fix(llm): resolve catalog capabilities for reasoning-mode queries

reasoning_mode_for (the add/edit form's reasoning-knob endpoint) evaluated
rules against an empty capability set, so a declared provider whose modes
are capability-gated never offered the knob; only id-glob rules (deepseek,
openai, anthropic) could match. It now resolves the model's capabilities
from the provider catalog first.

DeclaredProvider also gains llm_model_info (find in the listing) — until
now only anthropic/ollama overrode it, which is why a declared model's
context_length never refreshed from the catalog either (maybe_refresh_meta
always got None).

And DeepInfra's entry learns a second mode: models tagged 'reasoning' but
not 'reasoning_effort' (R1, DeepSeek-V4-Flash/Pro) accept the plain effort
levels per DeepInfra's docs — graded steps stay behind the
reasoning_effort tag.

providers.yaml

@@ -190,13 +190,17 @@ providers:
       base_capabilities: [function_calling]
     reasoning:
       # Flat reasoning_effort (none/minimal/low/medium/high/xhigh/max);
-      # "none" disables reasoning where the model supports it. Models tagged
-      # `reasoning` but not `reasoning_effort` always think — no knob.
+      # "none" disables reasoning where the model supports it.
       request: { kind: effort, remap: { disabled: none } }
       modes:
         - when: { capability: reasoning_effort }
           values: [disabled, minimal, low, medium, high, xhigh, max]
           default: high
+        # Models tagged only `reasoning` (R1, DeepSeek-V4-…) accept the plain
+        # levels — graded steps are a `reasoning_effort`-tag affair.
+        - when: { capability: reasoning }
+          values: [disabled, low, medium, high]
+          default: high
 
   - id: lm_studio
     name: "LM Studio"