feat: model_override adapter with parameterized adapter config

[mcowger]

Why

Some LLM providers don't respect reasoning-related fields in the request body. Instead, they expose reasoning variants as separate model names — e.g. deepseek-r1 (with reasoning) vs deepseek-r1-fast (without). When a client sends reasoning: { effort: "none" } or enable_thinking: false, the provider ignores it because the client addressed the "thinking" model, not the "fast" one.

Plexus currently has no way to bridge this gap — the router picks a target model, and that's what gets sent to the provider. There was no mechanism to say "if the client is asking for no reasoning, switch to the fast variant instead."

What This Enables

Conditional model rewriting based on request content. You can now configure rules that say:

"When the target model is deepseek-r1 AND any of these conditions are true (reasoning disabled, thinking turned off, budget set to zero, etc.), rewrite the model name to deepseek-r1-fast before sending it to the provider."

This means:

• Clients can keep using a single model alias (e.g. glm-5.1) and let Plexus automatically pick the right provider variant based on what features they're requesting
• Providers that use separate model names for reasoning/non-reasoning variants are now first-class citizens in Plexus — no manual model switching required
• The rewrite is transparent to the client — they still see the canonical model name in billing/usage tracking

Bonus Fix

The OpenAI chat→chat transformer was silently dropping any fields it didn't explicitly know about (e.g. enable_thinking, chat_template_kwargs, thinking_budget, budget_tokens, thinking). This meant even if you configured conditions for those fields, the adapter could never match them because the fields were gone by the time it saw the payload.

Now, same-API-type transformations (chat→chat) preserve all unknown fields from the original request body, overlaying only the fields that need explicit transformation. This makes the adapter useful for any non-standard field a provider might use.

How to Use It

Configure the model_override adapter on a per-model basis in the provider settings (via the Plexus UI or management API):

1. Open the provider in the UI, expand the model entry (e.g. zai-org/GLM-5.1-FP8)
2. Under Model Adapters, enable Model Override
3. Add rules specifying:
   • Match model — the provider model name to match against (e.g. zai-org/GLM-5.1-FP8)
   • Rewrite to — the model name to send instead (e.g. glm-5.1-fast)
   • Conditions — dotted-path fields and values, any match triggers the rewrite (OR semantics)

Example conditions for detecting "no reasoning" requests:

Field path	Value
reasoning.enabled	false
reasoning.effort	"none"
enable_thinking	false
thinking.type	"disabled"
chat_template_kwargs.enable_thinking	false
thinking_budget	0
budget_tokens	0

If value is left empty, the condition matches on field presence alone (any value).

Implementation Notes

• Adapter config upgraded from bare strings to uniform { name, options } entries. Legacy format is normalized lazily on read — no DB migration needed, rows self-heal on next save
• Adapter interface gains optional options parameter on all hooks; existing adapters are backward-compatible
• Frontend includes an inline rule editor for model_override conditions in the per-model adapter section
• 1344 backend tests passing, frontend build + typecheck + lint clean