Merge remote-tracking branch 'origin/main' into codex/repair-pr-442

tools/audio/elevenlabs_tts.py

@@ -36,7 +36,9 @@ class ElevenLabsTTS(BaseTool):
     install_instructions = (
         "Set the ELEVENLABS_API_KEY environment variable:\n"
         "  export ELEVENLABS_API_KEY=your_key_here\n"
-        "Get a key at https://elevenlabs.io"
+        "Get a key at https://elevenlabs.io\n"
+        "If fal_elevenlabs_tts is available, use it instead to access ElevenLabs "
+        "speech through fal.ai without a separate ElevenLabs key."
     )
     fallback = "openai_tts"
     fallback_tools = ["openai_tts", "piper_tts"]

tools/audio/fal_elevenlabs_music.py

@@ -0,0 +1,231 @@
+"""Generate music with ElevenLabs Music through fal.ai.
+
+This provider uses OpenMontage's shared ``FAL_KEY`` credential and the fal.ai
+queue API, then downloads the generated MP3 to a project-local path.
+"""
+
+from __future__ import annotations
+
+import math
+import os
+import time
+from pathlib import Path
+from typing import Any
+
+from tools.base_tool import (
+    BaseTool,
+    Determinism,
+    ExecutionMode,
+    ResourceProfile,
+    RetryPolicy,
+    ToolResult,
+    ToolRuntime,
+    ToolStability,
+    ToolStatus,
+    ToolTier,
+)
+
+
+class FalElevenLabsMusic(BaseTool):
+    """Generate a precisely timed music track through fal.ai."""
+
+    name = "fal_elevenlabs_music"
+    version = "0.1.0"
+    tier = ToolTier.GENERATE
+    capability = "music_generation"
+    provider = "fal.ai"
+    stability = ToolStability.BETA
+    execution_mode = ExecutionMode.ASYNC
+    determinism = Determinism.STOCHASTIC
+    runtime = ToolRuntime.API
+
+    dependencies = ["env:FAL_KEY"]
+    install_instructions = (
+        "Set FAL_KEY to a fal.ai API key. "
+        "Get one at https://fal.ai/dashboard/keys"
+    )
+    fallback_tools = ["music_gen", "google_music"]
+    agent_skills = ["music", "elevenlabs"]
+
+    capabilities = [
+        "generate_background_music",
+        "generate_instrumental",
+    ]
+    supports = {
+        "instrumental": True,
+        "style_control": True,
+        "exact_duration": True,
+    }
+    best_for = [
+        "precisely timed instrumental background music",
+        "high-quality ElevenLabs Music through a shared fal.ai account",
+        "short-form social video soundtracks",
+    ]
+    not_good_for = [
+        "offline generation",
+        "free music sourcing",
+        "sub-3-second sound effects",
+    ]
+
+    input_schema = {
+        "type": "object",
+        "required": ["prompt", "duration_seconds"],
+        "properties": {
+            "prompt": {
+                "type": "string",
+                "description": "Music description including mood, style, and instruments",
+            },
+            "duration_seconds": {
+                "type": "number",
+                "minimum": 3,
+                "maximum": 600,
+                "description": "Exact target length in seconds",
+            },
+            "force_instrumental": {
+                "type": "boolean",
+                "default": True,
+                "description": "Generate music without vocals",
+            },
+            "output_path": {
+                "type": "string",
+                "default": "fal_music_output.mp3",
+            },
+        },
+    }
+
+    resource_profile = ResourceProfile(
+        cpu_cores=1,
+        ram_mb=256,
+        vram_mb=0,
+        disk_mb=50,
+        network_required=True,
+    )
+    retry_policy = RetryPolicy(
+        max_retries=0,
+        retryable_errors=["rate_limit", "timeout"],
+    )
+    idempotency_key_fields = ["prompt", "duration_seconds", "force_instrumental"]
+    side_effects = [
+        "writes an MP3 file to output_path",
+        "submits one paid fal.ai generation request",
+    ]
+    user_visible_verification = [
+        "Listen to the generated music for mood, mix, and duration",
+    ]
+
+    _MODEL = "fal-ai/elevenlabs/music"
+    _QUEUE_URL = f"https://queue.fal.run/{_MODEL}"
+    _POLL_INTERVAL_SECONDS = 5
+    _MAX_WAIT_SECONDS = 600
+
+    def _get_api_key(self) -> str | None:
+        return os.environ.get("FAL_KEY") or os.environ.get("FAL_AI_API_KEY")
+
+    def get_status(self) -> ToolStatus:
+        return ToolStatus.AVAILABLE if self._get_api_key() else ToolStatus.UNAVAILABLE
+
+    def estimate_cost(self, inputs: dict[str, Any]) -> float:
+        """fal bills $0.80 per output minute, rounded up to a full minute."""
+        duration = inputs.get("duration_seconds")
+        if duration is None:
+            raise ValueError("duration_seconds is required for cost estimation")
+        return round(math.ceil(float(duration) / 60.0) * 0.80, 2)
+
+    def execute(self, inputs: dict[str, Any]) -> ToolResult:
+        api_key = self._get_api_key()
+        if not api_key:
+            return ToolResult(
+                success=False,
+                error="No fal.ai API key found. " + self.install_instructions,
+            )
+
+        duration = inputs.get("duration_seconds")
+        if duration is None:
+            return ToolResult(success=False, error="duration_seconds is required")
+        duration = float(duration)
+        if not 3 <= duration <= 600:
+            return ToolResult(
+                success=False,
+                error="duration_seconds must be between 3 and 600",
+            )
+
+        import requests
+
+        started = time.time()
+        headers = {
+            "Authorization": f"Key {api_key}",
+            "Content-Type": "application/json",
+        }
+        payload = {
+            "prompt": inputs["prompt"],
+            "music_length_ms": round(duration * 1000),
+            "force_instrumental": bool(inputs.get("force_instrumental", True)),
+        }
+
+        try:
+            submit_response = requests.post(
+                self._QUEUE_URL,
+                headers=headers,
+                json=payload,
+                timeout=30,
+            )
+            submit_response.raise_for_status()
+            queue_data = submit_response.json()
+            status_url = queue_data["status_url"]
+            response_url = queue_data["response_url"]
+
+            deadline = time.monotonic() + self._MAX_WAIT_SECONDS
+            while True:
+                if time.monotonic() >= deadline:
+                    return ToolResult(
+                        success=False,
+                        error="fal.ai music generation timed out while waiting in the queue",
+                        duration_seconds=round(time.time() - started, 2),
+                    )
+                time.sleep(self._POLL_INTERVAL_SECONDS)
+                status_response = requests.get(status_url, headers=headers, timeout=20)
+                status_response.raise_for_status()
+                status = status_response.json().get("status", "UNKNOWN")
+                if status == "COMPLETED":
+                    break
+                if status in {"FAILED", "CANCELLED"}:
+                    return ToolResult(
+                        success=False,
+                        error=f"fal.ai music generation {status.lower()}",
+                        duration_seconds=round(time.time() - started, 2),
+                    )
+
+            result_response = requests.get(response_url, headers=headers, timeout=30)
+            result_response.raise_for_status()
+            result_data = result_response.json()
+            audio_url = result_data["audio"]["url"]
+
+            audio_response = requests.get(audio_url, timeout=120)
+            audio_response.raise_for_status()
+            output_path = Path(inputs.get("output_path", "fal_music_output.mp3"))
+            output_path.parent.mkdir(parents=True, exist_ok=True)
+            output_path.write_bytes(audio_response.content)
+        except Exception as exc:
+            safe_error = str(exc).replace(api_key, "[REDACTED]")
+            return ToolResult(
+                success=False,
+                error=f"fal.ai ElevenLabs Music generation failed: {safe_error}",
+                duration_seconds=round(time.time() - started, 2),
+            )
+
+        return ToolResult(
+            success=True,
+            data={
+                "provider": "fal.ai",
+                "model": self._MODEL,
+                "prompt": inputs["prompt"],
+                "duration_seconds": duration,
+                "force_instrumental": payload["force_instrumental"],
+                "output": str(output_path),
+                "format": "mp3",
+            },
+            artifacts=[str(output_path)],
+            cost_usd=self.estimate_cost(inputs),
+            duration_seconds=round(time.time() - started, 2),
+            model=self._MODEL,
+        )

