Spaces:
Sleeping
Sleeping
Commit History
-
fix: Round 17 audit β critical/high bug fixes (5 bugs, cross-checked)β
- H1: validate_citations regex now matches References:/Reference/Sources (Primary) - H2: _strip_sql_comments rewritten as state machine, preserves --//**/ inside strings - H3: SQL citation count fixed: 1 source per query, not 1 per row - M1: Context budget now accounts for web context size before local allocation - M2: max_context_chars default aligned to 12000 (was 0 in code vs 12000 in docs) 10 agents dispatched: 5 audit + 3 fix + 2 cross-check. 175/175 tests passing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>f9f7706 -
fix: Round 14 β 28 Tier 1 + Tier 2 bugs fixed across 17 source filesβ
Anti-hallucination integrity (T1): - #100: Detect verification LLM system failure (all calls fail β refuse) - #101: Fix validate_citations SQL/web source matching (dead code β working) - #102: Citation count uses chunks (citable units) not unique files - #103: Clamp max_iterations to min 1 (can't bypass via iterations=0) Pre-release quality (T2 HIGH): - #104: Add LIKE ESCAPE in all SQL fallback paths - #105: Gemini safety block returns "" (was bypassing stack) - #106: Cap reasoning model budget at 128000 - #107: Handle non-numeric temperature/max_tokens gracefully - #108: Fix clarification history duplication Pre-release quality (T2 MEDIUM): - #109: Anthropic temperature clamp to 1.0 - #110: SQL query 10-second timeout via progress handler - #111: Rich markup escape for user/LLM content - #112: All 6 readers wrapped in try/except (corrupt files don't abort) - #113: Collection cache invalidation after re-ingestion - #114: Web UI message history capped at 200 - #115: Setup wizard confiβ¦f95cdb7 -
fix: pre-release audit round 12 β 33 bugs fixed across all tiersβ
Tier 1 (ship-blockers): - README/verifier layer count corrected to 7-layer/10-point - SQL keyword regex now strips quoted strings before checking - validate_citations counts unique sources, extracts from body only - Provider-specific error messages for all 3 LLM backends - Missing config error handling in ingest.py entry point Tier 2 (quality): - SQL injection: alphanumeric validation on interpolated values - LIKE wildcard escaping with ESCAPE clause - Fallback builds fresh keyword query instead of re-running failed SQL - NaN/NaT/inf filtering across all tabular readers - Merged docx table cells deduplicated via element identity - .env double-escaping fix in setup wizard - Verification LLM exceptions skip correction instead of triggering it - References check handles SQL and web sources - Dead pre-loop validate_citations removed - KB meta extension detection uses Path.suffix - QU prompt omits SQL fields when no schema available - Redundant collection.count() eliminated - Row padding fβ¦fbd18c8
-
fix: add word-level fuzzy SQL matching for country name variantsβ
Country names like Korea, Republic of do not contain South Korea as a substring, so phrase-level LIKE fails. Word-level fuzzy extracts significant content words (dropping directional/geopolitical qualifiers) and matches individually: WHERE Country LIKE %Korea%. Three-step strategy: exact -> phrase fuzzy -> word-level fuzzy. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>d4a1a18 -
fix: SQL fuzzy matching fallback for country names with alternate formsβ
Exact match (=) tried first; if 0 rows, auto-retries with LIKE '%...%'. Match type (exact/fuzzy) transparently reported in UI source summaries. Fixes queries like "South Korea" matching "South Korea (Republic of Korea)". Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>6b689a5 -
fix: strip trailing semicolons from LLM-generated SQL and add SQL-route fallbackβ
Two bugs prevented SQL retrieval from working: 1. LLMs append trailing semicolons to SQL (~90%% of the time). _validate_sql() rejected these as potential injection attacks. Fix: rstrip(';') before validation (internal semicolons still blocked). 2. When route=sql and the LLM SQL query failed, the keyword-based SQL fallback never triggered (condition excluded route=sql). Fix: expanded fallback to build fresh keyword query for route=sql. Verified end-to-end: China PTS scores now returns 49 rows (was 0). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>f97b9fe -
fix: Round 8 audit β 15 bugs fixed across 10 files (1 CRITICAL, 7 HIGH, 3 MEDIUM, 4 LOW)β
Security fixes: - CRITICAL: execute comment-stripped SQL query (not original) to prevent injection bypass - HIGH: iterative comment stripping to handle nested comment attacks - HIGH: expand dangerous SQL keyword blocklist from 11 to 23 entries - HIGH: data loss prevention β deferred clear only on first successful embed Robustness fixes: - HIGH: parse_verification_result(None) crash guard - HIGH: try/except on all verification loop generate() calls - HIGH: empty rows guard in Excel reader - MEDIUM: strict boolean normalization for verification pass/fail - MEDIUM: R-style "na" added to null string detection - MEDIUM: broad exception handling for Gemini API errors Minor fixes: - LOW: distinct error message for empty LLM response vs no sources - LOW: bounds check on setup wizard model selection - LOW: route/sql_query keys in CLI and web fallback dicts - LOW: SQL fallback extended to route="both" Cross-checked by 2 verification agents β all fixes confirmed correct. 165/165 tests passing,β¦9093d8f -
fix: 10 bugs (4 HIGH + 6 MEDIUM) from comprehensive codebase auditβ
