Add job run logs, OpenRouter model picker, and discipline grouping.

- Job logs: each job's stdout/stderr is teed into outputs/<id>/job.log
  (survives restarts) and served at GET /jobs/{id}/log as text/plain, so
  full run logs can be shared for debugging and refinement.
- Model picker: GET /models proxies OpenRouter's public model list with
  per-1M-token pricing (1h cache, 502 on failure); the UI shows a model
  dropdown with costs when OpenRouter compute is selected, and the pick
  overrides vision+text models for that job (Classic and Agent modes).
- Conflicts in the report view are grouped by discipline pair
  (collapsible sections, severity-ordered within groups) instead of one
  flat severity-only list.

backend/jobs.py

@@ -12,7 +12,9 @@ not. No external queue/DB.
 """
 
 import json
+import contextlib
 import os
+import sys
 import time
 import uuid
 import shutil
@@ -20,6 +22,7 @@ import threading
 from typing import Dict, Optional
 
 from backend import config
+from backend import llm
 from backend.agents.runner import run_agent_pipeline
 from backend.pipeline.runner import run_pipeline
 from backend.email_sender import send_conflict_report, send_review_required
@@ -29,6 +32,40 @@ _lock = threading.Lock()
 PIPELINE_MODES = {"classic", "agent"}
 
 
+class _Tee:
+    """Write to both the real stream and the job log file."""
+
+    def __init__(self, stream, log_file) -> None:
+        self._stream = stream
+        self._log = log_file
+
+    def write(self, data):
+        self._stream.write(data)
+        self._log.write(data)
+
+    def flush(self):
+        self._stream.flush()
+        self._log.flush()
+
+
+@contextlib.contextmanager
+def _tee_log(log_path: str, header: str):
+    """Mirror stdout/stderr into a per-job log file for the duration of a run.
+
+    sys.stdout is process-global, so two concurrent jobs would interleave in
+    each other's logs - acceptable for this single-user tool (same tradeoff as
+    the LLM cost globals in llm.py).
+    """
+    with open(log_path, "a", encoding="utf-8") as log_file:
+        log_file.write(header + "\n")
+        real_out, real_err = sys.stdout, sys.stderr
+        sys.stdout, sys.stderr = _Tee(real_out, log_file), _Tee(real_err, log_file)
+        try:
+            yield
+        finally:
+            sys.stdout, sys.stderr = real_out, real_err
+
+
 def _set(job_id: str, **fields) -> None:
     with _lock:
         _jobs[job_id].update(fields)
@@ -36,13 +73,14 @@ def _set(job_id: str, **fields) -> None:
 
 def create_job(pdf_path: str, source_filename: str, email: Optional[str] = None,
                project_input: Optional[Dict] = None, text_local: bool = False,
-               pipeline_mode: str = "classic") -> str:
+               pipeline_mode: str = "classic", model: Optional[str] = None) -> str:
     """Register a job and kick off its background thread. Returns the job_id."""
     pipeline_mode = pipeline_mode.strip().lower()
     if pipeline_mode not in PIPELINE_MODES:
         raise ValueError(f"Unsupported pipeline mode: {pipeline_mode!r}")
     # Agent mode v1 is OpenRouter-only.
     text_local = bool(text_local and pipeline_mode == "classic")
+    model = (model or "").strip() or None
     job_id = uuid.uuid4().hex[:12]
     with _lock:
         _jobs[job_id] = {
@@ -53,6 +91,7 @@ def create_job(pdf_path: str, source_filename: str, email: Optional[str] = None,
             "project_input": project_input or {},
             "text_local": text_local,
             "pipeline_mode": pipeline_mode,
+            "model": model,
             "stage": None,
             "created_at": time.time(),
             "finished_at": None,
@@ -60,54 +99,26 @@ def create_job(pdf_path: str, source_filename: str, email: Optional[str] = None,
             "error": None,
         }
     threading.Thread(target=_run, args=(
-        job_id, pdf_path, project_input, text_local, pipeline_mode,
+        job_id, pdf_path, project_input, text_local, pipeline_mode, model,
     ),
                      daemon=True).start()
     return job_id
 
