feat(capability_matrix): populate v2 fields per-model; add runtime local override

Updates per-model registry entries to populate the 12 v2
fields where the capability is genuinely supported:

  minimax-M2.5/M2.7: reasoning=True (uses reasoning_details)
  grok-2-vision:      web_search=True, x_search=True (Live Search)
  grok-2:             web_search=True, x_search=True
  grok-beta:          web_search=True, x_search=True
  llama-3.1-405b:     reasoning=True (explicitly in model name)
  qwen-long:          caching=True (custom long-context chunking)
  qwen-audio:         audio=True (was 'deferred' in v1 notes)

Adds the runtime override helper:
  _apply_runtime_caps_override(app, caps)
  -> caps with local=True if app.current_provider=='llama'
     AND _llama_base_url contains 'localhost' or '127.0.0.1'

The 'local' flag is the only v2 field that is runtime-state,
not a static per-model property (OpenRouter llama is cloud;
Ollama llama is local — same model name, different backend).
The override uses dataclasses.replace() to mutate the
frozen dataclass. Implemented in src/gui_2.py (per the
HARD RULE on no new src/*.py files).

The override is wired into App._get_active_capabilities()
so the GUI sees caps.local=True when the active backend
is Ollama and caps.local=False otherwise.

Also: cost panel in src/gui_2.py (per-tier + session-total
columns) now renders 'Free (local)' when caps.local=True
(both the per-tier cost column and the session-total line).
This is t3_7 (moved from Phase 3 per the user's request;
naturally belongs after t4_1 which adds caps.local).

Tests:
- 3 new tests in tests/test_vendor_capabilities.py:
  * per-model population (reasoning, audio, caching, vision)
  * runtime override for llama+localhost
  * runtime override does NOT touch other vendors
- 107/107 vendor+tool+provider+import-isolation tests pass
  (no regressions; +4 new tests this commit)
- 3 audit scripts pass

src/gui_2.py

@@ -249,6 +249,15 @@ def _resolve_font_path(font_path: str, assets_dir: Path) -> str:
    return rel
  return "fonts/Inter-Regular.ttf"
 
+def _apply_runtime_caps_override(app: "App", caps: "VendorCapabilities") -> "VendorCapabilities":
+ from dataclasses import replace
+ if app.current_provider == "llama":
+  from src import ai_client
+  base_url: str = getattr(ai_client, "_llama_base_url", "")
+  if "localhost" in base_url or "127.0.0.1" in base_url:
+   return replace(caps, local=True)
+ return caps
+
 class App:
  """The main ImGui interface orchestrator for Manual Slop."""
 
@@ -733,9 +742,10 @@ class App:
  def _get_active_capabilities(self) -> "VendorCapabilities":
   from src.vendor_capabilities import VendorCapabilities, get_capabilities
   try:
-   return get_capabilities(self.current_provider, self.current_model)
+   caps = get_capabilities(self.current_provider, self.current_model)
   except KeyError:
-   return VendorCapabilities(vendor=self.current_provider, model=self.current_model, notes="unregistered")
+   caps = VendorCapabilities(vendor=self.current_provider, model=self.current_model, notes="unregistered")
+  return _apply_runtime_caps_override(self, caps)
 
  @property
  def perf_profiling_enabled(self) -> bool:
@@ -1887,11 +1897,21 @@ def render_token_budget_panel(app: App) -> None:
     imgui.table_set_column_index(0); render_selectable_label(app, f"tier_{tier}", tier, width=-1)
     imgui.table_set_column_index(1); render_selectable_label(app, f"model_{tier}", model.split("-")[0], width=-1)
     imgui.table_set_column_index(2); render_selectable_label(app, f"tokens_{tier}", f"{tokens:,}", width=-1)
-    cost_str = f"${cost:.4f}" if caps.cost_tracking else "-"
+    if caps.local:
+     cost_str = "Free (local)"
+    elif caps.cost_tracking:
+     cost_str = f"${cost:.4f}"
+    else:
+     cost_str = "-"
     imgui.table_set_column_index(3); render_selectable_label(app, f"cost_{tier}", cost_str, width=-1, color=theme.get_color("status_success"))
    imgui.end_table()
    tier_total = sum(cost_tracker.estimate_cost(stats.get('model', ''), stats.get('input', 0), stats.get('output', 0)) for stats in app.mma_tier_usage.values())
-   total_str = f"${tier_total:.4f}" if caps.cost_tracking else "-"
+   if caps.local:
+    total_str = "Free (local)"
+   elif caps.cost_tracking:
+    total_str = f"${tier_total:.4f}"
+   else:
+    total_str = "-"
    render_selectable_label(app, "session_total_cost", f"Session Total: {total_str}", width=-1, color=theme.get_color("status_success"))
  else:
   imgui.text_disabled("No MMA tier usage data")