tools/audio/fal_elevenlabs_tts.py

@@ -0,0 +1,359 @@
+"""Generate ElevenLabs speech through fal.ai using the shared FAL credential."""
+
+from __future__ import annotations
+
+import os
+import time
+from pathlib import Path
+from typing import Any
+
+from tools.base_tool import (
+    BaseTool,
+    Determinism,
+    ExecutionMode,
+    ResourceProfile,
+    RetryPolicy,
+    ToolResult,
+    ToolRuntime,
+    ToolStability,
+    ToolStatus,
+    ToolTier,
+)
+
+
+class FalElevenLabsTTS(BaseTool):
+    """Generate expressive narration with ElevenLabs models hosted by fal.ai."""
+
+    name = "fal_elevenlabs_tts"
+    version = "0.1.0"
+    tier = ToolTier.VOICE
+    capability = "tts"
+    provider = "fal.ai"
+    stability = ToolStability.BETA
+    execution_mode = ExecutionMode.ASYNC
+    determinism = Determinism.STOCHASTIC
+    runtime = ToolRuntime.API
+
+    dependencies = ["env:FAL_KEY"]
+    install_instructions = (
+        "Set FAL_KEY to a fal.ai API key. No separate ElevenLabs key is needed. "
+        "Get a fal.ai key at https://fal.ai/dashboard/keys"
+    )
+    fallback_tools = ["google_tts", "piper_tts", "elevenlabs_tts"]
+    agent_skills = ["elevenlabs"]
+
+    capabilities = [
+        "text_to_speech",
+        "voice_selection",
+        "expressive_delivery",
+        "multilingual",
+        "word_timestamps",
+    ]
+    supports = {
+        "voice_cloning": False,
+        "multilingual": True,
+        "offline": False,
+        "native_audio": True,
+        "inline_audio_tags": True,
+        "word_timestamps": True,
+    }
+    best_for = [
+        "expressive ElevenLabs narration through an existing fal.ai connection",
+        "emotionally directed voiceover with Eleven v3 audio tags",
+        "multilingual narration without a separate ElevenLabs credential",
+    ]
+    not_good_for = [
+        "offline generation",
+        "voice cloning or private custom ElevenLabs voices",
+    ]
+
+    _MODELS = {
+        "eleven-v3": "fal-ai/elevenlabs/tts/eleven-v3",
+        "multilingual-v2": "fal-ai/elevenlabs/tts/multilingual-v2",
+        "turbo-v2.5": "fal-ai/elevenlabs/tts/turbo-v2.5",
+    }
+    _MODEL_ALIASES = {
+        "eleven_v3": "eleven-v3",
+        "eleven_multilingual_v2": "multilingual-v2",
+        "multilingual_v2": "multilingual-v2",
+        "eleven_turbo_v2_5": "turbo-v2.5",
+        "turbo_v2_5": "turbo-v2.5",
+        **{value: key for key, value in _MODELS.items()},
+    }
+    _PRICE_PER_CHARACTER = {
+        "eleven-v3": 0.0001,
+        "multilingual-v2": 0.0001,
+        "turbo-v2.5": 0.00005,
+    }
+    _POLL_INTERVAL_SECONDS = 2
+    _MAX_WAIT_SECONDS = 300
+
+    input_schema = {
+        "type": "object",
+        "required": ["text"],
+        "properties": {
+            "text": {
+                "type": "string",
+                "description": "Text to speak. Eleven v3 supports inline tags such as [whispers].",
+            },
+            "voice": {
+                "type": "string",
+                "default": "Rachel",
+                "description": "fal.ai ElevenLabs voice name or ID",
+            },
+            "voice_id": {
+                "type": "string",
+                "description": "Alias for voice, for compatibility with tts_selector",
+            },
+            "model_id": {
+                "type": "string",
+                "default": "eleven-v3",
+                "description": "eleven-v3, multilingual-v2, or turbo-v2.5",
+            },
+            "stability": {
+                "type": "number",
+                "default": 0.5,
+                "minimum": 0,
+                "maximum": 1,
+            },
+            "similarity_boost": {
+                "type": "number",
+                "default": 0.75,
+                "minimum": 0,
+                "maximum": 1,
+            },
+            "style": {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 1,
+            },
+            "speed": {
+                "type": "number",
+                "default": 1.0,
+                "minimum": 0.7,
+                "maximum": 1.2,
+            },
+            "language_code": {
+                "type": "string",
+                "description": "Optional ISO 639-1 language code",
+            },
+            "timestamps": {
+                "type": "boolean",
+                "default": False,
+            },
+            "apply_text_normalization": {
+                "type": "string",
+                "default": "auto",
+                "enum": ["auto", "on", "off"],
+            },
+            "output_format": {
+                "type": "string",
+                "default": "mp3_44100_128",
+                "enum": [
+                    "mp3_22050_32",
+                    "mp3_44100_64",
+                    "mp3_44100_96",
+                    "mp3_44100_128",
+                    "mp3_44100_192",
+                    "pcm_16000",
+                    "pcm_24000",
+                    "pcm_44100",
+                    "pcm_48000",
+                    "opus_48000_64",
+                    "opus_48000_96",
+                    "opus_48000_128",
+                    "opus_48000_192",
+                ],
+            },
+            "seed": {"type": "integer"},
+            "output_path": {"type": "string"},
+        },
+    }
+
+    resource_profile = ResourceProfile(
+        cpu_cores=1,
+        ram_mb=256,
+        vram_mb=0,
+        disk_mb=50,
+        network_required=True,
+    )
+    retry_policy = RetryPolicy(
+        max_retries=0,
+        retryable_errors=["rate_limit", "timeout"],
+    )
+    idempotency_key_fields = [
+        "text",
+        "voice",
+        "voice_id",
+        "model_id",
+        "stability",
+        "similarity_boost",
+        "style",
+        "speed",
+        "language_code",
+        "seed",
+    ]
+    side_effects = [
+        "writes an audio file to output_path",
+        "submits one paid fal.ai ElevenLabs speech request",
+    ]
+    user_visible_verification = [
+        "Listen to the generated voice sample before approving full narration",
+    ]
+
+    def _get_api_key(self) -> str | None:
+        return os.environ.get("FAL_KEY") or os.environ.get("FAL_AI_API_KEY")
+
+    def get_status(self) -> ToolStatus:
+        return ToolStatus.AVAILABLE if self._get_api_key() else ToolStatus.UNAVAILABLE