 
 def _run(job_id: str, pdf_path: str, project_input: Optional[Dict] = None,
-         text_local: bool = False, pipeline_mode: str = "classic") -> None:
+         text_local: bool = False, pipeline_mode: str = "classic",
+         model: Optional[str] = None) -> None:
     out_dir = os.path.join(config.OUTPUT_DIR, job_id)
     try:
         _set(job_id, status="running")
         # Keep a copy of the source PDF so its sheets can be viewed later.
         os.makedirs(out_dir, exist_ok=True)
-        # Persist minimal job metadata so the disk fallback in get_job can
-        # recover the recipient email / pipeline mode after a server restart
-        # (plain json.dump, matching the _dump style used elsewhere).
-        with open(os.path.join(out_dir, "job.json"), "w", encoding="utf-8") as f:
-            json.dump({
-                "job_id": job_id,
-                "email": _jobs[job_id].get("email"),
-                "pipeline_mode": pipeline_mode,
-                "source": _jobs[job_id].get("source"),
-            }, f, indent=2)
-        shutil.copy2(pdf_path, os.path.join(out_dir, "source.pdf"))
-        runner = run_agent_pipeline if pipeline_mode == "agent" else run_pipeline
-        runner_kwargs = {
-            "out_dir": out_dir,
-            "on_stage": lambda name: _set(job_id, stage=name),
-            "project_input": project_input,
-            "source_name": _jobs[job_id].get("source"),
-        }
-        if pipeline_mode == "classic":
-            runner_kwargs["text_local"] = text_local
-        else:
-            runner_kwargs["require_review"] = config.AGENT_REQUIRE_REVIEW
-        report = runner(pdf_path, **runner_kwargs)
-        report.setdefault("summary", {})["pipeline_mode"] = pipeline_mode
-        if report["summary"].get("agent_status") == "needs_review":
-            # Human-review gate: hold the job, don't email the unreviewed report.
-            _set(job_id, status="needs_review", report=report,
-                 finished_at=time.time(), stage=None)
-            email = _jobs[job_id].get("email")
-            if email:
-                review_url = f"{config.APP_BASE_URL.rstrip('/')}/?job={job_id}"
-                send_review_required(email, report, review_url)
-        else:
-            _set(job_id, status="done", report=report, finished_at=time.time(), stage=None)
-            _notify(job_id, report, out_dir)
+        header = (f"=== Job {job_id} | {pipeline_mode} | {_jobs[job_id].get('source')} | "
+                  f"model={model or 'default'} | "
+                  f"started {time.strftime('%Y-%m-%d %H:%M:%S %Z', time.gmtime())} UTC ===")
+        with _tee_log(os.path.join(out_dir, "job.log"), header):
+            _run_pipeline(job_id, pdf_path, out_dir, project_input, text_local,
+                          pipeline_mode, model)
     except Exception as e:
         print(f"[Jobs] Job {job_id} failed: {e}")
         _set(job_id, status="error", error=str(e), finished_at=time.time())
@@ -119,6 +130,54 @@ def _run(job_id: str, pdf_path: str, project_input: Optional[Dict] = None,
             pass
 
