dependencies-and-contracts.md rule 1 says domains must not import
internal/infrastructure. internal/daemon and internal/agentexec both did,
and for exactly the thing the doc carves out: "internal/eventbus is an
approved shared application contract ... it MUST remain broker-neutral."
The Publisher/Consumer/Requester interfaces existed but lived inside the
NATS package, so a caller could depend on the behaviour yet still had to
import the implementation to name it. They now live in internal/eventbus,
and nats.Client asserts against eventbus.Bus.
The larger violation was ownership of meaning. The doc says "message schemas
stay with their owning domains; the event bus transports messages, it does
not own their meaning." The bus exported TaskEnvelope and a PublishTask
method, so the transport knew what a unit of work was, and it exported the
archie.agent.* subject helpers, so it also owned the agent protocol.
- TaskEnvelope, its routing Kind, the label vocabulary and the task
subjects move to internal/domain/workintake, which encodes and decodes
its own bytes. This starts internal/domain/ per organisation.md.
- The agent request/response/system subjects move to internal/agentexec,
which defines what those messages mean.
- internal/workflow keeps only the kind-to-registry mapping; the label
table stays single and lives with the domain that reads forge issues.
- The bus now carries opaque payloads on plain-string subjects.
Consumers declare the smallest interface they need rather than taking the
whole Bus: daemon.TaskBus is publish-unique/fetch/request, agentexec.
RequestBus is publish-request/reply-inbox, and archie-agent's stageBus is
fetch/respond. None can reach what it does not use.
Two defects this surfaced:
- archie-agent declared its own JetStream stream with a second copy of the
name, subjects, retention, dedup window, MaxDeliver and TTLs that
nats.Connect already sets -- two definitions of one stream, free to
diverge. Config now takes Subjects and FilterSubject from composition,
which is what let the agent use the shared client and delete its
hand-rolled setup.
- Replying to a request needs core NATS, not the JetStream publish path:
a reply inbox is ephemeral and belongs to no stream, so a durable
publish to it fails. The old code hid this by using the raw connection.
The contract now distinguishes Respond from Publish. The agentexec
round-trip test caught it after I had made the same mistake in
archie-agent.
Also translated the SDK's ErrNoResponders into eventbus.ErrNoResponders, so
the daemon's taskrun retry no longer imports the NATS SDK to name a
transient condition. The SDK is now confined to the nats package, the *rpc
packages (themselves NATS infrastructure), and cmd/*.
The agentexec test fake previously hand-rolled a JetStream consumer; it now
drains the client's own consumer, which is both closer to production and
avoids conflicting consumers on a work-queue stream.
Verified: go build, go vet, gofmt clean; full test suite passes.
internal/config both defined the types every package imports and performed
the file I/O to produce them. Importing a settings struct therefore pulled
in a TOML decoder and a YAML decoder, and the shared model owned discovery,
decoding, overlays, defaulting and validation all at once. See
docs/architecture/configuration.md, which requires loading to move out and
internal/config to be dissolved.
internal/config is now types only -- no os, no filepath, no toml. The new
package owns loading, one concern per file:
features.go the closed set of recognised feature files
discovery.go directory scan and classification
decode.go TOML/YAML decoding, format dispatch
defaults.go filling absent values, no errors
validate.go judging supplied values, no mutation
provenance.go which file contributed what
loader.go Loader wiring the above; File/Overlay/Dir
Beyond relocating, this fixes what the old code conflated:
- Defaulting and validation were interleaved. applyAgentDefaults and
applyDispatchDefaults returned validation errors; validateContainers and
validateSingleIdentity quietly mutated the config. There was no point at
which you could see what the operator actually supplied. They are now
separate passes: applyDefaults never fails, validate never writes.
- Errors were fmt.Errorf strings prefixed "config: ", so a caller could not
distinguish operator-fixable input from an unreadable file without
matching message text. Five sentinels now carry that distinction.
- dataHome() read XDG_DATA_HOME directly and discarded the error from
os.UserHomeDir, so defaulting could not be tested without the
environment. It is injectable on Loader and no longer swallows the error.
- Nothing recorded where a value came from. With overlays, feature files
and conf.d/ all able to set the same field, "which file set this?" was
answerable only by re-deriving precedence by hand. Provenance records it.
- Feature files were applied in map iteration order, making load order and
any resulting error arbitrary. Discovery now returns them sorted.
- loadMainConfig reported "no config.yaml or config.toml found in %s" with
an empty string: the directory was lost when it was extracted from
loadDirInto, so the error named no directory.
- Unreadable or malformed conf.d/ extras were skipped silently, which
presents as a setting the operator wrote simply not taking effect.
- Decode errors from the main config were returned bare, without naming
the file that failed to parse.
