Section 1 of the adversarial self-review decision was superseded on
2026-08-24: it assumed daemon-owned in-process execution and a daemon-side
second Pool.Acquire, both removed by archie-core-q15y. It is now re-decided
rather than merely marked dead, so the document is Active again.
The reviewer is an agent.Subagent run from inside the task-scoped worker.
ai-sdk v0.1.22 is already pinned, so this needs no SDK bump, and it adds no
host executor, no second container acquire and no nested container lifecycle
-- the open question the supersession left.
Subagent.Run passes Prompt and never populates Messages, so conversation
isolation is a construction fact rather than prompt text. It does NOT give
filesystem isolation: the sub-agent shares the parent's process, working
directory and credentials, so the .git-stripped snapshot survives from the
original design and is load-bearing, and the reviewer's toolset must be
read-only, rooted at the snapshot, and must exclude the worktreerpc
publication grant -- otherwise a reviewer could push the branch it exists to
block. Run() not Tool(), so the implementer cannot elect to review itself.
Findings return through a closure-captured tool because Run yields only text,
and are read even when Run errors, since captured findings survive.
Also decides fail-closed: a review that fails to RUN parks the task rather
than opening an unreviewed PR. ReviewEnabled is opt-in, so an operator who
turned the gate on wants the gate. This is why h019.2 models "ran and found
nothing" separately from "did not run" -- collapsing them would make an
outage indistinguishable from a clean review.
h019.3 is unblocked and rewritten with the construction rules. h019.4's
description said the task parks as waiting_human, contradicting section 4's
decision of StatusParked; corrected, and the fail-closed rule added.
Autonomous workflows now always hand a complete task to a scoped archie-agent container. Embedded NATS is the default and external NATS changes only broker placement; legacy agent and containers.enabled inputs decode for migration but cannot select an execution path. The daemon flushes task-event subscriptions before a worker can publish, and runtime updates snapshot and restore the configured worker image.
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.
Render completed ToolCallEvents as Telegram-safe streaming blocks
with compact name/status and a short cleaned preview. Summarize
file contents and listings instead of dumping source or quoted
JSON. Collapse repeated legacy turn-budget failures.
Remove max_tokens turn gating and the 200000 turn_budget_chars
default so absent or commented config cannot restore an aggregate
cap. Keep per-result max_result_chars and spill.
Confine find/grep discovery to the active workspace/worktree.
Refs #604
archie-core-7d5u.5 (idempotency and poll/webhook parity): the dedup
mechanism (TaskEnvelope.IdempotencyKey + PublishUnique + JetStream
Nats-Msg-Id dedup) and the shared dispatch predicate were already fully
wired by 7d5u.4. What was missing: proof the dedup actually holds, and
observability for a wedged receiver.
- internal/infrastructure/eventbus/nats/dedup_test.go: regression test
proving PublishUnique suppresses a duplicate publish on the same
WorkQueuePolicy stream ARCHIE_TASKS uses in production.
- internal/forge/webhook/receiver.go: Receiver.Status() tracks
authenticated deliveries separately from successful publishes; a GET
to the receiver's listen address (GitHub only ever POSTs) now returns
it as JSON, so a wedged/non-delivering receiver is observable instead
of indistinguishable from an idle repo.
Poll/webhook parity (disabling webhook still polls) needed no code
change: Cycle()/Run() never reference cfg.Forge.Intake anywhere in
internal/daemon, only setupForgeWebhook gates the webhook HTTP server.
archie-core-h019.1 (design: adversarial self-review stage): one-page
decision at docs/prds/adversarial-self-review.md. Reviewer runs in a
second workspace pointed at a .git-stripped snapshot of the reviewed
commit, never the implementer's worktree, so isolation is a property of
what's mounted rather than a prompt instruction. Findings contract is
workflow.ReviewFinding, owned by internal/domain/workflow. A surviving
error-level finding sets StatusParked, not WaitingHuman -- the epic's
informal wording named two different states in the actual machine; this
resolves which.
Both changes reviewed by a fresh subagent with no memory of the
implementation, per CLAUDE.md's adversarial-verification requirement;
zero blocking findings, two minor coverage gaps closed.
Adds t2db.3: schema-by-example field mapping for the no-code playbook epic.
An operator picks a captured event, clicks through its payload to bind named
fields to JSON paths, and previews the resolution against a real event
before saving -- a missing, null, or type-changed path fails loudly (named
by field and event) rather than handing an agent a blank value.
