Hugging Face's logo

Spaces:
MCP-1st-Birthday
/
DeepBoner
Running

App Files Community
1
DeepBoner / docs /bugs /ACTIVE_BUGS.md
VibecoderMcSwaggins's picture
VibecoderMcSwaggins
fix: Resolve Free Tier synthesis issue with server-side API keys
a205fc5
preview code
|
raw
history blame contribute delete
4.02 kB

A newer version of the Gradio SDK is available: 6.1.0

Upgrade

Active Bugs

Last updated: 2025-11-30

Note: Completed bug docs archived to docs/bugs/archive/ See also: Code Quality Audit Findings (2025-11-30)

P0 - Blocker

(None)

P1 - Important

P1 - Memory Layer Not Integrated (Post-Hackathon)

Issue: #73 Spec: SPEC_08_INTEGRATE_MEMORY_LAYER.md

Problem: Structured memory (hypotheses, conflicts) is isolated in "God Mode" only. Solution: Extract memory into shared service, integrate into Simple and Advanced modes. Status: Spec written. Blocked until post-hackathon.

Resolved Bugs

P0 - Free Tier Synthesis Incorrectly Uses Server-Side API Keys FIXED

File: docs/bugs/P1_SYNTHESIS_BROKEN_KEY_FALLBACK.md Found: 2025-11-30 (Testing) Resolved: 2025-11-30

  • Problem: Simple Mode crashed with "OpenAIError" on HuggingFace Spaces when user provided no key but admin key was invalid.
  • Root Cause: Synthesis logic bypassed the Free Tier judge and incorrectly used server-side keys via get_model().
  • Fix: Implemented synthesize() in HFInferenceJudgeHandler to use free HuggingFace Inference, ensuring consistency with the judge phase.

P0 - Synthesis Fails with OpenAIError in Free Mode FIXED

File: docs/bugs/P0_SYNTHESIS_PROVIDER_MISMATCH.md Found: 2025-11-30 (Code Audit) Resolved: 2025-11-30

  • Problem: "Simple Mode" (Free Tier) crashed with OpenAIError.
  • Root Cause: get_model() defaulted to OpenAI regardless of available keys.
  • Fix: Implemented auto-detection in judges.py (OpenAI > Anthropic > HuggingFace).
  • Added extensive unit tests and regression tests.

P0 - Simple Mode Never Synthesizes FIXED

PR: #71 (SPEC_06) Commit: 5cac97d (2025-11-29)

  • Root cause: LLM-as-Judge recommendations were being IGNORED
  • Fix: Code-enforced termination criteria (_should_synthesize())
  • Added combined score thresholds, late-iteration logic, emergency fallback
  • Simple mode now synthesizes instead of spinning forever

P3 - Magentic Mode Missing Termination Guarantee FIXED

Commit: d36ce3c (2025-11-29)

  • Added final_event_received tracking in orchestrator_magentic.py
  • Added fallback yield for "max iterations reached" scenario
  • Verified with test_magentic_termination.py

P0 - Magentic Mode Report Generation FIXED

Commit: 9006d69 (2025-11-29)

  • Fixed _extract_text() to handle various message object formats
  • Increased max_rounds=10 (was 3)
  • Added temperature=1.0 for reasoning model compatibility
  • Advanced mode now produces full research reports

P1 - Streaming Spam + API Key Persistence FIXED

Commit: 0c9be4a (2025-11-29)

  • Streaming events now buffered (not token-by-token spam)
  • API key persists across example clicks via gr.State
  • Examples use explicit None values to avoid overwriting keys

P2 - Missing "Thinking" State FIXED

Commit: 9006d69 (2025-11-29)

  • Added "thinking" event type with hourglass icon
  • Yields "Multi-agent reasoning in progress..." before blocking workflow call
  • Users now see feedback during 2-5 minute initial processing

P2 - Gradio Example Not Filling Chat Box FIXED

Commit: 2ea01fd (2025-11-29)

  • Third example (HSDD) wasn't populating chat box when clicked
  • Root cause: Parentheses in HSDD (Hypoactive Sexual Desire Disorder)
  • Fix: Simplified to Testosterone therapy for Hypoactive Sexual Desire Disorder?

P1 - Gradio Settings Accordion WONTFIX

Decision: Removed nested Blocks, using ChatInterface directly. Accordion behavior is default Gradio - acceptable for demo.

How to Report Bugs

  1. Create docs/bugs/P{N}_{SHORT_NAME}.md
  2. Include: Symptom, Root Cause, Fix Plan, Test Plan
  3. Update this index
  4. Priority: P0=blocker, P1=important, P2=UX, P3=edge case