 
+def _run_pipeline(job_id: str, pdf_path: str, out_dir: str,
+                  project_input: Optional[Dict], text_local: bool,
+                  pipeline_mode: str, model: Optional[str]) -> None:
+    """The body of a job run; executes inside the job's tee'd log capture."""
+    # Persist minimal job metadata so the disk fallback in get_job can
+    # recover the recipient email / pipeline mode after a server restart
+    # (plain json.dump, matching the _dump style used elsewhere).
+    with open(os.path.join(out_dir, "job.json"), "w", encoding="utf-8") as f:
+        json.dump({
+            "job_id": job_id,
+            "email": _jobs[job_id].get("email"),
+            "pipeline_mode": pipeline_mode,
+            "source": _jobs[job_id].get("source"),
+        }, f, indent=2)
+    shutil.copy2(pdf_path, os.path.join(out_dir, "source.pdf"))
+    runner = run_agent_pipeline if pipeline_mode == "agent" else run_pipeline
+    runner_kwargs = {
+        "out_dir": out_dir,
+        "on_stage": lambda name: _set(job_id, stage=name),
+        "project_input": project_input,
+        "source_name": _jobs[job_id].get("source"),
+    }
+    if pipeline_mode == "classic":
+        runner_kwargs["text_local"] = text_local
+    else:
+        runner_kwargs["require_review"] = config.AGENT_REQUIRE_REVIEW
+    if model:
+        print(f"[Jobs] Model override for this run: {model}")
+        llm.set_model_override(model)
+    try:
+        report = runner(pdf_path, **runner_kwargs)
+    finally:
+        if model:
+            llm.set_model_override(None)
+    report.setdefault("summary", {})["pipeline_mode"] = pipeline_mode
+    if report["summary"].get("agent_status") == "needs_review":
+        # Human-review gate: hold the job, don't email the unreviewed report.
+        _set(job_id, status="needs_review", report=report,
+             finished_at=time.time(), stage=None)
+        email = _jobs[job_id].get("email")
+        if email:
+            review_url = f"{config.APP_BASE_URL.rstrip('/')}/?job={job_id}"
+            send_review_required(email, report, review_url)
+    else:
+        _set(job_id, status="done", report=report, finished_at=time.time(), stage=None)
+        _notify(job_id, report, out_dir)
+
+
 def _notify(job_id: str, report: Dict, out_dir: str) -> None:
     email = _jobs[job_id].get("email")
     if not email:

backend/llm.py

@@ -24,6 +24,16 @@ _clients: Dict[str, OpenAI] = {}
 # set_stage/cost pattern (single-user tool).
 _text_local = False
 
+# Per-job model override (user picked a model in the UI). Same module-global
+# pattern: set by the job runner before the pipeline starts, cleared after.
+_model_override: Optional[str] = None
+
+
+def set_model_override(model: Optional[str]) -> None:
+    """Override the model for all OpenRouter calls (vision + text), or None to clear."""
+    global _model_override
+    _model_override = (model or "").strip() or None
+
 
 def set_text_backend(local: bool) -> None:
     """Choose whether text (no-image) calls go to the local endpoint this run."""
@@ -171,12 +181,13 @@ def _resolve_backend(has_images: bool, model_override: Optional[str]) -> Dict[st
             "usage": False,          # local has no OpenRouter usage accounting
             "local": True,
         }
-    # Vision, or text-on-OpenRouter (default / fallback).
+    # Vision, or text-on-OpenRouter (default / fallback). A per-job override
+    # (user's UI model pick) wins over per-call and env defaults.
     default_model = config.MODEL if has_images else config.TEXT_MODEL
     return {
         "base_url": config.AI_BASE_URL,
         "api_key": config.AI_API_KEY,
-        "model": model_override or default_model,
+        "model": _model_override or model_override or default_model,
         "usage": True,
         "local": False,
     }

backend/main.py

@@ -41,6 +41,27 @@ def health():
             "email_configured": bool(config.SMTP_HOST and config.SMTP_USER and config.SMTP_PASSWORD)}
 
 
+@app.get("/models")
+def list_models():
+    """Available OpenRouter models with per-1M-token pricing for the UI picker."""
+    from backend.models import fetch_models
+    models = fetch_models()
+    if models is None:
+        raise HTTPException(status_code=502,
+                            detail="Could not fetch the model list from OpenRouter")
+    return {"models": models, "default": config.MODEL, "default_text": config.TEXT_MODEL}
+
+
+@app.get("/jobs/{job_id}/log")
+def job_log(job_id: str):
+    """The full captured stdout/stderr log of a job run (persists on disk)."""
+    path = os.path.join(config.OUTPUT_DIR, job_id, "job.log")
+    if not os.path.isfile(path):
+        raise HTTPException(status_code=404, detail="Log not found for this job")
+    with open(path, encoding="utf-8", errors="replace") as f:
+        return Response(content=f.read(), media_type="text/plain")
+
+
 @app.post("/check")
 async def check(
     file: UploadFile = File(...),
@@ -51,6 +72,7 @@ async def check(
     work_type: Optional[str] = Form(None),
     text_local: bool = Form(False),
     pipeline_mode: str = Form("classic"),
+    model: Optional[str] = Form(None),
 ):
     """
     Accept a PDF, start a background conflict check, and return a job_id
@@ -86,7 +108,7 @@ async def check(
     }
     job_id = create_job(tmp_path, source_filename=file.filename, email=email,
                         project_input=project_input, text_local=text_local,
-                        pipeline_mode=pipeline_mode)
+                        pipeline_mode=pipeline_mode, model=model)
     return JSONResponse({
         "job_id": job_id,
         "status": "queued",

