Evan
6785807633
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
Utility scripts for maintaining the LibreFang registry.
validate.py
Validates all TOML content files across the registry.
python scripts/validate.py
What It Checks
Per content type:
- Providers -- required fields, valid tiers, non-negative costs, no duplicate model IDs
- Agents -- required fields (name, description, module), name matches directory
- Hands -- required fields (id, name, description), valid category, [agent] section, id matches directory
- Integrations -- required fields (id, name), [transport] section, id matches filename
- Skills -- [skill] section with name, [runtime] with valid type
- Plugins -- name matches directory, [hooks] section, hook files exist
Cross-type checks:
- Routing alias collisions between agents and hands (reported as warnings)
- Cross-file duplicate model IDs within the same provider
Requirements
- Python 3.11+ (uses
tomllib) - Or Python 3.8+ with
pip install tomli
Exit Codes
0-- all checks passed1-- one or more validation errors