WeKnora/internal/agent/tools
lyingbug 04adc13272
fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687)
* fix(retrieval): keep index writes and shared-KB lookups correct

Index writes
- Image OCR/caption chunks were indexed without IsEnabled, so every engine
  but Postgres stored them disabled and retrieval never returned them.
  The SQLite engine re-enables the affected rows at startup.
- FAQ edits, similar-question additions and import merges re-index under
  the old SourceID and relied on the engine overwriting it. Postgres and
  SQLite kept the stale row (ON CONFLICT DO NOTHING); ES v8 and Qdrant
  mint a new document ID and kept both. FAQ re-indexing now deletes the
  old rows first, and Postgres/SQLite BatchSave upserts by
  (source_id, source_type).
- Postgres: drop the GORM default tag on is_enabled, which replaced false
  with true on insert and indexed disabled chunks as enabled.
- SQLite: BatchSave no longer attaches vectors and FTS rows to the wrong
  rows when part of a batch already exists, and vecTables is guarded
  against concurrent map writes.
- CopyIndices: Postgres filters to the copied knowledge, pages by id and
  keeps is_enabled; SQLite copies every row of a chunk (generated
  questions included) with stable source IDs and enabled state.

Shared knowledge bases
- Chat merge: FAQ answer population and neighbor expansion look chunks up
  without the caller-tenant filter, like parent resolution (#3342).
- Neighbor expansion never cuts the retrieval hit; the length budget goes
  to the text adjacent to it.
- FAQ negative questions are applied whenever an FAQ KB is in scope and
  to chunks of shared FAQ KBs.
- Search results get image_info for shared-KB chunks.
- search_knowledge reads FAQ metadata from the search result instead of
  one tenant-scoped query per hit, so shared FAQs render their answers.

* fix(retrieval): put every retrieval score on one scale

Scores from different retrieval paths were ranked together while living on
different scales, so ordering depended on which path produced a hit.

Fusion
- RRF ranked a chunk by its position in the concatenation of every
  vector (or keyword) list, appended in goroutine completion order. The
  second list's best hit ranked behind every hit of the first, and the
  order changed between identical requests. Each list is now ranked on
  its own by score and a chunk takes its best rank.
- RRF is divided by its maximum, so hybrid scores land in [0, 1] like
  vector-only (cosine) and keyword-only (rescaled BM25) results. Raw RRF
  topped out near 0.016 and lost to any single-retriever hit it was ranked
  against across searches (document targets, model groups, FAQ calls);
  rerank's base-score term and MMR's relevance term had nothing to use.
- Keyword-only BM25 is rescaled per list; engines' BM25 is not comparable.
- FAQ iterative retrieval fuses each round like the first pass instead of
  sorting raw BM25 and cosine together, starts at twice the depth already
  searched, triggers when any single vector list is full (the old summed
  count never matched with more than one list) and replaces results per
  round.

Rerank and chat pipeline
- The FAQ boost is no longer capped at 1; capping made strong FAQs tie at
  1.0 and fall to the tie-breaker. The composite score before boosts is
  kept as composite_score.
- The FAQ direct-answer threshold is compared against that pre-boost
  score, and the FAQ that cleared it is the one marked match="exact"
  rather than the first FAQ.
- Graph hits no longer carry a fabricated retrieval score of 1.0, which
  ranked them above every scored hit when rerank did not run; the
  composite score uses the model score in its place.

Engines
- OpenSearch and Weaviate return (1 + cos) / 2; their drivers now report
  cosine similarity and map thresholds onto the engine scale, so a
  threshold means the same on every engine.
- Milvus L2 returned squared distance, ranked farthest-first downstream,
  and took the threshold as a radius; scores and radius are converted.
- The multi-store normalizer no longer maps Milvus through (s + 1) / 2,
  which put it on a different scale from every other engine and from its
  own single-store results.

Docs updated for fusion, normalization, FAQ boost and iterative recall.

