Add a self-evolution subsystem that reviews idle conversations in an
isolated agent and durably learns from them — patching/creating skills,
finishing unfinished tasks, and backfilling missed memory.
- Trigger: background idle scan, fires when a session is idle >= N min AND
(>= N turns OR context usage > 80%). In-memory cursor reviews only new
messages so a session never re-learns old content.
- Isolated review agent: same model, restricted toolset, hard write-guard
confining edits to the workspace (built-in skills are protected).
- Safety: file-level backup before edits + evolution_undo tool; notify the
user ONLY when a workspace file actually changed (no-nag rule); capped
concurrency.
- Records to memory/evolution/<date>.md, surfaced in the memory UI's
renamed "Self-Evolution" tab (merged with dream diaries).
- Hide internal [SCHEDULED]/[EVOLUTION]/backup_id markers from chat history
display (also fixes scheduler marker leakage) while keeping them in stored
content for undo.
- Flat config: self_evolution_enabled (default off until release),
self_evolution_idle_minutes (15), self_evolution_min_turns (6).
- Tests: tests/test_evolution.py (stub + real model modes, 7 scenarios).
- Add language labels and copy buttons to code blocks
- Enhance drag-and-drop to full chat view
- Fix data consistency bugs in message operations
- Use RLock to prevent deadlock in conversation store"
Replace the broad `~/.cow` directory check with a regex that matches
only the credential file path (`\.cow[/\\]\.env`), so legitimate access
to other `~/.cow/` subdirectories (e.g. skills) is no longer blocked.
Drop the incomplete env/printenv blocking rule per reviewer feedback.
Rewrite test_invariant_bash.py to use the correct Bash().execute()
API and cover both the blocked and allowed cases.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
_stdio_send (single pipe) must remain serialized under _call_lock,
but SSE and streamable-http use independent HTTP requests and can
safely execute concurrently across sessions.
- Scope _call_lock to stdio transport only
- Add _http_lock with double-checked pattern to protect _http_session_id
initialization during concurrent streamable-http requests
- Use reader thread + queue.Queue instead of select.select() which does not
work with pipes on Windows (only sockets)
- Make MCP server timeout configurable via mcp.json (default 120s)
- Validate JSON-RPC response id to skip stale responses from timed-out calls
- Log MCP server stderr at WARNING level instead of DEBUG for visibility
- numpy soft dependency: try/except import + _HAS_NUMPY flag; _encode_embedding
and _decode_embedding fall back to struct.pack/unpack; search_vector falls back
to pure-Python cosine loop — startup never fails without numpy reinstalled
- SQLite UPSERT guard: _HAS_UPSERT = sqlite_version_info >= (3,24,0); save_chunk
and save_chunks_batch fall back to INSERT OR REPLACE on SQLite < 3.24 with a
one-time startup warning about potential FTS rowid drift
- _bm25_rank_to_score floor: 0.3 + 0.69*(|rank|/(1+|rank|)) → always in [0.3, 0.99),
prevents small-corpus matches scoring 0.0 and being filtered by min_score
- detect_index_dim BLOB-aware: check isinstance(raw, bytes) first and return
len(raw)//4 before json.loads, so /memory status works after embedding format switch
- Comment: "CJK single-char" → "CJK tokens shorter than 3 characters"
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
matched_count only counted cjk_words hits; pure ASCII queries had
cjk_words=[] so matched_count=0 and all SQL-matched rows were filtered
out. Change to count across all tokens (cjk_words + ascii_words) so
the LIKE fallback works correctly when FTS5 is unavailable.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Search tool now supports 4 backends with unified output (bocha,
qianfan, zhipu, linkai) and a routing layer:
- strategy 'auto' (default): pick first configured in canonical order
bocha > qianfan > zhipu > linkai
- strategy 'fixed': pin a specific provider
- agent may pass `provider` to override per-call (only exposed when
≥2 providers configured + auto strategy)
Add embedding_provider config knob with native support for
openai / dashscope / doubao / zhipu / linkai, plus an in-chat
/memory status and /memory rebuild-index workflow for switching
vendors safely.
When reloading a conversation, failed tool calls incorrectly showed checkmark instead of X because the is_error field was lost in the history rendering pipeline. Propagate is_error from DB extraction through to the frontend rendering to match the live SSE behavior.
Browser sessions now reuse a Chromium user profile across runs by default
(`~/.cow/browser_profile`), so users only log in to a site once.
Three launch modes are selectable via `tools.browser` in config.json:
- persistent (default): Playwright Chromium with a persistent user_data_dir
- cdp: attach to an externally launched real Chrome via `cdp_endpoint`
(full fingerprints, ideal for sites with strict bot detection)
- fresh: clean context every run, set `persistent: false`
Also:
- Self-heal when the user closes the browser window mid-session: detect
closed page/context/browser via close listeners and exception scanning,
then transparently relaunch on the next request.
- Graceful CDP shutdown: disconnect only, never kill the user's Chrome.
- Friendly errors when the CDP endpoint is unreachable or the persistent
profile is locked, so the LLM can guide the user instead of looping.
- Fix tool config being silently overwritten by workspace config in
AgentInitializer; per-tool user settings (e.g. browser.cdp_endpoint)
are now merged instead of replaced.
- Update zh / en / ja docs with the new login-persistence section,
including the Chrome 137+ requirement to pair --remote-debugging-port
with a dedicated --user-data-dir.
Boot MCP servers (npx/uvx) on a background thread instead of blocking
agent init. Built-in tools serve traffic immediately while MCP comes
online; each new agent reads whatever is ready at creation time.
Idempotent via _mcp_loaded flag — concurrent sessions never re-fork
subprocesses. Per-server failures are isolated and warmup is triggered
in app.py so loading overlaps with channel startup.
Stability fixes in mcp_client.py:
- Fix stderr buffer overflow: start daemon thread to continuously drain
stderr pipe, preventing 64KB buffer fill that blocks child process
- Fix notification interference: loop readline and skip JSON-RPC messages
without 'id' field (notifications) instead of treating them as responses
- Fix concurrent race condition: wrap send+receive in _call_lock so
multiple sessions cannot interleave reads/writes on the same client
- Fix missing timeout: use select.select() with 30s timeout in
_readline_with_timeout() to prevent infinite block on dead MCP server
Config improvements in tool_manager.py:
- Add _normalize_mcp_configs() to support both list format (mcp_servers)
and dict format (mcpServers used by Claude Desktop / Cursor)
- Add _load_mcp_configs() to load from ~/cow/mcp.json first, falling back
to config.json mcp_servers field for backward compatibility
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Two bugs found during end-to-end validation with Amap and Chrome DevTools
MCP servers:
1. MCP tools were loaded into ToolManager._mcp_tool_instances but never
added to the agent's tool list. AgentInitializer._load_tools() only
iterated tool_classes (built-in tools). Added a second pass to append
all MCP tool instances.
2. When a MCP server config contains an "env" dict, it was passed directly
to subprocess.Popen, replacing the entire process environment. This
caused npx to fail because PATH and other inherited vars were missing.
Fixed by merging config env on top of os.environ.
Validated with:
- @amap/amap-maps-mcp-server (12 tools, stdio + API key env var)
- chrome-devtools-mcp (29 tools, stdio + remote debugging port)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