backend/models.py

@@ -0,0 +1,65 @@
+"""
+models.py - Fetch the available OpenRouter model list with pricing (cached).
+
+The /models endpoint is public (no API key needed). Results are normalized to
+per-1M-token USD costs for display and cached in memory for an hour; callers
+degrade gracefully when OpenRouter is unreachable.
+"""
+
+import time
+from typing import List, Optional
+
+import httpx
+
+from backend import config
+
+_CACHE_TTL_SECONDS = 3600
+_cache = {"at": 0.0, "models": None}
+
+
+def _per_mtok(rate) -> float:
+    """OpenRouter pricing is USD per token (as a string); display is per 1M."""
+    try:
+        return round(float(rate) * 1_000_000, 4)
+    except (TypeError, ValueError):
+        return 0.0
+
+
+def _fetch_openrouter_models() -> Optional[List[dict]]:
+    """Raw GET of the OpenRouter model list; None on any failure."""
+    try:
+        response = httpx.get(f"{config.AI_BASE_URL.rstrip('/')}/models", timeout=10)
+        response.raise_for_status()
+        data = response.json().get("data")
+        return data if isinstance(data, list) else None
+    except Exception as e:
+        print(f"[Models] OpenRouter /models fetch failed: {e}")
+        return None
+
+
+def fetch_models(force: bool = False) -> Optional[List[dict]]:
+    """Normalized model list for the UI picker, or None when unavailable."""
+    if (
+        not force
+        and _cache["models"] is not None
+        and time.time() - _cache["at"] < _CACHE_TTL_SECONDS
+    ):
+        return _cache["models"]
+    data = _fetch_openrouter_models()
+    if data is None:
+        return None
+    models = [
+        {
+            "id": item.get("id") or "",
+            "name": item.get("name") or item.get("id") or "",
+            "prompt_usd_per_mtok": _per_mtok((item.get("pricing") or {}).get("prompt")),
+            "completion_usd_per_mtok": _per_mtok((item.get("pricing") or {}).get("completion")),
+            "context_length": item.get("context_length"),
+        }
+        for item in data
+        if item.get("id")
+    ]
+    models.sort(key=lambda m: m["id"])
+    _cache["models"] = models
+    _cache["at"] = time.time()
+    return models

frontend/index.html

@@ -120,6 +120,10 @@
       <input type="radio" name="compute" value="openrouter" checked> OpenRouter &mdash; all stages (fastest, paid)</label>
     <label style="display:block;font-weight:400;margin-top:6px">
       <input type="radio" name="compute" value="local"> Hybrid &mdash; text stages on local LLM (cheaper, slower)</label>
+    <div id="modelPick" style="margin-top:10px">
+      <label for="model" style="font-weight:400">Model <span class="opt" id="modelNote">loading...</span></label>
+      <select id="model" style="width:100%;margin-top:6px;padding:10px;border-radius:8px;border:1px solid var(--line);background:#0c0e13;color:var(--text)"></select>
+    </div>
   </div>
   <button class="btn full" id="run" disabled>Run conflict check</button>
   <div class="status" id="status"></div>
@@ -163,6 +167,10 @@ runBtn.addEventListener('click',async e=>{
   });
   const compute=(document.querySelector('input[name="compute"]:checked')||{}).value;
   fd.append('text_local', compute==='local' ? 'true' : 'false');
+  if(compute==='openrouter'){
+    const modelSel=document.getElementById('model');
+    if(modelSel.value) fd.append('model', modelSel.value);
+  }
   const pipelineMode=(document.querySelector('input[name="pipeline_mode"]:checked')||{}).value||'classic';
   fd.append('pipeline_mode',pipelineMode);
   try{
@@ -222,6 +230,33 @@ function syncPipelineOptions(){
 document.querySelectorAll('input[name="pipeline_mode"]').forEach(el=>el.addEventListener('change',syncPipelineOptions));
 syncPipelineOptions();
 
