refactor(server): adopt uv and modular typed FastAPI structure
This commit is contained in:
@@ -0,0 +1,16 @@
|
||||
"""Register routes in their original order without changing public paths."""
|
||||
|
||||
from fastapi import APIRouter
|
||||
|
||||
from s2s_client.api.routes import apipilot, caller, config, search, sessions
|
||||
from s2s_client.realtime.proxy import realtime_proxy
|
||||
from s2s_client.services.reasoning import reasoning
|
||||
|
||||
router = APIRouter()
|
||||
router.include_router(config.router)
|
||||
router.include_router(apipilot.router)
|
||||
router.add_api_route("/api/reasoning", reasoning, methods=["POST"])
|
||||
router.add_api_websocket_route("/v1/realtime", realtime_proxy)
|
||||
router.include_router(caller.router)
|
||||
router.include_router(search.router)
|
||||
router.include_router(sessions.router)
|
||||
@@ -0,0 +1,141 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Request
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
from s2s_client.models import requests as models_requests
|
||||
from s2s_client.providers import apipilot as providers_apipilot
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get("/api/apipilot/tools", response_model=None)
|
||||
async def apipilot_list_tools(
|
||||
request: Request,
|
||||
include_unauthorized: bool = True,
|
||||
refresh: bool = False,
|
||||
) -> dict[str, Any] | JSONResponse:
|
||||
"""Public proxy for ApiPilot tool discovery (guide §2.1).
|
||||
|
||||
Forwards Authorization / x-demo-session headers from the caller to the
|
||||
upstream backend verbatim and returns the list of `ToolDefinition` records
|
||||
exactly as documented:
|
||||
|
||||
{ "name": "...", "description": "...", "parameters": {...}, "requires_auth": true/false }
|
||||
|
||||
A short in-process TTL cache is applied (default 5 min, configurable via
|
||||
S2S_APIPILOT_TTL_SEC). The client may force a refresh via `?refresh=true`
|
||||
(e.g. after a user just logged in and previously saw only requires_auth tools)."""
|
||||
if not settings.S2S_APIPILOT_TOOLS_URL:
|
||||
return JSONResponse(
|
||||
status_code=501,
|
||||
content={
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "APIPILOT_NOT_CONFIGURED",
|
||||
"message": "ApiPilot no está disponible en este despliegue (S2S_APIPILOT_TOOLS_URL no establecido).",
|
||||
"status_code": 501,
|
||||
"raw": None,
|
||||
},
|
||||
},
|
||||
)
|
||||
auth, demo = providers_apipilot._apipilot_parse_authorization(request)
|
||||
try:
|
||||
tools = await providers_apipilot._apipilot_fetch_tools(
|
||||
auth_header=auth,
|
||||
demo_session=demo,
|
||||
include_unauthorized=bool(include_unauthorized),
|
||||
force_refresh=bool(refresh),
|
||||
)
|
||||
except HTTPException as exc:
|
||||
# Normalize to envelope-style payload so downstream code is uniform.
|
||||
detail = (
|
||||
exc.detail
|
||||
if isinstance(exc.detail, dict)
|
||||
else {
|
||||
"code": "APIPILOT_ERROR",
|
||||
"message": str(exc.detail) if exc.detail else "Error",
|
||||
"status_code": exc.status_code,
|
||||
"raw": None,
|
||||
}
|
||||
)
|
||||
return JSONResponse(
|
||||
status_code=exc.status_code,
|
||||
content={"success": False, "data": None, "error": detail},
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT] /api/apipilot/tools OK tools=%d include_unauthorized=%s refresh=%s",
|
||||
len(tools),
|
||||
bool(include_unauthorized),
|
||||
bool(refresh),
|
||||
)
|
||||
return {
|
||||
"success": True,
|
||||
"data": {
|
||||
"count": len(tools),
|
||||
"include_unauthorized": bool(include_unauthorized),
|
||||
"tools": tools,
|
||||
},
|
||||
"error": None,
|
||||
}
|
||||
|
||||
|
||||
@router.post("/api/apipilot/execute")
|
||||
async def apipilot_execute(request: Request, body: models_requests.ApipilotExecuteRequest) -> JSONResponse:
|
||||
"""Public proxy for ApiPilot /execute (guide §2.2).
|
||||
|
||||
Accepts `{name, arguments}`, runs the mandatory PRE-CHECK flow (fresh tool
|
||||
discovery, `requires_auth` gate, strict JSON-Schema argument validation),
|
||||
forwards the request to the upstream backend, and returns the envelope
|
||||
`{success, data, error}`.
|
||||
|
||||
Show only `error.message` to the end user. `error.code`, `error.status_code`
|
||||
and `error.raw` are for internal auditing (guide §2.2, recommended UI errors)."""
|
||||
if not settings.S2S_APIPILOT_TOOLS_URL:
|
||||
return JSONResponse(
|
||||
status_code=501,
|
||||
content={
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "APIPILOT_NOT_CONFIGURED",
|
||||
"message": "ApiPilot no está disponible en este despliegue (S2S_APIPILOT_TOOLS_URL no establecido).",
|
||||
"status_code": 501,
|
||||
"raw": None,
|
||||
},
|
||||
},
|
||||
)
|
||||
auth, demo = providers_apipilot._apipilot_parse_authorization(request)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=API_ENDPOINT_EXECUTE name=%r argsKeys=%s authReceived=%s",
|
||||
(body.name or ""),
|
||||
sorted(list((body.arguments or {}).keys())) if isinstance(body.arguments, dict) else [],
|
||||
("Y" if auth or demo else "none"),
|
||||
)
|
||||
envelope = await providers_apipilot._apipilot_execute_tool(
|
||||
auth_header=auth,
|
||||
demo_session=demo,
|
||||
name=body.name,
|
||||
arguments=body.arguments if isinstance(body.arguments, dict) else {},
|
||||
)
|
||||
status_code = 200
|
||||
if (not envelope.get("success")) and isinstance(envelope.get("error"), dict):
|
||||
code = envelope["error"].get("status_code")
|
||||
try:
|
||||
code_int = int(code)
|
||||
if 400 <= code_int < 599:
|
||||
status_code = code_int
|
||||
except Exception:
|
||||
pass
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT] /api/apipilot/execute name=%s success=%s status=%s",
|
||||
body.name,
|
||||
envelope.get("success"),
|
||||
status_code,
|
||||
)
|
||||
return JSONResponse(status_code=status_code, content=envelope)
|
||||
@@ -0,0 +1,283 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from urllib.parse import urlencode
|
||||
|
||||
import httpx
|
||||
from fastapi import APIRouter, HTTPException
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
from s2s_client.providers import caller as providers_caller
|
||||
from s2s_client.services import context as services_context
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get("/api/user/phone")
|
||||
async def user_by_phone(phoneNumber: str) -> JSONResponse:
|
||||
"""HTTP passthrough: fetches caller identity / profile from the external
|
||||
info endpoint set via VOCERO_USER_PHONE_AUTH_URL and forwards the raw
|
||||
JSON to the browser.
|
||||
|
||||
The proxy NEVER inspects this payload nor injects it into the realtime
|
||||
WebSocket session. It is only used by:
|
||||
- the browser UI to render a caller name header (#ident-user-name)
|
||||
- the /api/reasoning HTTP body user_context field (browser's choice).
|
||||
|
||||
When VOCERO_USER_PHONE_AUTH_URL is unset we return 503 so the UI can
|
||||
silently skip identity loading (backward compatible with generic deploys).
|
||||
|
||||
When S2S_LOGIN_BY_PHONE is set, the proxy first performs a login-by-phone
|
||||
POST with the caller phone and (if a bearer token is extracted) forwards
|
||||
it as Authorization: Bearer on the subsequent profile GET.
|
||||
"""
|
||||
|
||||
if not settings.VOCERO_USER_PHONE_AUTH_URL:
|
||||
raise HTTPException(
|
||||
status_code=503,
|
||||
detail="VOCERO_USER_PHONE_AUTH_URL no está configurado en este despliegue.",
|
||||
)
|
||||
phone = (phoneNumber or "").strip()
|
||||
if not phone:
|
||||
raise HTTPException(status_code=400, detail="Se requiere el campo phoneNumber.")
|
||||
|
||||
# 0) Login-by-phone (optional — only if S2S_LOGIN_BY_PHONE env is set).
|
||||
login_token = None
|
||||
if settings.S2S_LOGIN_BY_PHONE:
|
||||
login_token, _login_obj = await providers_caller._login_by_phone(phone)
|
||||
|
||||
target_url = f"{settings.VOCERO_USER_PHONE_AUTH_URL}?{urlencode({'phoneNumber': phone})}"
|
||||
app_logging.logger.debug(
|
||||
"[EXT][USER-BY-PHONE] GET upstream=%s phoneLen=%d bearer=%s",
|
||||
settings.VOCERO_USER_PHONE_AUTH_URL,
|
||||
len(phone),
|
||||
"yes" if login_token else "no",
|
||||
)
|
||||
try:
|
||||
headers = {}
|
||||
if login_token:
|
||||
headers["Authorization"] = f"Bearer {login_token}"
|
||||
async with httpx.AsyncClient(timeout=15.0, follow_redirects=True) as http:
|
||||
resp = await http.get(target_url, headers=headers or None)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("[EXT][USER-BY-PHONE] unreachable: %r", exc)
|
||||
raise HTTPException(status_code=502, detail="No se puede conectar con el servicio de información del usuario.") # noqa: B904
|
||||
# Forward the upstream status + JSON verbatim; never rewrite the payload.
|
||||
if resp.status_code >= 500:
|
||||
app_logging.logger.warning(
|
||||
"[EXT][USER-BY-PHONE] upstream HTTP %s: %.200s",
|
||||
resp.status_code,
|
||||
resp.text,
|
||||
)
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
raise HTTPException( # noqa: B904
|
||||
status_code=502,
|
||||
detail="El servicio de información del usuario devolvió un JSON no válido.",
|
||||
)
|
||||
return JSONResponse(status_code=resp.status_code if resp.status_code != 204 else 200, content=payload)
|
||||
|
||||
|
||||
@router.get("/api/user/reports")
|
||||
async def user_reports(phoneNumber: str | None = None) -> JSONResponse:
|
||||
"""Fetch + normalize the scheduled reports list for the caller UI.
|
||||
|
||||
Mirrors the same sequence used in the WebSocket connect handler and
|
||||
/api/reasoning:
|
||||
0. login-by-phone (optional) → bearer token
|
||||
1. GET S2S_REPORT_LIST with ?phoneNumber= (if phone provided) + Bearer auth
|
||||
2. run the same resolver used for prompt injection: filter 3 fields,
|
||||
sort DESC, build hints + entries → JSON returned verbatim so the
|
||||
browser can render a "reports loaded" summary in the UI header.
|
||||
|
||||
Returns 503 when S2S_REPORT_LIST is not configured (generic deploy with no
|
||||
reports feature enabled) so the browser silently skips UI rendering.
