- Caught all-target recall failures inside the fire-and-forget auto-recall path.
- Kept first-turn recall eligible for retry after an engine failure.
- Added regression coverage for the background failure contract.
- Warned when a scoped recall target fails while preserving partial results from healthy targets.
- Re-threw the underlying failure when every target fails so recall cannot masquerade as an empty search.
- Added tool-level regression coverage for total and partial scoped failures.
Fixes#7364
Kept the hard timeout and worker reap for steady-state embed requests while allowing first-use runtime installation and model bootstrap to finish without SIGKILL stranding the install lock.
Added deterministic coverage for initialization outliving the embed timeout budget and corrected the changelog contract.
Fixes#7352
Extended the shutdown busy-timeout clamp from the retain bank to all owned banks so a locked shared bank (per-project-tagged) cannot stall teardown for the default 5s SQLite timeout.
Fixes#7351
Embed-worker init/embed requests awaited the reply with no timeout, so a
wedged fastembed/onnxruntime runtime blocked the turn memory recall or the
shutdown consolidation forever, hanging headless -p/--mode json runs and
leaving __omp_worker_mnemopi_embed unreaped. The #5753 fix only bounded the
dispose-time consolidate await, not the embed IPC beneath it.
Bound every request with an unref-ed timeout; on expiry fail the request
and SIGKILL-reap the worker so the next call respawns a fresh child.
Fixes#7352
Capped synchronous SQLite busy waits before starting bounded final consolidation, then spent only the remaining shutdown deadline on asynchronous drains.
Added regression coverage for a locked Mnemopi writer in the headless teardown path.
Fixes#7351
- Serialized backend transitions across runtime state, tools, and prompts.
- Rehydrated Mnemopi listeners after clear and enqueue maintenance.
- Made memory.backend the sole post-migration local runtime gate.
Fixes#5638
Pre-fix resumed sessions wrote cumulative transcript rows under the
incremental ${sessionId}-<ts> source_id shape, so summing every prefixed
legacy row could overshoot the real retained prefix and permanently skip
unseen turns. Use per-row max instead: it can only under-count, which at
worst re-stores one suffix before an explicit cursor row takes over.
Adds a regression seeding a legacy bank with two incremental rows plus a
cumulative resumed row and asserting turns 7-8 still get retained.
Persisted the retained user-turn cursor in transcript metadata and restored it when sessions resume, including legacy rows from before the cursor existed.
Made forced lifecycle retention slice from that cursor so enqueue and shutdown no longer add cumulative snapshots beside incremental windows.
Fixes#6058
Review follow-ups:
- The corruption retry now goes THROUGH the sidecar heal, so a cache
broken in both ways (truncated model blob AND stale/missing
config/tokenizer sidecars) recovers in one pass instead of the retry
escaping with a sidecar error.
- defaultLocalModelInitializer is exported from core as the shared
initializer and the coding-agent embed worker now uses it instead of
calling FlagEmbedding.init directly, so omp's subprocess embeddings
inherit both heals; fastembed/onnxruntime still load only in the
child address space.
recall (includeFacts) surfaces facts.fact_id as a result id, but
store.get only searched working_memory + episodic_memory, so every
surfaced fact id was a dead end for 'read memory://<id>' and
memory_edit ('not found in any scoped bank').
- store.get now falls back to the facts table (visibility mirrors
factRecall: same-session or scope='global'), returning a read-only
row with memory_store 'fact' and the full triple as content.
- coding-agent labels the store honestly ('fact') in memory:// reads
and reports not_editable (instead of not_found) for memory_edit ops
on fact ids; the facts table stays immutable.
Fixes#4725
Interactive shutdown (AgentSession.dispose) now runs a bounded
consolidation on the current session only and skips fresh LLM fact
extraction. The heavier cross-session consolidation with extraction is
still performed by the /memory enqueue command and the backend enqueue
path.
This avoids blocking /quit and /exit on a fresh LLM round-trip
and a full sleepAllSessions scan.
- Add full and extract options to consolidate() and
forceRetainCurrentSession()
- Route dispose() through consolidate({ full: false, extract: false })
- Route /memory enqueue and backend enqueue through
consolidate({ full: true })
Fixes#3641
Recall silently clipped every result to 500 chars mid-word with no marker,
and memory_edit update replaces content wholesale by id. There was no way
for an agent to inspect the full row before overwriting it: Mnemopi.get
existed but nothing surfaced it, and the advertised URI only served the
file-backed memory summary. The natural recall/inspect/update loop had no
inspect step.