+
+    def _resolve_model(self, requested: str | None) -> tuple[str, str]:
+        model_name = requested or "eleven-v3"
+        model_name = self._MODEL_ALIASES.get(model_name, model_name)
+        if model_name not in self._MODELS:
+            choices = ", ".join(self._MODELS)
+            raise ValueError(f"model_id must be one of: {choices}")
+        return model_name, self._MODELS[model_name]
+
+    def estimate_cost(self, inputs: dict[str, Any]) -> float:
+        model_name, _ = self._resolve_model(inputs.get("model_id"))
+        return round(
+            len(inputs.get("text", "")) * self._PRICE_PER_CHARACTER[model_name],
+            4,
+        )
+
+    @staticmethod
+    def _output_extension(output_format: str) -> str:
+        return {
+            "mp3": "mp3",
+            "pcm": "pcm",
+            "opus": "opus",
+        }.get(output_format.split("_", 1)[0], "audio")
+
+    def execute(self, inputs: dict[str, Any]) -> ToolResult:
+        api_key = self._get_api_key()
+        if not api_key:
+            return ToolResult(
+                success=False,
+                error="No fal.ai API key found. " + self.install_instructions,
+            )
+
+        text = str(inputs.get("text", "")).strip()
+        if not text:
+            return ToolResult(success=False, error="text is required")
+
+        try:
+            model_name, model_id = self._resolve_model(inputs.get("model_id"))
+        except ValueError as exc:
+            return ToolResult(success=False, error=str(exc))
+
+        stability = float(inputs.get("stability", 0.5))
+        similarity_boost = float(inputs.get("similarity_boost", 0.75))
+        speed = float(inputs.get("speed", 1.0))
+        if not 0 <= stability <= 1 or not 0 <= similarity_boost <= 1:
+            return ToolResult(
+                success=False,
+                error="stability and similarity_boost must be between 0 and 1",
+            )
+        if not 0.7 <= speed <= 1.2:
+            return ToolResult(success=False, error="speed must be between 0.7 and 1.2")
+
+        output_format = inputs.get("output_format", "mp3_44100_128")
+        voice = inputs.get("voice") or inputs.get("voice_id") or "Rachel"
+        payload: dict[str, Any] = {
+            "text": text,
+            "voice": voice,
+            "stability": stability,
+            "similarity_boost": similarity_boost,
+            "speed": speed,
+            "timestamps": bool(inputs.get("timestamps", False)),
+            "apply_text_normalization": inputs.get("apply_text_normalization", "auto"),
+            "output_format": output_format,
+        }
+        for optional in ("language_code", "seed", "style"):
+            if inputs.get(optional) is not None:
+                payload[optional] = inputs[optional]
+
+        import requests
+
+        started = time.time()
+        headers = {
+            "Authorization": f"Key {api_key}",
+            "Content-Type": "application/json",
+        }
+        queue_url = f"https://queue.fal.run/{model_id}"
+
+        try:
+            submit_response = requests.post(
+                queue_url,
+                headers=headers,
+                json=payload,
+                timeout=30,
+            )
+            submit_response.raise_for_status()
+            queue_data = submit_response.json()
+            status_url = queue_data["status_url"]
+            response_url = queue_data["response_url"]
+
+            deadline = time.monotonic() + self._MAX_WAIT_SECONDS
+            while True:
+                if time.monotonic() >= deadline:
+                    return ToolResult(
+                        success=False,
+                        error="fal.ai ElevenLabs speech timed out while waiting in the queue",
+                        duration_seconds=round(time.time() - started, 2),
+                    )
+                time.sleep(self._POLL_INTERVAL_SECONDS)
+                status_response = requests.get(status_url, headers=headers, timeout=20)
+                status_response.raise_for_status()
+                status = status_response.json().get("status", "UNKNOWN")
+                if status == "COMPLETED":
+                    break
+                if status in {"FAILED", "CANCELLED"}:
+                    return ToolResult(
+                        success=False,
+                        error=f"fal.ai ElevenLabs speech {status.lower()}",
+                        duration_seconds=round(time.time() - started, 2),
+                    )
+
+            result_response = requests.get(response_url, headers=headers, timeout=30)
+            result_response.raise_for_status()
+            result_data = result_response.json()
+            audio_url = result_data["audio"]["url"]
+
+            audio_response = requests.get(audio_url, timeout=120)
+            audio_response.raise_for_status()
+            default_output = f"fal_elevenlabs_tts.{self._output_extension(output_format)}"
+            output_path = Path(inputs.get("output_path", default_output))
+            output_path.parent.mkdir(parents=True, exist_ok=True)
+            output_path.write_bytes(audio_response.content)
+        except Exception as exc:
+            safe_error = str(exc).replace(api_key, "[REDACTED]")
+            return ToolResult(
+                success=False,
+                error=f"fal.ai ElevenLabs speech failed: {safe_error}",
+                duration_seconds=round(time.time() - started, 2),
+            )
+
+        data = {
+            "provider": self.provider,
+            "model": model_id,
+            "voice": voice,
+            "text_length": len(text),
+            "stability": stability,
+            "similarity_boost": similarity_boost,
+            "speed": speed,
+            "output": str(output_path),
+            "format": output_format,
+        }
+        if payload["timestamps"] and "timestamps" in result_data:
+            data["timestamps"] = result_data["timestamps"]
+
+        return ToolResult(
+            success=True,
+            data=data,
+            artifacts=[str(output_path)],
+            cost_usd=self.estimate_cost({**inputs, "model_id": model_name, "text": text}),
+            duration_seconds=round(time.time() - started, 2),
+            model=model_id,
+        )