|
||||
Response shape on success:
|
||||
{
|
||||
"count": N,
|
||||
"wrappedLen": X,
|
||||
"hints": [ "• Report #1: '<label>' — scheduled on <date>", ... ],
|
||||
"entries": [
|
||||
{"sourceScheduleLabel": "...", "date": "...", "podcastScript": "..."},
|
||||
...
|
||||
]
|
||||
}
|
||||
|
||||
USER FIX 2026-09-11: remove mass injection of scheduled reports.
|
||||
• Even this BROWSER-FACING endpoint (/api/user/reports) now honours the new
|
||||
S2S_INJECT_REPORTS default=False gate: when S2S_INJECT_REPORTS is not
|
||||
explicitly true, we return a polite 403 + empty response — the endpoint
|
||||
does NOT execute any upstream S2S_REPORT_LIST HTTP call, does NOT expose
|
||||
any podcastScript bodies, and does NOT emit entries/hints. This avoids
|
||||
a subtle loophole where the browser could still fetch scheduled reports
|
||||
through /api/user/reports while the LLM prompt paths were gated.
|
||||
"""
|
||||
# ── MASS-INJECTION KILL SWITCH (user request) ─────────────────────────
|
||||
if not settings.S2S_INJECT_REPORTS:
|
||||
return JSONResponse(
|
||||
status_code=200,
|
||||
content={
|
||||
"count": 0,
|
||||
"wrappedLen": 0,
|
||||
"hints": [],
|
||||
"entries": [],
|
||||
"skipped": True,
|
||||
"reason": "S2S_INJECT_REPORTS está deshabilitado en este despliegue; no se muestran reportes programados en la interfaz ni se envían al modelo.",
|
||||
},
|
||||
)
|
||||
# ───────────────────────────────────────────────────────────────────────
|
||||
if not settings.S2S_REPORT_LIST:
|
||||
raise HTTPException(
|
||||
status_code=503,
|
||||
detail="S2S_REPORT_LIST no está configurado en este despliegue.",
|
||||
)
|
||||
phone = (phoneNumber or "").strip() or None
|
||||
# 0) Login-by-phone if enabled. Bearer token used only if login succeeded
|
||||
# (same rule as WS connect / reasoning handlers — never-fail).
|
||||
login_token = None
|
||||
if settings.S2S_LOGIN_BY_PHONE and phone:
|
||||
login_token, _login_obj = await providers_caller._login_by_phone(phone)
|
||||
|
||||
reports_raw = await providers_caller._fetch_reports_list(phone, login_token)
|
||||
# Re-run the same resolver used for prompt injection → identical logic
|
||||
# guarantees UI and LLM see exactly the same filtered/sorted list.
|
||||
ctx_str = services_context._resolve_reports_context(reports_raw)
|
||||
if not ctx_str or not isinstance(reports_raw, list):
|
||||
return JSONResponse(
|
||||
{
|
||||
"count": 0,
|
||||
"wrappedLen": 0,
|
||||
"hints": [],
|
||||
"entries": [],
|
||||
"skipped": True,
|
||||
"reason": "Lista vacía, error del servicio de origen o ningún contenido disponible.",
|
||||
}
|
||||
)
|
||||
# Rebuild hints + normalized entries with the exact filtered output
|
||||
items_list: list = reports_raw
|
||||
# Re-derive filtered + sorted list (same as _resolve_reports_context) so
|
||||
# we don't accidentally expose raw unfiltered upstream payload to the UI.
|
||||
filtered: list[dict] = []
|
||||
for item in items_list:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
cleaned: dict = {}
|
||||
label_val: object = None
|
||||
if item.get("sourceScheduleLabel") is not None:
|
||||
label_val = item["sourceScheduleLabel"]
|
||||
elif isinstance(item.get("sourceSchedule"), dict):
|
||||
ss = item["sourceSchedule"]
|
||||
for k in ("label", "name", "title"):
|
||||
if ss.get(k) is not None:
|
||||
label_val = ss[k]
|
||||
break
|
||||
if label_val is not None:
|
||||
cleaned["sourceScheduleLabel"] = label_val
|
||||
date_val: object = None
|
||||
if item.get("date") is not None:
|
||||
date_val = item["date"]
|
||||
elif isinstance(item.get("sourceSchedule"), dict):
|
||||
ss = item["sourceSchedule"]
|
||||
for k in ("date", "scheduledAt", "publishedAt"):
|
||||
if ss.get(k) is not None:
|
||||
date_val = ss[k]
|
||||
break
|
||||
if date_val is not None:
|
||||
cleaned["date"] = date_val
|
||||
script_val: object = None
|
||||
for k in ("podcastScript", "script", "text", "content"):
|
||||
if item.get(k) is not None:
|
||||
script_val = item[k]
|
||||
break
|
||||
if script_val is not None:
|
||||
cleaned["podcastScript"] = script_val
|
||||
if cleaned:
|
||||
filtered.append(cleaned)
|
||||
filtered.sort(key=lambda r: services_context._parse_date_key(r.get("date")))
|
||||
# 2026-09-11 user fix: configure report quick-hint limits through .env.
|
||||
# Apply the SAME cap used by the LLM prompt resolver: after sort by newest,
|
||||
# keep only first S2S_REPORTS_QUICK_HINT_MAX entries. This keeps counts between
|
||||
# /api/user/reports UI JSON and the LLM prompt identical — avoids confusing
|
||||
# mismatches where the UI shows 20 hints but the prompt only saw 5.
|
||||
total_raw_ui = len(filtered)
|
||||
cap_ui = max(1, int(settings.S2S_REPORTS_QUICK_HINT_MAX or 5))
|
||||
truncated_ui_note: str | None = None
|
||||
if total_raw_ui > cap_ui:
|
||||
filtered = filtered[:cap_ui]
|
||||
truncated_ui_note = (
|
||||
f"Se muestran los {cap_ui} reportes más recientes de un total de {total_raw_ui}. "
|
||||
"Ajuste la variable de entorno S2S_REPORTS_QUICK_HINT_MAX para cambiar la cantidad."
|
||||
)
|
||||
import datetime as _dt
|
||||
|
||||
# Deduplicate by label for the UI JSON response only.
|
||||
# NOTE: the LLM prompt injection uses the full non-deduped list (different
|
||||
# dates = different content even when the scheduled report name repeats).
|
||||
# We only dedup entries_out, hints_list, and entries for the browser payload.
|
||||
seen_labels: set[str] = set()
|
||||
dedup_filtered: list[dict] = []
|
||||
for r in filtered:
|
||||
lbl_raw = r.get("sourceScheduleLabel")
|
||||
if lbl_raw is None:
|
||||
# Items with no label are kept as-is (can't meaningfully dedupe)
|
||||
dedup_filtered.append(r)
|
||||
continue
|
||||
key = str(lbl_raw).strip()
|
||||
if not key:
|
||||
dedup_filtered.append(r)
|
||||
continue
|
||||
if key in seen_labels:
|
||||
continue
|
||||
seen_labels.add(key)
|
||||
dedup_filtered.append(r)
|
||||
hints_list: list[str] = []
|
||||
entries_out: list[dict] = []
|
||||
for idx, r in enumerate(dedup_filtered, start=1):
|
||||
entries_out.append(r)
|
||||
label_piece = str(r["sourceScheduleLabel"]).strip() if r.get("sourceScheduleLabel") else ""
|
||||
date_piece = ""
|
||||
if r.get("date") is not None:
|
||||
raw_d = r["date"]
|
||||
try:
|
||||
if isinstance(raw_d, (int, float)) and not isinstance(raw_d, bool):
|
||||
ts_sec = float(raw_d)
|
||||
if ts_sec > 1e12:
|
||||
ts_sec = ts_sec / 1000.0
|
||||
dt = _dt.datetime.fromtimestamp(ts_sec, tz=_dt.UTC)
|
||||
date_piece = dt.strftime("%Y-%m-%d %H:%M UTC")
|
||||
else:
|
||||
s = str(raw_d).strip()
|
||||
if "T" in s and len(s) >= 16:
|
||||
date_piece = s.replace("T", " ")[:16]
|
||||
else:
|
||||
date_piece = s
|
||||
except Exception:
|
||||
date_piece = str(raw_d)[:32]
|
||||
if label_piece and date_piece:
|
||||
hints_list.append(f"• Reporte #{idx}: '{label_piece}' — programado para {date_piece}")
|
||||
elif label_piece:
|
||||
hints_list.append(f"• Reporte #{idx}: '{label_piece}'")
|
||||
elif date_piece:
|
||||
hints_list.append(f"• Reporte #{idx}: (sin título) — programado para {date_piece}")
|
||||
resp_body = {
|
||||
"count": len(entries_out),
|
||||
"rawCount": total_raw_ui,
|
||||
"cap": cap_ui,
|
||||
"wrappedLen": len(ctx_str),
|
||||
"hints": hints_list,
|
||||
# Strip the long podcastScript from the summary JSON to keep the
|
||||
# browser response lightweight (UI only needs label/date).
|
||||
"entries": [
|
||||
{
|
||||
"sourceScheduleLabel": r.get("sourceScheduleLabel"),
|
||||
"date": r.get("date"),
|
||||
}
|
||||
for r in entries_out
|
||||
],
|
||||
}
|
||||
if truncated_ui_note is not None:
|
||||
resp_body["truncated"] = True
|
||||
resp_body["note"] = truncated_ui_note
|
||||
return JSONResponse(resp_body)
|
||||
@@ -0,0 +1,54 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, Request
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
from s2s_client.core import urls as core_urls
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def _effective_s2s_url(request: Request) -> str:
|
||||
return settings.SPEECH_TO_SPEECH_URL or core_urls._proxy_public_url(request)
|
||||
|
||||
|
||||
@router.get("/api/config")
|
||||
async def config(request: Request) -> dict[str, Any]:
|
||||
"""Client bootstrap: whether web search is available, whether the deploy runs
|
||||
behind a load balancer (so the browser uses the /api/session proxy),
|
||||
and whether the user may instead set a direct
|
||||
s2s server URL. The LB address itself is intentionally NOT included.
|
||||
|
||||
2026-09-24: new top-level `apipilot` flag. When True the deploy exposes the
|
||||
new `/api/apipilot/tools` and `/api/apipilot/execute` proxy endpoints (see
|
||||
docs/client/tool-calling.md) that the browser may call directly instead of
|
||||
hardcoding upstream tool URLs / names."""
|
||||
app_logging.logger.debug(
|
||||
"[INTERNAL] /api/config requested client=%s", request.client.host if request.client else "?"
