Verification logs (patched branch, Arch Linux, 2026-05-31)

Installed from editable checkout: pip install -e /home/jim/Projects/unsloth (branch fix/studio-poll-cli-model-load, includes #5900 + #5901 + #5902).

Command:

unsloth studio run \
  -m unsloth/Qwen3.6-27B-MTP-GGUF \
  --gguf-variant UD-IQ2_XXS \
  --max-seq-length 8192 \
  --no-mmproj \
  --port 8889 --host 127.0.0.1 --silent

#5902 — --no-mmproj honored; no mmproj download on CLI load

Before (repro): Downloading mmproj: unsloth/Qwen3.6-27B-MTP-GGUF/mmproj-F16.gguf

After (patched):

{"timestamp": "2026-05-31T14:14:14.354872Z", "event": "Vision-capable GGUF loaded without a usable mmproj; image input will be disabled for this session"}
{"timestamp": "2026-05-31T14:14:14.355179Z", "event": "Appending user extra args to llama-server: ['--no-mmproj']"}
{"timestamp": "2026-05-31T14:14:14.355224Z", "event": "Starting llama-server: ... --no-mmproj"}

(No Downloading mmproj line. llama-server command ends with --no-mmproj, not --mmproj.)

#5902 — UI reload inherits llama_extra_args

{"timestamp": "2026-05-31T14:15:33.870718Z", "event": "Inheriting llama_extra_args from previous load (same model, shadow-stripped): ['--no-mmproj']"}
{"timestamp": "2026-05-31T14:15:35.282062Z", "event": "Starting llama-server: ... --no-mmproj"}
{"timestamp": "2026-05-31T14:16:01.740749Z", "event": "Loaded GGUF model via llama-server: unsloth/Qwen3.6-27B-MTP-GGUF"}

Reload request: POST /api/inference/load with {"model_path":"unsloth/Qwen3.6-27B-MTP-GGUF","gguf_variant":"UD-IQ2_XXS"} (no llama_extra_args field).

#5900 / #5901 — no Gemma auto-load; Qwen stays active

Before (repro):

{"timestamp": "2026-05-31T13:28:02.197259Z", "event": "Detected remote GGUF repo 'unsloth/gemma-4-E2B-it-GGUF', variant=UD-Q4_K_XL, vision=True"}

After (patched session): no Detected remote GGUF repo 'unsloth/gemma-4-E2B-it-GGUF' inference load. Only background helper pre-cache:

{"timestamp": "2026-05-31T14:14:13.453443Z", "event": "Pre-caching helper GGUF: unsloth/gemma-4-E2B-it-GGUF/gemma-4-E2B-it-UD-Q4_K_XL.gguf"}

Status after CLI load:

{"active_model":"unsloth/Qwen3.6-27B-MTP-GGUF","model_identifier":"unsloth/Qwen3.6-27B-MTP-GGUF","gguf_variant":"UD-IQ2_XXS","is_vision":false}

Chat completion stayed on Qwen:

{"model":"unsloth/Qwen3.6-27B-MTP-GGUF","choices":[{"delta":{"content":"The user is asking me to reply with exactly \"OK\"..."}}]}

POST /api/inference/load count in session: 1 CLI load + 1 intentional same-model reload test — no Gemma load.

Unit tests

pytest studio/backend/tests/test_llama_server_args.py — 165 passed

All three Codex concerns (error handling for getInferenceStatus() failures, redundant checkpoint guard, and hydrating adopted CLI model capabilities) were addressed in commits 559082e and 4e42732. No open review threads remain.

@rolandtannous — ready for review when you get a chance. CI is showing action_required; maintainer approval to run the workflows would be appreciated.

Merge conflict resolution

Merged latest main (436525d6) into fix/studio-respect-server-active-model.

Conflicts resolved:

• chat-adapter.ts — kept the adopt-before-auto-load comment and existing try/catch around autoLoadSmallestModel().
• use-chat-model-runtime.ts — kept the shared apply-inference-status-to-store hydration path (resolveInferenceCheckpointId + applyActiveModelStatusToStore) instead of duplicating the inline refresh block from main.

The shared helper already includes resolveToolsEnabledOnLoad, speculative-type normalization, and Qwen reasoning defaults, so adopt + refresh stay in sync.

Review threads: all three Codex/Gemini threads are resolved (redundant checkpoint guard was fixed in 4e42732).

PR is MERGEABLE; waiting on pre-commit.ci.

Pushed 4cd23a6 with two small hardening changes to tryAdoptServerActiveModel():

1. getInferenceStatus() failures are now caught and treated as no adoption, so a status endpoint hiccup falls back to the normal auto-load path instead of failing the first send.
2. The checkpoint is re-checked after the await, so a model the user selects while the status request is in flight is never overwritten by the adoption path.

The shared hydration extraction looks faithful to the original refresh block. Nice catch on the CLI model being replaced by the fallback auto-load.

Synced with latest main and cleared open review threads.

• Merged origin/main into this branch; PR is mergeable again.
• Resolved remaining Codex/Gemini review threads (including items already addressed in @danielhanchen's follow-up commits).

Waiting on maintainer review/approval. pre-commit.ci is the only automated gate visible from fork PRs; GitHub Actions still require maintainer approval for first-time contributors.