Three fixes across mnemopi and coding-agent:
- recall now appends an ellipsis marker when it clips content and reports
truncated=true plus full_length. The cap is exposed as
RecallOptions.contentPreviewChars (default 500, 0 disables). The factLine
200-char clip used by the enhanced-context sandwich gets the same marker.
- Under the mnemopi backend the read-tool URI scheme now routes an id host
to Mnemopi.get() across every session's scoped banks, returning the row
as text/markdown with a YAML-frontmatter header (bank, store, source,
timestamp, importance, veracity). The root namespace remains for the
file-backed summary. Miss errors now name the backend explicitly.
- Updated the recall and memory_edit tool prompts to document the
truncation marker and require reading the full memory before any
wholesale content update.
Fixes#4443
Added an embedText projection for remember() so stored transcripts can remain readable while embeddings, FTS indexing, and embedding-model rebuilds use marker-free text. Updated coding-agent retention to pass the marker-free projection and strip retained protocol markers from recall display.
Fixes#4395
Auto-retain now slices the transcript after the last retained user turn before storing an episode, preventing cumulative duplicate session transcripts in mnemopi banks.
Fixes#4396
/quit and /exit hung for many seconds because AgentSession.dispose()
awaited MnemopiSessionState.dispose() unconditionally, and that path
runs consolidate() (state.ts:421) which fires a fresh LLM fact
extraction for the just-retained transcript and then awaits
flushExtractions() per owned bank. One LLM round-trip per shutdown,
no upper bound, no visible status.
- Add a timeoutMs option to MnemopiSessionState.dispose. When the cap
fires the in-flight consolidate is detached to the background and the
SQLite handles close once it settles, so writes never race a closed
handle.
- AgentSession.dispose passes SHUTDOWN_CONSOLIDATE_BUDGET_MS = 1_500 on
the user-visible shutdown path. Per-turn maybeRetainOnAgentEnd has
already retained earlier turns, so the worst case is losing episodic
promotion for the last few turns. State-replacement disposes
(mnemopiBackend.start) stay unbounded.
- InteractiveMode.shutdown surfaces a 'Closing session…' status before
dispose runs so the brief pause is explained rather than mysterious.
Two regression tests in memory-tools.test.ts cover (1) dispose returns
within the budget when flushExtractions stalls and the deferred close
still runs once consolidate settles, and (2) unbounded dispose still
runs the full #2320 consolidate-then-close pipeline.
Fixes#3641
- Removed the canonical model variant indexing, selection, and tracking logic from the model registry and resolver.
- Eliminated the `canonical` sub-command, tab view, search tokens, and equivalence configuration structures from the CLI and model selector components.
- Refined model identification, lookup, and provider fallback resolution to bind exclusively to standard, raw model IDs.
- Relocated the equivalence utility script within the catalog package to support script-only policy generation.
- Added `tiny` as a first-class model role to override online models for lightweight background tasks.
- Updated session title generation, auto-thinking difficulty classification, unexpected-stop detection, and mnemopi backend to resolve via the `tiny` role before falling back to `smol`.
- Updated configuration schema and documentation to reflect the new role precedence.
- Added an extractText override to pi-mnemopi remember paths so stored content and mined facts can use different text.
- Routed coding-agent mnemopi retention to store the full transcript while extracting only user-authored turns.
- Tightened deterministic Instruction extraction to require an explicit I/you subject.
Fixes#3372
- Established shared `subprocess` infrastructure to standardize worker IPC, environment resolution, and error handling.
- Migrated mnemopi, speech-to-text, tiny-model, and TTS clients to utilize consolidated worker-client utilities.
- Implemented common runtime helpers for ONNX model loading, logging, and process readiness probing.
- Eliminated redundant local spawn logic and environment mapping across all inference worker clients.
After `shutdownMnemopiEmbedClient()` clears `#worker` (session dispose, or
worker crash), mnemopi still holds the cached `LocalEmbeddingModel` wrapper.
The next embed re-spawned a fresh subprocess that had never received
`init`, and the bare `embed` request tripped the "embed before init" guard,
breaking local embeddings for the rest of the process.
- Carry `model` + `cacheDir` in every `embed` IPC; bind both into the
`MnemopiSubprocessEmbeddingModel` closure when the wrapper is created.
- Worker calls `ensureLoaded(model, cacheDir)` in `handleEmbed` (idempotent
for the same key, so steady-state embeds pay nothing). Drops the
"embed before init" guard — `embed` self-initializes.
- Promotes the internal `WorkerHandle` interface to `MnemopiEmbedWorkerHandle`
so the test seam can construct a fake worker.