|
||||
)
|
||||
primary_prompt = settings.S2S_PRIMARY_PROMPT
|
||||
out = {
|
||||
"search": bool(settings.SERPER_KEY),
|
||||
"lb": bool(settings.LOAD_BALANCER_URL),
|
||||
"allowDirect": not settings.LOAD_BALANCER_URL,
|
||||
"s2sUrl": _effective_s2s_url(request),
|
||||
"primaryPrompt": primary_prompt,
|
||||
"reasoningType": settings.S2S_REASONING_TYPE,
|
||||
"injectProfile": settings.S2S_INJECT_PROFILE,
|
||||
"debugPrompt": settings.S2S_DEBUG_PROMPT,
|
||||
"startSessionMode": settings.S2S_START_SESSION_MODE,
|
||||
"theme": settings.S2S_THEME,
|
||||
"apipilot": bool(settings.S2S_APIPILOT_TOOLS_URL),
|
||||
}
|
||||
app_logging.logger.debug(
|
||||
"[INTERNAL] /api/config returned promptLen=%d reasoning=%s startSessionMode=%s theme=%s apipilot=%s",
|
||||
len(primary_prompt),
|
||||
settings.S2S_REASONING_TYPE,
|
||||
settings.S2S_START_SESSION_MODE or "-",
|
||||
settings.S2S_THEME or "-",
|
||||
out["apipilot"],
|
||||
)
|
||||
return out
|
||||
@@ -0,0 +1,90 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
|
||||
import httpx
|
||||
from fastapi import APIRouter, HTTPException
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
from s2s_client.models import requests as models_requests
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post("/api/search")
|
||||
async def search(req: models_requests.SearchRequest) -> JSONResponse:
|
||||
"""Proxy a Google search via Serper.dev. The key stays on the server unless
|
||||
the user brought their own (then theirs is used for this request only)."""
|
||||
query = (req.query or "").strip()
|
||||
if not query:
|
||||
raise HTTPException(status_code=400, detail="La consulta está vacía.")
|
||||
|
||||
key = (req.key or "").strip() or settings.SERPER_KEY
|
||||
has_user_key = bool((req.key or "").strip())
|
||||
if not key:
|
||||
# No server key and the user didn't supply one — search is unavailable.
|
||||
raise HTTPException(status_code=503, detail="La búsqueda no está configurada.")
|
||||
|
||||
headers = {"X-API-KEY": key, "Content-Type": "application/json"}
|
||||
payload = {"q": query, "num": settings.MAX_RESULTS}
|
||||
app_logging.logger.debug(
|
||||
"[EXT][SERPER] search POST %s query=%s userKey=%s num=%d",
|
||||
settings.SERPER_URL,
|
||||
json.dumps(query, ensure_ascii=True)[:200],
|
||||
has_user_key,
|
||||
settings.MAX_RESULTS,
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=12.0) as http:
|
||||
resp = await http.post(settings.SERPER_URL, headers=headers, json=payload)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("Serper unreachable: %r", exc)
|
||||
raise HTTPException(status_code=502, detail="No se puede conectar con el proveedor de búsqueda.") # noqa: B904
|
||||
app_logging.logger.debug(
|
||||
"[EXT][SERPER] search RESP status=%s len=%dB",
|
||||
resp.status_code,
|
||||
len(resp.content or b""),
|
||||
)
|
||||
|
||||
if resp.status_code != 200:
|
||||
# Serper's error body carries the real reason (e.g. "Not enough
|
||||
# credits") and contains no key, so it's safe to log and relay.
|
||||
body = resp.text[:300]
|
||||
app_logging.logger.warning("Serper error %s: %s", resp.status_code, body)
|
||||
msg = None
|
||||
try:
|
||||
msg = resp.json().get("message")
|
||||
except Exception:
|
||||
pass
|
||||
detail = f"Error del proveedor de búsqueda ({resp.status_code})"
|
||||
if msg:
|
||||
detail += f": {msg}"
|
||||
raise HTTPException(status_code=502, detail=detail)
|
||||
|
||||
data = resp.json()
|
||||
results = []
|
||||
for item in (data.get("organic") or [])[: settings.MAX_RESULTS]:
|
||||
results.append(
|
||||
{
|
||||
"title": item.get("title", ""),
|
||||
"snippet": item.get("snippet", ""),
|
||||
"url": item.get("link", ""),
|
||||
}
|
||||
)
|
||||
|
||||
# A direct answer when Google has one — saves the model a hop.
|
||||
box = data.get("answerBox") or {}
|
||||
answer = box.get("answer") or box.get("snippet") or None
|
||||
if not answer:
|
||||
kg = data.get("knowledgeGraph") or {}
|
||||
answer = kg.get("description") or None
|
||||
|
||||
app_logging.logger.debug(
|
||||
"[EXT][SERPER] search PARSED hasAnswer=%s resultCount=%d titles=%s",
|
||||
bool(answer),
|
||||
len(results),
|
||||
[r.get("title", "")[:40] for r in results],
|
||||
)
|
||||
return JSONResponse({"query": query, "answer": answer, "results": results})
|
||||
@@ -0,0 +1,182 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
from fastapi import APIRouter, HTTPException, Request
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post("/api/session")
|
||||
async def session(request: Request) -> JSONResponse:
|
||||
"""Relay a session grant or queue ticket, keeping the LB address server-side.
|
||||
|
||||
The grant's `connect_url` contains the compute host and short-lived token the
|
||||
browser needs to connect directly to the allocated speech service."""
|
||||
client_ip = request.client.host if request.client else "?"
|
||||
if not settings.LOAD_BALANCER_URL:
|
||||
# No LB configured — this deploy is direct-mode only; the browser should
|
||||
# never call this. 404 so it's indistinguishable from a missing route.
|
||||
raise HTTPException(status_code=404, detail="No encontrado.")
|
||||
|
||||
app_logging.logger.debug("[EXT][LB] session: client=%s", client_ip)
|
||||
url = f"{settings.LOAD_BALANCER_URL.rstrip('/')}/session"
|
||||
app_logging.logger.debug("[EXT][LB] session POST %s (handshake)", url)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=15.0) as http:
|
||||
lb = await http.post(url, headers={"Content-Type": "application/json"}, content="{}")
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("Load balancer unreachable: %r", exc)
|
||||
raise HTTPException(status_code=502, detail="No se puede conectar con el servicio de voz.") # noqa: B904
|
||||
app_logging.logger.debug(
|
||||
"[EXT][LB] session RESP status=%s len=%dB",
|
||||
lb.status_code,
|
||||
len(lb.content or b""),
|
||||
)
|
||||
|
||||
# The queue is full: the LB replies 503 {state:"at_capacity"}. Relay it as-is
|
||||
# so the client shows a soft "try again shortly", not a hard error.
|
||||
if lb.status_code == 503:
|
||||
body = _safe_json(lb)
|
||||
if body.get("state") == "at_capacity":
|
||||
app_logging.logger.debug("[EXT][LB] session: at_capacity — queue full")
|
||||
return JSONResponse({"state": "at_capacity"}, status_code=503)
|
||||
|
||||
if lb.status_code != 200:
|
||||
# The LB's error body may name the reason (e.g. capacity); it carries no
|
||||
# secret, so relay a trimmed copy.
|
||||
app_logging.logger.warning("Session handshake failed %s: %s", lb.status_code, lb.text[:300])
|
||||
raise HTTPException(status_code=502, detail=f"No se pudo establecer la sesión ({lb.status_code}).")
|
||||
|
||||
data = lb.json()
|
||||
state = data.get("state", "?")
|
||||
connect_url = (data.get("connect_url") or data.get("connectUrl") or "")[:120]
|
||||
session_id = data.get("session_id") or data.get("sessionId")
|
||||
app_logging.logger.debug(
|
||||
"[EXT][LB] session PARSED state=%s sessionId=%s hasConnectUrl=%s connectUrl=%s",
|
||||
state,
|
||||
session_id,
|
||||
bool(connect_url),
|
||||
connect_url,
|
||||
)
|
||||
|
||||
# Busy pool: the LB queued us. Relay the ticket for subsequent polling.
|
||||
if data.get("state") == "queued":
|
||||
app_logging.logger.debug(
|
||||
"[EXT][LB] session: queued queueId=%s position=%s",
|
||||
data.get("queue_id") or data.get("queueId"),
|
||||
data.get("position"),
|
||||
)
|
||||
return JSONResponse(data)
|
||||
|
||||
|
||||
@router.get("/api/queue/{queue_id}")
|
||||
async def queue_status(queue_id: str, request: Request) -> JSONResponse:
|
||||
"""Relay a waiting ticket's position or its newly claimed session grant."""
|
||||
client_ip = request.client.host if request.client else "?"
|
||||
if not settings.LOAD_BALANCER_URL:
|
||||
raise HTTPException(status_code=404, detail="No encontrado.")
|
||||
|
||||
app_logging.logger.debug(
|
||||
"[EXT][LB] queue poll: client=%s queueId=%s",
|
||||
client_ip,
|
||||
queue_id[:16],
|
||||
)
|
||||
|
||||
url = f"{settings.LOAD_BALANCER_URL.rstrip('/')}/queue/{queue_id}"
|
||||
app_logging.logger.debug("[EXT][LB] queue GET %s", url)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=15.0) as http:
|
||||
lb = await http.get(url)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("Load balancer unreachable: %r", exc)
|
||||
raise HTTPException(status_code=502, detail="No se puede conectar con el servicio de voz.") # noqa: B904
|
||||
app_logging.logger.debug(
|
||||
"[EXT][LB] queue RESP status=%s len=%dB",
|
||||
lb.status_code,
|
||||
len(lb.content or b""),
|
||||
)
|
||||
|
||||
if lb.status_code == 404:
|
||||
# Ticket unknown/expired (reaped after we stopped polling). Tell the client
|
||||
# to start over rather than spin.
|
||||
app_logging.logger.debug("[EXT][LB] queue: queueId=%s EXPIRED (404)", queue_id[:16])
|
||||
return JSONResponse({"state": "expired"}, status_code=404)
|
||||
|
||||
if lb.status_code != 200:
|
||||
app_logging.logger.warning("Queue poll failed %s: %s", lb.status_code, lb.text[:300])
|
||||
raise HTTPException(status_code=502, detail=f"No se pudo consultar la cola de espera ({lb.status_code}).")
|
||||
|
||||
data = lb.json()
|
||||
state = data.get("state", "?")
|
||||
position = data.get("position")
|
||||
app_logging.logger.debug(
|
||||
"[EXT][LB] queue PARSED queueId=%s state=%s position=%s sessionId=%s",
|
||||
queue_id[:16],
|
||||
state,
|
||||
position,
|
||||
data.get("session_id") or data.get("sessionId"),
|
||||
)
|
||||
|
||||
return JSONResponse(data)
|
||||
|
||||
|
||||
@router.delete("/api/queue/{queue_id}")
|
||||
async def queue_leave(queue_id: str) -> dict[str, bool]:
|
||||
"""Leave the queue from the explicit 'Leave queue' button (a real fetch)."""
|
||||
if not settings.LOAD_BALANCER_URL:
|
||||
raise HTTPException(status_code=404, detail="No encontrado.")
