WeKnora/internal/agent/tools
lyingbug 093c16cbb3
fix(agent): end the turn when the completion cap truncates an answer (#3449)
* fix(agent): end the turn when the completion cap truncates an answer

A round that came back with finish_reason=length and no tool calls used to
fall through analyzeResponse as non-terminal. With no tool calls to run,
appendToolResults pushed the half-written answer back into the history as a
plain assistant message with nothing telling the model to continue, so the
next round rewrote the answer from the top, hit the same cap, and repeated
until the round budget ran out or the user cancelled.

Three guards, each independently load-bearing:

- analyzeResponse gains a truncation case: deliver the partial text and end
  the turn. A cap hit that produced no text at all has nothing to hand over
  and defers to the existing bounded empty-content retry. No continuation
  nudge is sent — it only grows the prompt with the discarded fragment, and
  assistant prefill, the reliable form, is unavailable on most
  OpenAI-compatible endpoints.
- A consecutive-length breaker stops the loop when truncation keeps landing
  inside tool-call arguments, the one shape that still legitimately loops.
- The stuck-loop detector now counts an identical lack of content. A model
  burning its whole budget on reasoning returns empty every round, which used
  to land in the else branch and reset the counter, so the guard could never
  fire on the case that needed it most.

The answer event and its Done marker carry a truncated flag through the SSE
metadata, and the chat UI shows the same style of notice it already uses for
fallback answers.

Fixes #3446

* fix(agent): treat unterminated reasoning as no answer and keep the truncation marker

Review follow-up on three ways the truncation path could still mislead.

An inline <think> block that the cap cut off never gets its closing tag, so
the pair regex left it whole and the round looked like it had produced an
answer. The truncation case then skipped the empty-content retry it exists
for and emitted the chain of thought as the final answer. StripThinkBlocks
now drops a dangling <think> through end of input, which is what the
streaming splitter already does with the same text, so the two agree on what
counts as an answer.

The truncation marker only rode on the SSE metadata, and a finished
conversation is rebuilt from agent_steps rather than replayed from stream
events. A reloaded, shared or re-opened turn therefore lost the notice and
its half-written answer looked complete. AgentStep carries the flag now — it
is a jsonb column, so no migration — and the frontend marks the rebuilt
answer event and message from it.

The consecutive-length guard ran before the round was recorded, so a final
round of "let me look that up" plus a truncated tool call handed that
preamble over as the final answer, with its tool calls never refused and the
preamble never retracted from the answer area. The guard now records the
round and fails its tool calls the way every other truncated round does, and
a response carrying tool calls never donates its text as the answer.
2026-09-20 13:17:50 +08:00
..
browserskill.go feat(browser): polish connection settings, open tasks in a new window, and streamline prompts (#3193) 2026-09-11 21:28:58 +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 fix(browser): align BrowserSkill 0.3.0 and repair task lifecycle 2026-09-17 11:54:12 +08:00
browserskill_result.go fix(browser): align BrowserSkill 0.3.0 and repair task lifecycle 2026-09-17 11:54:12 +08:00
browserskill_result_test.go fix(browser): align BrowserSkill 0.3.0 and repair task lifecycle 2026-09-17 11:54:12 +08:00
browserskill_schema.go fix(browser): align BrowserSkill 0.3.0 and repair task lifecycle 2026-09-17 11:54:12 +08:00
browserskill_schema_test.go fix(browser): align BrowserSkill 0.3.0 and repair task lifecycle 2026-09-17 11:54:12 +08:00
browserskill_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
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 refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +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 refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +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 perf(sandbox): reduce redundant remote calls 2026-09-17 17:47:24 +08:00
output_links_test.go perf(sandbox): reduce redundant remote calls 2026-09-17 17:47:24 +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 refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
query_knowledge_graph_test.go Simplify KB duplicate API and improve naming/docs coverage. 2026-07-08 20:55:54 +08:00
read_document.go fix(agent): make read_document queries keyword-based and bound its pages 2026-09-18 15:09:25 +08:00
read_document_test.go fix(agent): make read_document queries keyword-based and bound its pages 2026-09-18 15:09:25 +08:00
read_file.go fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +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(mcp)!: persist tool catalogs and add guided configuration (#3118) 2026-09-09 13:34:56 +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 fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +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 fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +08:00
sandbox_write.go fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +08:00
sandbox_write_test.go fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +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(agent): allow keyword retry after search_knowledge rerank rejection 2026-09-18 16:06:52 +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_mmr_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(agent): allow keyword retry after search_knowledge rerank rejection 2026-09-18 16:06:52 +08:00
search_knowledge_test.go fix(agent): allow keyword retry after search_knowledge rerank rejection 2026-09-18 16:06:52 +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 fix(sandbox): make skill env capture fill blanks only 2026-08-27 14:32:00 +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 perf(sandbox): reduce redundant remote calls 2026-09-17 17:47:24 +08:00
shell_exec_test.go fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +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_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 refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +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_reader.go perf(sandbox): reduce redundant remote calls 2026-09-17 17:47:24 +08:00
workspace_reader_test.go fix(sandbox): separate file access from artifact publishing (#3356) 2026-09-17 16:18:01 +08:00