The 40 loader tests moved with the code and their assertions are unchanged,
so the defaulting and validation rewrite is behaviour-preserving.
Document.Config is the temporary seam: still internal/config.Config, named
as a field so the compromise is visible at each use site, with its deletion
condition recorded in doc.go. Building typed per-domain sections now, while
every consumer still reads config.Config, would mean two shapes kept in sync
by hand with no consumer for the new one; that belongs with the dissolution
work, not ahead of it.
No consumer outside cmd/archied changed.
Verified: go build, go vet, gofmt clean; go test ./internal/config/... and
./internal/infrastructure/configuration/... pass. Pre-existing gateway and
telegram failures are unchanged.
The event bus was inspecting forge issue labels ("bug", "feature",
"bootstrap") to pick a subject. That put a forge vocabulary inside
infrastructure and duplicated the label table already owned by
workflow.Route -- adding a label meant remembering both places, and
nothing would have caught it if you forgot.
The label table now lives once, in internal/workflow, which already owns
label semantics:
- workflow.Kind names the routing category, with labelKinds as the
single label vocabulary and kindWorkflows mapping kind to registry
entry. Route consumes the ordered kind list so a "bug,feature" task
still falls through to feasibility when no tdd workflow is
registered, exactly as the switch did.
- nats.TaskKind is a closed, validated set of subject tokens.
PublishTask rejects an unknown kind rather than silently delivering
it to the default queue; the zero kind means default, so messages
queued before this field decode unchanged.
- The daemon classifies at the publish site and sets TaskEnvelope.Kind.
Also fixes two defects this exposed:
- drainNATS never reached its SQLite fallback. Replacing the old
(nil, nil) no-message signal with ErrNoMessage in 492ca20 made that
case continue at the top of the loop, but no-message is precisely
when the fallback must run -- requeued tasks (waiting_human approval,
retry-parked) never go through a NATS publish, so nothing would ever
arrive to trigger them. go vet caught it as unreachable code.
- config.classifyFeatureFile silently overwrote duplicate feature
files, so config.gateway.yaml and conf.d/gateway.yaml together
applied one at random. Its own doc comment recorded the bug
("or "" on success/duplicate"). The known-feature list in the error
message is now derived from knownFeatureNames instead of being
spelled out a second time beside it.
A test also called t.Fatalf from a non-test goroutine, where it does not
stop the test.
Verified: go build, go vet, gofmt clean. Pre-existing gateway (18) and
telegram (1) failures are unchanged in count -- they are lost routing
wiring from the parallel telegram merges, tracked separately.
Relocating internal/nats as-is would have cemented its problems into the
approved layout, so this is a rewrite rather than a move.
What was wrong:
- Conn() *nats.Conn, PublishMsg(*nats.Msg) and Fetch() jetstream.Msg pushed
SDK types into all four consumers, so the broker was not replaceable --
the opposite of what dependencies-and-contracts.md requires.
- PublishTask took seven positional parameters, six of them strings, where a
transposed argument was a silent bug.
- Labels travelled as a comma-separated string and were re-split on every
publish.
- Fetch returned (nil, nil) for 'no message', which every caller had to
remember to special-case.
- The logger field was stored and never used.
- Stream name, consumer name and every timeout were hardcoded constants.
- Errors were inconsistently wrapped; several paths returned bare errors.
- Connect repeated nc.Close() on each failure branch.
What replaces it:
- One concern per file: config, errors, subjects, message, client,
publisher, consumer.
- Publisher/Consumer/Requester interfaces with compile-time assertions, so
callers depend on behaviour and can be faked without a broker.
- A Message wrapper keeps jetstream types behind the boundary; consumers no
longer import the NATS SDK at all.
- TaskEnvelope with []string labels and JSON methods preserving the
comma-separated wire form for already-queued messages.
- Sentinel errors (ErrNoMessage, ErrNotConnected, ErrNoReplyAddress,
ErrInvalidConfig) and %w wrapping with operation context throughout.
- Config with validation and defaults; a single deferred cleanup in Connect.
- CoreConn() as the one documented escape hatch, for the *rpc packages that
are themselves NATS infrastructure.
Consumers migrated: cmd/archied, cmd/archie-agent, internal/daemon,
internal/agentexec. Behaviour, subjects and wire format unchanged.
