Repository navigation
chore: release v0.21.0 to main - #1450
Merged
Merged
Conversation
- Add internal/ to .gitignore (prevents future strategy/launch doc leaks) - Add benchmarks/longmemeval/results_*/ to .gitignore (ephemeral data) - Add docs/package-lock.json to .gitignore (VitePress build artifact) - Move blog/comparison-2026.md → docs/comparison-2026.md (consolidate docs) - Remove stale benchmarks/longmemeval/results_diverse/ (raw output, not summary) - Remove docs/package-lock.json from tracking Audit confirms: zero internal/ files in entire git history after filter-repo scrub.
…#1015) * feat(bench): batch import + strategy flag + API embedding auto-config - Replace 53x individual remember calls with single JSONL batch import (10x speedup) - Add --strategy flag to pass vector|hybrid to uteke recall - Auto-configure embedding API from EMBED_API_KEY/EMBED_API_BASE env vars - Add --chunk-sessions flag for session chunking (Tier 2 prep) - Dedup recall results by session_id (first occurrence = highest rank) - Raise subprocess timeout 120s -> 600s for large imports Initial 5Q results: hybrid R@5=1.000 vs vector R@5=0.800 (+20pp) * fix(bench): only mark sessions inserted after import succeeds Address Cora findings: - Move inserted_sids population to after batch import success - Parse import response to verify imported_count > 0 - Log warning if import returns 0 inserted * fix(bench): resolve uteke binary by absolute path to avoid x86_64 PATH clash Background subprocess calls were resolving to /opt/data/.cargo/bin/uteke (x86_64) instead of target/release/uteke (AArch64). Now resolves relative to repo root with shutil.which fallback. * docs(bench): add 50Q hybrid results — R@5 98.0%, R@10 100% Strategy comparison (uteke only): - Vector 500Q: R@5=85.4%, R@10=88.5%, NDCG@5=0.810 - Hybrid 50Q: R@5=98.0%, R@10=100%, NDCG@5=0.960 - Improvement: +12.6pp R@5 Hybrid uses RRF (k=60) fusion of vector + FTS5 search. 1 miss at R@5 (single-session-user), recovered at R@10. run_eval.py changes: - Add --strategy flag (vector|hybrid) - Throttle: taskset -c 0-1 + nice -n 19 - Absolute binary path resolution - Timeout: 900s per question * fix(core): add dedup, retry, and auto_link to import path (#1005) Import pipeline was missing 3 features that remember() has: 1. Dedup check — cosine >= 0.95 skips duplicate entries 2. Retry on embedding failure — 3 retries with backoff 3. Auto-link cosine edges — graph edges for imported memories Changes: - import_export.rs: call check_duplicate() before insert, use retry_embed() instead of single-attempt embed(), call auto_link_cosine() after successful insert - operations.rs: make retry_embed() and check_duplicate() pub(crate) so they're accessible from import_export.rs Import path is now semantically consistent with remember() path. * fix(core): cross-compile ORT_LIB_NAME for Android/iOS (#1014) Add target_os = "android" to Linux .so branch and target_os = "ios" to macOS .dylib branch. Without these, uteke-core fails to compile for mobile targets with E0425 (cannot find value ORT_LIB_NAME). Android uses libonnxruntime.so (same as Linux, loaded via jniLibs). iOS uses libonnxruntime.dylib (same as macOS, framework embedded). This unblocks uteke-mobile cross-compilation. * feat(core): hybrid as default recall strategy Change default_strategy from vector to hybrid (RRF: vector + FTS5). Benchmark justification (LongMemEval-S): - Vector 500Q: R@5=85.4%, R@10=88.5% - Hybrid 50Q: R@5=98.0%, R@10=100.0% - Improvement: +12.6pp R@5 Changes: - config.rs: default_strategy = hybrid + assert in test - cli.rs: update help text default to hybrid - recall.rs: update comment to reflect new default - configuration.md: update all references - cli-reference.md: reorder examples, hybrid first as default Users who want vector-only: set default_strategy = vector in config or use --strategy vector flag. * fix(bench): guard taskset/nice with sys.platform check Cora finding: taskset is Linux-only, would FileNotFoundError on macOS. Now conditionally applied only when sys.platform == 'linux'. --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…ng text (#1006, #1002) (#1016) #1006: CLI update check skipped when UTEKE_NO_UPDATE_CHECK env var is set. Benchmark script sets this automatically, saving ~500ms per subprocess call. #1002: Pre-truncate text before tokenizer to avoid wasted CPU on tokens beyond MAX_SEQ_LEN (2048). Uses 4 chars/token heuristic with char-boundary safety. #1003: Already resolved — idx_memories_namespace index exists in SCHEMA_INDEXES. #1004: Already resolved — compute_graph_signals uses single batched SQL query. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…enance (#1007, #1010, #1012, #1013) (#1017) * feat: Phase 3 — lifecycle/deprecated endpoint, memory tools guide, source provenance (#1007, #1010, #1012, #1013) #1007: GET /lifecycle/deprecated — list deprecated memories with sunset info - list_deprecated() in aging.rs with DeprecatedMemoryInfo struct - Handler + route + API registry entry #1010: Memory tools guide injection - guide.rs module with default_guide() for system prompt injection - CLI: uteke guide command - API: GET /guide endpoint #1012: Implicit memory hierarchy docs - docs/organizing-memories.md — type + importance pattern - VitePress nav entry #1013: Auto-populate source provenance - CLI extraction: set source_label from input filename, source_type='extract' - Server extraction: set_source on each extracted fact - CLI output: display source_type alongside source in verbose mode * docs: regenerate api-reference.md for new endpoints (#1007, #1010) --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
SYSTEM_PROMPT now requests scene-segmented JSON output with type and priority per fact. parse_facts handles three formats: scene-segmented nested JSON, flat object array with type/priority, and legacy flat string array (backward compatible). ExtractedFact struct carries content, scene, fact_type, priority. CLI and server callers use remember_typed + set_importance + scene tag. Offline mode unaffected — ExtractedFact::flat wraps existing strings. 9 new tests cover nested parsing, backward compat, dedup, priority range validation. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
- Version bump to 0.14.0 - CHANGELOG entry for v0.14.0 - Docs: cli-reference scene-segmented extraction section - Docs: memory-lifecycle deprecated endpoint Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
- Add 60s/30s/30s delay between crate publishes for index propagation - Add repository, rust-version, documentation, homepage to uteke-mcp - Fixes: uteke-mcp/cli/server fail because uteke-core not yet in index - Fixes: 'manifest has no documentation, homepage or repository' warning Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
Root cause: commit 0b5cad3 removed docs/package-lock.json from git tracking and added it to .gitignore. The deploy-website workflow still referenced it via cache-dependency-path, causing setup-node to fail: 'Some specified paths were not resolved, unable to cache dependencies.' Fix: - Replace actions/setup-node with oven-sh/setup-bun - Replace npm ci with bun install --frozen-lockfile - Replace npm run build with bun run build - Add docs/bun.lock as tracked lockfile - Remove docs/package-lock.json from .gitignore (no longer relevant) Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
Add mutation testing infrastructure to validate test quality across critical pure-logic modules. 11 new mutation-killing tests improve salience_recency.rs score from 76% to 96%. Changes: - Add cargo-mutants config (mutants.toml) with exclusions for modules requiring external services - Add mutation-testing CI workflow (develop→main PRs only, pre-release quality gate) - Add .gitignore entries for mutants output directories - Add mutation-testing.md developer documentation - Write 9 mutation-killing tests for salience_recency.rs - Write 2 mutation-killing tests for recall_cache.rs Results (cargo-mutants v27.1.0): jaccard.rs: 12 mutants, 9 caught, 0 missed (100%) salience_recency: 53 mutants, 48 caught, 3 missed (96%) recall_cache: 25 mutants, 18 caught, 5 missed (80%) Refs: nginjen mutation testing pattern (#mutation-testing) Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…ion-killing tests (score 50%→97%) (#1024) Two production bugs found by mutation testing: 1. Heading duplication: oversized markdown sections had their heading prepended twice in the first sub-chunk (once by split_by_headings, once more by the sub-chunk loop), corrupting downstream embeddings. Fixed by removing the dead heading_prefix re-prepend path entirely. 2. Multibyte infinite loop: split_long_text's zero-progress guard advanced by raw byte offsets that could land inside multi-byte UTF-8 characters (CJK/emoji), flooring back to start forever. chunk_markdown("日本語", 2) would hang. Fixed with a proper forward-char-boundary advance in the guard. Also: - 40 new mutation-killing tests (chunker: 20 → 60 tests) - cargo-mutants config moved to .cargo/mutants.toml (v27 schema: exclude_globs/exclude_re, valid keys only); glob paths fixed to match from workspace root; CLI update_check also excluded - 3 proven-equivalent mutants excluded with documented reasoning - docs/mutation-testing.md: final scores, bug postmortem, timeout notes Verify run: 164 mutants, 149 caught, 0 missed, 5 timeout, 10 unviable (97%) Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