|
||||
app_logging.logger.debug("[EXT][LB] queue LEAVE (button) queueId=%s", queue_id[:16])
|
||||
await _lb_leave(queue_id)
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
@router.post("/api/queue/end")
|
||||
async def queue_end(request: Request) -> dict[str, bool]:
|
||||
"""Leave the queue on teardown/tab-close (navigator.sendBeacon, which can only
|
||||
POST). Body: { queueId }. Best-effort; the LB reaps the ticket on TTL anyway."""
|
||||
if not settings.LOAD_BALANCER_URL:
|
||||
raise HTTPException(status_code=404, detail="No encontrado.")
|
||||
qid = await _queue_id(request)
|
||||
if qid:
|
||||
app_logging.logger.debug("[EXT][LB] queue LEAVE (teardown) queueId=%s", qid[:16])
|
||||
await _lb_leave(qid)
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
async def _lb_leave(queue_id: str) -> None:
|
||||
"""Best-effort: tell the LB to drop a waiting ticket."""
|
||||
url = f"{settings.LOAD_BALANCER_URL.rstrip('/')}/queue/{queue_id}"
|
||||
app_logging.logger.debug("[EXT][LB] queue DELETE %s", url)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=5.0) as http:
|
||||
resp = await http.delete(url)
|
||||
app_logging.logger.debug(
|
||||
"[EXT][LB] queue DELETE RESP queueId=%s status=%s",
|
||||
queue_id[:16],
|
||||
resp.status_code,
|
||||
)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("Queue leave failed: %r", exc)
|
||||
|
||||
|
||||
def _safe_json(response: httpx.Response) -> dict[str, Any]:
|
||||
try:
|
||||
body = response.json()
|
||||
except Exception:
|
||||
return {}
|
||||
return body if isinstance(body, dict) else {}
|
||||
|
||||
|
||||
async def _queue_id(request: Request) -> str:
|
||||
"""Pull `queueId` from a JSON body, tolerating sendBeacon's blob posts."""
|
||||
try:
|
||||
data = await request.json()
|
||||
except Exception:
|
||||
return ""
|
||||
return (data or {}).get("queueId", "") if isinstance(data, dict) else ""
|
||||
@@ -0,0 +1,212 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from s2s_client.core import logging as app_logging
|
||||
|
||||
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
|
||||
load_dotenv(os.path.join(ROOT_DIR, ".env"), override=False)
|
||||
app_logging.logger.debug("Loaded .env from %s", ROOT_DIR)
|
||||
|
||||
|
||||
def _normalize_reasoning_type(value: str) -> str:
|
||||
normalized = (value or "").strip().strip('"').strip("'").replace("-", "_").upper()
|
||||
if normalized == "OPENAI":
|
||||
return "OPENAI"
|
||||
if normalized in {"NODE_RED", "NODERED"}:
|
||||
return "NODE_RED"
|
||||
return "PROXY"
|
||||
|
||||
|
||||
SERPER_KEY = os.environ.get("SERPER_API_KEY", "").strip()
|
||||
S2S_PRIMARY_PROMPT = os.environ.get("S2S_PRIMARY_PROMPT", "").strip()
|
||||
if S2S_PRIMARY_PROMPT:
|
||||
S2S_PRIMARY_PROMPT = S2S_PRIMARY_PROMPT.replace("\\n", "\n")
|
||||
# External user-by-phone info endpoint. When set, GET /api/user/phone proxies
|
||||
# to this URL (passing ?phoneNumber=) and forwards the JSON payload to the
|
||||
# browser so the UI can render caller identity / caller context.
|
||||
VOCERO_USER_PHONE_AUTH_URL = os.environ.get("VOCERO_USER_PHONE_AUTH_URL", "").strip().rstrip("/")
|
||||
# Feature flag: when "true" (case-insensitive) => injects the resolved caller
|
||||
# profile into the realtime session (patch session.update client->upstream,
|
||||
# append profile to the LLM system instructions prompt instructions, and prepend it to the
|
||||
# reasoning user_context for the /api/reasoning HTTP body.
|
||||
# Default = disabled (generic deploy; pure passthrough; all characterization lives
|
||||
# in the backend RAG per original architectural decision.)
|
||||
S2S_INJECT_PROFILE = (os.environ.get("S2S_INJECT_PROFILE", "") or "").strip().lower() in {"1", "true", "yes", "on"}
|
||||
# Endpoint URL for fetching the latest per-caller conversation summary, used when
|
||||
# both S2S_INJECT_PROFILE=true AND S2S_LATEST_SUMMARY is set. Completely
|
||||
# generic: the proxy performs a plain GET S2S_LATEST_SUMMARY?phoneNumber=<x>
|
||||
# and expects JSON back (optionally wrapped as {"result": <value>}). Empty
|
||||
# string means the feature is off (no network call, nothing injected).
|
||||
S2S_LATEST_SUMMARY = (os.environ.get("S2S_LATEST_SUMMARY", "") or "").strip()
|
||||
# Static / hardcoded latest-summary text. When set (non-empty string), it takes
|
||||
# PRIORITY over S2S_LATEST_SUMMARY: the proxy SKIPS the HTTP fetch entirely and
|
||||
# injects this raw plain-text value directly into the prompt as the latest
|
||||
# conversation summary. Designed for cases where the operator wants a clean,
|
||||
# essential, pre-cleaned summary snippet without depending on an upstream API.
|
||||
# Bypasses all HTTP logic (no login-by-phone bearer forwarding, no timeout, no
|
||||
# JSON unwrapping) — the string is passed as-is to _resolve_latest_summary_context
|
||||
# (which still applies the 1600-char cap + the LATEST_SUMMARY_HINT wrapper).
|
||||
S2S_LATEST_SUMMARY_TEXT = (os.environ.get("S2S_LATEST_SUMMARY_TEXT", "") or "").strip()
|
||||
if S2S_LATEST_SUMMARY_TEXT:
|
||||
# Interpret \n escape sequences so multi-line summaries can be written as a
|
||||
# single env line (matches S2S_PRIMARY_PROMPT convention above).
|
||||
S2S_LATEST_SUMMARY_TEXT = S2S_LATEST_SUMMARY_TEXT.replace("\\n", "\n")
|
||||
# Optional: login-by-phone endpoint. When set (and S2S_INJECT_PROFILE=true and
|
||||
# phoneNumber is available), before fetching user profile / latest summary the proxy
|
||||
# first performs a POST S2S_LOGIN_BY_PHONE with {"phoneNumber": "..."} JSON body,
|
||||
# extracts an auth token from the response (if any), and forwards it as
|
||||
# Authorization: Bearer <token> for subsequent profile / summary / reports HTTP calls.
|
||||
S2S_LOGIN_BY_PHONE = (os.environ.get("S2S_LOGIN_BY_PHONE", "") or "").strip().rstrip("/")
|
||||
# Optional: list of scheduled reports / podcasts endpoint. When set (and S2S_INJECT_PROFILE=true)
|
||||
# the proxy performs a plain GET S2S_REPORT_LIST, unwraps the JSON array (or {"result": [...]}),
|
||||
# filters per-item fields (sourceScheduleLabel, date, podcastScript), sorts by date DESC,
|
||||
# and injects the compiled block into the LLM instructions / user_context between
|
||||
# the caller profile block and the latest conversation summary block.
|
||||
S2S_REPORT_LIST = (os.environ.get("S2S_REPORT_LIST", "") or "").strip().rstrip("/")
|
||||
# Feature flag: when "true" (case-insensitive) => actually injects the REPORT LIST
|
||||
# contents (podcastScript) into the LLM instructions / context. When "false" (DEFAULT)
|
||||
# the proxy NEVER injects scheduled reports into the prompt — not even the TOC — and
|
||||
# skips the upstream S2S_REPORT_LIST network call entirely, fixing the user issue:
|
||||
# "All reports are currently injected with their complete podcastScript."
|
||||
#
|
||||
# Historical note (2026-09-11): before this flag existed, if S2S_INJECT_PROFILE=true AND
|
||||
# S2S_REPORT_LIST was set the server eagerly fetched every scheduled report for the
|
||||
# caller, serialized all their full podcastScript fields into a single block (capped at
|
||||
# 12000 chars) and appended it to every LLM turn. That was a huge prompt-bloat injection
|
||||
# the user explicitly flagged as unwanted. The safe default is therefore DISABLED: to
|
||||
# restore mass-report-injection, operators must opt in with S2S_INJECT_REPORTS=true.
|
||||
S2S_INJECT_REPORTS = (os.environ.get("S2S_INJECT_REPORTS", "") or "").strip().lower() in {"1", "true", "yes", "on"}
|
||||
# Max number of scheduled reports to surface in the QUICK-HINT line block (the TOC of
|
||||
# label + date shown before the serialized JSON entries). Also applied as a hard cap to
|
||||
# the final filtered+serialized entries list — so the wrapped prompt block never carries
|
||||
# content for more than N reports, even when the upstream API returns 20+. Configurable
|
||||
# from .env; value is integer-parsed and clamped to [1, 50] (invalid values fall back to
|
||||
# the default = 5, which is the user's requested "max 3-5" default range). User request
|
||||
# 2026-09-11: "Limit report quick hints to 3-5 entries, configurable through .env."
|
||||
try:
|
||||
_S2S_REPORTS_QUICK_HINT_MAX_RAW = int((os.environ.get("S2S_REPORTS_QUICK_HINT_MAX", "") or "5").strip())
|
||||
except Exception:
|
||||
_S2S_REPORTS_QUICK_HINT_MAX_RAW = 5
|
||||
S2S_REPORTS_QUICK_HINT_MAX = max(1, min(50, _S2S_REPORTS_QUICK_HINT_MAX_RAW))
|
||||
del _S2S_REPORTS_QUICK_HINT_MAX_RAW
|
||||
# Feature flag: when "true" → prepend a TODAY date + anti-hallucination guard to
|
||||
# every LLM prompt and session instructions. Fixes user bug 3 2026-09-11:
|
||||
# "Qwen2.5 has a training cutoff around mid-2024 and produces Chinese meta-comments
|
||||
# about 2026 reports: 'Today is 2023; why are these reports dated 2026?'"
|
||||
# Default = ON (safe even when empty/unset). Explicit S2S_INJECT_TODAY="false" to disable.
|
||||
# Injected text contains:
|
||||
# • The actual date: "TODAY is YYYY-MM-DD" (ISO, server local date).
|
||||
# • Earlier reports are historical records; do not question their dates.
|
||||
# • No internal meta-comments or prompt introspection.
|
||||
# • No thinking leaks with GPTQ Int4: only words Vocero says aloud.
|
||||
# • Retrieve report content through RAG rather than inventing it from summaries.
|
||||
S2S_INJECT_TODAY = (os.environ.get("S2S_INJECT_TODAY", "") or "").strip().lower() not in {"0", "false", "no", "off"}