Add gateway/runtime-owned commands that remain usable when LLM credits
are exhausted:
- /start — acknowledgement without consuming a reply
- /new [name] (alias: /reset) — create a fresh session
- /topic [off|help|<session-id>] — session switching for threaded chats
- /retry — remove last assistant message, replay last user turn
- /undo [N] — remove last N messages from history (default: 1)
- /title [name] — set or display session title
- /branch [name] (alias: /fork) — create child session with inherited history
- /compress [here N|focus topic|--preview|--dry-run] (alias: /compact)
Design:
- sessionTracker maps channel+thread to active session, auto-creating
implicit sessions with the legacy sessionKey format for backward
compatibility with existing persisted data
- /new and /branch create explicit UUID-backed sessions
- SessionStore extended with DeleteRecentMessages, MessageCount, and
SaveMessages for undo/retry/branch/compress operations
- SessionContext extended with Title, ParentSessionID, BranchName
- All commands report 'not configured' when session store isn't wired
Session resolution is wired into the LLM responder so /new, /branch,
and /topic switches affect subsequent chat turns.
golangci-lint run --fix plus the formatters: errorlint, gocritic,
sloglint, usestdlibvars, usetesting, gci, gofumpt, goimports.
160 issues -> 130.
One autofix was wrong and had to be reverted by hand. gocritic rewrote
ctx, cancel = context.WithTimeout(ctx, m.prefetchTimeout)
to `:=` inside an if-block in internal/memory/manager.go. That does not
compile, which is the good outcome — had it compiled, the shadowed ctx
would have scoped the timeout to the if-block and the prefetch deadline
would silently never have applied. Restored the assignment and commented
why it must not be a declaration.
Worth recording: --fix is not a safe no-op. It broke the build on a
24-file change, and the failure mode it was one compiler error away from
was a silent behaviour change.
First slice of the tau cherry-pick strategy: copy-and-mutate rather than
extracting tau to pkg/. Exporting would force designing metrics, session
and logger seams upfront, before archie-core knows which of them it wants
differently — a cost paid for reuse not yet proven. ai-sdk earned library
status by stabilising across two consumers; nothing in tau/internal has.
indexing is the cheapest high-value lift: 512 LoC, one file, and its only
coupling to tau was three calls to process-global config path helpers.
Nothing else in tau imports it.
Mutations from upstream:
- path helpers become an explicit indexing.Config. Two archied instances
share a host (archie and winter), so they must not share one index.
- the child-process helper is archied's own workspace-codesearch
subcommand, dispatched before flag parsing so it touches no config,
store or NATS.
- deferred db.Close calls explicitly discarded; archie-core runs errcheck.
The child process is not incidental: google/codesearch calls fatal exits on
a corrupt index and leaks mmapped regions. Verified end to end against this
repo — 2.2MB indexed, correct hits for BuildSystemPrompt, [] for no match,
and a deliberately corrupted index returns "corrupt index" with exit 1
instead of taking the process down.
Every lifted file carries a provenance header naming its tau path and
commit (4893818d0c76), so refreshing from upstream is a diff rather than
archaeology.
The chat agent's entire system prompt was the four-sentence static string
in gateway.DefaultPersonas(). It carried no tool inventory, no environment
block and no instruction precedence, so the model invented its own
capabilities: asked to set something up it announced it "only has the
memory editing tool", then offered to walk through installing software it
has no tool to install.
Renders a template modelled on tau's agent.md.tpl + tau.agent.md:
instruction precedence, core rules, communication rules, a <tools> block
and an <env> block. The persona stays the style layer on top; the rules
and the tool inventory live in the template so switching persona cannot
remove them.
The tool list is derived from the same core.ToolSet handed to the model,
so the prompt cannot drift from what the agent can actually call, and an
empty toolset renders an explicit "no tools are available" rather than
silence the model fills in for itself.
Tool metadata is third-party data from MCP servers, so it is markup-escaped
(<, >, & only — not xml.EscapeText, which mangles prose into 
/')
and whitespace-flattened, so a description cannot forge a closing tag or a
second "- tool: ..." list entry.
Operator escape hatch: reload gateway config (notably the sender
allowlist) or recover a wedged adapter from chat, with no shell access to
the host.
Start becomes a supervisor loop that relaunches the bot on request, so a
restart is scoped to the gateway: the daemon keeps running and in-flight
agent tasks are untouched. Exiting the process would also have restarted
under the unless-stopped policy, but would have killed running work.
Two failure modes are handled deliberately:
- The handler runs on the very bot the supervisor is about to stop, so it
hands off over a buffered channel and returns instead of tearing down
inline, which would deadlock the restart it just requested. A duplicate
request while one is in flight is dropped, not queued.
- A failed config reload logs and relaunches on the previous settings, so
a bad config edit cannot take chat down permanently -- which would also
remove the means to fix it.
Authorisation is inherited from authorizedMessage: only allowlisted
senders reach any handler, so /restart is admin-only by construction.
main.go supplies Reload, which re-reads config from disk and refreshes
token and allowlist; other fields still need a full daemon restart, since
they are wired at construction.
Allowlist (16.33). telegram.New was called with a nil allowlist and
isChatAllowed returned true whenever the list was empty, so any Telegram
user who found the bot could talk to it; AllowedChatIDs was not plumbed
into config, so there was no way to close it. Chat tools run with the
daemon's own authority, so this had to be fixed before wiring any real
tools to the chat agent.
