Introduce ConfigStorage abstraction and LLMConfigStore class with
dependency injection for i18n, UUID generation, and auth profile hooks.
All CRUD operations (add/update/delete/slots) are platform-agnostic.
Electron can implement ConfigStorage with fs + getAiDataDir.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move platform ID collision detection, normalization, conflict detection,
member merge, and message dedup-sort from electron/main/merger to a
shared package with zero Node.js dependencies.
Also fix pre-existing unused-variable TS errors in summary test.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move session summary generation (573 lines) to shared package with
SummaryDeps injection for DB/LLM/i18n. Pure algorithms (isValidMessage,
filterValidMessages, splitIntoSegments, prompt builders) are now shared.
Electron summary/index.ts implements SummaryDeps and delegates.
Added 14 unit tests covering message filtering, segmentation,
summary generation, and eligibility checks.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move AgentEventHandler, TokenUsage, AgentRuntimeStatus, AgentStreamChunk
to packages/node-runtime/src/ai/agent/event-handler.ts.
Token estimation and event-to-chunk mapping are now shared.
Electron agent/types.ts re-exports from node-runtime.
Added 8 unit tests covering token estimation, tool tracking, usage cloning.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move buildSystemPrompt from electron/main/ai/agent/ to shared package.
i18n t() is now injected via BuildSystemPromptOptions parameter.
Types OwnerInfo, MentionedMember, SkillContext are shared.
Electron prompt-builder.ts injects its own t() and delegates.
Added 8 unit tests with mock translation function.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move tokenizeForFts and tokenizeQueryForFts from electron/main/nlp/ to
packages/node-runtime/src/nlp/fts-tokenizer.ts. Uses the already-shared
getJieba() internally. Electron ftsTokenizer.ts now re-exports.
Added 9 unit tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move remote LLM API operations into shared module with optional
headers and logger injection. Electron wraps with UA headers and
aiLogger; server re-exports directly.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move URL normalization helpers and PiModel construction into a shared
llm-builder module. Electron and server both delegate to the core
builder, with Electron adding optional headers and provider validation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move the file-based AI logging implementation from Electron-specific
code to a shared AiLogger class in @openchatlab/node-runtime. Both
Electron and Server/CLI now use the same logger writing to
~/.chatlab/logs/ai/. Server-side agent, tool adapter, and compression
now produce the same structured log files as Electron.
The 4-file preprocessor wrapper directory was entirely re-exports from
@openchatlab/node-runtime after the pipeline unification. Replace all
consumers with direct imports and add logger injection support to
PreprocessingPipelineOptions so Electron retains aiLogger integration.
Unify the duplicated preprocessing logic between Electron (wrapWithPreprocessing)
and Server (applyPreprocessing) into a single applyPreprocessingPipeline() function
in @openchatlab/node-runtime. Both platforms now delegate to the same implementation,
eliminating ~50 lines of redundant code and fixing a redundant token counting bug
in the Server version.
- Create runAgentCore() in node-runtime/src/ai/agent/ encapsulating
PiAgentCore construction, history conversion, event subscription,
abort forwarding, tool round management, and usage collection
- Re-export pi-agent-core/pi-ai types (AgentTool, Type, Model, etc.)
and functions (completeSimple, streamSimple) from node-runtime
- Refactor Server agent.ts to use runAgentCore, removing all direct
pi-agent-core/pi-ai imports (~335→~210 lines)
- Remove pi-agent-core and pi-ai from Server package.json dependencies
- Refactor Electron agent/index.ts and event-handler.ts to use
runAgentCore with DI hooks (streamFn, onConvertToLlm, onDebugContext)
- Document remaining Electron pi-ai usage points for future migration
Move compression logic from Electron to shared package with pluggable
LLM adapter interface. Integrate into server agent with pre-run
compression support. Electron side becomes a thin compatibility wrapper.
Extract SkillManager from Electron to @openchatlab/node-runtime.
Create shared createActivateSkillTool factory.
Integrate skill menu into server agent system prompt and SSE route.
- Extract AIConversationManager to @openchatlab/node-runtime for Electron + Server reuse
- Add /_web/ai/conversations/* HTTP endpoints for conversation/message CRUD
- Create FetchAIAdapter to replace WebAIAdapter stub
- Implement server-side Agent with SSE streaming (/_web/ai/agent/stream)
- Add agentApi SSE client shim in frontend registry
- Migrate API key storage from encrypted llm-config.json to auth-profiles.json
- Add @openchatlab/config auth-profiles module for credential management
Move platform-agnostic NLP types, stopwords, POS tag definitions, and
text utilities into @openchatlab/core. Move segmenter engine, word
frequency computation, and dict manager into @openchatlab/node-runtime.
Electron nlp/ becomes a thin re-export layer; server nlp.ts shrinks
from ~450 to ~85 lines retaining only HTTP route definitions. Both
platforms now share the same NLP implementation via node-runtime.
Also fixes createJiebaNlpProvider to use shared getJieba() with disk
dict loading (was using empty Jieba instance causing degraded POS tags
in language preference analysis), adds ensureDefaultDict at server
startup, and adds /_web/nlp/* HTTP routes with window.nlpApi shim.
Split PathProvider into dual-root architecture: systemDir (~/.chatlab/)
for config/logs/cache/ai/settings, and userDataDir (~/.chatlab/data/ by
default) for chat databases. Both Electron and CLI share the same
config.toml for user_data_dir resolution.
- Refactor PathProvider interface (getSystemDir + getUserDataDir)
- Update config schema (data.dir → data.user_data_dir)
- Add writeConfigField() for config.toml manipulation
- Fix needsUnifiedDirMigration() to detect old Electron data even when
user_data_dir was already set by CLI (compare paths instead of
checking existence)
- Fix streamImport error handling: close db before deleting files on failure
- Add POST /_web/sessions/:id/query endpoint for parameterized readonly SQL
- Expose PreparedStatement.readonly property in DatabaseAdapter interface
- Fix Fastify error handler to respect statusCode on non-ApiError errors
- Implement FetchAdapter.pluginQuery via HTTP endpoint
- Add web-api-shim.ts: window.chatApi/aiApi polyfills for chart-* and
MessageList (pluginQuery, pluginCompute, getMemberActivity,
getAvailableYears, message browsing methods)
- Fix Sidebar: navigate to home after deleting the currently viewed session
Add rebuild-native.sh script that compiles better-sqlite3 in an isolated
temp directory for system Node.js, storing the binary at packages/server/native/.
DatabaseManager and openBetterSqliteDatabase now accept nativeBinding option.
CLI auto-detects non-Electron environment and uses the isolated binary.
Phase 1.7: add DatabaseManager to @openchatlab/node-runtime that handles
opening, caching, listing, and closing chat session databases using the
DatabaseAdapter and PathProvider interfaces from core.
Phase 1.3: implement PathProvider for CLI/service mode using
~/.chatlab/data/ as default data directory with CHATLAB_DATA_DIR
environment variable override support.
Phase 1.2: create @openchatlab/node-runtime package with better-sqlite3
adapter that implements the DatabaseAdapter interface from core. Also add
pragma() method to the DatabaseAdapter interface.
diguaandCursor