HIGH fixes: - H1: Gemini blocked-response detection in verifier (safety filter short-circuit) - H2: Config load crash guard in app_web.py (st.stop instead of traceback) - H3: Brace-escape user text in kb_meta.py prompts (prevent KeyError) - H4: Web UI clarification state tracking (pending_clarification_question) MEDIUM fixes: - M1: Preserve leading zeros as TEXT in sql_ingest type inference - M2: Deferred clearing in ingest.py prevents data loss on total failure - M3: Strip markdown fences from LLM-generated SQL in sql_retriever - M4: max_iterations=0 guard in verifier (skip verification, do not refuse) - M5: Add clarification QA to conversation history for pronoun resolution - M6: Remove hardcoded knowledge_base/ prefix in retriever source paths Also adds CLAUDE.md, docs/plans/, full test suite (162 tests, 17 files), and updates WORKLOG.md with audit results. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>1330e5c -
fix: 6-agent debug audit β 8 bugs fixed across codebaseβ
Multi-agent systematic audit found and fixed: HIGH: - Empty model="" overrode provider defaults, causing API errors when no model configured (llm/__init__.py + all 3 providers) - Vector-to-SQL fallback was dead code β QU layer now preserves sql_query regardless of route, and prompt asks LLM to generate fallback sql_query - SQL validation strengthened with keyword blocklist (INSERT, DELETE, DROP, ALTER, CREATE, ATTACH, DETACH, PRAGMA, LOAD_EXTENSION) β first layer of two-layer SQL injection defense MEDIUM: - Verification prompt no longer leaks internal chunk ID naming (CHUNK-LOCAL, CHUNK-SQL) into correction loop β uses user-facing language instead - config_loader now gives friendly FileNotFoundError directing user to run setup.py, instead of raw traceback - config.yaml opened with explicit encoding="utf-8" for cross-platform safety - OpenAI model filter narrowed from startswith("o") to startswith("o1","o3","o4") 153 tests pass (152 existing + 1 new SQL validation test). β¦106354e -
fix: harden route parsing, column dedup, and column name accessβ
- Normalize QU route output (strip/lowercase) before validation - Fix column name deduplication to handle suffix collisions (e.g., 'Score_A', 'Score_A', 'Score_A_2' no longer produces duplicates) - Use defensive .get() for column name access in SQL result formatting Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>a8fd301 -
fix: 7 bugs from multi-agent debug review of SQL layerβ
- Column name deduplication after sanitization (Score-A/Score_A collision) - _safe_str() preserves None in Stata/SPSS/R data loaders - Reject inf/Infinity in column type inference - Guard against n=1 in _get_sample_values (ZeroDivisionError) - NULL values render as "N/A" in SQL context (not "None") - Defensive .get() in build_schema_summary for malformed schema - Backtick-quoted table names in _extract_table_from_query regex Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>d6a01c7 -
fix: 4 bugs found during comprehensive code reviewβ
- Sort sample values numerically when all values are numeric (was lexicographic) - Handle CSV BOM (utf-8-sig) so Excel-exported CSVs do not corrupt first header - Wrap file_path.relative_to() in try/except to prevent crash on edge-case paths - Fix schema summary colon placement (was appended after description instead of header) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>86e20a0 -
feat: add LLM-powered column descriptions with codebook detectionβ
During SQL ingestion, each table columns are now described by the LLM: 1. Search same directory for codebook/documentation files (PDF, DOCX, TXT, MD) 2. If codebook found, pass its text + column metadata to LLM for descriptions 3. If no codebook, LLM infers column meanings from names, types, samples 4. Descriptions stored in sql_schemas.json alongside existing column metadata Column descriptions are always visible to the chatbot: - build_schema_summary() includes descriptions in the QU prompt - format_sql_results_as_context() includes descriptions with SQL results - Graceful degradation: LLM failure is non-fatal Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>3d1d5b4 -
fix: include sample values in SQL schema summary for better query generationβ
The LLM was generating SQL queries with wrong column values (e.g., guessing country name format) because the schema summary only showed column names and types. Now includes up to 3 sample values per column so the LLM can see actual data format (e.g., Country: "China", "United States", "Brazil"). Before: - table (N rows): Country (TEXT), Year (INTEGER) After: - table (N rows, from PTS/data.xlsx): Country (TEXT) e.g. "China", "United States" Year (INTEGER) e.g. "1976", "2000" This fixes the issue where asking "PTS scores for China" would route to SQL but generate queries that returned no results. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>353f65a
-
fix: prevent NameError when QU disabled and fix connection leakβ
- Add route="vector" and sql_query=None defaults before the `if qu_enabled:` block in both app_cli.py and app_web.py, preventing NameError when query understanding is disabled. - Wrap sqlite3 connection in try/finally in sql_retriever.py to ensure conn.close() runs even if execute/fetchmany raises. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>39c2d11 -
feat: add SQL result formatting and schema summary builderβ
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>203c044 -
feat: add SQL retriever β validated read-only query executionβ
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>54bc2bb