Now chat.telegram.allowed_user_ids configures it and an empty list denies
everyone: a bot handle is public, so failing open is not a safe default.
The check matches the sender (from.id) rather than the chat, so adding
the bot to a group cannot be used to inherit access. Rejections log the
sender id and answer once, so a legitimate user missing from the list can
tell the bot is misconfigured rather than dead. Startup warns when the
gateway is enabled with an empty list.
The previous TestIsChatAllowed asserted 'empty allowlist allows all' --
it encoded the vulnerability -- and is replaced by fail-closed tests.
Command menu (16.34). SetMyCommands was never called, so Telegram showed
no menu and the commands Router implements were undiscoverable; asked
about /commands the LLM confidently answered it had none. The published
list mirrors what Router actually handles. Failure is logged, not fatal:
it costs discoverability, not function.
Streamed chat replies hung on the first token: the draft rendered an
empty cursor, the typing indicator never cleared, and the turn never
completed.
RouteStream consumed stream.TextStream, but ai-sdk's channel contract
makes FullStream authoritative and requires draining it until close --
its writes are synchronous, so an unread FullStream applies backpressure
and stalls the producer. Once its buffer filled, the producer blocked,
TextStream stopped yielding, and the range loop blocked forever.
TextStream was the wrong source regardless: it is explicitly best-effort
and drops deltas when not drained, so a reply reconstructed from it can
silently lose text. Range over FullStream and collect StreamPartTextDelta
parts, exactly as the SDK documents.
Also bumps ai-sdk v0.1.17 -> v0.1.18 (build, full suite and lint clean).
Upgrades go-telegram/bot v1.18.0 -> v1.22.0 and uses the Bot API's rich
message support instead of hand-rolled formatting.
The previous commit converted LLM Markdown into Telegram's HTML subset,
on the premise that the API could not take Markdown directly and had no
table element. Both are true of v1.18.0 but not of v1.22.0, which adds
sendRichMessage/sendRichMessageDraft taking InputRichMessage{Markdown},
plus RichBlockTableCell for native tables. markdownToHTML and its tests
are deleted: LLM Markdown, tables included, now goes to Telegram as-is.
Replies also stream. runtime.ChatStream already returned a TextStream
and sendRichMessageDraft renders partial output, so the only missing
piece was a gateway seam: gateway.LLMStreamResponder plus Router.
RouteStream, which degrades to the blocking Route when unset so any
adapter can call it unconditionally. Local commands answer from local
state and are not streamed; an unrecognised /command is, since Route
hands it to the LLM. main.go derives both responders from one shared
turn implementation.
Draft updates are throttled to one per 700ms to respect per-chat rate
limits, and every streaming/rich path falls back rather than dropping a
reply: a rejected rich send retries unformatted, and a failed draft
update is skipped since the final message is authoritative.
archied's container-mode agent tasks were all failing with "nats: no
responders available for request" in production. Root cause: pool.go's
selfNetwork() auto-detects the daemon's own Docker network by looking up
a container named after os.Hostname(), then joins spawned agent
containers to that same network so they can resolve "nats" by name.
On carina this detection was silently failing (wrong/stale hostname vs.
actual container ID) and returning "", so every per-task agent container
landed on the default bridge network instead — unable to resolve "nats",
never subscribing, hence "no responders" on every request.
selfNetwork() swallowed every failure silently (only logged on success),
so this had no diagnostic trail.
Fix: added Containers.Network config field (containers.network in
config.toml) so deployments can name the network explicitly instead of
relying on fragile self-detection; selfNetwork() remains as a fallback
but now logs a warning on every failure path so this doesn't silently
recur. Wired through container.Config and cmd/archied/main.go.
Checkpoint commit covering concurrent work across several archie-core-abg
epics to avoid losing in-progress state:
- Memory manager (18.7-18.16): background sync pipeline, prefetch with
timeout, memory-write notification, threat scanning, shutdown drain
with abandoned-write tracking, frozen snapshot pattern. Wired
ScanContent and NotifyMemoryToolWrite into HandleToolCall so scanning
and notification actually apply to writes, not just exist as unused
primitives.
- Fixed a literal unresolved merge-conflict that had been committed to
internal/memory/scrubber/scrubber.go.
- Tool provider/registry, MCP client/transport (stdio, HTTP, SSE),
multimodal results, disclosure.
- Pairing device auth store, rate limiting.
- Gateway compression, session store, tasks.
- Various workflow, plugin host, and agentexec updates.
