Commit History

Fix TypeScript error: remove invalid role check in user message branch
b312316
Running

Pulastya B commited on

Fix ChatMessage object handling in pruning logic
6a89a08

Pulastya B commited on

Fix Mistral message ordering: remove orphaned tool messages during pruning
b54c2e5

Pulastya B commited on

Add comprehensive final summary instructions to system prompt
b7bc364

Pulastya B commited on

Fix enhanced summary crash: handle best_model dict structure and add fallback
7f3326d

Pulastya B commited on

Fix session memory: preserve uploaded files for follow-up requests
b213e33

Pulastya B commited on

Fix plot rendering: extract from workflow_history, remove debug code, update system prompt
5992afe

Pulastya B commited on

debug: Add always-visible red debug box
c82abb7

Pulastya B commited on

debug: Add visible debug section for plots
154fb5a

Pulastya B commited on

fix: Extract plots from workflow_history like reports
55d3b25

Pulastya B commited on

debug: Add console logging for plot extraction
7ea590f

Pulastya B commited on

fix: Extract plots from ALL visualization tools
f898051

Pulastya B commited on

feat: Add inline plot viewing in chat
49fbcb2

Pulastya B commited on

feat: Enhanced summary with metrics and plot URLs
fad6660

Pulastya B commited on

Fix: Handle infinity/NaN values in JSON serialization
84d9eaa

Pulastya B commited on

Fix: Add mock tool responses for all blocking points
24ea09f

Pulastya B commited on

Fix: Add Mistral tool extraction support
fed3e24

Pulastya B commited on

Fix: Strip whitespace from API keys
50f9263

Pulastya B commited on

Fix Mistral import and API method
9ae6bf4

Pulastya B commited on

Fix Mistral package version - use >=0.0.7 instead of >=1.0.0
2d15e4f

Pulastya B commited on

Add Mistral AI integration - 1B tokens/month (33x Groq limits)
be4eb33

Pulastya B commited on

Fix Phase 1 errors: schema extraction and message type handling
7d775b3

Pulastya B commited on

Refactor: Move workflow context out of LLM prompts into structured state
2797314

Pulastya B commited on

Fix TPM rate limiting: Add automatic retry with delay parsing
3e672a1

Pulastya B commited on

Remove Gemini fallback and improve rate limit error messages
7c2ff18

Pulastya B commited on

Fix UnboundLocalError on Gemini fallback
523d661

Pulastya B commited on

Fix syntax error: Proper try-except indentation in compression function
5fb3ea4

Pulastya B commited on

Fix compression crash: Add defensive checks for model data structure
230b136

Pulastya B commited on

Fix TPM rate limiting: Add token budget management for Groq 12K/min limit
c206ce6

Pulastya B commited on

fix: Correct indentation in _compress_tool_result method
74cd041

Pulastya B commited on

feat: Add production-grade tool result compression for Groq
f35ddc4

Pulastya B commited on

fix: Suppress harmless multiprocessing warnings from ydata-profiling
1ab1ded

Pulastya B commited on

fix: Support follow-up requests without re-uploading file
ba50130

Pulastya B commited on

fix: Configure high-quality ydata profiling for HuggingFace 16GB RAM
bdf714a

Pulastya B commited on

fix: Update Groq SDK to >=0.13.0 for httpx compatibility
e873289

Pulastya B commited on

docs: Add comprehensive guide for dynamic prompt system
72a3bd7

Pulastya B commited on

feat: Add dynamic prompt system for small context window models (Groq support)
b8bcf55

Pulastya B commited on

fix: Use stable gemini-2.5-flash instead of experimental model with stricter rate limits
562b130

Pulastya B commited on

fix: Support both GOOGLE_API_KEY and GEMINI_API_KEY env vars for HuggingFace compatibility
fde5dd3

Pulastya B commited on

feat: Migrate to HuggingFace Spaces for 16GB free RAM
09cd93c

Pulastya B commited on

fix: Auto-optimize ydata profiling for memory constraints
f1ab2a8

Pulastya B commited on

fix: Clarify report intent and fix parameter issues
4d07a53

Pulastya B commited on

fix: Handle output_dir parameter mismatch in ydata_profiling
03b24f8

Pulastya B commited on

fix: Show report view buttons for all analysis responses
d6ba760

Pulastya B commited on

fix: Correct ToolCall object structure for Gemini text parser
943877f

Pulastya B commited on

feat: Implement text-based tool calling for Gemini (ReAct pattern)
0310ce5

Pulastya B commited on

fix: Remove system_instruction parameter from chat endpoint
eeeb8b7

Pulastya B commited on

fix: Add Gemini safety settings and handle blocked responses
f8fdbd6

Pulastya B commited on

fix: Remove Gemini tool calling - use text-only mode
8cbfaa1

Pulastya B commited on

chore: Force Render rebuild - clear Docker cache
9a765c3

Pulastya B commited on