|
||||
# Feature flag: S2S_REPORTS_INJECT_MODE controls what the server sends into the LLM
|
||||
# prompt for scheduled reports. Values (case-insensitive, default="minimal"):
|
||||
# • "minimal" → ONLY last N = S2S_REPORTS_QUICK_HINT_MAX items as a pure
|
||||
# TOC (label + date ONLY). NO podcastScript is ever exposed. This
|
||||
# the user's "Keep reports only as a MINIMAL summary"
|
||||
# fix. Token budget: ~50 tokens instead of ~3200.
|
||||
# • "full" → legacy behaviour: full JSON array with podcastScript
|
||||
# (still capped to S2S_REPORTS_QUICK_HINT_MAX items). Used to be
|
||||
# the default before 2026-09-11; kept only for explicit opt-in
|
||||
# because of the user explicitly flagged the massive script injection
|
||||
# as unwanted on this session.
|
||||
# • "off" / "none" → no reports injection at all (same as S2S_INJECT_REPORTS=false)
|
||||
# even when S2S_INJECT_REPORTS=true. Use this to keep the HTTP
|
||||
# fetch running while keeping the prompt clean, or as a redundant kill.
|
||||
S2S_REPORTS_INJECT_MODE = (os.environ.get("S2S_REPORTS_INJECT_MODE", "") or "").strip().lower()
|
||||
if S2S_REPORTS_INJECT_MODE not in {"minimal", "full", "off", "none"}:
|
||||
S2S_REPORTS_INJECT_MODE = "minimal"
|
||||
# Feature flag: when "true" the proxy logs the FULL PROMPT TEXT (not just
|
||||
# lengths) going to the upstream LLM/realtime backends. Includes:
|
||||
# - WS session.update session.instructions (before/after patch)
|
||||
# - /api/reasoning NODE_RED instructions + user_context full text
|
||||
# - /api/reasonING OPENAI full system message + user transcript
|
||||
# Default = off; only length summaries are logged (current behaviour).
|
||||
# WARNING: setting this on will log potentially PII / sensitive caller
|
||||
# profile data / user transcripts. Use only in development / debugging.
|
||||
S2S_DEBUG_PROMPT = (os.environ.get("S2S_DEBUG_PROMPT", "") or "").strip().lower() in {"1", "true", "yes", "on"}
|
||||
S2S_START_SESSION_MODE = (os.environ.get("S2S_START_SESSION_MODE", "") or "").strip().upper()
|
||||
S2S_THEME = (os.environ.get("S2S_THEME", "") or "").strip().lower()
|
||||
if S2S_THEME and S2S_THEME not in {"white", "dark"}:
|
||||
S2S_THEME = ""
|
||||
S2S_REASONING_TYPE = _normalize_reasoning_type(os.environ.get("S2S_REASONING_TYPE", "PROXY"))
|
||||
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "").strip()
|
||||
OPENAI_BASE_URL = os.environ.get("OPENAI_BASE_URL", "https://api.openai.com/v1").strip().rstrip("/")
|
||||
OPENAI_REASONING_MODEL = os.environ.get("OPENAI_REASONING_MODEL", "gpt-4.1-mini").strip()
|
||||
OPENAI_ORGANIZATION = os.environ.get("OPENAI_ORGANIZATION", "").strip()
|
||||
OPENAI_PROJECT = os.environ.get("OPENAI_PROJECT", "").strip()
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
# APIPILOT — Backend AquaPortal dynamic-tool bridge (docs/client/tool-calling.md)
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
# Base URL for ApiPilot dynamic tool discovery and execution. When configured,
|
||||
# the proxy sends GET <url>/tools with include_unauthorized=true (guide §2.1)
|
||||
# to discover tools, and POST <url>/execute (§2.2) to invoke one. The trailing
|
||||
# slash is optional; the proxy normalizes it with rstrip("/") below.
|
||||
#
|
||||
# Example: S2S_APIPILOT_TOOLS_URL=https://aquachile.azurianlab.com/api/v1/apipilot
|
||||
S2S_APIPILOT_TOOLS_URL = os.environ.get("S2S_APIPILOT_TOOLS_URL", "").strip().rstrip("/")
|
||||
# Explicit execution URL override (guide §2.2). When set, it takes precedence
|
||||
# over S2S_APIPILOT_TOOLS_URL for POST execution calls. Remove trailing slashes
|
||||
# and append "/execute" only if the URL does not already end with that suffix.
|
||||
# Example 1 (base): S2S_APIPILOT_TOOLS_EXECUTE_URL=https://aquachile.azurianlab.com/api/v1/apipilot
|
||||
# → POST https://aquachile.azurianlab.com/api/v1/apipilot/execute
|
||||
# Example 2: S2S_APIPILOT_TOOLS_EXECUTE_URL=https://aquachile.azurianlab.com/api/v1/apipilot/tools
|
||||
# → POST https://aquachile.azurianlab.com/api/v1/apipilot/tools/execute
|
||||
S2S_APIPILOT_TOOLS_EXECUTE_URL = os.environ.get("S2S_APIPILOT_TOOLS_EXECUTE_URL", "").strip().rstrip("/")
|
||||
# Optional fixed bearer token, used only when the caller supplies no session
|
||||
# token (Authorization / x-demo-session). Useful for staging service tokens.
|
||||
S2S_APIPILOT_SERVICE_TOKEN = os.environ.get("S2S_APIPILOT_SERVICE_TOKEN", "").strip()
|
||||
# 2026-09-25 SUPER API KEY (TEMPORARY AQUAPORTAL AUTHENTICATION BYPASS).
|
||||
# When set, send all three header forms for maximum compatibility:
|
||||
# 1) X-API-Key: <key>
|
||||
# 2) Authorization: Bearer <key>
|
||||
# 3) x-demo-session: <key>
|
||||
# Highest priority; completely disables the unnecessary login_by_phone call.
|
||||
# Clear the value to restore standard login.
|
||||
S2S_APIPILOT_API_KEY = os.environ.get("S2S_APIPILOT_API_KEY", "").strip().strip("\"'")
|
||||
# Tool discovery cache TTL in seconds. The guide recommends a five-minute
|
||||
# client cache; the server uses the same default: 300 seconds.
|
||||
try:
|
||||
_APIPILOT_TTL_RAW = int((os.environ.get("S2S_APIPILOT_TTL_SEC", "") or "300").strip())
|
||||
except Exception:
|
||||
_APIPILOT_TTL_RAW = 300
|
||||
APIPILOT_CACHE_TTL_SEC = max(15, min(3600, _APIPILOT_TTL_RAW))
|
||||
del _APIPILOT_TTL_RAW
|
||||
# HTTP timeout for ApiPilot discovery and execution calls, in seconds.
|
||||
try:
|
||||
_APIPILOT_TO_RAW = float((os.environ.get("S2S_APIPILOT_TIMEOUT_SEC", "") or "15.0").strip())
|
||||
except Exception:
|
||||
_APIPILOT_TO_RAW = 15.0
|
||||
APIPILOT_HTTP_TIMEOUT = max(1.0, min(120.0, _APIPILOT_TO_RAW))
|
||||
del _APIPILOT_TO_RAW
|
||||
|
||||
|
||||
# Node-RED reasoning engine endpoint (NODE_RED mode).
|
||||
# Examples: http://localhost:1881 or http://s2s-reasoning:1880 (Docker network).
|
||||
NODE_RED_REASONING_URL = os.environ.get("S2S_REASONING_NODE_RED_URL", "").strip().rstrip("/")
|
||||
# Speech-to-speech load balancer URL. When set, the browser POSTs /api/session
|
||||
# (which proxies <lb>/session here, server-side) and connects to the URL the LB
|
||||
# returns (the original flow). The LB address itself is never sent to the browser.
|
||||
# When empty, the user may instead set a direct s2s server URL in Settings and the
|
||||
# browser connects to it straight (no load balancer).
|
||||
LOAD_BALANCER_URL = os.environ.get("LOAD_BALANCER_URL", "").strip()
|
||||
# Direct s2s server URL pinned by the deploy. Takes priority over the load
|
||||
# balancer: when set, LB allocation and queuing are disabled, and the browser
|
||||
# connects to this URL directly. Unlike the LB address it is NOT a secret —
|
||||
# /api/config sends it to the client, which
|
||||
# shows it read-only in Settings.
|
||||
SPEECH_TO_SPEECH_URL = os.environ.get("SPEECH_TO_SPEECH_URL", "").strip()
|
||||
# Optional same-origin WebSocket relay target. When set, the browser dials this
|
||||
# app over ws(s)://<this-app>/v1/realtime and the server relays frames to the
|
||||
# upstream speech-to-speech endpoint, keeping the internal host private.
|
||||
S2S_PROXY_TARGET = os.environ.get("S2S_PROXY_TARGET", "").strip()
|
||||
if SPEECH_TO_SPEECH_URL or S2S_PROXY_TARGET:
|
||||
LOAD_BALANCER_URL = ""
|
||||
SERPER_URL = "https://google.serper.dev/search"
|
||||
# Cap results so the tool output stays small enough to feed back to the model.
|
||||
MAX_RESULTS = 5
|
||||
@@ -0,0 +1,62 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
|
||||
|
||||
# Resolve the execution URL for the startup banner using the same normalization
|
||||
# as _apipilot_resolve_execute_url.
|
||||
def _resolve_exec_url_for_startup_banner() -> str:
|
||||
base = (settings.S2S_APIPILOT_TOOLS_EXECUTE_URL or settings.S2S_APIPILOT_TOOLS_URL).strip().rstrip("/")
|
||||
if not base:
|
||||
return ""
|
||||
if base.lower().endswith("/execute"):
|
||||
return base
|
||||
return f"{base}/execute"
|
||||
|
||||
|
||||
_STARTUP_APIPILOT_EXEC_URL = _resolve_exec_url_for_startup_banner()
|
||||
del _resolve_exec_url_for_startup_banner
|
||||
|
||||
app_logging.logger.info(
|
||||
"[STARTUP] Other externals — reasoning=%s nodeRed=%s serper=%s lb=%s s2sProxy=%s s2sDirect=%s userAuth=%s reportsApi=%s injectReports=%s reportsHintMax=%d reportsInjectMode=%s injectToday=%s summaryApi=%s summaryText=%s loginApi=%s injectProfile=%s debugPrompt=%s startSessionMode=%s theme=%s apipilotToolsUrl=%s apipilotExecuteUrlOverride=%s apipilotServiceToken=%s apipilotTtl=%ds apipilotTimeout=%.1fs apipilotReasoningPass2=%s apipilotApiKeyBypass=%s",
|
||||
settings.S2S_REASONING_TYPE,
|
||||
settings.NODE_RED_REASONING_URL or "-",
|
||||
bool(settings.SERPER_KEY),
|
||||
bool(settings.LOAD_BALANCER_URL),
|
||||
bool(settings.S2S_PROXY_TARGET),
|
||||
bool(settings.SPEECH_TO_SPEECH_URL),
|
||||
bool(settings.VOCERO_USER_PHONE_AUTH_URL),
|
||||
bool(settings.S2S_REPORT_LIST),
|
||||
settings.S2S_INJECT_REPORTS,
|
||||
settings.S2S_REPORTS_QUICK_HINT_MAX,
|
||||
settings.S2S_REPORTS_INJECT_MODE,
|
||||
settings.S2S_INJECT_TODAY,
|
||||
bool(settings.S2S_LATEST_SUMMARY),
|
||||
bool(settings.S2S_LATEST_SUMMARY_TEXT),
|
||||
bool(settings.S2S_LOGIN_BY_PHONE),
|
||||
settings.S2S_INJECT_PROFILE,
|
||||
settings.S2S_DEBUG_PROMPT,
|
||||
settings.S2S_START_SESSION_MODE or "-",
|
||||
settings.S2S_THEME or "-",
|
||||
settings.S2S_APIPILOT_TOOLS_URL or "-",
|
||||
(settings.S2S_APIPILOT_TOOLS_EXECUTE_URL + f"(resolved:{_STARTUP_APIPILOT_EXEC_URL})")
|
||||
if settings.S2S_APIPILOT_TOOLS_EXECUTE_URL
|
||||
else "-",
|
||||
"Y" if bool(settings.S2S_APIPILOT_SERVICE_TOKEN) else "-",
|
||||
settings.APIPILOT_CACHE_TTL_SEC,
|
||||
settings.APIPILOT_HTTP_TIMEOUT,
|
||||
"Y" if (bool(settings.S2S_APIPILOT_TOOLS_URL) or bool(settings.S2S_APIPILOT_TOOLS_EXECUTE_URL)) else "-",
|
||||
(
|
||||
"YES head="
|
||||
+ (
|
||||
settings.S2S_APIPILOT_API_KEY[:6] + "..."