tools/audio/google_tts.py

@@ -27,7 +27,6 @@ from tools.base_tool import (
 from tools.google_credentials import (
     get_access_token,
     service_account_configured,
-    has_google_credentials,
 )
 
 
@@ -44,7 +43,8 @@ class GoogleTTS(BaseTool):
 
     dependencies = []
     install_instructions = (
-        "Auth option A — API key: set GOOGLE_API_KEY (or GEMINI_API_KEY) to a\n"
+        "Auth option A — TTS-only API key: set GOOGLE_TTS_API_KEY.\n"
+        "  GOOGLE_API_KEY or GEMINI_API_KEY remain supported for broader Google setups.\n"
         "  Google Cloud API key with Text-to-Speech enabled.\n"
         "  Enable the API at https://console.cloud.google.com/apis/library/texttospeech.googleapis.com\n"
         "Auth option B — service account: set GOOGLE_APPLICATION_CREDENTIALS to the\n"
@@ -149,12 +149,16 @@ class GoogleTTS(BaseTool):
     }
 
     def _get_api_key(self) -> str | None:
-        return os.environ.get("GOOGLE_API_KEY") or os.environ.get("GEMINI_API_KEY")
+        return (
+            os.environ.get("GOOGLE_TTS_API_KEY")
+            or os.environ.get("GOOGLE_API_KEY")
+            or os.environ.get("GEMINI_API_KEY")
+        )
 
     def get_status(self) -> ToolStatus:
         # Available via either an API key or a service-account JSON. Both paths
         # are honoured by execute() — so this no longer over-reports.
-        if has_google_credentials():
+        if self._get_api_key() or service_account_configured():
             return ToolStatus.AVAILABLE
         return ToolStatus.UNAVAILABLE
 
@@ -204,7 +208,11 @@ class GoogleTTS(BaseTool):
         try:
             result = self._generate(inputs, api_key=api_key, bearer_token=bearer_token)
         except Exception as exc:
-            return ToolResult(success=False, error=f"Google TTS failed: {exc}")
+            safe_error = str(exc)
+            for credential in (api_key, bearer_token):
+                if credential:
+                    safe_error = safe_error.replace(credential, "[REDACTED]")
+            return ToolResult(success=False, error=f"Google TTS failed: {safe_error}")
 
         result.duration_seconds = round(time.time() - start, 2)
         result.cost_usd = self.estimate_cost(inputs)
@@ -266,16 +274,14 @@ class GoogleTTS(BaseTool):
         url = f"https://texttospeech.googleapis.com/{api_version}/text:synthesize"
 
         headers = {"Content-Type": "application/json"}
-        params: dict[str, str] = {}
         if bearer_token:
             headers["Authorization"] = f"Bearer {bearer_token}"
         elif api_key:
-            params["key"] = api_key
+            headers["x-goog-api-key"] = api_key
 
         response = requests.post(
             url,
             headers=headers,
-            params=params,
             json=payload,
             timeout=120,
         )

tools/audio/tts_selector.py

@@ -45,6 +45,10 @@ class TTSSelector(BaseTool):
                 "type": "string",
                 "description": "Provider-specific voice ID. Passed through to the selected TTS provider.",
             },
+            "voice": {
+                "type": "string",
+                "description": "Provider-specific voice name or ID. fal.ai ElevenLabs accepts names such as Rachel.",
+            },
             "voice_language": {
                 "type": "string",
                 "enum": ["zh", "en"],
@@ -58,7 +62,7 @@ class TTSSelector(BaseTool):
             },
             "model_id": {
                 "type": "string",
-                "description": "TTS model to use (e.g. eleven_multilingual_v2). Passed through to provider.",
+                "description": "TTS model to use (e.g. eleven-v3 or eleven_multilingual_v2). Passed through to provider.",
             },
             "stability": {
                 "type": "number", "minimum": 0, "maximum": 1,
@@ -100,6 +104,24 @@ class TTSSelector(BaseTool):
                 "default": "text",
                 "description": "Use 'ssml' only when the selected provider supports tags such as <break>.",
             },
+            "language_code": {
+                "type": "string",
+                "description": "Provider-specific language code, such as en-US for Google or en for fal.ai ElevenLabs.",
+            },
+            "timestamps": {
+                "type": "boolean",
+                "default": False,
+                "description": "Request word timestamps when the selected provider supports them.",
+            },
+            "apply_text_normalization": {
+                "type": "string",
+                "enum": ["auto", "on", "off"],
+                "description": "Text normalization mode for providers that support it.",
+            },
+            "seed": {
+                "type": "integer",
+                "description": "Optional generation seed for providers that support reproducible speech.",
+            },
             "voice_performance": {
                 "type": "object",
                 "description": "Structured voice-performance plan or section delivery cues from the script artifact.",

tools/graphics/google_imagen.py

@@ -119,9 +119,12 @@ class GoogleImagen(BaseTool):
                     "imagen-4.0-generate-001",
                     "imagen-4.0-fast-generate-001",
                     "imagen-4.0-ultra-generate-001",
+                    "gemini-2.5-flash-image",
                 ],
                 "default": "imagen-4.0-generate-001",
-                "description": "Imagen model variant",
+                "description": "Imagen model variant, or a Gemini image model "
+                "(gemini-*) routed through generate_content. Use "
+                "gemini-2.5-flash-image when the project has no Imagen access.",
             },
             "number_of_images": {
                 "type": "integer",
@@ -177,13 +180,111 @@ class GoogleImagen(BaseTool):
     def estimate_cost(self, inputs: dict[str, Any]) -> float:
         model = inputs.get("model", "imagen-4.0-generate-001")
         n = inputs.get("number_of_images", 1)
+        if model.startswith("gemini-"):
+            # ~1290 output tokens per image at $30/1M tokens
+            return 0.039 * n
         if "ultra" in model:
             return 0.06 * n
         if "fast" in model:
             return 0.02 * n
         return 0.04 * n
 