* perf(retrieval): bound rerank, agent and pipeline cost; stop failing on slow or missing models

Rerank
- Rerankers report the longest document a request can carry
  (max_document_chars / max_request_chars minus the query) and the rerank
  stage fits its own passages to it, trimming appended captions, OCR and
  generated questions first. One chunk with a large screenshot's OCR used
  to exceed the vendor limit and fail the whole batch, so every candidate
  lost its score and the threshold stopped applying.
- Rerank HTTP requests default to a 60 s timeout; chat and agent contexts
  carry no deadline, so a stalled self-hosted rerank server held the turn
  open.
- OCR and caption chunks no longer repeat their own text from image_info in
  the passage.
- The chat pipeline and the agent tool rerank at most 200 candidates, best
  retrieval score first.
- A rerank model that cannot be loaded degrades to retrieval order instead
  of failing every chat turn, as the search APIs already do; without rerank
  results the merge stage keeps only RerankTopK hits instead of enriching
  every one.

Retrieval APIs
- knowledge-search match_count and rerank.top_k are capped at 200
  (unbounded values multiplied into tens of thousands of billed rerank
  passages); normalizedMatchCount clamps to the pool size so the
  over-retrieval arithmetic cannot overflow.
- hybrid-search with rerank recalls at least rerank.top_k deep.

Agent
- search_knowledge fits its rendered output to four fifths of the tool
  output budget, dropping the lowest-ranked rows and telling the model how
  many it omitted; the model's view is rebuilt from Data, which registry
  truncation never reached.
- Agent searches skip neighbor/parent/related enrichment rows, which were
  never retrieved yet tripled the rerank input.
- ParallelToolCalls is enabled. The model was always told it may call tools
  in parallel while the engine ran them one by one; only read-only tools
  overlap, anything else stays a barrier.

Chat pipeline
- Query expansion searches keywords only (its variants are local rewrites
  whose embeddings repeat the main search) and is skipped when keyword
  matching is off.
- Entity extraction, a second LLM call, is skipped for intents that need no
  KB retrieval and uses the rewritten query.
- Partial-overlap dedup tokenizes each text once instead of per pair, and
  only compares token overlap between texts within 3x of each other's size.

Storage
- Migration 000112 adds btree indexes on embeddings(knowledge_id) and
  (chunk_id); document deletes, chunk re-index and enable/tag updates
  scanned the whole table.
- Shared-KB knowledge rows are fetched in one query instead of one per ID.
- Drop GORM Debug() from the ParadeDB keyword query and the knowledge batch
  lookup, which logged SQL and user queries on every search.

Docs updated for the API limits, rerank timeout and passage fitting, agent
parallel tools and output budget, and pipeline changes.

* fix(retrieval): make agent tools and pipeline stages report what they did

Agent tools
- query_knowledge_graph now queries the graph store: entity names from the
  query are matched in each KB's graph, relations are returned (and shown to
  the model), and the entities' source chunks lead the results, with text
  search as a supplement. It used to run text search only, so a graph-only
  KB always answered "no relevant graph information".
- search_knowledge reports failures instead of "no matching chunks": when
  every search fails the tool fails with the reason; partial failures are
  listed. A failed query embedding falls back to keyword search for hybrid
  KBs, as the chat pipeline does.
- Keyword mode uses rerank to order hits, not to reject them (identifiers
  score low), and the empty-result hint no longer sends keyword mode back to
  keyword mode.
- Dedup keeps siblings under one parent, no longer merges every image chunk
  of a document through chunk_index 0, and keeps the better-scored copy.
- Search rows omit a <match> excerpt that only repeats the content; snippet
  terms are segmented for Chinese queries and skip stopwords, and FAQ
  matched questions are chosen by match strength.
- read_document query mode returns next_offset when truncated and resumes
  from offset.
- wiki_search over-fetches under document/tag scopes before filtering and
  says when every match was out of scope.
- Prompts point to read_document(id=cN, context=k) for surrounding text.
- The agent editor hides the retrieval-strategy section in agent mode,
  where search_knowledge uses the global retrieval settings.