|
||||
if len(settings.S2S_APIPILOT_API_KEY) > 6
|
||||
else settings.S2S_APIPILOT_API_KEY
|
||||
)
|
||||
+ " (3 FORMS!)"
|
||||
)
|
||||
if settings.S2S_APIPILOT_API_KEY
|
||||
else "-",
|
||||
)
|
||||
del _STARTUP_APIPILOT_EXEC_URL
|
||||
@@ -0,0 +1,33 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
|
||||
logger = logging.getLogger("s2s")
|
||||
_logging_configured = False
|
||||
if not _logging_configured:
|
||||
_handler = logging.StreamHandler()
|
||||
_handler.setFormatter(
|
||||
logging.Formatter(
|
||||
"%(asctime)s %(levelname)-7s [%(name)s] %(message)s",
|
||||
datefmt="%Y-%m-%d %H:%M:%S",
|
||||
)
|
||||
)
|
||||
logging.basicConfig(level=logging.DEBUG, handlers=[_handler], force=True)
|
||||
_lvl_env = (os.environ.get("LOG_LEVEL") or os.environ.get("S2S_LOG_LEVEL") or "INFO").strip().upper()
|
||||
_is_debug = _lvl_env in {"DEBUG", "TRACE", "10"}
|
||||
# Keep noisy loggers quiet unless LOG_LEVEL explicitly enables debug.
|
||||
logging.getLogger("httpx").setLevel(logging.DEBUG if _is_debug else logging.WARNING)
|
||||
logging.getLogger("websockets").setLevel(logging.DEBUG if _is_debug else logging.INFO)
|
||||
logging.getLogger("uvicorn").setLevel(logging.DEBUG if _is_debug else logging.INFO)
|
||||
logging.getLogger("uvicorn.access").setLevel(logging.DEBUG if _is_debug else logging.INFO)
|
||||
logging.getLogger("httpcore").setLevel(logging.DEBUG if _is_debug else logging.WARNING)
|
||||
logger.setLevel(logging.DEBUG if _is_debug else logging.DEBUG) # s2s always uses at least DEBUG in development
|
||||
_logging_configured = True
|
||||
logger.debug(
|
||||
"LOG_LEVEL env=%s — noisy-logger levels: httpx=%s uvicorn=%s websockets=%s",
|
||||
_lvl_env,
|
||||
logging.getLevelName(logging.getLogger("httpx").level),
|
||||
logging.getLevelName(logging.getLogger("uvicorn").level),
|
||||
logging.getLevelName(logging.getLogger("websockets").level),
|
||||
)
|
||||
@@ -0,0 +1,53 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from urllib.parse import parse_qsl, urlencode, urlsplit, urlunsplit
|
||||
|
||||
from fastapi import Request, WebSocket
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
|
||||
|
||||
def _url_with_query(url: str, **params: str) -> str:
|
||||
target = urlsplit(url)
|
||||
merged_query = dict(parse_qsl(target.query, keep_blank_values=True))
|
||||
for key, value in params.items():
|
||||
if value:
|
||||
merged_query[key] = value
|
||||
return urlunsplit(
|
||||
(
|
||||
target.scheme,
|
||||
target.netloc,
|
||||
target.path,
|
||||
urlencode(merged_query, doseq=True),
|
||||
target.fragment,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def _proxy_public_url(request: Request) -> str:
|
||||
if not settings.S2S_PROXY_TARGET:
|
||||
return ""
|
||||
forwarded_proto = (request.headers.get("x-forwarded-proto") or request.url.scheme).split(",")[0].strip()
|
||||
forwarded_host = (
|
||||
(request.headers.get("x-forwarded-host") or request.headers.get("host") or request.url.netloc)
|
||||
.split(",")[0]
|
||||
.strip()
|
||||
)
|
||||
ws_scheme = "wss" if forwarded_proto in {"https", "wss"} else "ws"
|
||||
root_path = (request.scope.get("root_path") or "").rstrip("/")
|
||||
return f"{ws_scheme}://{forwarded_host}{root_path}/v1/realtime"
|
||||
|
||||
|
||||
def _proxy_upstream_url(ws: WebSocket) -> str:
|
||||
target = urlsplit(settings.S2S_PROXY_TARGET)
|
||||
merged_query = dict(parse_qsl(target.query, keep_blank_values=True))
|
||||
merged_query.update(parse_qsl(ws.url.query, keep_blank_values=True))
|
||||
return urlunsplit(
|
||||
(
|
||||
target.scheme,
|
||||
target.netloc,
|
||||
target.path or "/v1/realtime",
|
||||
urlencode(merged_query, doseq=True),
|
||||
target.fragment,
|
||||
)
|
||||
)
|
||||
@@ -0,0 +1,25 @@
|
||||
"""Assemble the client API and retain its existing documentation URLs."""
|
||||
|
||||
import os
|
||||
|
||||
from fastapi import FastAPI
|
||||
from fastapi.responses import RedirectResponse
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
|
||||
from s2s_client.api.router import router
|
||||
from s2s_client.core import config, diagnostics # noqa: F401 - retain the startup banner
|
||||
|
||||
app = FastAPI(title="s2s-demo")
|
||||
app.include_router(router)
|
||||
|
||||
|
||||
@app.get("/project", include_in_schema=False)
|
||||
@app.get("/project/", include_in_schema=False)
|
||||
@app.get("/project/index.html", include_in_schema=False)
|
||||
@app.get("/public/docs.html", include_in_schema=False)
|
||||
async def project_documentation() -> RedirectResponse:
|
||||
return RedirectResponse("/docs/proposals/vocero-architecture.html", status_code=307)
|
||||
|
||||
|
||||
# The existing FastAPI /docs page remains registered ahead of this mount.
|
||||
app.mount("/docs", StaticFiles(directory=os.path.join(config.ROOT_DIR, "docs"), html=True), name="documentation")
|
||||
@@ -0,0 +1,34 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class SearchRequest(BaseModel):
|
||||
query: str
|
||||
# Optional user-supplied key (fallback when the deploy has no server key).
|
||||
# Used for this request only; never stored.
|
||||
key: str | None = None
|
||||
|
||||
|
||||
class ReasoningRequest(BaseModel):
|
||||
transcript: str
|
||||
instructions: str = ""
|
||||
language: str = ""
|
||||
user_context: str = ""
|
||||
# Optional phone number. When S2S_INJECT_PROFILE is true the proxy fetches
|
||||
# the caller profile from VOCERO_USER_PHONE_AUTH_URL and:
|
||||
# 1. prepends the serialized profile to user_context before feeding the
|
||||
# engine (NODE_RED or OPENAI);
|
||||
# 2. appends the profile context to the LLM instructions prompt.
|
||||
phoneNumber: str | None = None
|
||||
# Optional podcast episode ID. When set the proxy fetches the episode from
|
||||
# the Aquachile AzurianLab API and injects it as the PRIMARY context into
|
||||
# both user_context (prepended) and LLM instructions prompt (appended first).
|
||||
episode_id: str | None = None
|
||||
|
||||
|
||||
class ApipilotExecuteRequest(BaseModel):
|
||||
"""Body for the ApiPilot execute proxy endpoint. Mirrors §2.2 request shape."""
|
||||
|
||||
name: str
|
||||
arguments: dict = {}
|
||||
@@ -0,0 +1,597 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
from collections.abc import Callable
|
||||
from time import monotonic
|
||||
from typing import Any, cast
|
||||
|
||||
import httpx
|
||||
from fastapi import HTTPException, Request
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
|
||||
# In-process cache and asynchronous lock: one caller refreshes while others
|
||||
# read the stale entry. `_APIPILOT_CACHE[auth_fingerprint] = (fetched_at_monotonic, tools_list)`.
|
||||
_APIPILOT_CACHE: dict[str, tuple[float, list[dict]]] = {}
|
||||
_APIPILOT_CACHE_LOCK = asyncio.Lock()
|
||||
|
||||
# Monotonic time helper for duration measurements unaffected by NTP drift.
|
||||
_monotonic_now: Callable[[], float] = monotonic
|
||||
|
||||
|
||||
def _apipilot_auth_fingerprint(auth_header: str | None, demo_session: str | None) -> str:
|
||||
"""Return a short string used as cache key scoped to the caller identity.
|
||||
|
||||
We don't want to share cached tool-lists across users with different auth
|
||||
tokens (requires_auth flags can be token-dependent via /tools?include_unauthorized=true
|
||||
because the back-end may still attach per-role metadata)."""
|
||||
parts: list[str] = []
|
||||
if auth_header:
|
||||
# Don't cache the raw bearer. SHA-256 truncated 12 chars = safe fingerprint.
|
||||
import hashlib
|
||||
|
||||
parts.append("h:" + hashlib.sha256(auth_header.encode("utf-8")).hexdigest()[:12])
|
||||
if demo_session:
|
||||
parts.append("d:" + demo_session)
|
||||
return "|".join(parts) if parts else "anon"
|
||||
|
||||
|
||||
def _apipilot_parse_authorization(request: Request | None) -> tuple[str | None, str | None]:
|
||||
"""Extract (Authorization header value, x-demo-session header value) from a FastAPI request.
|
||||
|
||||
Returns a tuple of two optional strings. Both are forwarded to the upstream
|
||||
ApiPilot backend verbatim when non-empty (see docs/client/tool-calling.md).
