The memory-extraction prompt concatenated its instructions, few-shot
examples, and the user message into a single user turn, so a small local
model could not distinguish instructions from input and frequently echoed
the Globex/weather examples instead of extracting facts.
Send the instructions as a real system turn and the raw text as the user
turn. The tiny worker protocol gains a systemPrompt field, and Mnemopi
completion input carries task metadata so the backend selects the right
prompt per call.
Drop the code-built MEMORY_EXTRACTION_TEMPLATE rather than porting it:
prompt text belongs in .md files, and resolveMemoryCompletionInput already
overrides that template for every extraction call, so Mnemopi rendered it
only for the result to be discarded.
Measured on ONNX q4 CPU, LFM2.5-1.2B memory extraction improved from 1/8
to 5/8 once the roles were separated.
buildWhere() appended a redundant hard `channel_id = ?` clause on top of
the `(session_id = ? OR scope = 'global' OR channel_id = ?)` visibility
clause. The hard AND nullified the `scope='global'` branch, so any global
row whose channel_id differed from the recall channelId — including rows
imported via importFromDict() with channel_id NULL — was silently dropped.
Channel isolation is fully preserved by the visibility OR-clause alone
(other-channel, non-global, cross-session rows still fail all three
disjuncts), so removing the hard clause restores global visibility without
leaking other channels.
Fixes#8525
- Replaced time-based sleeps and polling loops with event-driven promise resolvers and fake timers across agent and tool tests.
- Migrated test suites to share in-memory auth storage and fixtures using lifecycle hooks.
- Updated catalog model definitions, metadata, and configurations.
Session title generation, TTS speech enhancement, commit-message
generation, the auto-thinking and unexpected-stop classifiers, memory
extraction/consolidation, the commit analysis/summary/changelog/map/reduce
passes and the mnemopi LLM callback each aborted or degraded on the first
transient blip. Several returned null, which made a provider overload
indistinguishable from a legitimate empty result.
The commit analysis, summary, changelog and reduce passes also fed a
provider error message straight into their response parsers: they never
checked stopReason, so a failed request produced garbage instead of
surfacing the error. The map phase's own retry helper only caught thrown
errors, so a resolved stopReason "error" bypassed it entirely.
Sites deliberately left unwrapped: the Anthropic web_search provider
(server-side execution, billed per search - a re-request duplicates a real
side effect), the legacy streamSimple shim (already-emitted events would
duplicate), the auth-gateway health probe (a probe must report the state
it observed), and the script paths whose own retry logic tracks per-attempt
usage or re-requests only the failed subset.
- Updated user agent and openrouter titles in packages/ai from Oh-My-Pi to omp.
- Integrated getOpenRouterHeaders into image generation tool requests in packages/coding-agent.
- Updated provider documentation and test assertions to reflect the rebrand.
An interrupted fastembed model download leaves <cacheDir>/<model>/ with
sidecars and a truncated model.onnx_data but no model.onnx. Upstream
retrieveModel short-circuits on the existing dir (and reuses a leftover
partial <model>.tar.gz), so FlagEmbedding.init throws "Model file not
found at .../model.onnx" every session: semantic recall silently dies
machine-wide and reconcileEmbeddingModel re-enqueues the same
never-embeddable rows on every store open.
quarantineCorruptModelFile only matched "Protobuf parsing failed", never
this partial-extraction variant. Add clearIncompleteModelCache: a
"Model file not found" init failure now removes the incomplete model dir
and the leftover partial archive (containment-guarded to a direct child
of the fastembed cache root) and retries init exactly once, so the next
attempt re-downloads cleanly and recall self-heals.
Fixes#7916
- mnemopi provider parity 'diagnose, validate, graph' does ~6.7s of real
work under bun --parallel=8 on loaded runners; raised its per-test
timeout to 30s (default 5s flaked twice in three CI runs).
- utils LRUCache updateAgeOnGet drove a 30ms TTL with real 20ms sleeps
(10ms margin); now drives performance.now() via a mocked clock, so the
contract is asserted deterministically with no wall-clock wait.
- Implemented in-house, zero-dependency utility modules in `pi-utils` covering DOM manipulation, markdown parsing, templating, browser automation helpers, and terminal buffers.
- Migrated packages across the repository to consume the new internal utilities and `omptype` schema validators instead of external dependencies.
- Removed multiple external runtime and development dependencies including Zod, Marked, LRU cache, Turndown, and Puppeteer browser packages.
- Introduce `@oh-my-pi/omptype` as a new ArkType-compatible schema validation package featuring a lazy JIT runtime, JSON Schema emission, and compatibility adapters.
- Replace `arktype` across workspace packages and test utilities with `@oh-my-pi/omptype`.
- Add benchmark suites, tests, and documentation for the new validation engine and adapters.
- Update workspace build, test runner, and release configurations to include the new package.
The auto-merge during conflict resolution placed the page-size Added
section under [17.2.3] (which already had the upstream's think-block
fix) and left an empty ### Fixed header. Move the Added section back
under [Unreleased] where it belongs; drop the empty header.
No code changes.
- Restricted the reasoning-wrapper removal to leading <think> blocks so a
literal think tag after real content is preserved instead of deleted.
- Added coverage asserting mid-content think tags survive cleanOutput.
Fixes#7231
- Removed MiniMax-style think wrappers in cleanOutput so reasoning-model
responses no longer leak into consolidation summaries or corrupt fact
extraction (the wrapper previously survived parsing and every stored fact
became reasoning prose).
- Added remote consolidation and remote extraction regression coverage.
Fixes#7231
can1357