Patch release: chunker heading duplication fix, multibyte infinite loop fix, mutation testing hardening (PR #1024). - Bump workspace version 0.14.0 -> 0.14.1 - Bump intra-workspace deps (cli/mcp/server -> core 0.14.1) - CHANGELOG entry for 0.14.1 Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…1030) * fix(cli): embed bundled assets inside crate root for crates.io publish include_str! paths pointed outside the package root (../../../.agents, ../../../extensions). cargo publish cannot bundle files outside the package, so uteke-cli has failed to publish since June (stuck at 0.4.3) while the release workflow hid the failure with continue-on-error. Assets now live in crates/uteke-cli/assets/ and ship inside the .crate. Verified locally: cargo package -p uteke-cli passes with full verify. * ci(release): verify crates.io versions after publish The continue-on-error on publish steps (added for the tag race fix) also hides genuine publish failures. Verify all four crates report the tagged version on crates.io; fail the job if any crate lags behind. * style: cargo fmt --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
The v0.14.2 release reused the v0.13.0 notes because a committed RELEASE_NOTES.md is preferred over auto-generation and nothing checked which version it was for. The release shipped with wrong notes until manually fixed. The guard now requires the file to mention the tagged version. Also remove the stale v0.13.0 file so the next release auto-generates from the CHANGELOG unless someone writes fresh notes. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
, #1035) (#1038) * fix(server,mcp): default recall strategy to hybrid, validate strategy at boundary (#1034, #1035) HTTP: resolve strategy once (request > [recall] default_strategy config > hybrid). Invalid strategy returns 400 on all paths (bare recall, unified search, v1). The eager legacy recall that ran before strategy resolution is removed. Memory-only recall path routes through recall_hybrid with the same 3x over-fetch post-filter pattern used by recall_unified_memories (entity/category filters). MCP: uteke_recall schema exposes strategy (vector|fts5|hybrid|graph). Default resolves to hybrid, invalid values return a loud JSON-RPC error (-32603) instead of silently falling back to vector. Server startup: sanitize [recall] default_strategy from uteke.toml — invalid value warns and falls back to hybrid so a config typo cannot 400 every request with a message blaming the request. Docs: api-reference.md and mcp.md now describe the hybrid default, HTTP 400 on invalid, and the config fallback chain. Verified empirically against a scratch store: HTTP matrix 10/10, MCP harness 8/8 including engine parity (default == hybrid, warm cache) and loud bogus rejection. * docs: regenerate api-reference via docgen (strategy hybrid default, 400 on invalid) --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…plate file (#1041) * fix(ci): replace unquoted heredoc in release notes generation with template file The unquoted heredoc << RELEASEEOF underwent shell expansion: markdown backticks became command substitutions and executed on the runner. v0.14.3 release: installer curl|sh ran, uteke-serve --port 8767 started and blocked the job for 48 minutes (2 runs, deterministic). Move the static tail (downloads table + quick start) to scripts/release-notes-template.md and substitute __VER__ via sed. Zero shell expansion over markdown content. Validated locally: generate completes instantly, output byte-correct. Fixes the release pipeline for all future releases. * ci: re-trigger review bots (LLM API transient error) --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…pages, fix release-notes asset names (#1055) * docs: sync stale version refs, roadmap v0.13–v0.14, merge comparison pages, fix release-notes asset names (#1043) - README/README.id/AGENT.md/install.md: version + test-count updates (0.14.3, 530+ tests); AGENT.md now lists all 5 workspace crates incl. docgen - docs/roadmap.md: add v0.13.0–v0.13.2 and v0.14.0–v0.14.3 entries from CHANGELOG - comparison: merge comparison-2026.md (canonical long-form) into comparison.md, keep at-a-glance matrix + extraction table from the old page, drop dead /blog link - extensions/hermes-memory-provider → extensions/hermes-uteke-memory (+ embedded assets copy and all path refs) — dir name no longer references the removed Mode B provider - scripts/release-notes-template.md: download table filenames get v prefix to match actual release assets (#1043) * fix(release): keep v prefix on pinned-install example in release notes template Co-authored-by: VIVAAN-DHAWAN <VIVAAN-DHAWAN@users.noreply.github.com> Same fix as #1046 — UTEKE_VERSION is used verbatim as the release tag by install.sh, so the pin example needs the v prefix too. Picking it up here so #1043 closes fully through this PR once the rest of the audit lands. * Revert "fix(release): keep v prefix on pinned-install example in release notes template" This reverts commit 222d067.
