Implement the SendTimeout config field (previously silently ignored) via a
timeout-bounded write helper, and close two related races found during
adversarial review: Start()/Stop() could interleave across separate lock
acquisitions, and a subprocess spawned by a fresh Start() or a
crash-triggered restart could clobber a StateStopped already committed and
reported by a concurrent Stop(). Both spawn-commit paths now funnel through
a single guarded commitSpawnedProcess. Closes archie-core-abg.17.16,
archie-core-abg.17.23, archie-core-abg.17.41.
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).
internal/secret package:
- Engine interface (Name, Version, Resolve) for pluggable secret backends
- SecretRef type replacing TokenEnv/APIKeyEnv string fields
- ResolveOrEnv for backward-compatible env-var fallback
- Built-in env engine registered by default
- Registry with Register/Get/Resolve/LoadDir (yaegi-based)
- DefaultRegistry() singleton for one-off resolution
- 12 tests, race-clean
Scoped to foundation only. Provider/NATS/Telegram migration deferred
to xec.4 (separate bead — those call sites forward env var names to
subprocesses/runtimes and need eager-resolve-then-inject, not a simple
field rename).
40/40 packages pass with -race.
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.
- ToolCallGuardrailConfig + GuardrailEngine with RecordSuccess/RecordFailure
- ToolClassification bitmask (idempotent/mutating) with dispatch gating
- TurnBudget for token/char accounting with spill-to-disk
- AvailabilityCache with TTL + failure grace window
- Progressive disclosure engine for tool schema filtering
- Tool dispatch executor with parallel/serial classification
- RecordSuccess fix: now returns GuardrailDecision (no-progress threshold)
- All tests pass with -race, 58 new test functions across 6 test files
internal/memory/schema.go — normalizes memory-provider-exported
tool schemas between bare and wrapped OpenAI formats. Handles
both function-call wrapper objects and bare name+description+params
shapes. Converges to a consistent internal representation.
Resolve conflict in `.beads/` tracking files and scrubber implementation:
- Accept 8642f40's full implementation of StreamingContextScrubber with io.Writer interface, partial chunk boundary handling, nested tags, zero-alloc fast path, and comprehensive tests.
- Take incoming changes for issues tracking: close multiple verification tasks (18.10–18.13, 18.23–18.26) after adversarial review, update status for in-progress tasks (18.17, 18.18).
Pending bytes buffered while inside a <memory> block were unconditionally
emitted as literal text by Flush, leaking hidden memory-context content
into visible streamed output when a stream cut off mid-tag (e.g. "...secret</mem").
Track pendingInBlock at capture time so Flush discards in-block pending
bytes instead of emitting them. Also corrects stale doc comments claiming
underlying writer errors are surfaced (they're intentionally discarded).
Found by adversarial review of 18.10.
Stateful io.Writer that strips <memory>...</memory> fences from
streaming output, handling partial chunks split across tag
boundaries, nested tags, and missing closing tags.
framing.go: documented that readMessage caller must manage the
bufio.Reader lifetime. Creating a new bufio.Reader per call silently
drops buffered data and breaks multi-message streams.
transport.go: added crashCount check alongside startupFailures for
the MaxRetries limit — crash-looping subprocesses (spawn succeeds
but process immediately dies) now count toward the retry cap.
transport_test.go: replaced os.Exit(1) with syscall.Exit(1) in
crash-after-init behavior — Go's test harness intercepts os.Exit
and panics instead of exiting, keeping the process and its pipes
alive indefinitely. Replaced os.Exit(0) with runtime.Goexit() in
TestMCPServerHelper for clean goroutine exit.
Framing multiple-message test passes. Crash retry tests may need
further debugging in the transport spawn/reader lifecycle.
.beads/issues.jsonl + .beads/interactions.jsonl are the sync
mechanism — they're passive exports committed to git and synced
via refs/dolt/data on the remote. The local Dolt database
(embeddeddolt/) is gitignored as binary state.
227 total issues, 101 ready to work.
One verification bead per implementation task (91 total). Each blocks
its implementation — verification must pass before the task is done.
Verification acceptance criteria: independent adversarial review by
fresh agent, no dead code paths, no lint issues, tests pass, code
formatted, no hardcoded values in tests.
This enforces red-then-green + adversarial-verify for every
implementation across the full 78-task Hermes parity surface.
15 new issues created under multi-agent-collaboration epic (abg.16-abg.30).
3 P0 epics: gateway model, tool registry, memory providers.
Delivery system scoped to NATS JetStream (no separate actor engine needed).
Session persistence scoped to NellDB (replaces SQLite+FTS5 with vector search).
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