+    def _resolve_aspect_ratio(self, inputs: dict[str, Any]) -> str:
+        """Explicit aspect_ratio > derived from width/height > default 1:1."""
+        if "aspect_ratio" in inputs:
+            return inputs["aspect_ratio"]
+        if "width" in inputs and "height" in inputs:
+            import logging
+
+            aspect_ratio = _dims_to_aspect_ratio(inputs["width"], inputs["height"])
+            logging.getLogger(__name__).info(
+                "google_imagen: remapped %sx%s to nearest supported aspect ratio %s",
+                inputs["width"],
+                inputs["height"],
+                aspect_ratio,
+            )
+            return aspect_ratio
+        return "1:1"
+
+    def _execute_gemini(self, inputs: dict[str, Any], model: str) -> ToolResult:
+        """Generate via a Gemini image model (e.g. gemini-2.5-flash-image).
+
+        These models use generate_content with an image_config instead of the
+        Imagen :predict endpoint, and work on both auth paths (API key and
+        Vertex service account) through the shared genai client.
+        """
+        start = time.time()
+        try:
+            from google.genai import types
+            from tools.google_credentials import get_genai_client
+
+            client = get_genai_client()
+        except Exception as e:
+            return ToolResult(
+                success=False,
+                error=f"Failed to initialize Google GenAI client: {e}",
+            )
+
+        prompt = inputs["prompt"]
+        aspect_ratio = self._resolve_aspect_ratio(inputs)
+        number_of_images = inputs.get("number_of_images", 1)
+        config = types.GenerateContentConfig(
+            image_config=types.ImageConfig(aspect_ratio=aspect_ratio),
+        )
+
+        image_bytes: list[bytes] = []
+        try:
+            for _ in range(number_of_images):
+                response = client.models.generate_content(
+                    model=model, contents=prompt, config=config
+                )
+                for part in response.candidates[0].content.parts or []:
+                    inline = getattr(part, "inline_data", None)
+                    if inline and inline.data:
+                        image_bytes.append(inline.data)
+                        break
+        except Exception as e:
+            return ToolResult(
+                success=False, error=f"Gemini image generation failed: {e}"
+            )
+
+        if not image_bytes:
+            return ToolResult(
+                success=False,
+                error=f"No image data returned by {model} (text-only response).",
+            )
+
+        output_paths = self._output_paths(inputs.get("output_path"), len(image_bytes))
+        outputs: list[str] = []
+        for data, out_path in zip(image_bytes, output_paths):
+            out_path.parent.mkdir(parents=True, exist_ok=True)
+            out_path.write_bytes(data)
+            outputs.append(str(out_path))
+
+        return ToolResult(
+            success=True,
+            data={
+                "provider": "google_imagen",
+                "model": model,
+                "prompt": prompt,
+                "aspect_ratio": aspect_ratio,
+                "output": outputs[0],
+                "outputs": outputs,
+                "images_generated": len(outputs),
+            },
+            artifacts=outputs,
+            cost_usd=self.estimate_cost(inputs),
+            duration_seconds=round(time.time() - start, 2),
+            model=model,
+        )
+
     def execute(self, inputs: dict[str, Any]) -> ToolResult:
+        # Gemini image models go through generate_content via the shared genai
+        # client, which resolves auth (API key or Vertex service account) itself.
+        model = inputs.get("model", "imagen-4.0-generate-001")
+        if model.startswith("gemini-"):
+            return self._execute_gemini(inputs, model)
+
         # Two auth paths: an AI Studio API key, or a service-account JSON that
         # routes to Vertex AI (the AI Studio endpoint does not accept service
         # accounts). API key wins when both are present.
@@ -213,27 +314,9 @@ class GoogleImagen(BaseTool):
         import requests
 
         start = time.time()
-        model = inputs.get("model", "imagen-4.0-generate-001")
         prompt = inputs["prompt"]
 
-        import logging
-
-        logger = logging.getLogger(__name__)
-
-        # Resolve aspect ratio: explicit > derived from width/height > default
-        if "aspect_ratio" in inputs:
-            aspect_ratio = inputs["aspect_ratio"]
-        elif "width" in inputs and "height" in inputs:
-            requested_ratio = f"{inputs['width']}x{inputs['height']}"
-            aspect_ratio = _dims_to_aspect_ratio(inputs["width"], inputs["height"])
-            logger.info(
-                "google_imagen: remapped %s to nearest supported aspect ratio %s",
-                requested_ratio,
-                aspect_ratio,
-            )
-        else:
-            aspect_ratio = "1:1"
-
+        aspect_ratio = self._resolve_aspect_ratio(inputs)
         number_of_images = inputs.get("number_of_images", 1)
 