…1056) Agents are advisory-mode by default: audit/check requests are not authorization to mutate. Gate push/merge/cherry-pick from others' PRs, comments/edits on others' PRs/issues, PR retargeting, and anything irreversible or externally visible behind explicit maintainer approval. Correct flow: analyze → present options → wait → execute approved scope → report. Real incident 2026-08-17 documented as cautionary example.
All id call sites across uteke-core (remember, chunks, graph, edges, timeline, orphans, import) now mint UUIDv7. Storage and wire format unchanged (TEXT uuid); v4/v7 coexist — existing stores open unchanged. Adds two tests: v7 version nibble + ascending order for consecutive mints, and v4/v7 parse coexistence.
#1047) (#1061) Root cause was NOT a partial delete — soft_forget() correctly marks the row deprecated and removes the vector. The leak was read-side: - list()/search_content() never filtered deprecated rows → ghosts in 'uteke list' after forget - store.count(None) counted deprecated rows → doctor/verify reported permanent DB/Index MISMATCH after any soft-forget - load_all() (repair/verify source) included deprecated rows → repair() re-added soft-deleted vectors to the index, resurrecting them in recall Fix, uniform active-only contract: - list() (all 4 branches) + search_content(): AND deprecated = 0 - load_all(): AND deprecated = 0 (recompute_importance also stops wasting cycles on hidden rows) - count(): active-only for both None and Some(ns) paths — directly comparable to index.len() in doctor/verify - new count_all(): explicit include-deprecated totals for reporting Regression test: isolated temp-dir store (':memory:' stores resolve the vector index to a CWD file and cross-contaminate parallel test runs — that shared uteke_index.usearch pollution is also why this bug hid). Asserts soft-forgotten id absent from list/list-ns/load_all and doctor reports no MISMATCH.
…ace keyword misses (#1051) (#1062) uteke_search / CLI search go through store.search_content() (LIKE substring), which mapped namespace=None to the 'default' namespace instead of searching across all namespaces like list(None) does (#526). Memories stored in any other namespace were invisible to keyword search unless the caller explicitly passed that namespace. - namespace=None now searches across all namespaces (deprecated rows still excluded) - hyphenated identifiers keep working as literal substrings on the LIKE path (pinned by test), and the FTS5 phrase path already handles them (unicode61 adjacency) — probed both in-test Regression test: cross-namespace hit via None, scoped hit via Some(ns), full and partial hyphenated identifier matching.
… parity (#1037) (#1063) recall_hybrid() applied salience/recency boosts only on the cache-miss path; the cache-hit early return handed back raw cached scores. Same query + strategy returned different scores cold vs warm (delta ~0.13). Three-part fix: - Cache-hit read path now re-applies boosts (boost → sort → truncate → min_score), identical post-processing to the miss path via shared apply_salience_recency_boosts() helper. Cache intentionally stores RAW scores — boosts are time-dependent and re-applied per read. - Boost window: cache stores limit*4+16 candidates computed with min_score=0, so boosts can lift a memory from outside the raw top-N into the final top-N on warm reads too (cora finding — cached top-limit-only set would permanently exclude boostable candidates). - min_score thresholding now happens AFTER boosts on BOTH paths (previously miss-path Vector/Fts5 filtered raw scores while hit-path filtered boosted scores). Tests: cold/warm score parity (fails with max delta 0.125 pre-fix); boost-reorder-across-limit; noop-config warm hits respect limit.