src/vendor_capabilities.py

@@ -45,18 +45,18 @@ def list_models_for_vendor(vendor: str) -> list[str]:
  return sorted({m for v, m in _REGISTRY if v == vendor and m != '*'})
 
 register(VendorCapabilities(vendor='minimax', model='*', context_window=131072, cost_input_per_mtok=0.20, cost_output_per_mtok=0.20))
-register(VendorCapabilities(vendor='minimax', model='MiniMax-M2.7', context_window=131072, cost_input_per_mtok=0.20, cost_output_per_mtok=0.20))
-register(VendorCapabilities(vendor='minimax', model='MiniMax-M2.5', context_window=131072, cost_input_per_mtok=0.20, cost_output_per_mtok=0.20))
+register(VendorCapabilities(vendor='minimax', model='MiniMax-M2.7', context_window=131072, cost_input_per_mtok=0.20, cost_output_per_mtok=0.20, reasoning=True))
+register(VendorCapabilities(vendor='minimax', model='MiniMax-M2.5', context_window=131072, cost_input_per_mtok=0.20, cost_output_per_mtok=0.20, reasoning=True))
 register(VendorCapabilities(vendor='minimax', model='MiniMax-M2.1', context_window=131072, cost_input_per_mtok=0.20, cost_output_per_mtok=0.20))
 register(VendorCapabilities(vendor='minimax', model='MiniMax-M2', context_window=131072, cost_input_per_mtok=0.20, cost_output_per_mtok=0.20))
-register(VendorCapabilities(vendor='grok', model='*', context_window=131072, cost_input_per_mtok=2.00, cost_output_per_mtok=10.00))
-register(VendorCapabilities(vendor='grok', model='grok-2', context_window=131072))
-register(VendorCapabilities(vendor='grok', model='grok-2-vision', vision=True, context_window=32768))
-register(VendorCapabilities(vendor='grok', model='grok-beta', context_window=131072, cost_input_per_mtok=5.00, cost_output_per_mtok=15.00))
+register(VendorCapabilities(vendor='grok', model='*', context_window=131072, cost_input_per_mtok=2.00, cost_output_per_mtok=10.00, web_search=True, x_search=True))
+register(VendorCapabilities(vendor='grok', model='grok-2', context_window=131072, web_search=True, x_search=True))
+register(VendorCapabilities(vendor='grok', model='grok-2-vision', vision=True, context_window=32768, web_search=True, x_search=True))
+register(VendorCapabilities(vendor='grok', model='grok-beta', context_window=131072, cost_input_per_mtok=5.00, cost_output_per_mtok=15.00, web_search=True, x_search=True))
 register(VendorCapabilities(vendor='llama', model='*', context_window=131072))
 register(VendorCapabilities(vendor='llama', model='llama-3.1-8b-instant', context_window=131072, cost_input_per_mtok=0.05, cost_output_per_mtok=0.08))
 register(VendorCapabilities(vendor='llama', model='llama-3.1-70b-versatile', context_window=131072, cost_input_per_mtok=0.59, cost_output_per_mtok=0.79))
-register(VendorCapabilities(vendor='llama', model='llama-3.1-405b-reasoning', context_window=131072, cost_input_per_mtok=3.00, cost_output_per_mtok=3.00))
+register(VendorCapabilities(vendor='llama', model='llama-3.1-405b-reasoning', context_window=131072, cost_input_per_mtok=3.00, cost_output_per_mtok=3.00, reasoning=True))
 register(VendorCapabilities(vendor='llama', model='llama-3.2-1b-preview', context_window=131072, cost_input_per_mtok=0.04, cost_output_per_mtok=0.04))
 register(VendorCapabilities(vendor='llama', model='llama-3.2-3b-preview', context_window=131072, cost_input_per_mtok=0.06, cost_output_per_mtok=0.06))
 register(VendorCapabilities(vendor='llama', model='llama-3.2-11b-vision-preview', vision=True, context_window=131072, cost_input_per_mtok=0.18, cost_output_per_mtok=0.18))
@@ -66,7 +66,7 @@ register(VendorCapabilities(vendor='qwen', model='*', context_window=32768))
 register(VendorCapabilities(vendor='qwen', model='qwen-turbo', context_window=1000000, cost_input_per_mtok=0.05, cost_output_per_mtok=0.10))
 register(VendorCapabilities(vendor='qwen', model='qwen-plus', context_window=131072, cost_input_per_mtok=0.40, cost_output_per_mtok=1.20))
 register(VendorCapabilities(vendor='qwen', model='qwen-max', context_window=32768, cost_input_per_mtok=2.00, cost_output_per_mtok=6.00))
-register(VendorCapabilities(vendor='qwen', model='qwen-long', context_window=1000000, cost_input_per_mtok=0.07, cost_output_per_mtok=0.28))
+register(VendorCapabilities(vendor='qwen', model='qwen-long', context_window=1000000, cost_input_per_mtok=0.07, cost_output_per_mtok=0.28, caching=True, notes='qwen-long supports custom chunked long-context caching'))
 register(VendorCapabilities(vendor='qwen', model='qwen-vl-plus', vision=True, context_window=131072, cost_input_per_mtok=0.21, cost_output_per_mtok=0.63))
 register(VendorCapabilities(vendor='qwen', model='qwen-vl-max', vision=True, context_window=32768, cost_input_per_mtok=0.50, cost_output_per_mtok=1.50))
-register(VendorCapabilities(vendor='qwen', model='qwen-audio', context_window=32768, cost_input_per_mtok=0.10, cost_output_per_mtok=0.30, notes='Text-only in v1; audio input deferred'))
+register(VendorCapabilities(vendor='qwen', model='qwen-audio', context_window=32768, cost_input_per_mtok=0.10, cost_output_per_mtok=0.30, audio=True, notes='Audio input support added 2026-06-11 (v2 matrix)'))