- internal/domain/mapping: Mapping/Field types, path parsing/walking,
Resolve (per-field failure reporting), Validate (incl. duplicate names)
- internal/store/mappings.go: SQLite persistence, mirrors captures.go
- internal/webui/api_mapping.go: CRUD + preview HTTP API
- ui/src/mappings/: dashboard editor (clickable payload tree, live preview)
Design decisions recorded in docs/prds/payload-field-mapping.md. t2db.4
(binding a mapping + matcher to a workflow) is out of scope here.
Wire github.com/nats-io/nats-server/v2 into production startup so a
single-process deployment gets reaction delivery and task distribution
over an in-process server rather than a separate one
(docs/prds/embedded-nats.md).
Meaning change: [nats].url empty used to mean "no NATS, use the SQLite
ClaimNext flow"; it now means "start an embedded NATS server". The old
behaviour is the explicit opt-out [nats].mode = "off". mode resolves from
url when unset (url set -> external, url empty -> embedded), and
agent.mode="nats" / [containers] now require mode="external" (an embedded
loopback server cannot be reached by agent workers or containers).
The daemon owns the embedded server's lifecycle: StartEmbedded before
dialing the client, Shutdown after the client closes (LIFO cleanups). The
embedded server binds loopback on a random port, enables JetStream in a
store dir under the data directory, and leaves its logger nil so a startup
failure surfaces as a Connect error rather than an os.Exit.
Retention becomes a nats.Config field (default WorkQueuePolicy) so a future
reaction stream can fan out under LimitsPolicy instead of the hardcoded
competing-consumer policy that starves a second consumer on overlapping
subjects.
Adds POST /webhooks/capture/{source}: an unauthenticated endpoint (mounted
alongside /healthz, bypassing dashboard token auth by design) that persists
any inbound webhook archie has no binding for yet, so it can be inspected
and mapped later (t2db.2/t2db.3).
docs/prds/event-capture-storage.md decides SQLite over NATS JetStream for
storage: NATS is not unconditionally available until 7d5u.2 ships embedded
support, and capture's single-writer/single-reader access pattern doesn't
need JetStream's fan-out/replay machinery anyway.
internal/store/captures.go adds a captured_events table with prune-on-write
(retention age + row-count cap, both configurable). The HTTP handler applies
webhookguard redaction before persisting, and enforces two more independent
disk-bound mechanics before that: a per-request body-size cap and a
per-remote-address rate limit. New [capture] config section with documented
defaults; all fields optional, capture is on by default.
Adversarial review (manual, after the usual fresh-subagent pass hit a
session API limit mid-run) caught and fixed three real defects before this
landed, each with a regression test confirmed to fail against the pre-fix
code:
- the body-size cap silently no-op'd when CaptureMaxBodyBytes was left
unset, the one bound that limits a single payload's size rather than row
count or write rate
- the rate limiter was keyed by the request's own source path segment --
unregistered and attacker-chosen by design for this endpoint, violating
webhookguard.RateLimiter's documented bounded-key-space assumption and
letting a sender bypass the limit by rotating the segment; rekeyed to
remote address
- the retention prune compared time.RFC3339Nano strings, whose trimmed
variable-width fractional seconds break lexicographic ordering within the
same second; switched to fixed-width RFC3339
Closes archie-core-t2db.1.
archie-core-7d5u.1 -- closes with the decision recorded. Investigated three
mechanisms already in the tree rather than designing from scratch:
- No out-of-process extension boundary exists or is needed; in-process typed
families throughout, and plugins-and-extensions.md does not need amending.
- Reaction delivery reuses internal/eventbus's Publisher/Consumer contract,
but NOT the existing nats.Client unmodified: it hardcodes
jetstream.WorkQueuePolicy (client.go:65), the competing-consumer policy
correct for ARCHIE_TASKS and wrong for fan-out reactions -- two reactions on
overlapping subjects would hit the exact silent-starvation trap CLAUDE.md
already documents. Retention needs to become a Config field; reactions get
a second stream.
- Reactions in these two epics are producer-only (curator's WakeOnPrimaryInput
for cheap wake, or the existing pollNATS->publishTask shape for real work).
No veto/mutate-in-flight capability is being built here.