…umented (#1036) (#1064) ExportEntry had no namespace field — every exported row lost its namespace, so export→import collapsed multi-namespace stores into one. Also root-caused the reporter's 36-row delta: export() reads load_all() which filters deprecated=0 (soft-deleted rows excluded by design, but undocumented). - ExportEntry gains 'namespace' (serde default 'default' keeps old export files importable) - export() serializes m.namespace on every row - import(): caller-supplied namespace = explicit override for all rows; without it, per-row namespace wins → round-trips reconstruct namespaces - docgen/api-reference regenerated (no route change, freshness check) Test: 3-namespace × 2-row export shape (every row carries its ns), parse-side attribution preservation, legacy-row default fallback.
…confirm to apply (#1050) (#1065) A no-args uteke_dream call ran the maintenance pipeline with dry_run=false against ALL namespaces while the tool description said 'Safe to run periodically'. Real incident: single exploratory call mutated 4,067 rows store-wide. - dry_run defaults to TRUE — a no-args call can only preview - Applying requires explicit dry_run=false - Unscoped applying runs refused unless confirm_large=true (two-flag decision for whole-store maintenance) - Large-batch guard: applying runs projecting >100 changes refuse without confirm_large=true; preview computed first, so the refusal reports the projected count - Output announces scope ([SCOPE: ALL NAMESPACES]) on both preview and apply paths - Description rewritten: states destructive nature + dry-run-first guidance instead of 'Safe to run periodically' - docs/mcp.md tool table updated
…doc_search scores, room ids (#1052) (#1066) - uteke_stats: multi-line output — tiers (hot/warm/cold), pinned + deprecated split, recall cache hits/misses, and per-namespace breakdown when unscoped (was: single 'Total | Tags | DB' line) - uteke_doc_search: per-result score, matched chunk heading + 120-char snippet (ranking was invisible; results were bare slug — title) - uteke_room_memories: lines now include 8-char short id so the next tool call (pin/forget/graph edges) can act on the row - uteke_room_recall description states the existing-room_id precondition instead of failing only at call time - core: Store::count_pinned() + Uteke::{count_pinned, count_deprecated, namespace_counts} accessors (store field is private; MCP uses the public API surface)
…l ID-taking tools (#1048, #1049) (#1067) MCP printed 8-char short ids in recall/list but every ID-consuming tool required the full UUID (exact SQL match) — the basic loop recall → act silently no-opped. resolve_id_prefix() existed in core (#794); MCP never wired it. - resolve_id() helper: full UUID passes through; any shorter prefix resolves via resolve_id_prefix(); ambiguous prefixes error loudly; unknown prefixes error instead of silent not-found - Wired into uteke_forget, uteke_pin, uteke_unpin, uteke_graph_add_edge, uteke_graph_remove_edge - NEW uteke_get {id} — full record by id/prefix, no truncation (fills the read-by-id gap; recall/search return ranked excerpts) - NEW uteke_update {id, content?, tags?, metadata?, importance?, pinned?, memory_type?} — partial-update semantics matching HTTP PUT /memory (#659); content change re-embeds - Tool schemas + docs/mcp.md: id params documented as UUID-or-prefix Tests (5, scratch temp-dir stores): prefix + full + unknown resolution; uteke_get full record via short id; pin via short id; forget short id happy path + bogus prefix errors loudly; update partial fields leave content untouched.
… documents, timeline) (#1068) * feat: structural export — full-store round-trip (memories, rooms, graph, edges, documents, chunks, timeline) (#1057) uteke export only dumped the memories table; rooms, knowledge graph, memory edges, documents (+chunks) and timeline evaporated on machine-to-machine migration and cloud→OSS exit. Format (structural-v1): single NDJSON stream — manifest first line {"uteke_export":{format_version, section counts}} + tagged rows ({"type":"room"|"graph_node"|...}). Every line a JSON object — filterable with standard ndjson tooling; no zip/tar dependency. - export_full(): all 10 sections, ids verbatim, deprecated memories excluded (policy documented); embeddings dropped (portable) - import_full(): SINGLE TRANSACTION (atomic — failure rolls back the whole restore), two-pass dependency order (memories before FK junctions, documents before chunks, nodes before edges), INSERT OR IGNORE (idempotent re-import), FTS rebuilt after restore, unknown tags ignored (forward-compatible) - restored memories get NULL embeddings — load_all() already filters NULL from index builds (#992) and repair --reembed targets exactly these rows; result reports needs_reembed count - CLI: uteke export --full; uteke import auto-detects the manifest line and routes to the structural path (legacy JSONL unchanged) - cli-reference documented (previously the export format was entirely undocumented) Round-trip test: 2 memories + room + link + memory edge + document + chunk → export → fresh store → import → all sections restored with original ids (room points at restored memory id), second import is a no-op. * fix: chunk created_at missing from structural dump SELECT (code-scanning #684) The document_chunks SELECT dropped created_at when the dump block was restructured; import bound unwrap_or("") so every restored chunk got a silently-empty timestamp. Column restored on both sides; round-trip test now asserts chunk created_at verbatim. * fix: preserve exported source_type on structural import (code-scanning #686) Dump wrote source_type verbatim but import hardcoded 'import' — restored memories lost 'user'/'document' provenance. Bind the exported value; 'import' remains the fallback for rows lacking it.
