fix(ai): restore global reasoning toggle accidentally reverted by d90847bb
Commit 09f9e446 replaced per-message expandedReasoning (Set<number>) with
a global reasoningExpanded boolean ref, defaulting to collapsed so all
messages share the same toggle state. This avoided the flip-flop where
reasoning auto-expanded during streaming and collapsed afterward.
Commit d90847bb (SQL file references) inadvertently reverted this when
resolving merge conflicts during its large template restructure.
Changes:
- Replace expandedReasoning (Set<number>) with reasoningExpanded (ref(false))
- Replace per-index toggleReasoning(i) with global toggleReasoning()
- Template uses reasoningExpanded instead of expandedReasoning.has(i) || msg.isThinking
@
fix(ai): make reasoning expand/collapse consistent across messages
Replace per-message expandedReasoning Set with a global reasoningExpanded
boolean ref so all messages share the same toggle state. Default to collapsed.
This avoids the flip-flop where reasoning auto-expands during streaming and
collapses afterward, requiring repeated manual toggles.
- Replace expandedReasoning (Set<number>) with reasoningExpanded (boolean)
- Remove per-index toggleReasoning; use global flip instead
- Template uses reasoningExpanded instead of expandedReasoning.has(i) || msg.isThinking
@
* feat(ai): add task-oriented Agent actions with per-action contract
Introduce three Agent-native actions — query, exploreSchema,
executeAndExplain — so Agent mode surfaces task-oriented operations
instead of reusing Ask's SQL-producing action set.
- ai.ts: extend AiAction with the new actions; add ASK_ACTIONS /
AGENT_ACTIONS and defaultActionForMode / isValidActionForMode
helpers; raise maxTokens for the explanatory task actions.
- aiSkills.ts: add skill definitions (zh/en) for the three actions.
- aiAgentPlan.ts: task actions no longer emit a misleading
"unsupported_action" execute step; they execute via the
execute_query tool events, not the legacy client-side path.
- agent_loop.rs: per-action task-contract rules in both the prompt
augmentation and repair paths (query -> execute & answer from real
data; exploreSchema -> list_tables/get_columns; executeAndExplain
-> run current SQL & explain).
- i18n (en/zh-CN/zh-TW): new action labels, placeholders, a
generateNoExec label for Agent mode, and a task-oriented agent
modeHint.
es/it/ja/pt-BR have no `ai` section and fall back to `en`, matching
existing coverage.
* feat(ai): split Ask/Agent action menus with mode-aware defaults
Wire the new Agent task actions into the assistant UI so each mode
shows a distinct, intent-matching action set.
- actionButtons is now a computed returning Ask or Agent buttons
based on assistantMode. Agent menu: query / exploreSchema /
executeAndExplain / generate (labeled "生成但不执行" via
generateNoExec). Ask menu is unchanged.
- Switching mode lands on that mode's default (Ask -> generate,
Agent -> query); the shared `generate` is not carried across
because its label/semantics differ per mode. Vector DBs stay on
`generate` since their action menu is hidden and they lack SQL
tools (no execute_query contract).
- External Ask-style triggers (Fix with AI, Explain history) switch
to Ask mode when invoked from Agent mode so the action is valid
and the menu reflects what runs.
- Reset the active action to the mode default after each send.
* test(ai): cover Agent task-action contract and mode/action mapping
Lock in the deterministic parts of the Ask/Agent split so only the
LLM-behavior criteria need manual verification.
Backend (agent_loop.rs):
- query contract instructs the LLM to call execute_query and is not
treated as a SQL-producing action.
- exploreSchema contract points to list_tables/get_columns and says
not to execute data queries.
- executeAndExplain contract tells the LLM to run the current SQL.
- task actions do not require a SQL deliverable (a conclusion without
a fenced SQL block still satisfies the contract).
- query repair prompt also targets execute_query.
Frontend (aiActions.spec.ts):
- defaultActionForMode: Ask -> generate, Agent -> query (not generate).
- isValidActionForMode: generate valid in both; Ask-only actions
rejected in Agent mode and vice versa.
- ASK_ACTIONS / AGENT_ACTIONS composition (Agent menu starts with
query and still offers generate).
* fix(ai): correct action menu on mode-switched triggers and i18n gaps
Issues found during review of the Ask/Agent action split:
- [#I01] triggerAction (Fix with AI / Explain history) invoked from
Agent mode switched to Ask and set the action, but the mode-switch
watch then reset activeAction to the Ask default ("generate"),
overwriting the action just set — so the menu showed "Generate SQL"
during a fix. Add a suppressModeActionReset flag so programmatic
mode switches don't clobber the explicitly-set action.
- [#C01] Remove dead `unsupported_action` reason: buildAiAgentPlan no
longer produces it, so drop the type variant and the unreachable
skippedTitleKey case.
- [#I02] es/it/ja/pt-BR were missing the new Agent action keys
(query/exploreSchema/executeAndExplain/generateNoExec) and their
placeholders, causing English fallback in the Agent menu. Add the
translations to match each locale's existing style.
* test(ai): align app-tests with task-action split
- aiSkills: add query/exploreSchema/executeAndExplain to the expected
action set; broaden the id check (new ids are not _sql-suffixed) and
relax the userInstruction assertion (schema inspection need not mention SQL).
- aiAgentPlan: drop the unsupported_action skipped step for non-generate
actions (#C01 removed it from the plan and the reason union); add coverage
for task-oriented Agent actions not driving client-side execution.
