enhancer ¶

Provider-agnostic prompt orchestration for the streaming server.

Three operations the streaming server needs:

• enhance — polish a user prompt (add cinematic detail, fix syntax)
• auto_extend — generate a follow-on prompt for loop generation
• rewrite — rewrite a seed prompt for a user-directed rewrite flow

All three share the same orchestration: pick a provider in priority order, submit an LLMRequest, fall back to the next provider on retryable errors, and surface a structured :class:LLMResponse back to the caller.

System prompts are loaded from system_prompt_dir on construction and can be hot-reloaded via :meth:PromptEnhancer.reload_system_prompts. The streaming server's management endpoint calls that method in response to a rewrite_seed_prompts_started frame.

PromptEnhancer(*, providers: Sequence[LLMProvider], model: str, timeout_ms: int = 20000, temperature: float = 0.7, max_tokens: int | None = 256, system_prompt_dir: str | None = None)

enhancer = PromptEnhancer(
    providers=[CerebrasProvider(), GroqProvider()],
    model="gpt-oss-120b",
    system_prompt_dir="/etc/fastvideo/prompts",
)
response = await enhancer.enhance("a fox running through snow")

80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98

def __init__(
    self,
    *,
    providers: Sequence[LLMProvider],
    model: str,
    timeout_ms: int = 20000,
    temperature: float = 0.7,
    max_tokens: int | None = 256,
    system_prompt_dir: str | None = None,
) -> None:
    if not providers:
        raise ValueError("PromptEnhancer requires at least one LLMProvider")
    self._providers = list(providers)
    self._model = model
    self._timeout_ms = timeout_ms
    self._temperature = temperature
    self._max_tokens = max_tokens
    self._system_prompt_dir = system_prompt_dir
    self._system_prompts = self._load_system_prompts()

register_provider(provider: LLMProvider, *, priority: int = -1) -> None

104
105
106
107
108
109
110

def register_provider(self, provider: LLMProvider, *, priority: int = -1) -> None:
    """Insert an additional provider. ``priority=0`` makes it primary;
    ``priority=-1`` (default) appends as a fallback."""
    if priority < 0:
        self._providers.append(provider)
    else:
        self._providers.insert(priority, provider)

reload_system_prompts() -> None

112
113
114
115
116
117
118
119
120

def reload_system_prompts(self) -> None:
    """Re-read the system prompt files from ``system_prompt_dir``.

    The streaming server exposes this via a management endpoint so
    operators can iterate on prompt templates without restarting
    workers.
    """
    self._system_prompts = self._load_system_prompts()
    logger.info("prompt enhancer: reloaded system prompts from %s", self._system_prompt_dir or "defaults")