…d at recall (#1069) * feat: supersession workflow — mark stale decisions superseded, flagged at recall (#1053) Long-lived rooms accumulate revisited decisions that stay indistinguishable from current truth. The graph infra existed (typed memory_edges since v8) but was never a recall-layer concern. - EDGE_SUPERSEDED_BY type; Uteke::supersede(old,new,reason): wires the edge pair (old→new superseded_by, new→old supersedes) AND soft-deprecates the old memory in ONE transaction — partial failure rolls back entirely; recall cache invalidated for the namespace - Uteke::supersession_of(id): resolves the current-replacement pointer - MCP uteke_supersede {old_id,new_id,reason?} — accepts UUID or unambiguous prefix (resolve_id), self/unknown ids rejected loudly - MCP uteke_recall output flags stale hits: '⚠ superseded by <id> — verify before acting' (covers legacy/hard-restored deprecated rows that still surface) - docs/mcp.md updated Tests: edge pair + deprecation + hide-from-list + self/unknown rejection (core); short-id supersede via MCP executor. * test: nanos-precision scratch dirs — WAL busy race under parallel workspace runs * fix: re-supersession stacks edges + nondeterministic pointer lookup (code-scanning #687) Superseding the same memory twice left both superseded_by pairs (INSERT OR IGNORE) and supersession_of() picked LIMIT 1 with no ORDER BY. Now: prior pair deleted in-transaction before the new pair; lookup orders by created_at DESC deterministically. Test pins re-supersession replacing the pointer with no stacking.
v0.20.1 is cut from main with two cherry-picked fixes; its changelog entry must also live on develop so the next release branch (git merge -s ours origin/main) does not drop it. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
…) (#1412) The strategy arms (vector, fts5, hybrid, fusion) no longer touch counters: they are built from each other and work on a boost_window of candidates, so one default recall counted +3 per memory and bumped candidates that were never returned. The touch now happens once per user-level call on the final results: recall(), recall_hybrid() (cache hit or miss) and search(). recall_explained and the point-in-time candidate search are read-only. Adds a shared embedder-equipped test helper (test_support) and tests for every strategy. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
… in the core (#1414) (#1415) FallbackSettings (core) now owns the UTEKE_EMBED_FALLBACK_* override rules (env wins, empty env ignored). The CLI delegates to it instead of its own copy, and uteke-serve reads [embed_fallback] and applies it when api_key, base_url and model are all set. First step of #1355 (split by section). Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
…1416) (#1417) uteke-serve now applies graph_density_weight, graph_authority_weight, graph_rerank_enabled and jaccard_weight from [recall], as the CLI does. Defaults are unchanged when the keys are absent. Second step of #1355. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
uteke-serve now passes hot_days, warm_days and hot_boost from [tier] to the store at open, as the CLI does; absent keys keep the core defaults (7 / 30 days, boost 0.1). Third step of #1355. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
… path check) (#1421) (#1422) * fix(cli): harden uteke upgrade (tag chars, download size cap, archive path check) (#1421) - restrict the version tag to [0-9A-Za-z.-] (suffix included) and re-check it before building the URL/file name - cap the archive (128 MiB) and checksums file (1 MiB) while streaming and from Content-Length - component-based archive entry path check instead of contains("..") - stronger UTEKE_UPGRADE_SKIP_CHECKSUM warning Refs #1327 Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * docs(cli): state the real release archive sizes next to the download cap (#1421) Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
…) (#1423) Add uteke-core `RecallInput` / `RecallPolicy` / `RecallRequest`: defaults, limit cap, blank-query rejection, tag normalisation, RFC3339 parsing, search_type / strategy / min_score resolution and the CLI-via-server body now live in one module. The HTTP /recall handler, MCP uteke_recall and the CLI-via-server recall body use it. Extraction only: where the surfaces disagree, each surface's current behaviour is encoded as a policy value. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…target Unreleased (#1429) Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…1343) (#1425) Extract /remember, uteke_remember and the CLI-via-server body into uteke-core's remember_request module (RememberInput, RememberPolicy, RememberRequest), following the recall slice. No wire behaviour change. Refs #1343 Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
