Add Fireworks AI platform (provider 6)

The 9th registry row, pure Groq pattern: id "fireworks",
FIREWORKS_API_KEY > auth.json "fireworks" scope,
https://api.fireworks.ai/inference/v1 (note /inference/v1) with
KIGI_FIREWORKS_BASE_URL override, OpenAI listing + ChatCompletions +
Passthrough dialect, enrichment-backed metadata (models_dev_id
fireworks-ai) with the tool-calling listing restriction.

Fireworks native ids are deeply slashed (accounts/fireworks/models/glm-5p2);
the e2e pins the full round-trip: the managed key
(fireworks/accounts/fireworks/models/glm-5p2) parses back on the first
slash, and — the 404-risk property — the NATIVE id rides the inference
wire (entry.model and the resolved SamplerConfig.model) while the
fireworks/ prefix stays internal routing only.

Review (models.dev provider.toml + Fireworks docs): row facts confirmed,
registry integrity at 9, counts complete, e2e strong on all axes, zero
defects. One tradeoff logged as debt: restrict_to_enriched drops
fine-tuned/account-scoped deployed models (a headline Fireworks feature)
that can never be in models.dev.
This commit is contained in:
2026-07-21 11:03:50 -04:00
parent 9953a26b8d
commit e373ff8b29
4 changed files with 158 additions and 9 deletions
@@ -596,7 +596,8 @@ mod tests {
"anthropic",
"deepseek",
"groq",
"mistral"
"mistral",
"fireworks"
]
);
assert_eq!(default_id(&built), Some(XAI_API_KEY_METHOD_ID));
@@ -627,7 +628,8 @@ mod tests {
"anthropic",
"deepseek",
"groq",
"mistral"
"mistral",
"fireworks"
]
);
assert_eq!(default_id(&built), Some(CACHED_TOKEN_AUTH_METHOD_ID));
@@ -651,7 +653,8 @@ mod tests {
"anthropic",
"deepseek",
"groq",
"mistral"
"mistral",
"fireworks"
]
);
assert_eq!(default_id(&built), Some(CACHED_TOKEN_AUTH_METHOD_ID));
@@ -678,7 +681,8 @@ mod tests {
"anthropic",
"deepseek",
"groq",
"mistral"
"mistral",
"fireworks"
]
);
assert_eq!(default_id(&built), None);