Adds internal/secret: a pluggable Engine interface (Name/Version/Resolve)
resolved through a Registry, so secrets backends (sops, Bitwarden Secrets
Manager, Vault/OpenBao) aren't hard-coded into the binary. Only the "env"
engine is compiled in; custom engines are Yaegi-interpreted .go plugins
loaded via Registry.LoadDir, mirroring internal/plugin's conventions
(secretextract provides the generated, nil-guarded symbol table for the
Yaegi/Go interface boundary).
config.Forge.TokenEnv is replaced end-to-end with config.Forge.Token
(secret.SecretRef{Engine, Key}) -- finalize() defaulting, forge token
resolution in cmd/archied/main.go, and per-identity validation that now
requires an explicit token instead of silently resolving to "". No
backwards-compat shim.
Provider.APIKeyEnv, NATSConfig.TokenEnv, and TelegramConfig.TokenEnv are
deliberately not migrated here -- they're forwarded by name to
ai-sdk/runtime and subprocess workers rather than resolved centrally,
which needs its own eager-resolve-then-inject design pass
(archie-core-xec.4). The three shipped engine plugins (sops, bws,
vault/openbao) are tracked separately as archie-core-xec.1-3.
Adversarially reviewed by a fresh agent with no implementation context;
fixed the two findings that survived (missing per-identity token
validation, underdocumented nil-wrapper Resolve edge case).
SessionStore extended with SaveMessage, RecentMessages, SearchMessages.
NellDB-backed implementation uses a separate DocDB collection for messages
keyed by session:seq. Conversation history loaded into LLM context for each
Telegram message. Responses persisted. Substring search fallback (vector
search deferred to memory provider embedding integration).
Adapter.Store() exported to share the underlying NellDB engine for session
collections without opening a second log.
Telegram LLMResponder now:
- Saves inbound messages to session store
- Loads 20 most recent messages as chat.Message history
- Sends full conversation context to llm.Chat()
- Persists the assistant response
All 38 packages pass with -race.
LLMResponder adapter wraps llm.Chat() with model from cfg.Models[chat] (falls
back to builder). Gateway-local commands (/status, /models, /model, /spawn)
still handled directly. LLM created before gateway so it's available at
router construction time. All 38 packages pass.
Memory:
- MemoryManager created in main.go with built-in file-backed provider
- SystemPromptBlock() injected into every agent stage request via ExtraRules
- memoryPrompt() helper on Daemon, threaded through TaskContext.SystemPrompt
Guardrails:
- GuardrailEngine created from DefaultGuardrailConfig in main.go
- RecordSuccess/RecordFailure called after every agent stage run
- Threaded through TaskContext.Guardrails for per-task guardrail enforcement
Tool registry:
- NewRegistry() created at startup, MCP servers started from config
- Passed to Daemon.ToolRegistry for dynamic tool discovery
Daemon changes:
- Memory, Guardrails, ToolRegistry fields added (nil-safe, backward compat)
- TaskContext gains SystemPrompt + Guardrails fields
- Agent stage injects memory context into ExtraRules
- Agent stage records guardrail state after each run
Telegram LLM routing deferred (TODO comment) — gateway commands work.
All 38 packages pass with -race.
TaskCreator interface on gateway.Router allows chat users to create
tasks via /spawn <title>. Implemented as gateway-local command (no LLM
needed). StoreTaskCreator wraps the daemon's store and uses the first
configured repo as the task workspace with timestamp-based synthetic
issue numbers to avoid collisions with Gitea-issued tasks.
Wired into archied's gateway startup: when repos are configured,
router.Tasks is populated so /spawn works. When no repos are
configured, /spawn returns 'not configured'.
Closes: archie-core-abg.13
19 files touched. All fixes are in code — no lint configuration
weakened:
- Added unchecked error handling in defer cleanup paths
- Removed dead variables and unused functions
- Added missing imports (io in gitea.go)
- Simplified conditions (TrimSuffix, De Morgan, slices.Contains)
Also fixes JetStream TempDir teardown race (archie-core-340):
t.Cleanup(srv.Shutdown) now registers after t.TempDir() so
server shutdown (including JetStream files) completes before
temp dir removal. Added srv.WaitForShutdown() for deterministic
cleanup ordering.
Closes: archie-core-756, archie-core-340
Fix go vet/test failures by adding LinkBranch methods to stubForge, prCapturingForge, testForge, and fakeForge. Update test data from 'sam/archie' to 'acme/widget' and state label defaults from 'archie:*' to 'agent:*'. Add Taskfile.yml for project build automation. Implement container self-network detection so spawned agents join the daemon's Docker network.
- Introduce `-config-overlay` flag and `config.LoadOverlay()` to merge a base config with an overlay file, only overriding fields the overlay sets. This enables docker-compose to mount the base config from the host and apply only deployment-specific overrides.