- No single generic Source interface. workintake.TaskEnvelope already is
forge intake's typed contract and needs no new type -- its IdempotencyKey is
keyed on owner/repo/number, not delivery source, so a webhook-sourced
envelope dedups against a poll-discovered one for free. What's genuinely
shared is a small cross-cutting package for HMAC/rate-limit/capture/approval
mechanics, owned by neither domain.
Retitled and rescoped archie-core-7d5u.3 to match: it was still asking for
'one registry for every kind of inbound caller,' which this decision
explicitly rejects. Removed a false blocking dependency of t2db.1 on 7d5u.4
(GitHub-specific receiver) -- they are siblings sharing the new cross-cutting
package, not a chain -- and linked them instead.
archie-core-t2db.5 -- decides the five non-negotiables its description named
before capture (t2db.1) or the intake family (7d5u.3) exist to build against
it: per-source HMAC auth reusing internal/channels/webhook's existing scheme,
a draft/pending_approval/armed binding state machine modeled on telegram's
dangerous-command approval flow, per-source rate limiting (precedent:
pairing.MaxPendingPerPlatform) that rejects rather than silently drops,
blast-radius bounding via the same gate/diff-cap/sandbox every task already
gets rather than a new relaxation, and 7-day retention with best-effort
redaction reusing gateway/stream.go's sensitiveParameterKey heuristic.
The bead stays open: its code-level acceptance criteria constrain beads that
haven't landed yet and cannot be satisfied by a document alone.
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.
Per the sequencing call (adversarial pass first, docs last), the docs
now reflect the design the reviews confirmed.
configuration.md:
- Mutation ledger gains rows for SIGHUP reload, dashboard PATCH,
dashboard reset, and the runtime overlay store, each mapping to the
universal change protocol with what is and is not yet implemented.
- New section 'Implemented runtime reload and config overlay (2026-08)':
the Holder published-snapshot model, the reloadable-field criterion
(a field is reloadable when EVERY consumer re-reads it), SIGHUP
reload semantics, the overlay store (separate -config.sqlite, dotted
keys, denylist, bootstrap degrade), and the PATCH/reset paths.
safe-change-and-recovery.md:
- New section 'Runtime config overlay: degrade paths and recovery'
tabulating the three boot degrade paths and the reload degrade, all
verified by the adversarial passes, plus the three documented
recoveries (--no-config-overlay flag, rm the overlay file, dashboard
reset). Status line notes the overlay subset is implemented while
the full runtime-supervision protocol remains under design.
No new documents, per the constraint.
Task and event persistence now uses a dedicated SQLite sidecar derived from the configured state prefix, matching the independently persisted conversation store. The configured path now means a state-path prefix rather than a database file so fresh SQLite state never attempts to interpret the previous storage format.
Remove the retired implementation and dependency completely, strengthen SQLite migrations and concurrency behavior, restore backend-neutral coverage, and align configuration, operational guidance, UI labels, and deployment documentation with the new storage and host-daemon topology.
Eight approved decisions existed only as beads memories and were lost when
the tracker was removed. Recovered from a backup taken six minutes before
8bf0f6b and folded into the docs that own them, rather than a new document.
- migration-decisions: recorded position as of 2026-07-29, the deferred
private-input-DTO compromise, and the agreed internal/app/{archied,
agentworker} next step
- configuration: missing credential degrades a capability, only invalid
config is fatal; config generation moves from install.sh to archied setup
- identity: the three-layer invariants/SOUL/representation model, and why
a curator may only propose SOUL changes
- agent-system: the curator isolation invariant (curators are peers, never
on a chat turn's critical path)
- messaging-and-work-intake: semantic search over messages is an explicit
non-goal, with the measurements behind it
- safe-change-and-recovery: the /restart deadlock and lockout constraints
- plugins-and-extensions: dates the surprisal deferral
Also replaces the dead `**Beads issue:** archie-core-5d7` frontmatter across
all 12 documents with the GitHub issue it migrated to (#73), and rewrites
every other beads identifier to its issue number.
StageBaselineGate captured a failing gate command's full output but
discarded it: a 200-char clip went into a Warn log, and the terminal
error carried only res.Status. A park reason like "go build ./...
fails ... (status: failed)" gave no way to see the actual compiler
error, and the container that had it is already gone (AutoRemove).