- New regression test drives a fake worker, terminates + re-embeds the SAME
cached wrapper, and asserts every embed message still carries the bound
`(model, cacheDir)`.
Per review on #3034.
Moved mnemopi's local embedding provider out of the main agent process by
spawning a dedicated `Bun.spawn` child for fastembed + onnxruntime-node. The
agent CLI gains a hidden `__omp_worker_mnemopi_embed` dispatch; `loadMnemopi`
/ `loadMnemopiCore` install the subprocess-backed initializer through the
newly-exposed `setLocalModelInitializer` seam so every `embed()` call
round-trips through IPC instead of loading the NAPI module. The parent
SIGKILLs the child on dispose so the destructor that segfaults Bun on
Windows shutdown (NAPI finalizer at exit on npm installs, `process.dlopen`
constructor at session start on standalone binaries) never runs in any
address space the agent owns. Mirrors the tiny-model fix from #1607.
Adds `smokeTestMnemopiEmbedWorker` to `omp --smoke-test`, a new
`test/issue-3031-repro.test.ts` that pins the spawn/dispatch/signal-exit
contract and forbids re-importing `fastembed-runtime` from the agent surface,
and changelog entries.
Fixes#3031
Fix all Windows-specific test failures caused by path handling problems
and EBUSY errors from unclosed SQLite database handles.
Root causes fixed:
1. POSIX path assumptions: replaced hard-coded file:///tmp, /repo, etc.
with pathToFileURL/path.resolve/path.join computed expectations
2. shortenPath() now normalizes backslashes to forward slashes after ~
and respects home directory boundaries
3. HistoryStorage.resetInstance() leaked its Database — added #close()
that finalizes all prepared statements and closes the DB
4. AgentStorage gained the same resetInstance()/#close() pattern
5. SqliteAuthCredentialStore.close() leaked one-off prepared statements
from inline this.#db.prepare() calls — wrapped each in try/finally
6. model-cache.ts used a process-global DB even for custom dbPath —
now opens/closes per-call via withModelCacheDb
7. createAgentSession leaked AuthStorage on construction failure —
added ownsAuthStorage cleanup in catch block
8. MnemopiBackend.removeDbFiles() now truly best-effort (catches errors)
9. TempDir retry window expanded from 4x10ms to 40x25ms
10. TempDir prefix convention: non-@ prefixes created dirs relative to
cwd instead of os.tmpdir() — all test temp dirs now use @ prefix
11. Shell-escaped interpolated paths in bash tool tests
12. git core.autocrlf false in autoresearch test repo init
All 522 previously-failing Windows tests now pass.
Proactive linking (ingesting new memories into the episodic graph as they
are stored) could only be toggled through the MNEMOPI_PROACTIVE_LINKING
environment variable, unlike its sibling recall features polyphonicRecall
and enhancedRecall, which hosts drive through configureRecallFeatures() and
the coding-agent mnemopi.polyphonicRecall / mnemopi.enhancedRecall
config.yml settings. The write-path gate in store.ts read process.env
directly and the existing env-only proactiveLinkingEnabled() helper was
dead code, so host configuration never reached it.
- Add proactiveLinking to RecallFeatureFlags / configureRecallFeatures()
and rewrite proactiveLinkingEnabled() to fall back to the configured
default, matching the polyphonic/enhanced resolvers. The
MNEMOPI_PROACTIVE_LINKING env var still takes precedence when set.
- Route the store.ts proactiveLinkIfEnabled gate through
proactiveLinkingEnabled() instead of reading process.env directly.
- Add the mnemopi.proactiveLinking coding-agent config.yml setting (off by
default, /settings -> Memory -> Mnemopi) and wire it through
loadMnemopiConfig and createScopedResources.
Closes#2440
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Only recall legacy mnemopi banks when every working_memory row is scoped to the active cwd, so per-project recall cannot surface sibling project rows from an ancestor-derived bank.
Fixes#2412
The bank id used to be hashed from
`git.repo.resolveSync(cwd)?.repoRoot ?? path.resolve(cwd)`, so adding or
removing a `.git` anywhere above the working directory silently
repointed the same conversation to a new bank and stranded its
memories. Same cwd `/home/x/projects/repo` flipped between
`projects-<hash>` and `repo-<hash>` depending on whether the parent
directory still looked like a repo.
`packages/coding-agent/src/mnemopi/config.ts` now hashes
`path.resolve(cwd)` directly. Session startup also widens the recall
set with any sibling bank under `<dbDir>/banks/` whose
`working_memory` rows already carry the active cwd in
`metadata_json.$.cwd`, so memories stranded by the old, less-stable
derivation become visible again on the next session without manual
migration.
