feat(vision): vision_analyze returns pixels to vision-capable models, not aux text (#22955)

When the active main model has native vision and the provider supports
multimodal tool results (Anthropic, OpenAI Chat, Codex Responses, Gemini
3, OpenRouter, Nous), vision_analyze loads the image bytes and returns
them to the model as a multimodal tool-result envelope. The model then
sees the pixels directly on its next turn instead of receiving a lossy
text description from an auxiliary LLM.

Falls back to the legacy aux-LLM text path for non-vision models and
unverified providers.

Mirrors the architecture used in OpenCode, Claude Code, Codex CLI, and
Cline. All four converge on the same pattern: tool results carry image
content blocks for vision-capable provider/model combinations.

Changes
- tools/vision_tools.py: _vision_analyze_native fast path + provider
  capability table (_supports_media_in_tool_results). Schema description
  updated to reflect new behaviour.
- agent/codex_responses_adapter.py: function_call_output.output now
  accepts the array form for multimodal tool results (was string-only).
  Preflight validates input_text/input_image parts.
- agent/auxiliary_client.py: _RUNTIME_MAIN_PROVIDER/_MODEL globals so
  tools see the live CLI/gateway override, not the stale config.yaml
  default. set_runtime_main()/clear_runtime_main() helpers.
- run_agent.py: AIAgent.run_conversation calls set_runtime_main at turn
  start so vision_analyze's fast-path check sees the actual runtime.
- tests/conftest.py: clear runtime-main override between tests.

Tests
- tests/tools/test_vision_native_fast_path.py: provider capability
  table, envelope shape, fast-path gating (vision-capable model uses
  fast path; non-vision model falls through to aux).
- tests/run_agent/test_codex_multimodal_tool_result.py: list tool
  content becomes function_call_output.output array; preflight
  preserves arrays and drops unknown part types.

Live verified
- Opus 4.6 + Sonnet 4.6 on OpenRouter: model calls vision_analyze on a
  typed filepath, gets pixels back, reads exact text from images that
  no aux description could capture (font color irony, multi-line
  fruit-count list, etc.).

PR replaces the closed prior efforts (#16506 shipped the inbound user-
attached path; this PR closes the gap for tool-discovered images).

run_agent.py

@@ -11119,6 +11119,20 @@ class AIAgent:
 
         self._ensure_db_session()
 
+        # Tell auxiliary_client what the live main provider/model are for
+        # this turn. Used by tools whose behaviour depends on the active
+        # main model (e.g. vision_analyze's native fast path) so they see
+        # the CLI/gateway override instead of the stale config.yaml
+        # default. Idempotent — fine to call every turn.
+        try:
+            from agent.auxiliary_client import set_runtime_main
+            set_runtime_main(
+                getattr(self, "provider", "") or "",
+                getattr(self, "model", "") or "",
+            )
+        except Exception:
+            pass
+
         # Tag all log records on this thread with the session ID so
         # ``hermes logs --session <id>`` can filter a single conversation.
         from hermes_logging import set_session_context