Now the park error carries a bounded tail of the real output (tail,
not head, since a failing test's explanation is at the end after
pages of "ok" lines), rune-safe so it can't emit invalid UTF-8 into
a persisted park reason. The three existing byte bounds in this
stage (log line, agent mission, park error) are named and documented
as independently sized rather than left as bare numbers.
Also adds docs/architecture/observability.md, the design doc for the
larger task-observability epic (#450) this fix is the first step of.
- Reword docs and comments to drop vague "legacy" qualifiers where they no longer describe deprecation status
- Remove unused code: RecentEvents, MessageEvent.ToLegacy, index setState, stderr redaction tool, telegramOnlyCommands
- Delete or comment out tests covering removed or superseded behavior
NellDB v0.3.0 skips meta:* ids when rebuilding its rev cache on open, so
after any restart the counter Get returned a _rev with no cache entry and
every RMW Put failed with sdk: revision conflict -- task enqueues and
event inserts were permanently broken.
- Counters move to counter:task_id / counter:event_id.
- migrateCounters seeds the new keys from the legacy docs at open; any
read/write/validation failure aborts OpenStore so allocation can never
silently restart at 1. Legacy docs stay in place, skipped by scans.
- isReservedKey matches the counter ids exactly (a counter: prefix rule
would hide every task in a repo owned by "counter").
- Existing counters are validated (next_id >= 1) at open and at allocation.
- EnqueueIssue persists identity, which it previously dropped.
- Tests: reopen regression with exact post-reopen IDs and event
preservation, migration sequence carry-over for both counters,
fail-closed on read/write/invalid values, counter-owned repos,
identity round-trip.
Adversarial review: zero surviving findings.
internal/curator is a conforming engine family per the strict plugin
engine rule: typed CuratorEngine contract (Lifecycle + domain ops),
owning Registry (registration, discovery, start/health/stop with
failure isolation, reverse-order shutdown, ctx-bounded stop), and a
narrow typed Registrar — each curator receives a capability-filtered
view of the host at Bind, never the daemon.
Runtime: one loop per curator on an injectable clock (fake-clock
testable), best-effort wake nudges with the trigger decision kept in
Check (a dropped nudge only delays to the next check-in, never
corrupts accounting), per-pass timeout and a max-concurrent-passes
slot so curator bursts cannot starve chat turns, per-pass panic
recovery, and bounded shutdown even when a pass ignores cancellation.
curator_run / curator_action / curator_error ride the in-process
event bus so activity stays attributable.
Wired in cmd/archied/main.go (constructed beside memory, Start after
daemon startup, shutdown ordered before memory/LLM teardown) and
exposed as daemon.Daemon.Curators.
docs/ is the archie-core VitePress site (Archie-branded, see index.md).
This README.md was a Tau reference manual that was never linked from the
site index and doesn't belong in this repo.
The tau references in internal/tools/builtin/ are legitimate attribution
headers — those files were deliberately lifted from tau with source
commit hashes.
Fold the old docs/ into the VitePress site and rename docs-2 -> docs.
The 12 architecture PRDs become first-class pages at docs/architecture/
with sidebar nav, rather than being buried under an archive path.
Historical material stays at docs/archive/. Rewrites every docs-2 and
docs/prds/architecture reference across the repo. Site builds clean.
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.
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.
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).
Add config.Repo.AllowConcurrent (allow_concurrent toml key). Repos opted in
skip the daemon's default FIFO same-repo task serialization while still
respecting [containers].max_concurrency globally. Worktrees are already keyed
per issue number, so opted-in repos don't collide on disk.
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).
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.
Adds an implementation-status section and annotates each section
(binary split, NATS, container sandbox, /data volume, plugin layers,
skills, task lifecycle, phases) with what's actually built today vs.
aspirational. Reconciles the plugin design with the sibling
yaegi-plugin-system.md PRD, whose three phases are already
implemented but scoped narrower than this doc's Layer 1/2 split.
Implements the full PRD (docs/prds/yaegi-plugin-system.md): repos can
now define .archie/gate.go for diff-inspecting quality rules shell
commands can't express, .archie/stages/*.go for custom pipeline steps,
and skills can ship Go scripts run via a new run_go_script agent tool —
all interpreted in-process with Yaegi, with panics recovered so a bad
script can't take down the daemon. Hot reload (phase 4) needed no code:
every loader reads from disk per call and every task gets a fresh
clone, so nothing is ever cached to go stale.