+// --- model picker (OpenRouter compute only) ---
+let modelList=null;
+async function loadModels(){
+  const note=document.getElementById('modelNote'), sel=document.getElementById('model');
+  try{
+    const res=await fetch('/models');
+    if(!res.ok) throw new Error('list unavailable');
+    const data=await res.json();
+    modelList=data.models||[];
+    sel.innerHTML=modelList.map(m=>
+      '<option value="'+escAttr(m.id)+'"'+(m.id===data.default?' selected':'')+'>'+
+      esc(m.name||m.id)+' &mdash; $'+esc(m.prompt_usd_per_mtok)+' / $'+esc(m.completion_usd_per_mtok)+
+      ' per 1M tok</option>').join('');
+    note.textContent='('+modelList.length+' available)';
+  }catch(e){
+    sel.innerHTML='';
+    note.textContent='using configured default (list unavailable)';
+  }
+}
+function syncCompute(){
+  const openrouter=(document.querySelector('input[name="compute"]:checked')||{}).value==='openrouter';
+  document.getElementById('modelPick').style.display=openrouter?'block':'none';
+  if(openrouter&&!modelList) loadModels();
+}
+document.querySelectorAll('input[name="compute"]').forEach(el=>el.addEventListener('change',syncCompute));
+syncCompute();
+
 // --- sheet viewer ---
 function pageFor(num){ return sheetPage[num] || sheetPage[(num||'').toUpperCase()] || null; }
 function sheetSpan(num){
@@ -248,6 +283,43 @@ function closeSheet(){ document.getElementById('viewer').classList.remove('open'
 document.getElementById('viewer').addEventListener('click',e=>{ if(e.target.id==='viewer') closeSheet(); });
 document.addEventListener('keydown',e=>{ if(e.key==='Escape') closeSheet(); });
 
+// --- conflicts grouped by discipline pair ---
+const SEV_RANK={critical:0,high:1,medium:2,low:3};
+function sevRank(c){ const r=SEV_RANK[(c.severity||'').toLowerCase()]; return r==null?4:r; }
+function groupConflicts(conflicts){
+  // Group key: disciplines sorted alphabetically, joined ' vs ' (order-independent
+  // pair). Missing disciplines -> 'General'. Groups ordered by their most severe
+  // conflict, then name; items within a group ordered critical->high->medium->low.
+  const groups={};
+  for(const c of conflicts||[]){
+    const ds=(c.disciplines||[]).map(d=>String(d)).filter(Boolean).sort();
+    const key=ds.length?ds.join(' vs '):'General';
+    (groups[key]=groups[key]||[]).push(c);
+  }
+  const names=Object.keys(groups).sort((a,b)=>{
+    const ra=Math.min.apply(null,groups[a].map(sevRank)),
+          rb=Math.min.apply(null,groups[b].map(sevRank));
+    return (ra-rb)||a.localeCompare(b);
+  });
+  return names.map(name=>({name:name,
+    items:groups[name].slice().sort((x,y)=>sevRank(x)-sevRank(y))}));
+}
+function conflictCard(c){
+  let html='<div class="conflict '+esc(c.severity)+'">'+
+    '<div class="row"><span class="cat">'+esc(c.category)+'</span>'+
+    '<span class="pill '+esc(c.severity)+'">'+esc(c.severity)+'</span></div>'+
+    '<div class="loc">'+esc(c.location)+'</div>'+
+    '<div class="meta">'+esc((c.disciplines||[]).join(' vs '))+
+      ' &middot; sheets '+sheetList(c.sheets)+'</div>'+
+    '<div class="desc">'+esc(c.description)+'</div>';
+  if(c.evidence&&c.evidence.length){
+    html+='<div class="ev">'+c.evidence.map(e=>
+      '<div><span class="d">'+esc(e.discipline)+'</span> ('+sheetSpan(e.sheet)+'): "'+esc(e.source_text)+'"</div>').join('')+'</div>';
+  }
+  if(c.recommended_resolution){ html+='<div class="reso">Resolution: '+esc(c.recommended_resolution)+'</div>'; }
+  return html+'</div>';
+}
+
 function render(rep){
   const s=rep.summary;
   if(!currentJobId) currentJobId=new URLSearchParams(location.search).get('job');
@@ -279,20 +351,10 @@ function render(rep){
   } else if(!rep.conflicts.length){
     html+='<div class="empty">No cross-discipline conflicts detected.</div>';
   }
-  for(const c of rep.conflicts){
-    html+='<div class="conflict '+esc(c.severity)+'">'+
-      '<div class="row"><span class="cat">'+esc(c.category)+'</span>'+
-      '<span class="pill '+esc(c.severity)+'">'+esc(c.severity)+'</span></div>'+
-      '<div class="loc">'+esc(c.location)+'</div>'+
-      '<div class="meta">'+esc((c.disciplines||[]).join(' vs '))+
-        ' &middot; sheets '+sheetList(c.sheets)+'</div>'+
-      '<div class="desc">'+esc(c.description)+'</div>';
-    if(c.evidence&&c.evidence.length){
-      html+='<div class="ev">'+c.evidence.map(e=>
-        '<div><span class="d">'+esc(e.discipline)+'</span> ('+sheetSpan(e.sheet)+'): "'+esc(e.source_text)+'"</div>').join('')+'</div>';
-    }
-    if(c.recommended_resolution){ html+='<div class="reso">Resolution: '+esc(c.recommended_resolution)+'</div>'; }
-    html+='</div>';
+  for(const g of groupConflicts(rep.conflicts)){
+    html+='<details open style="margin-top:16px"><summary><b>'+esc(g.name)+' ('+g.items.length+')</b></summary>';
+    for(const c of g.items){ html+=conflictCard(c); }
+    html+='</details>';
   }
 
