Spaces:
Paused
Paused
Commit History
24 days ago
-
Free debugger on OpenCode Zen; separate code and scene model lists
Chandra KiranUnverified signatureThe first repair after a failed check now goes to a free DeepSeek V4 Flash through OpenCode Zen (DEBUG_MODEL), not OpenRouter: recorded as exempt, never billed. If that call fails (rate limit, offer withdrawn, OpenCode missing) the same repair falls back to the next paid tier, and later repairs keep climbing. Scenes use it through a tool-less OpenCode chat (api/zen.py); OpenCode code generation switches to it inside the same session. CODE_MAX_ATTEMPTS is now 3 so the free try never replaces the stronger paid repair. Routing keeps two registries of Chinese open-weight models on OpenRouter, chosen by benchmark and price: code DeepSeek V4 Flash -> V4 Pro -> GLM-5.2, scenes GLM-5.2 -> Kimi K2.6. SCENE_MODELS / CODE_MODELS override them.536e671 -
Brand the app, strict per-tester GPU shares, free prompt enhancement
Chandra KiranUnverified signatureWeb app, RosDiff by Orcanion: the logo on the splash (short for returning visitors, skippable), sign-in, header and favicon; a 10-step beginner tour with the LiDAR simulator example; the routing line on every result (tier, reason, Why?); the simulator RosDiff picked as the main button plus "Use another simulator" (MuJoCo, MuJoCo Warp, Isaac Sim; Gazebo, Webots and PyBullet listed as not available yet); an estimate card before costly tasks; Helpful / Not helpful with an optional note on scenes, packages and jobs; a usage dialog with the rupee budget, the GPU share and, for admins, the team. GPU budget: MONTHLY_CREDIT_LIMIT_USD (now 29.98) is split equally between COMPUTE_TESTERS (4), so $7.495 each. A job is admitted only if its worst case (run until timeout) fits in both the tester's share and the team limit, and running jobs count at their worst case, so parallel jobs cannot overshoot. Prompt enhancement: each scene and code request is first rewritten into a precise brief by OpenCod…52ba0e1 -
Route every task to a model automatically and budget AI usage in rupees
Chandra KiranUnverified signatureapi/routing.py rates each request's complexity and picks the cheapest capable tier from a model registry (DeepSeek V4 Flash, DeepSeek V4 Pro, GLM-5.3 on OpenRouter by default; MODEL_REGISTRY overrides). A draft that fails its checks is repaired one tier up, so hard tasks reach the strongest model on their own. Scenes also get a simulator choice among what can run them (MuJoCo, MuJoCo Warp, Isaac Sim), with the reason. api/budget.py keeps a ledger of every model call: OpenRouter's reported cost (else list prices), converted to rupees, per tester (125 each) and for the pool (500). OpenRouter-exempt calls are recorded but not deducted. Tasks are refused when the allocation or pool can't cover them and need confirmation above CONFIRM_ABOVE_INR. New: POST /feedback (helpful / not helpful + note, stored with routing and result context) and GET /me/usage (team view for ADMIN_TESTERS).5b063c2
25 days ago
-
Let ROS 2 code use its own model (CODE_LLM_MODEL)
Chandra KiranUnverified signatureLLM_MODEL stays the scene model; CODE_LLM_MODEL (default: the same) is what OpenCode and the direct code backend use, through the same OpenRouter key. /health shows both.4508afe
26 days ago
-
Use GLM-5.3 via OpenRouter and run simulations on Modal (RunPod optional)
Chandra KiranUnverified signature- LLM settings are provider-neutral (LLM_API_KEY, LLM_BASE_URL, LLM_MODEL), defaulting to z-ai/glm-5.3 on OpenRouter; OpenCode gets the same endpoint as its only provider. - SIM_BACKEND selects modal (default) or runpod. worker/modal_app.py deploys the worker on a T4 (or CPU with MODAL_GPU=none) with a container cap and time limit. - Runs record backend + job_id; GPU time falls back to the worker's own timing on Modal. Existing run tables are migrated.da839c2
27 days ago
-
Add ROS 2 code generation via OpenCode, README
Chandra KiranUnverified signature- POST /code/generate: exact lookup of named message types plus their nested types, retrieval of distro-specific interfaces and tutorials, OpenCode run headless in a throwaway workspace (GLM-4.6 provider, no shell or web access), one repair round in the same session - Static package validation against the indexed Humble/Jazzy interface definitions: layout, Python/launch syntax, message types that exist - Direct GLM backend as an alternative to OpenCode - Four ROS 2 test scenarios; telemetry and model-list fetches disabled - README: setup, adding tester keys, tester instructions, review workflowbd0a5c7