feat: improve docs site UX and update model registry#2
Merged
johnnichev merged 1 commit intomainfrom Mar 12, 2026
Merged
Conversation
- Upgrade MkDocs Material theme with tab navigation, sticky header, footer nav, custom purple/amber color scheme, Inter + JetBrains Mono fonts, emoji support, and code annotations - Revamp docs landing page with feature cards grid, install tabs, admonition-based learning path, and Material button links - Add custom CSS for card hover effects and dark mode tweaks - Fix GPT-5.4 pricing ($5.00/$22.50 → $2.50/$15.00, was using >272K tier instead of standard pricing) - Fix Gemini 3.1 Flash-Lite: correct model ID, pricing ($0.10/$0.40 → $0.25/$1.50), and max output tokens (8192 → 65536) - Add Gemini Embedding 2 model (gemini-embedding-2-preview, $0.20/M) - Update all docs from 145 → 146 model count across 8 files - Reorganize mkdocs.yml nav into logical tab groups (Core, Providers, RAG, Security, Reference) - Allow unsafe YAML tags in pre-commit for MkDocs emoji extensions Made-with: Cursor
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.
johnnichev
added a commit
that referenced
this pull request
Mar 24, 2026
- Bug #2: async confirm_action guard in sync _check_policy (was overwritten by Batch 2) - Bug #8: SQLiteVectorStore WAL mode + threading.Lock (was overwritten by Batch 3) - Bug #10: FileKnowledgeStore atomic write via tmp + os.replace (was overwritten by Batch 3) - Fix SQLite test cleanup for WAL mode extra files
johnnichev
added a commit
that referenced
this pull request
Apr 3, 2026
1. LLM eval score injection: _extract_score now uses LAST match (not first) and strips fenced user content before extraction. Scores clamped to [0, 10] range. Prevents "Score: 10" injection via echoed user content in judge output. 2. ReDoS in PII guardrail: custom_patterns now validated with a smoke test (search against "a"*100) after compilation. Invalid patterns raise ValueError. 3. ReDoS in security screening: extra_patterns same treatment as #2. 4. Path traversal in ToolLoader.from_directory: symlink-following glob results now checked with is_relative_to() to prevent loading .py files outside the intended plugin directory. All 3343 tests pass.
17 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
Test plan
pytest tests/ -x -q)mkdocs build)Made with Cursor