pi: patch omp to require reasoning_content for OpenRouter reasoning models

DeepSeek V4 Pro (and similar reasoning models reached via OpenRouter) reject
multi-turn requests in thinking mode with:

  400 The `reasoning_content` in the thinking mode must be passed back
  to the API.

omp's existing kimi placeholder injection (`requiresReasoningContentForToolCalls`)
covered this requirement only for `thinkingFormat == "openai"`. OpenRouter
sets `thinkingFormat == "openrouter"`, so the gate never fired even though
the underlying providers behind OpenRouter (DeepSeek, Kimi, etc.) all enforce
the same invariant.

This patch:

1. Extends `requiresReasoningContentForToolCalls` detection: any
   reasoning-capable model fronted by OpenRouter now sets the flag.
2. Extends the placeholder gate in `convertMessages` to accept
   `thinkingFormat == "openrouter"` alongside `"openai"`.

Cross-provider continuations are the dominant trigger: a conversation
warmed up by Anthropic Claude (whose reasoning is redacted/encrypted on
the wire) followed by a switch to DeepSeek V4 Pro via OpenRouter. omp
cannot synthesize plaintext `reasoning_content` from Anthropic's
encrypted blocks, so the placeholder satisfies DeepSeek's validator
without fabricating a reasoning trace. Real captured reasoning, when
present, short-circuits the placeholder via `hasReasoningField` and
survives intact.

Side benefit: also closes a latent gap where Kimi-via-OpenRouter
(`thinkingFormat == "openrouter"`) had the compat flag set but the
placeholder gate silently rejected it.

Applies cleanly on top of patch 0001.

home/progs/pi.nix

@@ -43,6 +43,10 @@ in
         # nullable unions with `Invalid tool parameters schema : field \`anyOf\`: missing field \`type\``.
         # Upstream PR: pending; applies cleanly against v14.2.1.
         ../../patches/omp/0001-openai-completions-retry-without-strict-on-deepseek-openrouter.patch
+        # Stub `reasoning_content` on tool-call assistant messages for OpenRouter reasoning models.
+        # Fixes DeepSeek V4 Pro et al. rejecting follow-up requests with `400 The \`reasoning_content\`
+        # in the thinking mode must be passed back to the API`. Mirrors the existing Kimi handling.
+        ../../patches/omp/0002-openai-completions-stub-reasoning-content-for-openrouter.patch
       ];
     }))
   ];