemon then reads
those same loose objects to push, running as its own non-root host
user, and fails with "openat objects/../..: permission denied".
containerEnv() now passes the daemon's own UID/GID as
WORKTREE_UID/WORKTREE_GID. hybridTrees.Push -- the single point
where a commit's objects are handed back for the actual push --
chowns the worktree to that owner first, via os.Lchown so a
legitimately-tracked-but-dangling symlink doesn't abort a push that
would otherwise have succeeded.
Closes archie-core-1786749700606-6-bf6aa32d.
archie-core-467 wired tool-call visibility into the interactive chat
gateway, but a workflow task's own transcript never showed what its
tools actually did -- only stage/agent-finish events existed, so
there was no way to confirm an agent's summary matched what it really
ran.
Adds a ToolCallReporter, invoked once per completed call from
toolExecute (the single choke point every tool call passes through
before reaching a model), reported via a new ToolSetOptions.OnToolCall
hook. Runner.Run grows a report parameter to carry it in: InProcessRunner
wires it through, since it executes in the same process as its tools;
SubprocessRunner and NATSRunner accept and ignore it, since their tool
calls happen in a different process with nothing here to observe them.
The workflow engine turns each report into a tool_call event on the
task's own Bus (agent.go, implement.go), riding the same NATS
event-forwarding archie-core-518 already built to get container
events onto the daemon's timeline.
Scoped to the central tool registry (read/write/edit/grep/shell/...)
built via BuildToolSet; capture tools (structured finish output) and
run_go_script build their ToolSet entries directly and are not yet
covered.
On a stage-handle failure, the main loop logged the error, called
Nak (which requests redelivery), and looped straight back into
FetchStage with no delay -- unlike the fetch-error branch three lines
above, which already backs off for a second. A deterministic failure
(a broken gate, a malformed request) therefore refetched and failed
again immediately, flooding the log with one "handle failed" line per
loop iteration instead of per genuine retry -- hundreds of identical
lines within the same second in production.
Adds the same time.Second backoff after Nak.
A workflow run through the container/NATS path never wired
workflow.TaskContext.Bus, so every tc.Emit call (stage_start,
stage_finish, outcome, parked) was a silent no-op. archied's own
in-process path sets Bus and always worked; anything dispatched to an
archie-agent worker did not, which meant the dashboard's per-task
timeline showed "No events yet" for every task regardless of status
or stage -- confirmed live across a Working task and two differently
parked tasks.
Bridges the gap the same way system logs already cross this boundary:
ForwardTaskEvents relays a per-task in-process *events.Bus to a new
NATS subject (SubjectForEvents), and a new daemon-side subscriber
(subscribeAgentEvents) republishes decoded events on the daemon's own
Bus, landing them in the same persist-and-broadcast pipeline an
in-process workflow already used.
Closes#518
cmd/archie-agent used to own worker construction, NATS lifecycle, task execution, MCP setup, and workflow wiring. It now owns process input only and invokes internal/app/agentworker, while transport-specific NATS, boot-brief, and git-safety mechanics live under infrastructure.