   const issues=rep.validated_issues||[];

tests/api/test_job_log.py

@@ -0,0 +1,77 @@
+import threading
+
+import pytest
+from fastapi.testclient import TestClient
+
+import backend.jobs as jobs
+from backend.main import app
+
+
+class _SyncThread:
+    """Drop-in threading.Thread replacement that runs the target inline."""
+
+    def __init__(self, target=None, args=(), kwargs=None, **_ignored):
+        self._target = target
+        self._args = args
+        self._kwargs = kwargs or {}
+
+    def start(self):
+        self._target(*self._args, **self._kwargs)
+
+
+@pytest.fixture
+def job_env(monkeypatch, tmp_path):
+    monkeypatch.setattr("backend.config.OUTPUT_DIR", str(tmp_path))
+    monkeypatch.setattr(threading, "Thread", _SyncThread)
+    monkeypatch.setattr("backend.jobs.send_conflict_report", lambda *a, **k: True)
+    pdf = tmp_path / "set.pdf"
+    pdf.write_bytes(b"%PDF-1.4\n")
+    yield tmp_path
+    jobs._jobs.clear()
+
+
+def test_job_log_captures_pipeline_output(job_env, monkeypatch):
+    def fake_runner(pdf_path, **kwargs):
+        print("STAGE banner: fake wave ran")
+        return {"source": "set.pdf", "summary": {"conflicts_found": 0}}
+
+    monkeypatch.setattr("backend.jobs.run_pipeline", fake_runner)
+    job_id = jobs.create_job(str(job_env / "set.pdf"), "set.pdf", pipeline_mode="classic")
+
+    log_path = job_env / job_id / "job.log"
+    assert log_path.is_file()
+    content = log_path.read_text()
+    assert "STAGE banner: fake wave ran" in content
+    assert job_id in content  # header line
+
+
+def test_job_log_endpoint_serves_log_and_404s(job_env, monkeypatch):
+    monkeypatch.setattr(
+        "backend.jobs.run_pipeline",
+        lambda pdf_path, **kw: {"source": "s", "summary": {}},
+    )
+    job_id = jobs.create_job(str(job_env / "set.pdf"), "set.pdf", pipeline_mode="classic")
+
+    client = TestClient(app)
+    ok = client.get(f"/jobs/{job_id}/log")
+    assert ok.status_code == 200
+    assert ok.headers["content-type"].startswith("text/plain")
+    assert "Job " + job_id in ok.text
+    assert client.get("/jobs/nope/log").status_code == 404
+
+
+def test_model_override_set_and_cleared_around_run(job_env, monkeypatch):
+    from backend import llm
+
+    seen = {}
+
+    def fake_runner(pdf_path, **kwargs):
+        seen["override"] = llm._model_override
+        return {"source": "set.pdf", "summary": {}}
+
+    monkeypatch.setattr("backend.jobs.run_pipeline", fake_runner)
+    jobs.create_job(str(job_env / "set.pdf"), "set.pdf",
+                    pipeline_mode="classic", model="openai/gpt-4o")
+
+    assert seen["override"] == "openai/gpt-4o"
+    assert llm._model_override is None  # cleared after the run

