Commit Graph
6 Commits
Author SHA1 Message Date
Abeautifulsnow ff31f44b42 feat(ai): surface live AI generation status with smooth timing 2026-08-24 20:28:12 +08:00
Abeautifulsnow 12da615daa fix(ai): require exact SQL confirmation for agent writes 2026-08-21 10:36:17 +08:00
Guoyu Su c7e7b7c9d9 feat(ai): unify model discovery and effort handling 2026-07-28 21:37:55 +08:00
Abeautifulsnow c300336281 feat(ai): context window management and token usage tracking
* @
feat(ai): add conversation context management and token usage tracking (Phase 4)

## Background
Phase 4 of AI agent loop upgrade: token usage extraction from LLM responses,
cost estimation display, and automatic context window management (summarization
when approaching limits).

## Changes

### Backend (Rust)
- New token_usage::TokenUsage — cross-turn token accumulation
- New agent_loop::maybe_compact — proactive context compaction: token estimation
  → cut-point selection → LLM summarization → fallback summary
  → tool-pair integrity protection → drain/insert
- New agent_loop::context_window_for_model — auto-detect context window by model
- New agent_loop::is_context_length_error — detect upstream context-length errors
- New agent_loop::compact_tool_result_for_context — JSON/text sampling for large results
- Modified agent_loop::run_agent_loop — pre-turn compaction check, retry on context error
- Modified agent_events::AgentEnd — split total_tokens into input_tokens/output_tokens
- New agent_events::ContextCompacted — compaction event with metrics
- New AiConfig.context_window — user-configurable context window size
- New AiChatMessage.kind — context summary message marker
- Modified stream_with_tools & 3 provider stream functions — extract TokenUsage
  - Claude: message_start(input) + message_delta(output)
  - OpenAI: stream_options { include_usage } → final usage chunk
  - Gemini: usageMetadata per chunk, keep last

### Frontend (TypeScript/Vue)
- AiAssistant.vue: token + cost display row, estimateCost() with 7 model families,
  contextCompacted UI step, pendingCompaction deferred apply,
  messagesForAgentHistory post-compaction history reconstruction
- EditorSettingsDialog.vue: contextWindow input (min=1000, auto-detect)
- settingsStore.ts: AiConfig.contextWindow field
- tauri.ts: AgentEvent type updates, AiChatMessage.kind
- i18n: 6 new keys in en.ts and zh-CN.ts

## Fixed Issues
- messages[0] dropped from LLM context after compaction
- estimate_text_tokens hard threshold causing 2.8x estimate jump
- context_compacted event field semantics mismatch with frontend insert position
- validate_summary English-only keywords causing fallback on non-English LLMs
- Stale agentTokens after conversation switch
@

* remove cost computation logic
2026-06-15 18:55:22 +08:00
Abeautifulsnow d845a318c6 feat(ai-agent): Phase 3 — explain_query tool, parallel/sequential execution, DB gating (#1187)
- 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
2026-06-15 13:14:59 +08:00
Abeautifulsnow 082e3bb4eb feat(ai): add agent tool calling loop 2026-06-12 13:18:36 +08:00