|
||||
"""
|
||||
if request is None:
|
||||
return None, None
|
||||
auth = None
|
||||
demo = None
|
||||
try:
|
||||
raw_auth = request.headers.get("authorization") or request.headers.get("Authorization")
|
||||
if isinstance(raw_auth, str) and raw_auth.strip():
|
||||
auth = raw_auth.strip()
|
||||
raw_demo = request.headers.get("x-demo-session") or request.headers.get("X-Demo-Session")
|
||||
if isinstance(raw_demo, str) and raw_demo.strip():
|
||||
demo = raw_demo.strip()
|
||||
except Exception:
|
||||
pass
|
||||
return auth, demo
|
||||
|
||||
|
||||
def _apipilot_resolve_execute_url() -> str:
|
||||
"""Resolve the final POST URL for ApiPilot tool execution.
|
||||
|
||||
Priority (guide §2.2 and explicit environment override):
|
||||
1. When S2S_APIPILOT_TOOLS_EXECUTE_URL is set, append "/execute" if needed.
|
||||
2. Fallback S2S_APIPILOT_TOOLS_URL + "/execute".
|
||||
If neither URL is configured, the caller (usually _apipilot_execute_tool)
|
||||
must return an APIPILOT_NOT_CONFIGURED error envelope before calling this.
|
||||
"""
|
||||
base = settings.S2S_APIPILOT_TOOLS_EXECUTE_URL or settings.S2S_APIPILOT_TOOLS_URL
|
||||
base = base.strip().rstrip("/")
|
||||
if not base:
|
||||
return ""
|
||||
if base.lower().endswith("/execute"):
|
||||
return base
|
||||
return f"{base}/execute"
|
||||
|
||||
|
||||
def _apipilot_strip_tool_for_llm(tool_def: dict) -> dict:
|
||||
"""Return a tool definition that is safe for LLM function-calling providers.
|
||||
|
||||
Guide §4 forbids passing raw /tools output directly to the model because
|
||||
requires_auth is outside the function-calling standard and some providers
|
||||
reject it. Project the native `ToolDefinition` into the OpenAI-compatible
|
||||
`{type: "function", function: {name, description, parameters}}`.
|
||||
"""
|
||||
if not isinstance(tool_def, dict):
|
||||
return {}
|
||||
name = tool_def.get("name") if isinstance(tool_def.get("name"), str) else ""
|
||||
description = tool_def.get("description") if isinstance(tool_def.get("description"), str) else ""
|
||||
parameters = tool_def.get("parameters")
|
||||
if not isinstance(parameters, dict):
|
||||
parameters = {"type": "object", "properties": {}, "required": []}
|
||||
out: dict = {
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": name,
|
||||
"description": description,
|
||||
"parameters": parameters,
|
||||
},
|
||||
}
|
||||
return out
|
||||
|
||||
|
||||
async def _apipilot_fetch_tools(
|
||||
*,
|
||||
auth_header: str | None,
|
||||
demo_session: str | None,
|
||||
include_unauthorized: bool = True,
|
||||
force_refresh: bool = False,
|
||||
refresh: bool | None = None,
|
||||
) -> list[dict]:
|
||||
"""Fetch ApiPilot tool definitions with a short in-process TTL cache.
|
||||
|
||||
Implements §2.1 (GET /tools?include_unauthorized=true). The cache key is
|
||||
scoped by caller auth fingerprint (see `_apipilot_auth_fingerprint`) so
|
||||
per-token variations in `requires_auth` or list length don't leak between
|
||||
identities.
|
||||
|
||||
Returns a list of tool definitions (parsed JSON, may be empty). Raises
|
||||
`HTTPException` only when `S2S_APIPILOT_TOOLS_URL` is set but the backend
|
||||
replied with a non-2xx / non-JSON response. When env is empty → returns
|
||||
`[]` silently (passthrough).
|
||||
"""
|
||||
# 2026-09-25 compatibility alias: WS connect uses `refresh`; when present,
|
||||
# apply it to force_refresh.
|
||||
if refresh is not None:
|
||||
force_refresh = bool(refresh) or bool(force_refresh)
|
||||
if not settings.S2S_APIPILOT_TOOLS_URL:
|
||||
return []
|
||||
import time as _time_mod
|
||||
|
||||
# 2026-09-25 fingerprint consistency: determine effective auth/demo values
|
||||
# first (SUPER API KEY takes precedence), then calculate the cache fingerprint.
|
||||
# An anonymous fingerprint with APIKEY headers would mismatch the cache and
|
||||
# demo session, causing Aquachile user_type=null and a 403 response.
|
||||
if settings.S2S_APIPILOT_API_KEY:
|
||||
final_auth: str | None = "BYPASS-API-KEY"
|
||||
_demo_used: str | None = settings.S2S_APIPILOT_API_KEY
|
||||
_effective_auth_for_fp = f"Bearer {settings.S2S_APIPILOT_API_KEY}"
|
||||
_effective_demo_for_fp = settings.S2S_APIPILOT_API_KEY
|
||||
else:
|
||||
final_auth = auth_header or (
|
||||
f"Bearer {settings.S2S_APIPILOT_SERVICE_TOKEN}" if settings.S2S_APIPILOT_SERVICE_TOKEN else None
|
||||
)
|
||||
_demo_used = demo_session
|
||||
_effective_auth_for_fp = (
|
||||
final_auth if isinstance(final_auth, str) and final_auth.strip() else (auth_header or "")
|
||||
)
|
||||
_effective_demo_for_fp = _demo_used if isinstance(_demo_used, str) and _demo_used.strip() else ""
|
||||
fp = _apipilot_auth_fingerprint(_effective_auth_for_fp, _effective_demo_for_fp)
|
||||
now = _time_mod.monotonic()
|
||||
cached = _APIPILOT_CACHE.get(fp)
|
||||
if (not force_refresh) and cached and (now - cached[0]) < settings.APIPILOT_CACHE_TTL_SEC:
|
||||
app_logging.logger.debug(
|
||||
"[APIPILOT-DISCOVERY] cache HIT ttl=%.1fs fp=%s tools=%d",
|
||||
settings.APIPILOT_CACHE_TTL_SEC - (now - cached[0]),
|
||||
fp,
|
||||
len(cached[1]),
|
||||
)
|
||||
return cached[1]
|
||||
# Prefer to serve stale (if any) rather than block many callers.
|
||||
stale_tools = cached[1] if cached else None
|
||||
async with _APIPILOT_CACHE_LOCK:
|
||||
# Double-check after acquiring lock (another coroutine may have refreshed).
|
||||
now2 = _time_mod.monotonic()
|
||||
recheck = _APIPILOT_CACHE.get(fp)
|
||||
if (not force_refresh) and recheck and (now2 - recheck[0]) < settings.APIPILOT_CACHE_TTL_SEC:
|
||||
return recheck[1]
|
||||
url = f"{settings.S2S_APIPILOT_TOOLS_URL}/tools"
|
||||
params = {"include_unauthorized": "true" if include_unauthorized else "false"}
|
||||
headers = {"accept": "application/json"}
|
||||
# 2026-09-25 SUPER API KEY overrides other authentication and sends all
|
||||
# three header forms simultaneously for maximum compatibility.
|
||||
if settings.S2S_APIPILOT_API_KEY:
|
||||
headers["X-API-Key"] = settings.S2S_APIPILOT_API_KEY
|
||||
headers["Authorization"] = f"Bearer {settings.S2S_APIPILOT_API_KEY}"
|
||||
headers["x-demo-session"] = settings.S2S_APIPILOT_API_KEY
|
||||
else:
|
||||
if final_auth:
|
||||
headers["Authorization"] = final_auth
|
||||
if _demo_used:
|
||||
headers["x-demo-session"] = _demo_used
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-DISCOVERY] → GET %s?include_unauthorized=%s fp=%s auth=%s demo=%s",
|
||||
url,
|
||||
params["include_unauthorized"],
|
||||
fp,
|
||||
("APIKEY" if settings.S2S_APIPILOT_API_KEY else ("Y" if final_auth else "-")),
|
||||
("APIKEY" if settings.S2S_APIPILOT_API_KEY else ("Y" if _demo_used else "-")),
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=settings.APIPILOT_HTTP_TIMEOUT, follow_redirects=True) as http:
|
||||
resp = await http.get(url, params=params, headers=headers)
|
||||
except Exception as exc:
|
||||
app_logging.logger.error("[APIPILOT-DISCOVERY] ✗ network error: %s", exc)
|
||||
if stale_tools is not None:
|
||||
app_logging.logger.warning(
|
||||
"[APIPILOT-DISCOVERY] using STALE cached fallback tools=%d", len(stale_tools)
|
||||
)
|
||||
return stale_tools
|
||||
raise HTTPException( # noqa: B904
|
||||
status_code=502,
|
||||
detail={
|
||||
"code": "APIPILOT_NETWORK_ERROR",
|
||||
"message": f"Error al contactar ApiPilot tools backend: {exc}",
|
||||
},
|
||||
)
|
||||
if resp.status_code >= 300:
|
||||
app_logging.logger.error(
|
||||
"[APIPILOT-DISCOVERY] ✗ backend HTTP %s body=%s", resp.status_code, resp.text[:400]
|
||||
)
|
||||
if stale_tools is not None:
|
||||
app_logging.logger.warning(
|
||||
"[APIPILOT-DISCOVERY] using STALE cached fallback tools=%d", len(stale_tools)
|
||||
)
|
||||
return stale_tools
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail={
|
||||
"code": "APIPILOT_BAD_UPSTREAM",
|
||||
"message": f"Backend ApiPilot tools devolvió HTTP {resp.status_code}",
|
||||
"status_code": resp.status_code,
|
||||
},
|
||||
)
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.error("[APIPILOT-DISCOVERY] ✗ non-JSON response: %s", resp.text[:500])
|
||||
if stale_tools is not None:
|
||||
return stale_tools
|
||||
raise HTTPException( # noqa: B904
|
||||
status_code=502,
|
||||
detail={"code": "APIPILOT_BAD_JSON", "message": "La respuesta de ApiPilot tools no es JSON válido."},
|
||||
)
|
||||
# Backend might return: list OR {"result": [...]} OR {"tools": [...]} OR
|
||||
# {"data": {"tools": [...]}}. Unwrap generic wrapper-style payloads.
|
||||
tools: list[dict] = []
|
||||
if isinstance(payload, list):
|
||||
tools = [t for t in payload if isinstance(t, dict)]
|
||||
elif isinstance(payload, dict):
|
||||
for key in ("tools", "result", "data"):
|
||||
cand = payload.get(key)
|
||||
if isinstance(cand, list):
|
||||
tools = [t for t in cand if isinstance(t, dict)]
|
||||
break
|
||||
if isinstance(cand, dict):
|
||||
sub = cand.get("tools") if isinstance(cand.get("tools"), list) else cand.get("result")
|
||||
if isinstance(sub, list):
|
||||
tools = [t for t in sub if isinstance(t, dict)]