Chat pipeline
- Intent labels are normalized; an unknown label retrieves instead of
  silently skipping the knowledge base, and web_search without web search
  enabled searches the knowledge bases.
- Image turns get a 2048-token rewrite budget, and a reply cut off by the
  cap is salvaged field by field instead of being discarded.
- History references are matched by how much of the query they cover;
  Jaccard against chunk-sized text never reached its threshold.
- Entity search resolves chunks of org-shared KBs within the turn's KB
  scope, skips chunks whose document is gone (it used to panic) and caps
  graph chunks at 30.
- Empty history is not fetched twice; fetched pages are cut on a rune
  boundary.

Retrieval
- A multi-KB search whose primary KB has no vectors embeds the query with a
  vector KB's model instead of failing on an empty model ID.
- Rerank passages include the chunk's heading breadcrumb, which is part of
  what was embedded.
- SQLite FTS searches the content column only and turns a lone Han
  character into a prefix query; TencentVectorDB ef follows TopK.

Docs updated for the agent tools and pipeline stages.

* fix(retrieval): address review findings on the retrieval fixes

- Restore NeedsRetrieval for web_search without web search enabled: the
  intent prompt "web_search" is how the user learns web search is off, and
  running KB retrieval instead bypassed it.
- query_knowledge_graph keeps the case of entity terms; Neo4j matches node
  names with case-sensitive CONTAINS, so lowercased terms never matched
  English entities.
- An empty search_knowledge or query_knowledge_graph result states partial
  failures in its text, which is all the model sees for an empty result.
- SQLite BatchSave replaces a source in one transaction, so a failed insert
  keeps the old rows instead of leaving the source unindexed.
- Reuse stringSliceValue and an exported searchutil.ContainsChinese instead
  of new copies; drop an unused named return and the FAQ obsolete-source
  delete that the full per-chunk delete now covers.