         parameters: dict[str, Any] = {

tools/graphics/hunyuan_image.py

@@ -0,0 +1,580 @@
+"""Tencent Hunyuan (腾讯混元) cloud image generation (3.0) via TokenHub API.
+
+Calls the Tencent TokenHub API (tokenhub.tencentmaas.com) using simple Bearer
+token authentication. This is the OpenAI-compatible API gateway for Tencent
+Hunyuan image models — no TC3-HMAC-SHA256 signing required.
+
+API flow: POST /v1/api/image/submit -> poll /v1/api/image/query ->
+download data[].url.
+
+Authentication uses a TokenHub API key obtained from the Tencent Cloud
+TokenHub console (https://console.cloud.tencent.com/tokenhub).
+"""
+
+from __future__ import annotations
+
+import os
+import time
+from pathlib import Path
+from typing import Any
+
+from tools.base_tool import (
+    BaseTool,
+    Determinism,
+    ExecutionMode,
+    ResourceProfile,
+    RetryPolicy,
+    ToolResult,
+    ToolRuntime,
+    ToolStability,
+    ToolStatus,
+    ToolTier,
+)
+
+_HOST = "tokenhub.tencentmaas.com"
+_SUBMIT_PATH = "/v1/api/image/submit"
+_QUERY_PATH = "/v1/api/image/query"
+
+# TokenHub model identifier for 混元生图 3.0
+_MODEL = "hy-image-v3.0"
+
+
+class HunyuanImage(BaseTool):
+    """Tencent Hunyuan cloud image generation (3.0) via TokenHub API."""
+
+    name = "hunyuan_image"
+    version = "0.1.0"
+    tier = ToolTier.GENERATE
+    capability = "image_generation"
+    provider = "hunyuan_cloud"
+    stability = ToolStability.EXPERIMENTAL
+    execution_mode = ExecutionMode.ASYNC
+    determinism = Determinism.SEEDED
+    runtime = ToolRuntime.API
+
+    dependencies = ["env:TENCENT_TOKENHUB_API_KEY"]
+    install_instructions = (
+        "Set TENCENT_TOKENHUB_API_KEY to your Tencent Cloud TokenHub API key.\n"
+        "  Get it at https://console.cloud.tencent.com/tokenhub"
+    )
+    agent_skills = ["visual-style"]
+
+    capabilities = ["generate_image", "text_to_image"]
+    supports = {
+        "negative_prompt": False,
+        "seed": True,
+        "custom_size": True,
+        "reference_image": True,
+        "prompt_rewrite": True,
+    }
+    best_for = [
+        "Hunyuan text-to-image via Tencent TokenHub API",
+        "simple Bearer-token auth (no TC3 signing required)",
+        "direct Tencent Cloud quota usage (not through a third-party gateway)",
+        "Chinese-language prompt understanding",
+    ]
+    not_good_for = [
+        "offline generation or air-gapped environments",
+        "users without Tencent Cloud account and real-name verification",
+    ]
+    fallback_tools = ["dashscope_image", "flux_image", "openai_image", "recraft_image"]
+
+    input_schema = {
+        "type": "object",
+        "required": ["prompt"],
+        "properties": {
+            "prompt": {
+                "type": "string",
+                "maxLength": 8192,
+                "description": (
+                    "Image description. Max 8192 UTF-8 characters. "
+                    "Supports Chinese and English. Be specific about subject, "
+                    "composition, style, and mood."
+                ),
+            },
+            "images": {
+                "type": "array",
+                "items": {"type": "string"},
+                "maxItems": 3,
+                "description": (
+                    "Reference images per upstream Images.N param (max 3). "
+                    "Each entry is a publicly accessible URL or a local file path "
+                    "(auto-encoded to base64 data URI). "
+                    "Single image: 50-5000px per side, base64 < 6MB. "
+                    "Formats: jpg/png/jpeg/webp/bmp/tiff."
+                ),
+            },
+            "resolution": {
+                "type": "string",
+                "default": "1024:1024",
+                "description": (
+                    'Image resolution as "W:H" (colon separator, per upstream '
+                    "Resolution param). W, H in [512, 2048], product (W*H) <= "
+                    '1024x1024 pixels. Examples: "1024:1024", "768:1024", '
+                    '"1024:576".'
+                ),
+            },
+            "seed": {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 4294967295,
+                "description": (
+                    "Random seed in [1, 4294967295]. "
+                    "Note: seed is ignored when revise is enabled (default)."
+                ),
+            },
+            "revise": {
+                "type": "integer",
+                "enum": [0, 1],
+                "default": 1,
+                "description": (
+                    "Prompt auto-rewrite toggle per upstream Revise param. "
+                    "1 = enabled (default, adds ~20s processing), 0 = disabled. "
+                    "When disabled, caller should handle prompt rewriting."
+                ),
+            },
+            "logo_add": {
+                "type": "integer",
+                "enum": [0, 1],
+                "default": 1,
+                "description": (
+                    "Add 'AI-generated' watermark per upstream LogoAdd param. "
+                    "1 = add watermark (default), 0 = no watermark. "
+                    "Values other than 0 or 1 are treated as 1."
+                ),
+            },
+            "logo_param": {
+                "type": "object",
+                "properties": {
+                    "logo_url": {
+                        "type": "string",
+                        "description": "Custom watermark image URL.",
+                    },
+                    "logo_image": {
+                        "type": "string",
+                        "description": "Custom watermark image as base64-encoded string.",
+                    },
+                },
+                "description": (
+                    "Custom watermark settings per upstream LogoParam. "
+                    "Default: \"图片由 AI 生成\" at bottom-right. "
+                    "Note: custom watermarks may not be supported by the engine "
+                    "(error: InvalidParameterValue.LogoParamErr)."
+                ),
+            },
+            "output_path": {
+                "type": "string",
+                "description": "Output file path for the generated image (PNG).",
+            },
+            "poll_interval_seconds": {
+                "type": "number",
+                "minimum": 2,
+                "default": 5.0,
+                "description": "Seconds between status polls.",
+            },
+            "timeout_seconds": {
+                "type": "integer",
+                "minimum": 60,
+                "default": 600,
+                "description": "Maximum seconds to wait for generation.",
+            },
+        },
+    }
+
+    resource_profile = ResourceProfile(
+        cpu_cores=1, ram_mb=512, vram_mb=0, disk_mb=100, network_required=True,
+    )
+    retry_policy = RetryPolicy(
+        max_retries=2,
+        backoff_seconds=2.0,
+        retryable_errors=["rate_limit", "timeout"],
+    )
+    idempotency_key_fields = [
+        "prompt",
+        "resolution",
+        "images",
+        "seed",
+        "revise",
+        "logo_add",
+        "logo_param",
+    ]
+    side_effects = [
+        "writes image file to output_path",
+        "calls Tencent TokenHub API (Bearer-token submit + poll + download)",
+    ]
+    user_visible_verification = [
+        "Inspect generated image for quality and prompt adherence",
+        "Check for watermark if logo_add=0 was requested",
+    ]
+