- Create `internal/natsrpc` package with reusable NATS request/reply primitives (Envelope, Client, Call, RegisterAll, Respond). Migrate storerpc, worktreerpc, and forgerpc to use it, eliminating duplicated marshal/unmarshal and error handling.
- Create `internal/yaegiutil` package with shared interpreter construction (stdlib + extra symbols), generic export resolution (Resolve), and panic recovery (Safe). Migrate all Yaegi-based surfaces (gate scripts, daemon plugins, skill plugins, workflow stages, skill scripts) to use it, reducing boilerplate and centralizing panic safety.
- Simplify `config.docker.toml` to contain only overlay fields (paths, container config) and remove the duplicated repos list – the base config is now the single source of truth.
- Update docker-compose.yml to pass both -config and -config-overlay flags and mount the base config from the host.
- Add tests for LoadOverlay, DockerConfigOverlaysExampleConfig, Envelope, and yaegiutil utilities.
Add [containers].volume_ttl (default 72h). Persistent-storage repos get a
per-repo bare Git cache (--reference-if-able --dissociate) so task
worktrees clone fast without repeated full network clones, while staying
fully independent of the cache's lifecycle — cache expiry can never
corrupt an active or parked task's worktree. Docker repo volumes are
labeled as Archie-owned and swept non-forced (a volume still attached to a
running container survives and retries next cycle); the repo cache
directory is swept by mtime. Both cleanups run at daemon startup and each
poll cycle.
Filed archie-core-756 (repo-wide golangci-lint baseline) and archie-core-340
(intermittent JetStream TempDir teardown flake) as separate follow-ups
rather than scope-creeping them into this change.
daemon.process() branches on ContainerPool != nil: sandboxed tasks publish
a taskrun.Request to archie.taskrun.<id> and await the response via the
new runViaAgent method, instead of running workflow.Route/workflow.Run
locally. Non-container mode is unchanged. Every durable side effect
(Store, Forge, git push) already landed via the storerpc/forgerpc/
worktreerpc proxies during archie-agent's run by the time runViaAgent
returns — it only parks the task itself on transport/setup failure, never
duplicating a terminal state archie-agent's own workflow.Run already
recorded.
Also fixes a real correctness gap: with concurrent multi-task dispatch
(archie-core-u64/g1l) plus containerized archie-agent, a shared queue-group
subscription could let one container answer a sibling's taskrun message
while having a *different* task's worktree mounted. archie-agent now reads
its boot-time task.json and subscribes to its own exact per-task subject
when present, falling back to the shared queue group only in dev/pool mode
(no task.json).
Adds agentexec.ProvidersFromConfig, deduped from cmd/archied's former
executionProviders.
Closes the archie-core-5zh epic: archie-agent runs an entire task's
workflow per invocation instead of one stage per round trip, with all
credentials staying daemon-side throughout.
Add internal/taskrun (Request/Response wire types) and
cmd/archie-agent/taskrun.go: runTask builds a workflow.Registry from the
container's own bind-mounted worktree, routes and runs the task's entire
workflow via workflow.Route/workflow.Run, using storerpc.Client/
forgerpc.Client for Store/Forge and a new hybridTrees that splits
Prepare/Push (proxied over worktreerpc — network ops needing the daemon's
credential) from CommitAll/Diff/ChangedFiles/ChangedLines (local git
against the mount).
Add config.TaskConfig.ToConfig() to rebuild a usable Config from the
curated payload, and storage.WorktreeMountDir (/data/worktree) — critical
fix: hybridTrees.Prepare discards the RPC response's host-side directory
and returns the container's fixed local mount path instead, since archied
and archie-agent see the same files at different paths.
Wired a queue-grouped core-NATS subscription on archie.taskrun.> in
cmd/archie-agent/main.go alongside the existing per-stage consumer, so
this is reachable in the running binary. End-to-end test drives the real
"bootstrap" workflow (no LLM) through real storerpc/forgerpc/worktreerpc
servers and a real local git remote — registry build, route, prepare,
commit, push, PR creation, and confirms the authoritative task state
lands in archied's store via RPC, not just in-memory.
archie-core-5zh.8 (daemon.go handoff) is unblocked.
Add registerTaskRPCServers() in cmd/archied/main.go: subscribes all three
RPC servers on the daemon's NATS connection whenever [nats] is configured,
using the same Store/Forge/worktree.Manager instances the daemon already
owns. archie-agent containers now have a live responder for the Store,
Forge, and worktree Prepare/Push calls proxied in archie-core-5zh.1-3.
Test spins an embedded NATS server and round-trips real storerpc/forgerpc/
worktreerpc clients against the registered handlers.
Add token_env to [nats] config, resolved and validated at daemon startup
(fails early if configured but the named env var is unset). Container
workers get NATS_URL/NATS_TOKEN; archie-agent honors both while CLI-supplied
URL still takes precedence. Anonymous auth remains the default for
single-node deployments.
