Spaces:
Running
Running
Commit History
4 days ago
-
Sync backend to GitHub 90c36af: Merge pull request #30 from siddhm11/fix/voice-daily-limit Running
github-actions[bot]Automated by .github/workflows/sync-hf-space.ymlf3765c7 -
Sync backend to GitHub 246f221: Merge pull request #26 from siddhm11/feat/auto-context-switch
github-actions[bot]Automated by .github/workflows/sync-hf-space.yml8706d24 -
Sync backend to GitHub 288744e: Merge pull request #25 from siddhm11/fix/context-bleed
github-actions[bot]Automated by .github/workflows/sync-hf-space.ymlbd70947 -
Sync backend to GitHub 912a16f: Video: 10-second clip prompts with start and end frames
github-actions[bot]Automated by .github/workflows/sync-hf-space.ymld730ddb
9 days ago
-
Sync backend to GitHub 184b474: Add a 1280x800 store screenshot of the rewrite card
github-actions[bot]Automated by .github/workflows/sync-hf-space.yml1286154
10 days ago
-
Sync backend to GitHub 6ff5595: Merge pull request #22: sign-in first, server capacity on the dashboard,
github-actions[bot]Automated by .github/workflows/sync-hf-space.ymlb69c0ee
11 days ago
-
Sync backend to GitHub d13146e: Roll main back to 4.9.0 (revert the 5.0.0 merge)
github-actions[bot]Automated by .github/workflows/sync-hf-space.ymlbdca29f
12 days ago
-
Sync backend to GitHub f8da076: Merge mvp-frontend: free tier without an account, one-click Improve, one
github-actions[bot]Automated by .github/workflows/sync-hf-space.yml159ebd9
27 days ago
-
Sync backend to GitHub 7a32980: Merge pull request #9: fix tester feedback and guide new users (4.7.0)
github-actions[bot]Automated by .github/workflows/sync-hf-space.yml149dd33
28 days ago
-
Sync backend to GitHub 5336509: feat(ui): add interactive score progression hero with collapsible 4-dime
github-actions[bot]Automated by .github/workflows/sync-hf-space.yml3125a17
-
Sync backend to GitHub f8d0b96: consent-gated memory, analytics API, structured logging
siddhm11Brings the Space up to date with 9 backend commits from GitHub main (ad58940..f8d0b96): - Passive memory written only on /enhance/accept, retrieval filtered on approved=true; existing unapproved vectors stop matching - Retrieval thresholds calibrated per layer (saved 0.24, passive 0.20) - New /api/user/analytics, /api/evaluate/prompt-improvement, /api/user/prompt-history/{id} - Account deletion ordered, retryable, profile deleted last - Prompt text removed from console logs; print -> JSON logger - Embedding LRU cache shared across memory layers Dockerfile, README.md and other Space-only files unchanged.10ce33e
-
Sync backend to GitHub ad58940: fix Whisper language detection
siddhm11 +1: Claude Opus 5Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NoNHrDfqGj7BLKagHkRM3Zae335b1 -
Sync backend to GitHub d419447: voice transcription, builder dashboard, analytics
siddhm11 +1: Claude Opus 5Brings the Space up to date with siddhm11/prompt_engineering_skeleton@d419447. Adds POST /voice-transcribe (the extension has been calling it and getting 404), the private builder dashboard API, and analytics telemetry. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NoNHrDfqGj7BLKagHkRM3Zb1f9886
-
Stop markdown emphasis reaching the composer
siddhm11 +1: Claude Opus 5The rewrite goes into a plain chat box, so ** shows up literally. Instructed in the system prompt and stripped in sanitize_output, with code fences, lone asterisks, dunders, lists and LaTeX all left alone. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKR7665bd1
-
Harden the vector store against the failure modes that hid a real outage
siddhm11 +1: Claude Opus 5Connectivity is now verified before a client is accepted; provisioning latches only on success and is retried; a broken client can be reset; reconnection is rate-limited; dimension mismatches are refused loudly; requests carry a timeout; and failed reads no longer look identical to empty results. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKRc61e3b2 -
Revert the Qdrant port normalisation; the premise was wrong
siddhm11 +1: Claude Opus 5Qdrant Cloud serves REST on 443 for reads and writes — verified live. The old cluster was simply gone. The diagnostics that found that stay. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKRa3dca10 -
Add Qdrant Cloud's REST port when the configured URL omits it
siddhm11 +1: Claude Opus 5Root cause of saved-prompt search never matching: the URL had no :6333, so requests hit 443 and were reset, and every failure was swallowed into an empty result. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKR78089ad -
Report Qdrant URL shape so a bad config is distinguishable from a dead cluster
siddhm11 +1: Claude Opus 5Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKR0352dbc -
Report vector-store health alongside embedding health
siddhm11 +1: Claude Opus 5Point counts are the decisive signal for why saved-prompt search matches nothing: empty means writes never landed, populated means the query is at fault. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKR72bd44e -