* fix(retrieval): address second review of the retrieval fixes

- query_knowledge_graph: under a document/tag scope, keep only relations
  whose entities come from an in-scope evidence chunk (the graph namespace
  is the whole KB); drop chunks whose document no longer exists; report a
  graph or text search failure even when the other source returned hits.
- search_knowledge: record the hybrid -> keyword fallback taken when the
  query embedding fails in mode_fallbacks, so an empty result is not read
  as "no semantic match".
- query understanding salvage: take a cut-off value only for the image
  description; a truncated rewrite_query or intent is dropped instead of
  replacing the user's query.
- Graph hits (no retrieval score) are kept past the no-rerank RerankTopK
  cut and the rerank candidate cap instead of always falling below them.
- FAQ boost is capped at 1 again so scores stay on the [0, 1] scale; FAQs
  tied at the cap are ordered by their pre-boost score.
- Negative-question filtering loads only candidates of FAQ knowledge bases.
- read_document query continuation starts one chunk before offset so the
  first match keeps its preceding context at a page boundary.
- graphSearchTerms and searchQueryTokens share one queryTerms splitter.
2026-09-25 10:48:18 +08:00
..
browserskill.go fix(browser): let shared-space agents drive the caller's local browser 2026-09-24 18:19:17 +08:00
browserskill_image.go fix(browser): complete task cancellation, screenshots, and result display (#3206) 2026-09-12 09:32:26 +08:00
browserskill_image_test.go fix(browser): complete task cancellation, screenshots, and result display (#3206) 2026-09-12 09:32:26 +08:00
browserskill_prompt.go chore: update BrowserSkill extension version to 0.3.1 and enhance localization support 2026-09-23 17:12:19 +08:00
browserskill_result.go fix(browser): use unmodified BrowserSkill upstream and remove downstream patches (#3563) 2026-09-23 00:22:34 +08:00
browserskill_result_test.go fix(agent): give local_browser one text cap and per-method signatures 2026-09-23 11:49:39 +08:00
browserskill_schema.go fix(agent): give local_browser one text cap and per-method signatures 2026-09-23 11:49:39 +08:00
browserskill_schema_test.go fix(agent): give local_browser one text cap and per-method signatures 2026-09-23 11:49:39 +08:00
browserskill_test.go fix(browser): let shared-space agents drive the caller's local browser 2026-09-24 18:19:17 +08:00
capabilities.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
chunk_snippet.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
chunk_snippet_test.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
data_analysis.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
data_analysis_duckdb_test.go test(agent): add end-to-end DuckDB excel tests and fix sheet enumeration (#1007) 2026-04-24 19:57:56 +08:00
data_analysis_materialize_test.go fix: deep-copy stored files and images when cloning a knowledge base 2026-06-03 14:45:59 +08:00
data_analysis_query_test.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
data_analysis_test.go feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
data_schema.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
database_query.go fix(agent): exclude disabled FAQ entries 2026-07-29 14:40:54 +08:00
database_query_test.go fix(agent): exclude disabled FAQ entries 2026-07-29 14:40:54 +08:00
definitions.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
definitions_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
exec_context.go feat: scope API MCP OAuth by principal 2026-06-30 20:01:05 +08:00
execution_policy.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
faq_snippet.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
faq_snippet_test.go feat(faq): enhance FAQ handling and localization support 2026-06-04 21:43:16 +08:00
file_mutation_queue.go feat(agent): unify sandbox tools and drop host preloaded skills (#3033) 2026-09-05 16:45:59 +08:00
file_mutation_queue_test.go feat(agent): keep long sandbox turns from truncating, overflowing, or rewriting files 2026-09-02 22:09:09 +08:00
image_markdown_output_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
json_repair.go feat(agent): keep long sandbox turns from truncating, overflowing, or rewriting files 2026-09-02 22:09:09 +08:00
json_repair_test.go fix(agent): recover tool arguments with a stray trailing fragment 2026-09-02 10:12:55 +08:00
list_documents.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
list_documents_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
mcp_catalog.go fix(chat): preserve steering continuity and composer focus 2026-09-09 20:15:23 +08:00
mcp_catalog_integration_test.go feat(mcp)!: persist tool catalogs and add guided configuration (#3118) 2026-09-09 13:34:56 +08:00
mcp_catalog_regression_test.go feat(mcp)!: persist tool catalogs and add guided configuration (#3118) 2026-09-09 13:34:56 +08:00
mcp_catalog_test.go fix(mcp): normalize JSON-encoded argument envelopes 2026-09-09 16:11:52 +08:00
mcp_directory_test.go feat(mcp)!: persist tool catalogs and add guided configuration (#3118) 2026-09-09 13:34:56 +08:00