Fixes#2412
- Replaced the bare `catch {}` blocks in `runEmbedding()` (`beam/helpers.ts`), `getLocalModel()`, and the local-model path of `embed()` (`embeddings.ts`) with structured `logger.debug` entries carrying the error plus per-site context (item count, model name); failure semantics stay best-effort.
- Threaded `MnemopiOptions.debug` through `resolveRuntimeOptions()` in `memory.ts` so `mnemopiDebugEnabled()` escalates these logs to `warn` when `mnemopi.debug` is set.
- Passed `mnemopi.debug` from coding-agent settings into provider options (`debug` added to the `MnemopiProviderOptions` pick in `src/mnemopi/config.ts`).
- Added `embedding-failure-logging.test.ts` asserting the logged context on a real local-model load failure and the debug→warn escalation; the changelog entry landed with the previous commit (same contiguous run).
Fixes#2322: Mnemopi: runEmbedding() and getLocalModel() silently swallow errors — mnemopi.debug produces no diagnostic output
- Added `mnemopi.polyphonicRecall` and `mnemopi.enhancedRecall` boolean settings (default off) to `settings-schema.ts` and `loadMnemopiConfig`, applied via the new `configureRecallFeatures()` in `createScopedResources`.
- Made `polyphonicRecallEnabled()`, `enhancedRecallEnabled()`, and `isEnhancedRecallEnabled()` fall back to the configured defaults while `MNEMOPI_POLYPHONIC_RECALL` / `MNEMOPI_ENHANCED_RECALL` env vars still win when set.
- Exported `configureRecallFeatures`/`RecallFeatureFlags` from the package root and `core` barrels; documented the settings in `docs/mnemosyne-memory-backend.md`.
- Added `recall-feature-flags.test.ts` covering defaults, config enablement, and env precedence; the mnemopi changelog hunk also carries the adjacent #2322 entry (same contiguous run).
Fixes#2323: Mnemopi: MNEMOPI_POLYPHONIC_RECALL and MNEMOPI_ENHANCED_RECALL not configurable via config.yml
The previous refactor dropped `if (this.aliasOf) return` into
consolidate(), which made `/memory enqueue` invoked from inside a
subagent a no-op. The old enqueue() body short-circuited only
forceRetainCurrentSession (via its own guard) but still flushed
extractions and slept on state.memory, which for aliased states points
at the parent's shared retain bank.
Moved the alias guard back out of consolidate(): forceRetainCurrentSession
keeps its own early-return (the subagent's transcript is the parent's
concern), so consolidate() runs the SQL-level flush+sleep on every
owned bank for both primary and aliased states. The lifecycle guard
stays in dispose() so disposing a subagent still does not flush, sleep,
or close the parent's memory.
Added a regression test: a /memory enqueue routed through the aliased
child state calls flushExtractions + sleepAllSessions(false) on the
parent's owned memory exactly once, and forceRetainCurrentSession runs
on the child (where its own guard returns early) but not on the parent.
Addresses #2327 review.
`/memory clear` (mnemopiBackend.clear) calls dispose() right before
removing the SQLite files. Running the consolidation pass first would
make a destructive clear spend tokens/time creating memories that get
deleted on the very next line, and a slow extraction could block the
clear path under llmMode: remote.
Added a `{ consolidate?: boolean }` option to
MnemopiSessionState.dispose; defaults to true so normal shutdown still
runs the SHMR/beam pipeline. mnemopiBackend.clear passes
`{ consolidate: false }` so the close path stays unsubscribe + close
only. Added a regression test that spies on forceRetainCurrentSession,
consolidate, flushExtractions, and sleepAllSessions to pin the new
behavior, while close still runs once per owned bank.
Addresses #2327 review.
MnemopiSessionState.dispose() now drains pending fact extractions and
runs sleepAllSessions on every owned bank before closing handles, and
AgentSession.dispose() awaits the result. This matches the manual
`/memory enqueue` slash command which was the only caller of the
consolidation pipeline.
Without the shutdown hook, episodic_memory, gists, consolidation_log,
graph_edges, and triples stayed empty for every deployment that never
typed `/memory enqueue|rebuild` — working memory accumulated forever
and long-term recall never formed.
Factored the consolidate step out of `mnemopiBackend.enqueue` into a
shared MnemopiSessionState#consolidate so the slash command and the
shutdown path share one implementation. Added two regression tests
verifying owned-bank consolidation order (flush -> sleep -> close, per
bank) and that aliased subagent dispose stays a no-op against the
parent.
Fixes#2320
can1357