+    # ------------------------------------------------------------------
+    # Credential helpers
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _api_key() -> str | None:
+        val = os.environ.get("TENCENT_TOKENHUB_API_KEY", "")
+        if val and not val.strip().startswith("#"):
+            return val.strip()
+        return None
+
+    # ------------------------------------------------------------------
+    # Tool contract methods
+    # ------------------------------------------------------------------
+
+    def get_status(self) -> ToolStatus:
+        if self._api_key():
+            return ToolStatus.AVAILABLE
+        return ToolStatus.UNAVAILABLE
+
+    def estimate_cost(self, inputs: dict[str, Any]) -> float:
+        """Estimate cost in USD.
+
+        Tencent TokenHub credit-based pricing (1 credit = 1.2 RMB ≈ $0.167 USD):
+        - hy-image-v3.0: ~0.5 credits/image → ~$0.08
+
+        Source: https://cloud.tencent.com.cn/document/product/1823/130054
+        """
+        _CREDIT_TO_USD = 1.2 / 7.2  # 1 credit = 1.2 RMB, ~7.2 RMB/USD
+        credits = 0.5
+        return round(credits * _CREDIT_TO_USD, 2)
+
+    def estimate_runtime(self, inputs: dict[str, Any]) -> float:
+        """Estimate wall-clock time in seconds.
+
+        Per upstream docs, prompt rewrite (revise=1) adds ~20s. Including
+        queuing and download, 120s is a safe upper-bound.
+        """
+        return 120.0
+
+    # ------------------------------------------------------------------
+    # Main execution
+    # ------------------------------------------------------------------
+
+    def execute(self, inputs: dict[str, Any]) -> ToolResult:
+        api_key = self._api_key()
+        if not api_key:
+            return ToolResult(
+                success=False,
+                error="TENCENT_TOKENHUB_API_KEY not set. " + self.install_instructions,
+            )
+
+        start = time.time()
+        try:
+            result = self._generate(inputs, api_key=api_key)
+        except Exception as exc:
+            return ToolResult(
+                success=False,
+                error=f"Hunyuan TokenHub image generation failed: {self._safe_error(exc)}",
+            )
+
+        result.duration_seconds = round(time.time() - start, 2)
+        return result
+
+    # ------------------------------------------------------------------
+    # Generation pipeline
+    # ------------------------------------------------------------------
+
+    def _generate(
+        self, inputs: dict[str, Any], *, api_key: str,
+    ) -> ToolResult:
+        import requests
+
+        # Guard: refuse to make paid API calls without an explicit output_path.
+        # A CWD-relative default would leak files into the project root when
+        # called by selectors or other automated tooling.
+        if not inputs.get("output_path"):
+            return ToolResult(
+                success=False,
+                error="output_path is required for hunyuan_image generation.",
+            )
+
+        payload = self._build_payload(inputs)
+        task_id = self._submit_task(payload, model=_MODEL, api_key=api_key)
+        image_urls = self._poll_task(
+            task_id,
+            model=_MODEL,
+            api_key=api_key,
+            poll_interval=float(inputs.get("poll_interval_seconds", 5.0)),
+            timeout_seconds=int(inputs.get("timeout_seconds", 600)),
+        )
+
+        output_paths = self._resolve_output_paths(
+            inputs["output_path"],
+            count=len(image_urls),
+        )
+        for path, url in zip(output_paths, image_urls):
+            download = requests.get(url, timeout=120)
+            download.raise_for_status()
+            path.parent.mkdir(parents=True, exist_ok=True)
+            path.write_bytes(download.content)
+
+        return ToolResult(
+            success=True,
+            data={
+                "provider": "hunyuan_cloud",
+                "route": "tokenhub",
+                "model": _MODEL,
+                "prompt": inputs["prompt"],
+                "resolution": payload.get("resolution", "1024:1024"),
+                "revise": payload.get("revise", 1),
+                "logo_add": payload.get("logo_add", 1),
+                "task_id": task_id,
+                "output": str(output_paths[0]),
+                "outputs": [str(p) for p in output_paths],
+                "images_generated": len(output_paths),
+            },
+            artifacts=[str(p) for p in output_paths],
+            cost_usd=self.estimate_cost(inputs),
+            model=_MODEL,
+        )
+
+    # ------------------------------------------------------------------
+    # Payload construction
+    # ------------------------------------------------------------------
+
+    def _build_payload(self, inputs: dict[str, Any]) -> dict[str, Any]:
+        """Build the request body for TokenHub image submit.
+
+        TokenHub async endpoints use snake_case versions of the upstream
+        SubmitTextToImageJob parameter names (e.g. Resolution -> resolution,
+        Images -> images).
+        """
+        payload: dict[str, Any] = {
+            "prompt": inputs["prompt"],
+        }
+
+        # Optional parameters (snake_case of upstream SubmitTextToImageJob params)
+        if inputs.get("resolution"):
+            payload["resolution"] = inputs["resolution"]
+        if inputs.get("seed") is not None:
+            payload["seed"] = int(inputs["seed"])
+        if "revise" in inputs:
+            payload["revise"] = int(inputs["revise"])
+        if "logo_add" in inputs:
+            payload["logo_add"] = int(inputs["logo_add"])
+        if inputs.get("logo_param"):
+            logo_param: dict[str, str] = {}
+            lp = inputs["logo_param"]
+            if lp.get("logo_url"):
+                logo_param["logo_url"] = lp["logo_url"]
+            if lp.get("logo_image"):
+                logo_param["logo_image"] = lp["logo_image"]
+            if logo_param:
+                payload["logo_param"] = logo_param
+
+        # Reference images — maps to upstream Images.N
+        # TokenHub accepts URLs or base64 data URIs in the images array
+        image_refs = inputs.get("images")
+        if image_refs:
+            payload["images"] = self._resolve_images(image_refs)
+
+        return payload
+
+    @staticmethod
+    def _resolve_images(refs: list[str]) -> list[str]:
+        """Resolve reference images to strings for the TokenHub API.
+
+        Each entry may be:
+        - An HTTP(S) URL → passed through unchanged
+        - A data URI (``data:...``) → passed through unchanged
+        - A local file path → base64-encoded as a data URI
+
+        Per upstream docs: single image 50-5000px per side, base64 < 6MB.
+        Formats: jpg/jpeg/png/bmp/tiff/webp.
+        """
+        import base64
+
+        resolved: list[str] = []
+        for ref in refs:
+            if ref.startswith("data:") or ref.startswith("http://") or ref.startswith("https://"):
+                resolved.append(ref)
+                continue
+
+            image_path = Path(ref)
+            if not image_path.is_file():
+                raise FileNotFoundError(f"Reference image not found: {ref}")
+
+            raw = image_path.read_bytes()
+            max_raw = 6 * 1024 * 1024  # 6MB per upstream limit
+            if len(raw) > max_raw:
+                raise ValueError(
+                    f"Image too large ({len(raw)} bytes). Max ~6MB raw."