* test(ai): pin locale in dialect prompt spec
buildSystemPrompt selects zh/en copy via currentLocale(), which reflects the
host navigator.language. The spec asserts English strings, so it failed on
zh-CN machines (e.g. Windows with a Chinese system locale) while passing on
CI's en-US runners. Pin the locale to en in beforeAll so the assertions are
deterministic regardless of the host OS locale.
* feat(ai): support editing sent user messages
Adds inline edit support for user messages in the AI chat panel.
Hover over a user message to reveal the edit button; confirming the
edit truncates all subsequent history and re-sends with the new content.
* fix(ai): fix IME composition and ref-focus regression in message edit
- Handle IME composition events in onEditKeydown to prevent accidental
submission on Enter during CJK candidate selection
- Replace per-render :ref focus callback with nextTick + data attribute
to avoid cursor jumping on every keystroke
- Extract visibleToActualIndex into aiMessageEdit.ts for testability
- Add 8 unit tests covering index mapping with contextSummary messages
* fix(ai): prevent data loss and mention pollution in message edit
- Guard connection/config before truncating messages to prevent silent data
loss when send() bails early
- Clear selectedMentions before resend to prevent stale chips from polluting
edited message content
* fix(ai): merge tool call status cards
* fix(ai): constrain markdown table overflow
* fix(ai): restore streaming of answer text via TextDelta events
The on_chunk closure was missing live AgentEvent::TextDelta emission for text content, causing the AI answer text to appear all at once after the turn completed. Reasoning deltas were unaffected.
Root cause: commit c30033628 rewrote the on_chunk closure and accidentally dropped the TextDelta emit line while keeping ReasoningDelta intact.
Fix: restore TextDelta emit in on_chunk for incremental streaming, and remove the post-turn full-TextDelta workaround which would duplicate content.
* test(ai): extract chunk_to_events and add streaming event tests
Extract the event-generation logic from the on_chunk closure into a pure function chunk_to_events() to make it testable, and add 6 unit tests covering all chunk content combinations: text-only, reasoning-only, mixed, empty, and edge cases.
This ensures a regression like the one fixed in the previous commit (where TextDelta emission was dropped while ReasoningDelta was kept) would be caught by tests.
* fix(ai): resolve Codex CLI from shell PATH on macOS
* fix(ai): hide Codex CLI subprocess windows on Windows
* feat(ai): allow to set environment variable for Codex CLI
* fix(ai): parse Codex MCP tool events
* fix(mcp): honor Postgres TLS settings in direct queries
* fix(ai): add quick proposal confirmation buttons (all locales)
When the assistant proposes an action, render Yes/No buttons below the
message so the user does not need to type a short reply — fixing the
issue where short replies caused the LLM to re-ask instead of executing.
- aiProposalDetect.ts: pure detectors for proposal sentences/short replies
- AiAssistant.vue: inline Yes/No buttons on last assistant proposal message
- ai.ts: system-prompt rule to skip re-confirmation on short affirmatives
- i18n: 3 keys added to all 7 locales (en/zh-CN/zh-TW/ja/es/it/pt-BR)
Tests: 55/55. TypeCheck: passed.
* fix(ai): add i18n keys and UI changes for proposal confirmation
* fix(i18n): add missing agent tool step translations for zh-TW, pt-BR, it, ja
* propagate explainData to agent step items for ExplainPlanViewer
* feat(ai): show safety check result for execute_query tool steps
- Add explain_query tool with structured EXPLAIN result, gated on supports_explain_plan()
- Add supports_sql_query() to gate execute_query/get_sample_data for non-SQL DBs (Redis, ES, MongoDB, etc.)
- Split agent loop tool dispatch: execute_query runs sequentially, all others run in parallel via join_all
- Wire explain_query result button to ExplainPlanViewer in AiAssistant + App.vue
- Fix O(n²) agentSteps rebuild: incremental O(1) push per event during streaming
- finally block falls back to full rebuild only when streaming push did not occur
AiAssistant.vue:
- Tool call steps now support click-to-expand/collapse for SQL args
and results (expandedSteps set); chevron rotates on open
- Remove fixed-open result display (was always visible, no toggle)
- Max result height raised to 48 (max-h-48) with scroll
ai.ts (buildModePromptLines agent branch):
- Replace vague "prioritize SQL" hint with explicit tool-use
instruction: must call execute_query, not just emit SQL text
- List available tools (list_tables, get_columns, execute_query,
get_sample_data) so LLM knows what it can call
- Clarify allowed statement types for execute_query
Move tool calling from non-streaming (complete) API calls to real
streaming SSE, so text, reasoning, and tool call arguments all arrive
incrementally — users see the AI think and act in real time.
- Extract ~370 lines of non-streaming tool-call functions from
agent_loop.rs (call_with_tools, call_openai_with_tools,
call_claude_with_tools, call_gemini_with_tools) and replace with
a single ai::stream_with_tools() dispatch call.
- Add streaming-with-tools infrastructure to ai.rs (~550 lines):
- StreamToolEvent enum: Chunk, ToolCallStart, ToolCallDelta,
ToolCallComplete — provider-agnostic, feeds into the
StreamingToolCallAccumulator
- stream_claude_with_tools(): parse SSE content_block_start/delta/
stop events, incremental input_json_delta for tool arguments
- stream_openai_with_tools(): parse SSE delta.tool_calls with
incremental function.arguments
- stream_gemini_with_tools(): parse SSE functionCall (Gemini
sends complete objects, not deltas — emit as one chunk)
- Cancellation support via tokio::select! in every streaming loop
- Extended timeout for reasoning models (600s vs 120s)
- StreamingToolCallAccumulator: collect partial tool call fragments
from streaming deltas, then deserialize into complete ToolCall
objects in index order once the stream ends.