38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
"""The Narrator role service (charter §5). Renders the digest, routes the model,
|
|
calls Ollama with one retry, logs the call (§10), and returns raw prose — tags
|
|
left intact for the client's TagExtractor to harvest (§2/§6). Raises ModelError
|
|
on failure for the handler to map to a 502.
|
|
"""
|
|
|
|
import random
|
|
from time import perf_counter
|
|
|
|
from . import call_log, ollama_client, prompts, routing
|
|
|
|
|
|
def run(canon_log: dict) -> str:
|
|
cfg = routing.for_role("narrator")
|
|
options = {**cfg.options, "seed": random.randint(0, 2**31 - 1)}
|
|
messages = [
|
|
{"role": "system", "content": prompts.system_prompt("narrator")},
|
|
{"role": "user", "content": prompts.render_digest(canon_log)},
|
|
]
|
|
|
|
start = perf_counter()
|
|
try:
|
|
text = ollama_client.chat(cfg.model, messages, options, think=cfg.think)
|
|
except ollama_client.ModelError as exc:
|
|
call_log.record(
|
|
role="narrator", model=cfg.model, options=options, messages=messages,
|
|
canon_log=canon_log, ok=False,
|
|
latency_ms=int((perf_counter() - start) * 1000), error=str(exc),
|
|
)
|
|
raise
|
|
|
|
call_log.record(
|
|
role="narrator", model=cfg.model, options=options, messages=messages,
|
|
canon_log=canon_log, ok=True,
|
|
latency_ms=int((perf_counter() - start) * 1000), response=text,
|
|
)
|
|
return text
|