…) (#1426) Add uteke-core ForgetInput / ForgetPolicy / ForgetRequest and resolve_memory_id: DELETE /forget query parsing, id-or-tag decoding, id resolution (full UUID, prefix, ambiguity), the existence check and the CLI-via-server URL now live in one module. HTTP /forget, MCP uteke_forget (and the shared MCP resolve_id) and the CLI-via-server forget use it. Extraction only: where the surfaces disagree, each surface's current behaviour is a policy value; the read-only gate stays HTTP-only. Refs #1343 Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
…1434) Writing to a non-default namespace now carries a one-sentence deprecation warning on HTTP (/remember, /room/remember, /extract, /import, /room/create, PUT /memory), MCP (uteke_remember, uteke_update, uteke_room_create) and the CLI (stderr only). The wording lives once in uteke-core; the server logs it once per distinct namespace. Routing, storage and reads are unchanged. Tool descriptions, uteke guide, skill and docs steer to rooms, tags, author. Refs #1427 Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
#1435) (#1436) resolve_id_prefix now escapes %, _ and the escape character, so an id prefix is never a pattern for any caller, and the HTTP forget policy validates the id like MCP (hex digits and '-', 400 otherwise). Before, DELETE /forget?id=%25 matched every memory whose id contains "25" and deleted it when exactly one matched. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
) (#1437) The api_registry table is now consulted by the router (unregistered method+path is a 404 before any handler runs) and by the read-only-token gate (derived from a new per-row writes flag). The source-scanning coverage test is replaced by tests built from the table. Refs #1344 Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
…1438) New "Reaching the server from another device on your LAN" section (token first, bind address, Host header behaviour, plain-HTTP caveat, firewall, Docker) and "Keeping the token out of the client config" in the MCP docs (stdio needs no token, static bearer only, no OAuth in the self-hosted server). Every claim was checked against a running server. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com> Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
…#1442) Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
AGENTS.md named the project room but did not require reading it before a task or writing progress to it afterwards, so decisions and release state lived only in whichever session made them. Spell out both steps, note that room recall is cross-namespace, and that the shared store differs from a local CLI store. Also record the owner rule that commits, PRs, comments and release notes carry no AI attribution trailers or lines. Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
* security(mcp): per-tool read-only gate for callers without write access (#1439) * security(mcp): refuse read-only tool calls as tool errors; pin the allowlist (#1439) * security(server): read-only tokens reach MCP read tools; writes stay refused (#1439) * docs: read-only tokens and MCP tools (#1439) --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
… retry of validation errors (#1443) * fix(core): retry_embed reports a missing embedder instead of panicking * fix(core): do not retry embedding validation errors * test(core): pin the missing-embedder error variant; doc wording * fix(core): recall reports a missing embedder instead of panicking ensure_embedder only returns Ok once the slot holds an embedder and nothing resets it to None, so the expect was unreachable today. Return an Embedding error instead so a future change cannot turn it into a panic. Adds a test that vector recall on a store with no usable embedder errors rather than panics. * fix(core): skip a missing RRF memory instead of panicking recall_rrf fills rrf_scores and memories in the same loops, so the expect could not fire today. Use filter_map and skip a missing id with a warning instead of panicking if that invariant ever breaks. take(limit) stays before the filter, so the normal path is unchanged. * style(core): wrap the RRF skip warning and note the short-result case --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