mcp_exposure.go feat(mcp)!: streamline setup and use short routing handles 2026-09-09 16:11:52 +08:00
mcp_exposure_test.go feat(mcp)!: streamline setup and use short routing handles 2026-09-09 16:11:52 +08:00
mcp_oauth.go refactor(agent): discover and invoke MCP tools on demand 2026-09-08 12:01:36 +08:00
mcp_schema.go refactor(agent): discover and invoke MCP tools on demand 2026-09-08 12:01:36 +08:00
mcp_schema_test.go refactor(agent): discover and invoke MCP tools on demand 2026-09-08 12:01:36 +08:00
mcp_tool.go fix(agent): honor MCP service advanced_config.timeout for CallTool window 2026-09-11 17:47:04 +08:00
mcp_tool_enabled_test.go feat(mcp): add per-tool enable toggle (#2989) 2026-09-05 17:19:20 +08:00
mcp_tool_image_test.go feat: auto-describe MCP tool result images via VLM 2026-03-25 21:38:15 +08:00
mcp_tool_test.go feat(tests): add comprehensive tests for MCPTool functionality 2026-03-25 22:08:29 +08:00
mcp_tool_timeout_test.go fix(agent): honor MCP service advanced_config.timeout for CallTool window 2026-09-11 17:47:04 +08:00
normalize_id.go feat(agent): enhance tool execution and message sanitization 2026-03-25 22:08:29 +08:00
normalize_id_test.go feat(agent): enhance tool execution and message sanitization 2026-03-25 22:08:29 +08:00
output_budget.go fix(agent): keep batched wiki_read_page results within output budget 2026-07-27 13:22:16 +08:00
output_budget_test.go fix(agent): keep batched wiki_read_page results within output budget 2026-07-27 13:22:16 +08:00
output_links.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
output_links_test.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
param_cast.go fix(agent): harden tool parameter parsing against LLM type mismatches (#1505) 2026-05-28 07:50:26 +08:00
param_cast_test.go refactor(prompt): streamline context handling in templates 2026-03-25 22:08:29 +08:00
param_validate.go feat(agent): implement memory consolidation and context management 2026-03-25 22:08:29 +08:00
param_validate_test.go feat(agent): implement memory consolidation and context management 2026-03-25 22:08:29 +08:00
persist.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
persist_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
python_syntax.go feat(agent): unify sandbox tools and drop host preloaded skills (#3033) 2026-09-05 16:45:59 +08:00
python_syntax_test.go refactor(skills): introduce write_skill_file and edit_skill_file tools for skill directory management 2026-09-02 15:08:05 +08:00
query_knowledge_graph.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
query_knowledge_graph_graph_test.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
query_knowledge_graph_test.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
read_document.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
read_document_test.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
read_file.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
read_file_test.go fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +08:00
read_web_page.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
registry.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
registry_outcome_test.go feat(agent): unify sandbox tools and drop host preloaded skills (#3033) 2026-09-05 16:45:59 +08:00
registry_test.go fix(agent/tools): sort function definitions for deterministic ordering 2026-05-25 16:47:14 +08:00
sandbox_diff.go feat(agent): stream live +/- progress for sandbox write and edit 2026-09-02 23:36:58 +08:00
sandbox_diff_test.go feat(agent): stream live +/- progress for sandbox write and edit 2026-09-02 23:36:58 +08:00
sandbox_edit.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
sandbox_edit_test.go feat(agent): stream live +/- progress for sandbox write and edit 2026-09-02 23:36:58 +08:00
sandbox_ls.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
sandbox_write.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
sandbox_write_test.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
sanitize_messages.go feat(browser): polish connection settings, open tasks in a new window, and streamline prompts (#3193) 2026-09-11 21:28:58 +08:00
sanitize_messages_test.go feat(browser): polish connection settings, open tasks in a new window, and streamline prompts (#3193) 2026-09-11 21:28:58 +08:00
schema_validity_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
scope_authorization.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
scope_authorization_test.go fix(agent): exclude disabled FAQ entries 2026-07-29 14:40:54 +08:00
search_conversations.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
search_knowledge.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
search_knowledge_metadata_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
search_knowledge_rerank_test.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
search_knowledge_test.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
search_memory.go feat(memory): introduce long-term memory feature with i18n updates 2026-08-13 18:00:02 +08:00
