Spaces:
Running
Running
Commit History
25 days ago
-
fix : model fix
29b315d
26 days ago
-
fix : model fix
3cfec19 -
fix(security): mask Gemini API key in logs, downgrade NIM/Groq model strings, add challenge license
b1b706a -
fix(api): fix HTTP 500 on reply endpoint due to kwarg mismatch and missing schema
bd72f20
27 days ago
-
fix(api): enforce strict version idempotency for context ingestion
90962fb -
fix(api): add root endpoint redirect to prevent HF Space UI 404s
d896c38 -
fix(core): resolve caching, lazy load, and thread leak defects
- Prevent generic fallback response from caching and poisoning state. - Read LOCAL_7B_P95 from environment variables instead of a magic hardcoded number. - Refactor local tier to stream generation and abort executor thread if deadline is exceeded. - Remove over-broad words 'JSON' and 'system' from default taboo list. - Wrap local model loading in a lazy-load function to prevent HF space boot failure.86a56f9
28 days ago
-
docs: add comprehensive system architecture mermaid diagram
c86035c -
ci: configure keepalive cron with active hf space url
f63a171 -
refactor(core): decouple logic from entrypoint and harden local slm constraints
- Extract LLM provider tiering, prompting, and retry logic from app.py into dedicated scripts/ modules. - Implement strict LlamaGrammar enforcement for Qwen2.5-3B local tier to eliminate JSON malformations. - Introduce validation+repair loop catching taboo constraints, word-count limits, and CTA proliferation. - Introduce dynamic budget checks for cloud-tier retries to prevent local starvation. - Fix FEW_SHOT_EXAMPLES substring-matching issue to correctly map all data triggers. - Restore TRIGGER PRIMACY in the local system prompt and configure local temperature (0.2) for optimal variance vs grounding. - Polish README and architecture documentation.c1c5ecb
29 days ago
-
fix(build): add huggingface-hub dependency for from_pretrained
ab1b502 -
fix(app): resolve powershell string syntax error
83dda90 -
fix(app): use Llama.from_pretrained to auto-download GGUF from hub
540645f -
fix(build): remove ollama from dockerfile & add cpu wheel index
026fe1f
30 days ago
-
docs: update README to version 1.0 and document 4-tier architecture
00235a3 -
Merge pull request #1 from i-win-again/main
Rachit Mangawajfvj0cfbac9
25 days ago
-
deleted bload and updated judge sim and gitignore
2dc82f8 -
feat: implement 4-tier LLM fail-fast cascade & benchmark-based local 3B selection
6b1caf3 -
new files
a38eb61
30 days ago
-
deleted bload and updated judge sim and gitignore
aedf01f
-
feat: implement 4-tier LLM fail-fast cascade & benchmark-based local 3B selection
e67482e -
new files
6f519fd -
final commit
Rachit-Mangawa6d6ea97
-
final commit
Rachit-Mangawa19836c6
-
feat: implement high-intelligence model rotation pool (v8.0) and align infrastructure
Rachit-Mangawa9e6280a
-
fix(infra): align Docker port with README and app.py (8080)
Rachit-Mangawad892581 -
feat: Scalable Multi-Agent Orchestrator (v7.0) with Multi-Key Rotation and FAST_TEST mode
Rachit-Mangawa08b98ed -
feat(infra): implement 5-tier hierarchical inference engine with key rotation
Rachit-Mangawa42c83f7 -
docs: generate high-fidelity Platinum v4.1 technical documentation
Rachit-Mangawafd5b9aa -
fix: apply critical tick timeout fix and schema elasticity for perfect 50/50 score
Rachit-Mangawa3858fba -
fix(infra): upgrade OpenRouter hierarchy and sanitize health check schema
Rachit-Mangawa2ce8902 -
fix(api): refactor OpenRouter call with model hierarchy and mandatory headers
Rachit-Mangawa83674d5 -
perf: reduce num_predict to 80 for sub-20s inference on CPU
Rachit-Mangawabe5289d -
perf: optimize local inference speed and increase internal timeout to 28s
Rachit-Mangawaf673c95 -
fix: sanitize health check schema and relocate model status to metadata
Rachit-Mangawaa219be1 -
feat: Upgrade to Llama 3.2 (3B) for superior autonomous reasoning
Rachit-Mangawa7580459 -
feat: evidence-based grounding anchors with generalized system prompt
Rachit-Mangawa801d089 -
fix: resolve message field mismatch, add hostility detection, and refine intent transition
Rachit-Mangawa7e9d7e2 -
feat: prioritize seasonal beats and trend signals for knowledge-driven engagement
Rachit-Mangawab583ed9 -
feat: Autonomous Local-First Engine (SmollM2-1.7B) with API fallback
Rachit-Mangawac508545 -
perf: Optimize for 30s timeout w/ SmollM2-1.7B and parallel execution
Rachit-Mangawa4be69d9 -
fix(deploy): add zstd dependency for ollama extraction
Rachit-Mangawac21f62a -
fix(deploy): use official ollama install script to fix 404 binary error
Rachit-Mangawad3dc97d -
feat: Integrate local Phi-3.5 fallback for API resilience
Rachit-Mangawa7f971bd
-
docs: update README.md with caveman style and HF metadata
Rachit-Mangawa323c8ef -
chore(deploy): add README.md with Hugging Face Space configuration
Rachit-Mangawa9d5af77 -
refactor(deploy): use direct git push to bypass sync action API bug
Rachit-Mangawa45ac092 -
fix(deploy): explicitly set private boolean to fix HF 400 error
Rachit-Mangawab6cb752 -
fix: switch to stable community sync action
Rachit-Mangawa952b95e -
fix: switch to official huggingface sync action
Rachit-Mangawac0d22dd