+                )
+
+            suffix = image_path.suffix.lower()
+            mime_map = {
+                ".jpg": "image/jpeg",
+                ".jpeg": "image/jpeg",
+                ".png": "image/png",
+                ".bmp": "image/bmp",
+                ".tiff": "image/tiff",
+                ".tif": "image/tiff",
+                ".webp": "image/webp",
+            }
+            mime = mime_map.get(suffix, "image/png")
+            data = base64.b64encode(raw).decode("ascii")
+            resolved.append(f"data:{mime};base64,{data}")
+        return resolved
+
+    # ------------------------------------------------------------------
+    # API communication (TokenHub OpenAI-compatible)
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _auth_headers(api_key: str) -> dict[str, str]:
+        """Build common request headers for TokenHub API calls."""
+        return {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+        }
+
+    def _submit_task(
+        self, payload: dict[str, Any], *, model: str, api_key: str,
+    ) -> str:
+        """Submit an image generation task and return the task ID.
+
+        POST /v1/api/image/submit
+        Request: {"model": "hy-image-v3.0", "prompt": "...", ...}
+        Response: {"id": "...", "status": "queued", ...}
+        """
+        import requests
+
+        body = {
+            "model": model,
+            **payload,
+        }
+        url = f"https://{_HOST}{_SUBMIT_PATH}"
+        resp = requests.post(
+            url,
+            json=body,
+            headers=self._auth_headers(api_key),
+            timeout=30,
+        )
+        data = self._json_or_raise(resp)
+        self._check_response(data)
+
+        task_id = data.get("id")
+        if not task_id:
+            raise RuntimeError(
+                f"TokenHub submit returned no task id: {data}"
+            )
+        return task_id
+
+    def _poll_task(
+        self,
+        task_id: str,
+        *,
+        model: str,
+        api_key: str,
+        poll_interval: float,
+        timeout_seconds: int,
+    ) -> list[str]:
+        """Poll /v1/api/image/query until completion, return image download URLs.
+
+        Response when completed:
+        {"status": "completed", "data": [{"url": "...", "revised_prompt": "..."}]}
+
+        The data array may contain multiple images. Each URL is valid for ~1 hour.
+        """
+        import requests
+
+        url = f"https://{_HOST}{_QUERY_PATH}"
+
+        deadline = time.time() + timeout_seconds
+        while time.time() < deadline:
+            time.sleep(poll_interval)
+
+            resp = requests.post(
+                url,
+                json={"model": model, "id": task_id},
+                headers=self._auth_headers(api_key),
+                timeout=30,
+            )
+            data = self._json_or_raise(resp)
+            self._check_response(data)
+
+            status = data.get("status", "")
+
+            if status == "completed":
+                result_data = data.get("data") or []
+                urls = [item.get("url") for item in result_data if item.get("url")]
+                if not urls:
+                    raise RuntimeError(
+                        f"TokenHub task {task_id} completed but no data[].url: {data}"
+                    )
+                return urls
+
+            if status == "failed":
+                error_info = data.get("error") or {}
+                error_msg = error_info.get("message", "unknown error")
+                raise RuntimeError(
+                    f"TokenHub task {task_id} failed: {error_msg}"
+                )
+
+            # queued / running / in_progress — continue polling
+            if status not in ("queued", "running", "in_progress"):
+                raise RuntimeError(
+                    f"TokenHub task {task_id} returned unknown status: {status}"
+                )
+
+        raise TimeoutError(
+            f"TokenHub task {task_id} did not finish within {timeout_seconds}s"
+        )
+
+    # ------------------------------------------------------------------
+    # Error handling helpers
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _safe_error(exc: Exception) -> str:
+        """Redact secret values from exception messages."""
+        msg = str(exc)
+        for var in ("TENCENT_TOKENHUB_API_KEY",):
+            val = os.environ.get(var, "")
+            if val:
+                msg = msg.replace(val, "[redacted]")
+        return msg
+
+    @staticmethod
+    def _json_or_raise(response: Any) -> dict[str, Any]:
+        """Parse JSON response body or raise with HTTP status."""
+        try:
+            return response.json()
+        except ValueError as exc:
+            raise RuntimeError(
+                f"Non-JSON response from TokenHub API: HTTP {response.status_code}"
+            ) from exc
+
+    @staticmethod
+    def _check_response(payload: dict[str, Any]) -> None:
+        """Check the TokenHub API response for errors.
+
+        TokenHub returns errors at the top level with an ``error`` field.
+        """
+        error = payload.get("error")
+        if error:
+            message = error.get("message", "unknown error")
+            code = error.get("code", error.get("type", "unknown"))
+            raise RuntimeError(
+                f"TokenHub API error: code={code}, message={message}"
+            )
+
+    # ------------------------------------------------------------------
+    # Output helpers
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _resolve_output_paths(base: str, count: int) -> list[Path]:
+        """Derive distinct paths for ``count`` images.
+
+        Single image keeps the base path unchanged; multiple images insert an
+        index before the extension (foo.png -> foo_1.png, foo_2.png, ...).
+        """
+        base_path = Path(base)
+        if count <= 1:
+            return [base_path]
+        stem = base_path.stem
+        suffix = base_path.suffix
+        parent = base_path.parent
+        return [parent / f"{stem}_{i}{suffix}" for i in range(1, count + 1)]

tools/graphics/image_selector.py

@@ -242,6 +242,25 @@ class ImageSelector(BaseTool):
             props = tool.input_schema.get("properties", {})
             if "query" in props and "query" not in adapted:
                 adapted["query"] = adapted.get("prompt", "")
+            # Normalize the selector's shared reference-image inputs for
+            # providers whose native contract accepts an ``images`` array.
+            if "images" in props and "images" not in adapted:
+                refs = (
+                    adapted.get("image_paths")
+                    or adapted.get("image_urls")
+                    or ([adapted["image_path"]] if adapted.get("image_path") else None)
+                    or ([adapted["image_url"]] if adapted.get("image_url") else None)
+                )
+                if refs:
+                    adapted["images"] = refs
+            # The selector exposes a provider-neutral ``model_name`` field,
+            # while several providers call the same input ``model``.
+            if (
+                "model_name" in adapted
+                and "model" in props
+                and "model" not in adapted
+            ):
+                adapted["model"] = adapted["model_name"]
             if "n" in adapted and "num_images" in props and "num_images" not in adapted:
                 adapted["num_images"] = adapted["n"]