Unblocks archie-core-5zh (promote archie-agent to per-task process).
Daemon previously processed one task at a time. Add bounded concurrent
dispatch for SQLite and NATS agent modes, reusing [containers].max_concurrency
(0 = unlimited). Same-repository tasks stay FIFO-serialized to avoid worktree
conflicts; different repositories now run concurrently.
Unblocks archie-core-l1q (NATS transport) and archie-core-g1l
(per-repo allow_concurrent override).
Implements the Forge interface for Gitea instances (tested against
git.catlow.cloud, Gitea v1.26.4). The forge.New factory now dispatches
on forge type, and config validation accepts 'gitea'.
Changes:
- internal/forge/gitea.go — GiteaClient implementing all 11 Forge
methods: issue polling (assigned + label), comments, PR creation,
PR state reconciliation, issue closure, reactions, state labels,
push verification. Handles edge cases: not-found PRs return
'closed', GetUserByName errors from the Gitea SDK are mapped to
user-friendly messages.
- internal/forge/forge.go — New() factory dispatching on forge type
(github/gitea). GitHub constructor renamed to NewGitHub.
- internal/forge/github_test.go — updated to use New() signature
- internal/config/config.go — forge.type accepts 'gitea', BotEmail
defaults change per forge type (gitea uses @gitea.local)
- cmd/archied/main.go — passes cfg.Forge.Type to forge.New()
Dependencies: added code.gitea.io/sdk/gitea v0.25.1
End-to-end verified against live Gitea instance: daemon starts clean,
registry built (5 workflows), web UI listening, no errors or warnings.
Fixes (4 items):
S4 — Add TypeScript, Deno, Bun cache ecosystems to
cacheVolumesByEcosystem. TypeScript shares node+pnpm volumes;
Deno and Bun get dedicated cache volumes.
R4 — Share single Docker client between container.Pool and
storage.DockerBackend. NewPool now accepts an optional
DockerClient in Config; if nil, creates its own. Pool
tracks ownership (ownCli) and only closes its own client.
S2 — Wire Storage.Teardown() call in daemon.process() after
workflow.Run(). Docker backend is a no-op; this closes the
interface contract for future backends.
R5 — Emit observability event on AugmentRegistry failure.
Previously only logged a warning; now emits a
'registry_augment_failed' event with error detail.
Promoted log level to Error.
Documentation (4 items):
D1 — Document PluginRegistry as reserved for future daemon
extension points (forge resolvers, storage backends, etc.)
S1 — Fix /data/ layout comment to reflect actual task.json path
(/data/worktree/task.json, not /data/task.json)
S3 — Add TODO(PRD §3) for session.jsonl, memory.jsonl, plugins/
volume — these need agent-side implementation first
N6 — Document that VolumeInspectOptions{} requires moby v25+
(go.mod pins compatible version)
N7 — Document that _Plugin.IValue is required by Yaegi interface
bridging; warn that go generate strips nil-guards
Test: TestCacheMountsForTypeScript verifies typescript ecosystem
returns node+pnpm volumes sorted by destination.
Verification: single client.New(client.FromEnv) in main.go;
all 21 storage tests pass; full suite green.
P1 (panic): nil Storage guard in daemon.process()
C1 (correctness): check WriteTaskJSON error — don't start blind
C2 (correctness): move 'working' label after container setup
C3 (correctness): warn on duplicate workflow names in registry
C4 (correctness): test that generated _Plugin wrapper has nil-guards
C5 (correctness): .agents/skills as file (ENOTDIR) not fatal
C6 (correctness): ecosystem case-insensitive in cacheMounts
N1 (correctness): TOCTOU race — treat 'already exists' as success
N2 (correctness): recover from panicking plugin.Name() at startup
--- Details ---
P1: d.Storage.Setup() is now guarded by a nil check. In normal
operation Storage is always set when ContainerPool is set, but
the invariant is now explicit and enforced.
C1: container.WriteTaskJSON() error was discarded with _. Now it
returns early with a park transition — the container never starts
without a boot-time brief.
C2: SetStateLabel('working') was called before container setup.
If Acquire failed, the task was parked but the label stayed
'working' permanently. Now the label is set only after successful
container setup (or immediately if no containers are configured).
C3: BuildRegistry and AugmentRegistry now log a warning when two
skills declare the same workflow name and one overwrites the other.
C4: TestGeneratedWrapperHasNilGuards verifies that nil WName/
WVersion don't panic. If go generate strips the nil-guards, this
test catches it before the daemon crashes.
C5: skill.Catalog() now returns nil (no skills) instead of
propagating ENOTDIR errors when .agents/skills is a file.
C6: cacheMounts() normalizes ecosystem to lowercase. 'Python',
'NODE', 'Go' all resolve correctly now.
