feat(providers): add reasoning_echo_policy field for OpenAI-compat reasoning_content handling (#90)

Refs librefang/librefang#4842 — long-term replacement for the substring
match that the OpenAI driver currently uses to decide how to handle
`reasoning_content` on historical assistant turns.

Three provider-specific behaviours that the driver must distinguish at
wire time, now expressed as catalog metadata:

* `strip`  — DeepSeek R1 / deepseek-reasoner. The API rejects requests
  that carry reasoning_content on previous assistant messages.
* `echo`   — DeepSeek V4 Flash. Thinking mode is on by default and the
  API rejects multi-turn requests when assistant turns containing
  tool_calls don't echo back the original reasoning text. This is the
  bug surfaced in librefang/librefang#4842.
* `empty_string` — Moonshot / Kimi K2 family. The field must be present
  (empty string) on tool_calls turns, with thinking disabled wire-side
  for multi-turn compatibility.
* `none` (default) — most providers; field is omitted entirely.

V4 Pro is intentionally NOT marked `echo` — librefang#4842 reports it
working out-of-the-box; flip when there's an empirical reproducer.

Marks affected models:

  providers/deepseek.toml
    deepseek-v4-flash → echo
    deepseek-reasoner → strip
  providers/moonshot.toml
    kimi-k2.6, kimi-k2.5, kimi-k2 → empty_string
  providers/kimi-coding.toml
    kimi-for-coding → empty_string
  providers/byteplus-coding.toml
    kimi-k2.5 → empty_string
  providers/novita.toml
    moonshotai/kimi-k2-thinking → empty_string

Tooling:

* schema.toml registers the field with the four enum options and a
  `none` default so existing TOML files keep parsing unchanged.
* scripts/validate.py rejects unknown enum values; verified with a
  hand-crafted negative case (`reasoning_echo_policy = "bogus"` →
  validation fails with the expected message).
* `python3 scripts/validate.py` passes (267 models).

The librefang side that consumes this field will land in a follow-up
PR — until then, registry consumers ignore the field via
`#[serde(default)]` and the existing substring fallback continues to
work, so this commit is safe to ship independently.

scripts/validate.py

@@ -35,6 +35,7 @@ except ImportError:
 
 VALID_TIERS = {"frontier", "smart", "balanced", "fast", "local"}
 VALID_MODALITIES = {"text", "image", "audio", "video", "music"}
+VALID_REASONING_ECHO_POLICIES = {"none", "strip", "echo", "empty_string"}
 VALID_HAND_CATEGORIES = {
     "communication", "content", "data", "development",
     "devops", "finance", "productivity", "research", "social",
@@ -102,6 +103,13 @@ def validate_provider_file(filepath: Path) -> list[str]:
         if tier is not None and tier not in VALID_TIERS:
             errors.append(f"{filepath.name}: Model '{label}' invalid tier '{tier}'")
 
+        policy = model.get("reasoning_echo_policy")
+        if policy is not None and policy not in VALID_REASONING_ECHO_POLICIES:
+            errors.append(
+                f"{filepath.name}: Model '{label}' invalid reasoning_echo_policy "
+                f"'{policy}' (valid: {', '.join(sorted(VALID_REASONING_ECHO_POLICIES))})"
+            )
+
         for cost_field in (
             "input_cost_per_m",
             "output_cost_per_m",