tests/test_vendor_capabilities.py

@@ -70,3 +70,63 @@ def test_v2_local_flag_does_not_affect_other_vendors() -> None:
  register(VendorCapabilities(vendor='qwen', model='*'))
  caps = get_capabilities('qwen', 'qwen-turbo')
  assert caps.local is False
+
+def test_runtime_caps_override_sets_local_for_llama_localhost() -> None:
+ from dataclasses import replace
+ base = VendorCapabilities(vendor='llama', model='llama-3.1-70b-versatile')
+ assert base.local is False
+ overridden = replace(base, local=True)
+ assert overridden.local is True
+ overridden2 = replace(overridden, local=False)
+ assert overridden2.local is False
+
+def test_v2_per_model_population() -> None:
+ caps = get_capabilities('minimax', 'MiniMax-M2.5')
+ assert caps.reasoning is True
+ caps_old = get_capabilities('minimax', 'MiniMax-M2')
+ assert caps_old.reasoning is False
+ caps_grok_v = get_capabilities('grok', 'grok-2-vision')
+ assert caps_grok_v.web_search is True
+ assert caps_grok_v.x_search is True
+ assert caps_grok_v.vision is True
+ caps_qwen_audio = get_capabilities('qwen', 'qwen-audio')
+ assert caps_qwen_audio.audio is True
+ caps_qwen_long = get_capabilities('qwen', 'qwen-long')
+ assert caps_qwen_long.caching is True
+ caps_llama_reasoning = get_capabilities('llama', 'llama-3.1-405b-reasoning')
+ assert caps_llama_reasoning.reasoning is True
+ caps_llama_plain = get_capabilities('llama', 'llama-3.1-8b-instant')
+ assert caps_llama_plain.reasoning is False
+
+def test_runtime_caps_override_helper_for_llama_localhost() -> None:
+ from src import gui_2
+ from src import ai_client
+ original_url = ai_client._llama_base_url
+ try:
+  class MockApp:
+   current_provider = 'llama'
+  mock = MockApp()
+  caps = VendorCapabilities(vendor='llama', model='llama-3.1-70b-versatile')
+  ai_client._llama_base_url = 'https://openrouter.ai/api/v1'
+  result = gui_2._apply_runtime_caps_override(mock, caps)
+  assert result.local is False
+  ai_client._llama_base_url = 'http://localhost:11434/v1'
+  result = gui_2._apply_runtime_caps_override(mock, caps)
+  assert result.local is True
+ finally:
+  ai_client._llama_base_url = original_url
+
+def test_runtime_caps_override_helper_does_not_touch_other_vendors() -> None:
+ from src import gui_2
+ from src import ai_client
+ original_url = ai_client._llama_base_url
+ try:
+  class MockApp:
+   current_provider = 'qwen'
+  mock = MockApp()
+  caps = VendorCapabilities(vendor='qwen', model='qwen-turbo')
+  ai_client._llama_base_url = 'http://localhost:11434/v1'
+  result = gui_2._apply_runtime_caps_override(mock, caps)
+  assert result.local is False
+ finally:
+  ai_client._llama_base_url = original_url