Report embedding health, and stop skipping embeds silently
siddhm11 +1: Claude Opus 5Saved-prompt search returns nothing in production and the embedding model's failure mode is silent in both directions. /health/llm now reports whether it loaded, and a skipped embed logs instead of passing quietly. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKR60af107 -
Return context_details from the streaming enhance endpoint too
siddhm11 +1: Claude Opus 5The two enhance endpoints described the same work differently — only the non-streaming one returned context_details — so a streaming client could count matched saved prompts but never name them. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKR2615516 -
Cap the OAuth state store
siddhm11 +1: Claude Opus 5/auth/google/login is unauthenticated by necessity, so the per-user rate limiter cannot cover it, and each call added a ten-minute entry with nothing bounding the total. It now refuses past _MAX_STATES instead of accumulating. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015akmAZh7sN51giQFyMuDKR5f7a127 -
Deploy the audit remediation backend
siddhm11 +1: Claude Opus 5Brings the Space in line with the tested tree. Two changes here are what production is currently missing, and sign-in cannot work without both: - /auth/google/login now returns a `state` handle - /auth/google/poll exists at all (it currently 404s) The extension's rewritten sign-in polls that endpoint from the service worker, because an MV3 action popup is destroyed the moment it loses focus and took the old postMessage listener down with it before Google ever redirected back. Also lands: the daily ration no longer fails open when Mongo is unreachable (one read failure previously granted everyone unlimited enhancements, which can drain the shared Groq org quota in minutes); Qdrant point ids are deterministic so deleting a saved prompt actually removes its vector; per-user rate limiting and a request body cap are wired up; CORS no longer pairs allow-all with credentials and /docs is closed in production; pasted credentials are redacted before being logged or embedded; and /voice-e…bd719d5
-
Fix unsatisfiable requirements that hung the build
Verified signaturesentence-transformers[onnx] is unsatisfiable: sentence-transformers 6.x needs transformers >=5.0,<6.0 while optimum-onnx 0.1.0 needs >=4.36,<4.58. pip backtracked through the whole release history instead of failing. Dropping the extra resolves in ~4s; embeddings are identical since ONNX and torch share the same MiniLM weights.c675631 -
Replace dead Groq models with a provider fallback chain
Verified signaturellama-3.3-70b-versatile and llama-3.1-8b-instant were decommissioned by Groq on 2026-08-16. The hardcoded model id meant every /enhance call failed with a 404, which the handler swallowed (it only rotated keys on 429), so the endpoint returned HTTP 200 with an empty enhancement. - services/providers.py: ordered fallback chain across models and providers, with dead-model detection, key rotation and a pooled HTTP client. Primary is qwen/qwen3.8-27b (reasoning off, best romanised-Hinglish fidelity of the surviving models), falling back to qwen3.6-27b, gpt-oss-120b and gpt-oss-20b. - Failures now surface as 429/503 with diagnostics instead of a silent 200. Empty completions are treated as failures, not successes. - BYOK: /enhance accepts a per-request user API key, never stored. - Romanised Hinglish is now detected and preserved (previously it was classified as English, and the prompt then ordered an English reply). - New /health/llm endpoint reports the chain and any dead models.8715f2a
-
Update backend from polished-with-website branch - new routers (feedback, saved_prompts), updated services and configs
siddhm11c0dd1c5
-
feat: update backend with complete prompt engine v4.0 - Enhanced main.py with request logging, CORS config, embedding preload - Updated config.py with tier-based model routing, rate limits, Stripe stubs - Expanded prompts.py with streaming, voice-enhance, feedback, history, usage endpoints - Added llm_service.py with Groq client pool and key rotation - Updated memory_service.py with passive learning, feedback analysis - Added migrate_embeddings.py for multilingual model migration - Updated schemas.py, auth.py, saved_prompts.py, requirements.txt - Removed prompt_engineering_skeleton directory
siddhm11257fe44
-
small change api
siddhm119fe6054 -
small change api
siddhm113db2097
-
Update backend: mode-aware enhance, saved prompts CRUD, voice-enhance, feedback endpoint
siddhm114d5cbc7
-
Merge branch 'main' of https://huggingface.co/spaces/siddhm11/prompt-engine
siddhm1187ed774 -
changes in sim .9 , database:
siddhm11d3974e0
-
Update backend/core/config.py
Verified signature310887e -
refactor for HF spaces: moved code to backend/
siddhm11515a3fb
-
Upload main.py
Verified signature360b843 -
Create Dockerfile
Verified signature976f9a1 -
Upload 2 files
Verified signature46e5f2b -
req docs
Verified signatureb112b48 -
initial commit
Verified signaturea42e2fc