search_memory_test.go feat(memory): introduce long-term memory feature with i18n updates 2026-08-13 18:00:02 +08:00
sequentialthinking.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
shell_command_output.go feat(sandbox): stream live shell and install command output 2026-09-12 10:16:39 +08:00
shell_command_output_test.go feat(sandbox): stream live shell and install command output 2026-09-12 10:16:39 +08:00
shell_env_extract.go feat(localsandbox): add host OS sandbox core and macOS Seatbelt backend (#3472) 2026-09-21 13:24:05 +08:00
shell_env_extract_test.go fix(sandbox): make skill env capture fill blanks only 2026-08-27 14:32:00 +08:00
shell_exec.go feat(lite): install and run skills on the host (#3661) 2026-09-24 21:30:34 +08:00
shell_exec_test.go feat(lite): install and run skills on the host (#3661) 2026-09-24 21:30:34 +08:00
shell_runtime_integration_test.go feat(sandbox): run sandboxed execs as root by default (#3067) 2026-09-07 13:03:35 +08:00
shell_stdin_test.go feat(agent): unify sandbox tools and drop host preloaded skills (#3033) 2026-09-05 16:45:59 +08:00
skill_file.go feat(agent): keep long sandbox turns from truncating, overflowing, or rewriting files 2026-09-02 22:09:09 +08:00
skill_file_test.go refactor(skills): introduce write_skill_file and edit_skill_file tools for skill directory management 2026-09-02 15:08:05 +08:00
skill_file_tree_test.go feat(agent): keep long sandbox turns from truncating, overflowing, or rewriting files 2026-09-02 22:09:09 +08:00
skill_resources.go feat(agent): unify sandbox tools and drop host preloaded skills (#3033) 2026-09-05 16:45:59 +08:00
skill_runtime_guard.go feat(sandbox): run sandboxed execs as root by default (#3067) 2026-09-07 13:03:35 +08:00
skill_runtime_guard_test.go feat(sandbox): run sandboxed execs as root by default (#3067) 2026-09-07 13:03:35 +08:00
strip_think.go fix(agent): end the turn when the completion cap truncates an answer (#3449) 2026-09-20 13:17:50 +08:00
strip_think_test.go refactor(agent): remove query display from DatabaseQuery component and update tool result structure 2026-03-25 22:08:29 +08:00
think_stream.go feat(agent): enhance event routing for reasoning and answers in streaming 2026-06-04 15:48:04 +08:00
think_stream_test.go feat(agent): enhance event routing for reasoning and answers in streaming 2026-06-04 15:48:04 +08:00
todo_write.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
tool.go feat: use language-neutral English prompts for multilingual LLM responses 2026-03-06 21:08:12 +08:00
tool_policy_coverage_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
truncate.go fix(agent): keep batched wiki_read_page results within output budget 2026-07-27 13:22:16 +08:00
truncate_test.go feat(agent): implement memory consolidation and context management 2026-03-25 22:08:29 +08:00
web_fetch.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
web_fetch_test.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
web_pages_test.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
web_search.go feat(web-search): add Serply provider 2026-09-17 12:25:09 +08:00
web_search_test.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
wiki_delete_page.go feat(wiki): add page revision history with diff, revert, and manual editing 2026-07-27 15:03:24 +08:00
wiki_flag_issue.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
wiki_index_overview_test.go perf(wiki): move ingest log to event table and index to on-demand API 2026-05-08 21:48:52 +08:00
wiki_link_mutation.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
wiki_link_mutation_test.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
wiki_read_issue.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
wiki_read_page_budget_test.go fix(agent): keep batched wiki_read_page results within output budget 2026-07-27 13:22:16 +08:00
wiki_rename_page.go feat(wiki): add page revision history with diff, revert, and manual editing 2026-07-27 15:03:24 +08:00
wiki_replace_text.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
wiki_replace_text_test.go fix: replace all exact wiki text matches 2026-08-05 19:30:40 +08:00
wiki_route_resolver.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
wiki_search_scope_test.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
wiki_source_refs.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
wiki_source_refs_test.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
wiki_tools.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
wiki_tools_test.go refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
wiki_update_issue.go fix(security): close the low-severity shared-space findings (#3416) 2026-09-18 22:58:46 +08:00
wiki_write_page.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00
wiki_write_page_test.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
workspace_layout.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
workspace_layout_test.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
workspace_reader.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
workspace_reader_test.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00