N1: ensureVolume() treats Docker's 'already exists' error as
success, closing the TOCTOU window between VolumeInspect and
VolumeCreate.
N2: safePluginInfo() wraps plugin.Name()/Version() calls in a
recover. A plugin with a panicking Name() no longer crashes the
daemon at startup.
Introduces the storage.Backend interface for pluggable container mount
management. The Docker implementation (DockerBackend) is the MVP —
no NFS/SMB/S3, just Docker volumes + bind mounts.
/data/ volume layout:
/data/worktree/ — bind mount of host worktree (always)
/data/repo/ — per-repo Docker volume (when persistent_storage = true)
/data/cache/go/ — shared GOMODCACHE volume
/data/cache/node/— shared npm cache volume
/data/cache/pnpm/— shared pnpm store volume
/data/cache/pip/ — shared pip cache volume
/data/cache/cargo/— shared Rust cargo cache volume
/data/task.json — boot-time brief (existing WriteTaskJSON)
Changes:
- internal/storage/: Backend interface, DockerBackend, Mount types,
ecosystem-to-cache-volume mapping, ConvertMounts helper
- container.Pool.Acquire: now accepts []storage.Mount instead of
hardcoding a single bind mount — mount list comes from the storage
backend
- daemon.process(): calls d.Storage.Setup() to build the mount list,
passes Ecosystem + PersistentStorage from repo config
- config.Repo.PersistentStorage: when true, a named Docker volume
(archie-repo-<owner>-<repo>) is mounted at /data/repo and survives
task completion
- main.go: creates DockerBackend when containers are enabled
21 tests: interface contract, ecosystem cache mounts (go/node/
python/rust/custom), worktree bind mount ordering, persistent
storage on/off/empty-owner guard, mount list sort+dedup, adversarial
(nonexistent worktree, empty ecosystem, unknown ecosystem).
Why: daemon-managed cache volumes mean warm GOMODCACHE/npm cache
across tasks. Per-repo persistent volumes preserve expensive build
artifacts. The interface leaves room for future backends without
rewiring container orchestration.
Daemon plugins (Yaegi-interpreted .go files) are now loaded from the
configured plugin_dir at startup. Each file must export a 'Plugin'
variable using the _Plugin wrapper struct, which bridges Yaegi types
to the Go plugin.Plugin interface.
Changes:
- internal/plugin/pluginextract/ — generated Yaegi symbol table for
the plugin package (mirrors wfextract pattern), including the
_Plugin interface wrapper that lets interpreted code implement
Go interfaces
- LoadDir now accepts optional symbol tables via variadic parameter,
avoiding an import cycle between plugin and pluginextract
- Plugin tests rewritten as behavioral (not structural), verifying
actual Yaegi interpretation of valid, invalid, and missing plugins
- config.PluginDir field for specifying the plugin directory
- daemon.PluginRegistry field for holding loaded plugins
- main.go wires plugin loading: LoadDir at startup, register into
daemon, log each loaded plugin
Why: the Plugin interface and LoadDir existed but weren't connected
to the daemon. Skills define workflows; daemon plugins are the
extension point for forge resolvers, storage backends, and other
core-daemon concerns.
The daemon no longer hardcodes workflow.Registry{...} in main.go.
Instead, skillbuild.BuildRegistry() scans .agents/skills/ for catalog
entries declaring metadata.archie.workflow and builds each workflow
from its Yaegi-interpreted stage plugins.
Built-in workflows (bootstrap, implement, tdd, feasibility, default)
serve as fallbacks when no skill declares a given workflow name. A
skill that declares metadata.archie.workflow: implement overrides the
built-in — skills define workflows, plugins define stages.
Why: skills must be extension primitives. Adding a workflow should
mean creating .agents/skills/archie-wf-<name>/plugins/*.go, not
modifying Go code in main.go. The catalog is the single source of
truth for what workflows exist.
Replaces field-existence checks with runtime behavior verification:
Gap 1 (per-task agent): FAILING
TestHandleMessageReadsWorkflowField verifies HandleMessage produces
different results when Workflow is set vs. unset. Currently identical
— HandleMessage ignores the Workflow field. Must run full multi-stage
workflow per PRD section 1.
Gap 3 (response/system split): PASSING
TestHandleMessageRoutesSystemMessagesSeparately verifies Channel
echoes from request to response. HandleMessage now reads input Channel
and sets it on the response envelope. Subject functions verified
distinct.
Gap 5 (daemon review): PASSING
TestReviewResultBlocksOnResultWhenRejected verifies ReviewResult
hook gates OnResult. Error blocks — OnResult never called. Nil
allows — OnResult called normally.
Agent processing extracted into agentexec.HandleMessage for testability.
cmd/archie-agent delegates to it.