tests/api/test_models_api.py

@@ -0,0 +1,64 @@
+from fastapi.testclient import TestClient
+
+import backend.models as models
+from backend import config
+from backend.main import app
+
+_PAYLOAD = {
+    "data": [
+        {
+            "id": "openai/gpt-4o",
+            "name": "GPT-4o",
+            "pricing": {"prompt": "0.0000025", "completion": "0.00001"},
+            "context_length": 128000,
+        },
+        {
+            "id": "google/gemini-2.5-pro",
+            "name": "Gemini 2.5 Pro",
+            "pricing": {"prompt": "0.00000125", "completion": "0.00001"},
+            "context_length": 1000000,
+        },
+    ]
+}
+
+
+def _reset_cache():
+    models._cache["models"] = None
+    models._cache["at"] = 0.0
+
+
+def test_models_endpoint_normalizes_pricing(monkeypatch):
+    _reset_cache()
+    monkeypatch.setattr(models, "_fetch_openrouter_models", lambda: _PAYLOAD["data"])
+    client = TestClient(app)
+    response = client.get("/models")
+    assert response.status_code == 200
+    body = response.json()
+    assert body["default"] == config.MODEL
+    assert body["default_text"] == config.TEXT_MODEL
+    by_id = {m["id"]: m for m in body["models"]}
+    assert by_id["openai/gpt-4o"]["prompt_usd_per_mtok"] == 2.5
+    assert by_id["openai/gpt-4o"]["completion_usd_per_mtok"] == 10.0
+    assert by_id["openai/gpt-4o"]["context_length"] == 128000
+
+
+def test_models_endpoint_caches(monkeypatch):
+    _reset_cache()
+    calls = []
+
+    def fake_fetch():
+        calls.append(1)
+        return _PAYLOAD["data"]
+
+    monkeypatch.setattr(models, "_fetch_openrouter_models", fake_fetch)
+    client = TestClient(app)
+    assert client.get("/models").status_code == 200
+    assert client.get("/models").status_code == 200
+    assert len(calls) == 1
+
+
+def test_models_endpoint_502_on_fetch_failure(monkeypatch):
+    _reset_cache()
+    monkeypatch.setattr(models, "_fetch_openrouter_models", lambda: None)
+    client = TestClient(app)
+    assert client.get("/models").status_code == 502

tests/test_llm_model_override.py

@@ -0,0 +1,26 @@
+from backend import config
+from backend.llm import _resolve_backend, set_model_override
+
+
+def test_override_wins_for_vision_and_text():
+    set_model_override("openai/gpt-4o")
+    try:
+        assert _resolve_backend(has_images=True, model_override=None)["model"] == "openai/gpt-4o"
+        assert _resolve_backend(has_images=False, model_override=None)["model"] == "openai/gpt-4o"
+    finally:
+        set_model_override(None)
+
+
+def test_override_beats_per_call_model_arg():
+    set_model_override("openai/gpt-4o")
+    try:
+        # Agents pass their AGENT_*_MODEL per call; the user's job pick wins.
+        assert _resolve_backend(has_images=False, model_override="other/model")["model"] == "openai/gpt-4o"
+    finally:
+        set_model_override(None)
+
+
+def test_no_override_keeps_defaults():
+    set_model_override(None)
+    assert _resolve_backend(has_images=True, model_override=None)["model"] == config.MODEL
+    assert _resolve_backend(has_images=False, model_override=None)["model"] == config.TEXT_MODEL