Merged
Conversation
Add five new memory and persistence features: - Persistent Sessions: SessionStore protocol with JSON file, SQLite, and Redis backends. Auto-save/load via AgentConfig with TTL expiry. - Summarize-on-Trim: LLM-generated summaries of trimmed messages injected as system context to preserve conversation history. - Entity Memory: LLM-based named entity extraction with deduplication, LRU pruning, and system prompt injection. - Knowledge Graph Memory: Relationship triple extraction with in-memory and SQLite storage, keyword-based querying. - Cross-Session Knowledge: Daily logs + persistent facts with auto-registered remember tool for durable memory across conversations. Also includes: - 4 new AgentObserver events (total: 19) - 5 new trace step types - 182 new tests (total: 1365) - 4 new module docs, 5 new examples (33-37) - Updated ARCHITECTURE, QUICKSTART, notebook, README, CHANGELOG, ROADMAP - Version bump: 0.15.0 -> 0.16.0 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
johnnichev
added a commit
that referenced
this pull request
Mar 24, 2026
Security: - Path traversal in JsonFileSessionStore — validate session_id (#9) - Unicode homoglyph bypass in injection screening — NFKD + zero-width strip + homoglyph map (#13) Data integrity: - FileKnowledgeStore._save_all() atomic write via tmp + os.replace (#10) - JsonFileSessionStore.save() atomic write (#31) Agent core: - astream() uses self._effective_model (was self.config.model) (#1) - Sync _check_policy rejects async confirm_action with clear error (#2) - Sync _streaming_call isinstance(chunk, str) guard (#18) Providers: - FallbackProvider stream()/astream() record success after consumption, not before — circuit breaker now works for streaming (#3) - Gemini response.text ValueError catch for tool-call-only responses (#4) Tools: - aexecute() uses run_in_executor(None) shared executor (#5) - execute() awaits coroutines from async tools via asyncio.run (#6) RAG: - Hybrid search O(n²) → O(1) via text_to_key dict lookup (#7) - SQLiteVectorStore thread safety + WAL mode (#8) Evals: - OutputEvaluator catches re.error on invalid regex (#11) - JsonValidityEvaluator respects expect_json=False (#12) 16 new regression tests. Full suite: 2000 passed.
25 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
SessionStoreprotocol with 3 backends (JSON file, SQLite, Redis), TTL expiry, auto-save/load viaAgentConfigMEMORY.mdwith auto-registeredremembertoolStats
Test plan
pytest tests/ -k "not e2e" -x -q— 1352 passed, 0 failuresflake8 src/— cleanmypy— passed (via pre-commit)bandit— passed (via pre-commit)mkdocs build— passes, no broken linkspython3 -m build && twine upload dist/*🤖 Generated with Claude Code