From eb98ff4c308eadd523857d60e391de00081fb71d Mon Sep 17 00:00:00 2001
From: "seahaven-openswe[bot]"
 <296972425+seahaven-openswe[bot]@users.noreply.github.com>
Date: Tue, 30 Jun 2026 15:31:22 -0400
Subject: [PATCH] feat: add 3 verified Fireworks models to selectable set (#79)

* Add 10 Fireworks models to selectable set

Surface additional Fireworks-served models in the profile editor so
they can be chosen per-thread, per-profile, and as team defaults. Each
entry carries its recommended efforts and image support; only MiniMax
M3 is multimodal.

Refs: #78

* Suppress reasoning_effort on non-reasoning models

Instruct-only Fireworks ids (kimi-k2-instruct-0905, mistral-large-3-fp8,
qwen3-30b-a3b-instruct-2507) don't reason, so sending reasoning_effort
either 400s (unusable at default effort) or is a silent no-op. Add a
per-model reasoning flag (default True) and omit the param entirely for
ids marked non-reasoning.

Refs: #78

* Gate out 7 undeployed Fireworks models

Account serverless probe returned 404 for 7 of the 10 proposed ids, so
only minimax-m3, gpt-oss-120b, and deepseek-v4-flash are callable. Keep
those 3 and drop the rest. All 3 survivors are reasoning-capable, so the
per-model reasoning-effort suppression added earlier is no longer needed
and is reverted.

Refs: #78

---------

Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
---
 agent/dashboard/options.py    | 21 ++++++++++++
 tests/test_fireworks_model.py | 61 ++++++++++++++++++++++++++++++++++-
 2 files changed, 81 insertions(+), 1 deletion(-)

diff --git a/agent/dashboard/options.py b/agent/dashboard/options.py
index bc26cc01..3d21fec5 100644
--- a/agent/dashboard/options.py
+++ b/agent/dashboard/options.py
@@ -42,6 +42,27 @@ SUPPORTED_MODELS: list[ModelOption] = [
         "default_effort": "high",
         "supports_images": False,
     },
+    {
+        "id": "fireworks:accounts/fireworks/models/minimax-m3",
+        "label": "MiniMax M3",
+        "efforts": ["medium", "high"],
+        "default_effort": "high",
+        "supports_images": True,
+    },
+    {
+        "id": "fireworks:accounts/fireworks/models/gpt-oss-120b",
+        "label": "gpt-oss-120b",
+        "efforts": ["low", "medium", "high"],
+        "default_effort": "medium",
+        "supports_images": False,
+    },
+    {
+        "id": "fireworks:accounts/fireworks/models/deepseek-v4-flash",
+        "label": "DeepSeek V4 Flash",
+        "efforts": ["none", "medium", "high"],
+        "default_effort": "high",
+        "supports_images": False,
+    },
 ]
 
 SUPPORTED_MODEL_IDS: frozenset[str] = frozenset(m["id"] for m in SUPPORTED_MODELS)
diff --git a/tests/test_fireworks_model.py b/tests/test_fireworks_model.py
index 368f31ca..096a8085 100644
--- a/tests/test_fireworks_model.py
+++ b/tests/test_fireworks_model.py
@@ -1,12 +1,27 @@
 import pytest
 
-from agent.dashboard.options import SUPPORTED_MODELS
+from agent.dashboard.options import (
+    SUPPORTED_MODEL_IDS,
+    SUPPORTED_MODELS,
+    model_supports_effort,
+    model_supports_images,
+)
 from agent.utils.model import (
     fallback_model_id_for,
     fireworks_reasoning_effort_for,
     provider_model_kwargs,
 )
 
+_FIREWORKS_PREFIX = "fireworks:accounts/fireworks/models/"
+
+NEW_FIREWORKS_MODELS = {
+    "minimax-m3": (["medium", "high"], "high", True),
+    "gpt-oss-120b": (["low", "medium", "high"], "medium", False),
+    "deepseek-v4-flash": (["none", "medium", "high"], "high", False),
+}
+
+_ALL_EFFORTS = ("none", "low", "medium", "high", "xhigh", "max")
+
 
 def test_fireworks_reasoning_effort_maps_effort() -> None:
     for effort in ("none", "low", "medium", "high", "xhigh", "max"):
@@ -56,6 +71,50 @@ def test_provider_model_kwargs_for_fireworks_unknown_effort_omits_reasoning() ->
     assert "model_kwargs" not in kwargs
 
 
+@pytest.mark.parametrize("slug", sorted(NEW_FIREWORKS_MODELS))
+def test_new_fireworks_model_is_supported(slug: str) -> None:
+    model_id = _FIREWORKS_PREFIX + slug
+    assert model_id in SUPPORTED_MODEL_IDS
+    model = next(m for m in SUPPORTED_MODELS if m["id"] == model_id)
+    efforts, default_effort, supports_images = NEW_FIREWORKS_MODELS[slug]
+    assert model["efforts"] == efforts
+    assert model["default_effort"] == default_effort
+    assert model["supports_images"] is supports_images
+
+
+@pytest.mark.parametrize("slug", sorted(NEW_FIREWORKS_MODELS))
+def test_new_fireworks_model_supports_only_listed_efforts(slug: str) -> None:
+    model_id = _FIREWORKS_PREFIX + slug
+    efforts = NEW_FIREWORKS_MODELS[slug][0]
+    for effort in efforts:
+        assert model_supports_effort(model_id, effort) is True
+    for effort in _ALL_EFFORTS:
+        if effort not in efforts:
+            assert model_supports_effort(model_id, effort) is False
+
+
+@pytest.mark.parametrize(
+    "slug",
+    [
+        "qwen3-coder-480b-a35b-instruct",
+        "kimi-k2-thinking",
+        "kimi-k2-instruct-0905",
+        "glm-4p6",
+        "mistral-large-3-fp8",
+        "deepseek-v3p2",
+        "qwen3-30b-a3b-instruct-2507",
+    ],
+)
+def test_unavailable_fireworks_models_are_gated_out(slug: str) -> None:
+    assert _FIREWORKS_PREFIX + slug not in SUPPORTED_MODEL_IDS
+
+
+@pytest.mark.parametrize("slug", sorted(NEW_FIREWORKS_MODELS))
+def test_only_minimax_m3_supports_images(slug: str) -> None:
+    model_id = _FIREWORKS_PREFIX + slug
+    assert model_supports_images(model_id) is (slug == "minimax-m3")
+
+
 def test_fireworks_falls_back_to_bedrock() -> None:
     assert (
         fallback_model_id_for("fireworks:accounts/fireworks/models/deepseek-v4-pro")