…1444) * fix(cli): an explicit --store never routes through a running server With [server] enabled = true and a server up, remember/recall/search/list/ stats/forget were sent to the server, which serves its own store, so an explicit --store was silently ignored and data went to the wrong database (the LongMemEval harness always passes --store). Server routing is now decided by should_route_via_server(), which returns false whenever --store is set; the cheap check runs before the network probe. UTEKE_HOME is unchanged. (#1439 B4) * test(bench): modal_fast50.py reads UTEKE_RELEASE like modal_fanout.py * fix(cli): keep routing --store pointing at the default store; changelog --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
* chore(release): v0.21.0 - version bump, changelog, docs sync Prepared on chore/prepare-0.21.0; the release PR into main is opened from a chore/release-* branch after the mutation-test gate. * docs(security): checksums are signed since v0.21.0, not since the release after v0.20.0 --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
* test(core): kill the mutants the 0.21.0 gate missed Exact-value tests for the mutants the pre-release gate (v0.20.1..develop, uteke-core) left alive: - lib.rs: FallbackSettings::with_env_overrides -> Default::default() - forget_request.rs: Display for ForgetRequestError -> Ok(Default::default()) - list_request.rs: Display for ListRequestError -> Ok(Default::default()) - remember_request.rs: Display for RememberRequestError -> Ok(Default::default()) - operations.rs recall_rrf: vector window `limit * 3` -> `limit + 3` - operations.rs recall_rrf: vector window `limit * 3` -> `limit / 3` - operations.rs recall_rrf: `score / max_rrf` -> `score * max_rrf` * test(core): assert only the env var the fallback test owns --------- Co-authored-by: ajianaz <ajianaz@users.noreply.github.com>
🔍 Cora AI Code Review✅ No issues found. Code looks good! Review powered by cora-code · BYOK · MIT |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Releases v0.21.0. This branch is
develop@ de1c78a plusgit merge -s ours origin/main. The tree is identical todevelop:git diff origin/develop HEADis empty. Full notes are inCHANGELOG.mdunder[0.21.0](39 PRs since v0.20.1).Why
To publish 0.21.0, which the owner approved as a minor release. Highlights:
recall_count(feat(core): count recall/search hits in recall_count, apart from explicit gets (#1337) #1397, fix(core): count a recall once, and only the memories it returns (#1407) #1412)uteke-servereads[embed_fallback],[tier]and more of[recall](refactor(server): read [embed_fallback] and resolve its env overrides in the core (#1414) #1415, refactor(server): read the graph-rerank and jaccard keys of [recall] (#1416) #1417, refactor(server): read [tier] from uteke.toml (#1418) #1419)uteke upgradehardening (fix(cli): harden uteke upgrade (tag chars, download size cap, archive path check) (#1421) #1422)--storerouting fix (fix(cli): an explicit --store never routes through a running server #1444)Testing
Main has no unique content. Checked before the
-s oursmerge:main.main-only commit since v0.20.0 is the v0.20.1 release (f89939e). Its changes are already on develop:docker-entrypoint.shand its test apply identically.crates/uteke-server/src/main.rshas the sameresolve_embedding,[embedding]/[vector]sections,UTEKE_EMBEDDING_BACKENDhandling and all 7 tests. Develop refactored the file afterwards (refactor(server): read [embed_fallback] and resolve its env overrides in the core (#1414) #1415, refactor(server): read the graph-rerank and jaccard keys of [recall] (#1416) #1417, refactor(server): read [tier] from uteke.toml (#1418) #1419), so the patch text no longer matches.[0.20.1]CHANGELOG section is identical.Pre-release mutation gate:
cargo mutants -p uteke-core --in-diffoverv0.20.1..develop. 159 mutants: 124 caught, 28 unviable, 0 timeouts, 7 missed. All 7 now have killing tests (#1449); re-testing those 7 gives 7 caught.Contract: CORE changes are reported to uteke-cloud in Gitea issues #174 (this release), #117, #135 and #151.
docs/core-contract.jsondiffers from v0.20.0 only in its version.CI on develop:
cargo test --workspace, fmt and clippy are green on every merged PR.LongMemEval fast50: not run for this release, because the dataset is not available locally.
recall_count) was gated by its own fast50 run on Modal, with identical aggregates (mean R@5 0.9800 vs 0.9800, 0 improved, 0 regressed; uteke-cloud#135).After the merge: tag
v0.21.0on the merge commit, then verify the release assets and the cosign bundle withcosign verify-blobas described inSECURITY.md.