|
||||
break
|
||||
# Validate minimal ToolDefinition contract §2.1: name + description + parameters.
|
||||
sanitized: list[dict] = []
|
||||
for raw in tools:
|
||||
name = raw.get("name")
|
||||
if not isinstance(name, str) or not name.strip():
|
||||
continue
|
||||
description = raw.get("description") if isinstance(raw.get("description"), str) else ""
|
||||
parameters = raw.get("parameters")
|
||||
if not isinstance(parameters, dict):
|
||||
parameters = {"type": "object", "properties": {}, "required": []}
|
||||
requires_auth = raw.get("requires_auth", False)
|
||||
if not isinstance(requires_auth, bool):
|
||||
# Some backends return 0/1; normalize to bool as required.
|
||||
try:
|
||||
requires_auth = bool(int(requires_auth))
|
||||
except Exception:
|
||||
requires_auth = False
|
||||
tool_def = {
|
||||
"name": name.strip(),
|
||||
"description": description,
|
||||
"parameters": parameters,
|
||||
"requires_auth": requires_auth,
|
||||
}
|
||||
sanitized.append(tool_def)
|
||||
_APIPILOT_CACHE[fp] = (now2, sanitized)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-DISCOVERY] ← OK tools=%s fp=%s status=%s upstreamFmt=%s cachedTools=%d",
|
||||
len(sanitized),
|
||||
fp,
|
||||
resp.status_code,
|
||||
"list" if isinstance(payload, list) else "object",
|
||||
len(sanitized),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and sanitized:
|
||||
app_logging.logger.debug(
|
||||
"[APIPILOT-DISCOVERY] raw first tool preview: %s",
|
||||
json.dumps(sanitized[0], ensure_ascii=False)[:400],
|
||||
)
|
||||
return sanitized
|
||||
|
||||
|
||||
def _apipilot_validate_arguments(arguments: dict | None, tool_def: dict) -> tuple[dict, list[str]]:
|
||||
"""Validate / execute arguments strictly against the tool's JSON-Schema parameters.
|
||||
|
||||
Implements §2.2 PRE-CHECK #3:
|
||||
• Remove unknown keys only when parameters.properties is nonempty.
|
||||
• AquaPortal tool.get_user_briefing has parameters.properties={} and
|
||||
required=[]: no explicit schema, so arguments remain flexible. The
|
||||
backend resolves phone from the token; preserve supplied arguments.
|
||||
• Validate required parameters and return errors for missing values.
|
||||
• Never invent parameters or add keys.
|
||||
|
||||
Returns `(filtered_args, list_of_validation_errors_in_spanish)`.
|
||||
If the returned errors list is non-empty, MUST block the execution (see
|
||||
the `_apipilot_execute_tool` caller).
|
||||
"""
|
||||
errors: list[str] = []
|
||||
schema = cast(dict[str, Any], tool_def.get("parameters")) if isinstance(tool_def.get("parameters"), dict) else {}
|
||||
properties = cast(dict[str, Any], schema.get("properties")) if isinstance(schema.get("properties"), dict) else {}
|
||||
required = cast(list[Any], schema.get("required")) if isinstance(schema.get("required"), list) else []
|
||||
required = [x for x in required if isinstance(x, str)]
|
||||
args = arguments if isinstance(arguments, dict) else {}
|
||||
|
||||
# 2026-09-25 empty-schema flexibility: preserve all arguments when no
|
||||
# properties are explicitly declared, as with AquaPortal get_user_briefing.
|
||||
schema_is_open: bool = (not isinstance(properties, dict)) or len(properties) == 0
|
||||
requires_auth_flag = bool(tool_def.get("requires_auth"))
|
||||
# 2026-09-25 auth-only tools: requires_auth=true, empty properties and
|
||||
# required=[], with a valid-session description, resolve user data from
|
||||
# the bearer JWT. Send arguments={} to avoid conflicts between a phone
|
||||
# argument and the token's user, which would produce a 403 response.
|
||||
auth_only_tool = False
|
||||
if schema_is_open and requires_auth_flag and len(required) == 0:
|
||||
_d = tool_def.get("description") if isinstance(tool_def.get("description"), str) else ""
|
||||
if (not _d) or "valid session token" in _d.lower() or "authenticated" in _d.lower():
|
||||
auth_only_tool = True
|
||||
if auth_only_tool:
|
||||
cleaned = {}
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-VALIDATE] tool=%s requires only an authenticated session → arguments forced to {} (avoid phone-argument/user-token conflicts)",
|
||||
tool_def.get("name") or "?",
|
||||
)
|
||||
elif schema_is_open:
|
||||
cleaned = dict(args)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-VALIDATE] tool=%s open schema (empty parameters.properties) → preserve all arguments N=%d keys=%s",
|
||||
tool_def.get("name") or "?",
|
||||
len(cleaned),
|
||||
sorted(list(cleaned.keys())),
|
||||
)
|
||||
else:
|
||||
cleaned = {}
|
||||
for key in args.keys():
|
||||
if key in properties:
|
||||
cleaned[key] = args[key]
|
||||
else:
|
||||
app_logging.logger.warning(
|
||||
"[APIPILOT-VALIDATE] tool=%s removing unknown arg=%s",
|
||||
tool_def.get("name") or "?",
|
||||
key,
|
||||
)
|
||||
# Check required fields only for a closed schema; open required=[] is vacuous.
|
||||
if not schema_is_open:
|
||||
for req in required:
|
||||
if req not in cleaned:
|
||||
errors.append(f"Falta el parámetro requerido: {req}")
|
||||
return cleaned, errors
|
||||
|
||||
|
||||
async def _apipilot_execute_tool(
|
||||
*,
|
||||
auth_header: str | None,
|
||||
demo_session: str | None,
|
||||
name: str,
|
||||
arguments: dict | None,
|
||||
) -> dict:
|
||||
"""Run a single ApiPilot tool via POST /execute.
|
||||
|
||||
Implements the full PRE-CHECK flow (§2.2) BEFORE sending the HTTP
|
||||
request:
|
||||
1. Fresh discovery (TTL cache; force_refresh=True if a tool is missing).
|
||||
2. requires_auth: return HTTP 401 when authentication is required but absent.
|
||||
3. Strict JSON-Schema validation: filter unknown parameters and check required.
|
||||
|
||||
Always return the standard `{success, data, error}` envelope (guide §2.2).
|
||||
Pre-check failures populate error.{code,message,status_code}, with success=false.
|
||||
"""
|
||||
name_clean = (name or "").strip() if isinstance(name, str) else ""
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=EXECUTE_ENTRYPOINT name=%r argsKeys=%s authHead=%.20s demo=%.20s",
|
||||
name_clean,
|
||||
sorted(list((arguments or {}).keys())) if isinstance(arguments, dict) else [],
|
||||
str(auth_header or "")[:20],
|
||||
str(demo_session or "")[:20],
|
||||
)
|
||||
if not settings.S2S_APIPILOT_TOOLS_URL:
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "APIPILOT_NOT_CONFIGURED",
|
||||
"message": "ApiPilot no está configurado en este despliegue (S2S_APIPILOT_TOOLS_URL no establecido).",
|
||||
"status_code": 501,
|
||||
"raw": None,
|
||||
},
|
||||
}
|
||||
if not name_clean:
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "TOOL_NAME_REQUIRED",
|
||||
"message": "Falta el campo obligatorio: name (nombre de la herramienta).",
|
||||
"status_code": 400,
|
||||
"raw": None,
|
||||
},
|
||||
}
|
||||
tools = await _apipilot_fetch_tools(auth_header=auth_header, demo_session=demo_session, force_refresh=False)
|
||||
tool_def = next((t for t in tools if t.get("name") == name_clean), None)
|
||||
if tool_def is None:
|
||||
# Unknown tool: refresh discovery and retry once.
|
||||
app_logging.logger.info("[APIPILOT-EXEC] tool=%s not found → forced re-discovery", name_clean)
|
||||
tools = await _apipilot_fetch_tools(auth_header=auth_header, demo_session=demo_session, force_refresh=True)
|
||||
tool_def = next((t for t in tools if t.get("name") == name_clean), None)
|
||||
if tool_def is None:
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "TOOL_NOT_FOUND",
|
||||
"message": (
|
||||
f"Herramienta «{name_clean}» no encontrada en el catálogo ApiPilot. "
|
||||
"Actualice la lista de herramientas y vuelva a intentarlo."
|
||||
),
|
||||
"status_code": 404,
|
||||
"raw": None,
|
||||
},
|
||||
}
|
||||
# ── PRE-CHECK 2: requires_auth ────────────────────────────────────────────
|
||||
requires_auth = bool(tool_def.get("requires_auth"))
|
||||
has_token = bool(auth_header) or bool(demo_session) or bool(settings.S2S_APIPILOT_SERVICE_TOKEN)
|
||||
if requires_auth and not has_token:
|
||||
app_logging.logger.warning("[APIPILOT-EXEC] tool=%s requires_auth=true blocked (no token)", name_clean)
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "AUTH_REQUIRED",
|
||||
"message": (
|
||||
f"La herramienta «{name_clean}» requiere autenticación. "
|
||||
"Inicie sesión o proporcione un token para continuar."
|
||||
),
|
||||
"status_code": 401,
|
||||
"raw": None,
|
||||
},
|
||||
}
|
||||
# Pre-check 3: strict JSON-Schema argument validation.
|
||||
cleaned_args, errors = _apipilot_validate_arguments(arguments, tool_def)
|
||||
if errors:
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "INVALID_ARGUMENTS",
|
||||
"message": " / ".join(errors),
|
||||
"status_code": 400,
|
||||
"raw": {
|
||||
"removed": sorted(list(set(arguments) - set(cleaned_args))) if isinstance(arguments, dict) else []
|
||||
},
|
||||
},
|
||||
}
|
||||
# ── HTTP: POST /execute ───────────────────────────────────────────────────
|
||||
url = _apipilot_resolve_execute_url()
|
||||
if not url:
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "APIPILOT_NOT_CONFIGURED",
|
||||
"message": "ApiPilot no está configurado en este despliegue (S2S_APIPILOT_TOOLS_URL y S2S_APIPILOT_TOOLS_EXECUTE_URL están vacíos).",
|
||||
"status_code": 501,
|
||||
"raw": None,
|
||||
},
|
||||
}
|
||||
headers = {"Content-Type": "application/json", "accept": "application/json,text/plain,*/*"}
|
||||
# 2026-09-25 SUPER API KEY (highest priority): bypass AquaPortal authentication.
|
||||
# Send all three header forms simultaneously for maximum compatibility:
|
||||
# - X-API-Key: <key>
|
||||
# - Authorization: Bearer <key>
|
||||
# - x-demo-session: <key>
|
||||
# Ignore service tokens and login_by_phone when the API KEY is set.
|
||||
if settings.S2S_APIPILOT_API_KEY:
|
||||
headers["X-API-Key"] = settings.S2S_APIPILOT_API_KEY
|
||||
headers["Authorization"] = f"Bearer {settings.S2S_APIPILOT_API_KEY}"
|
||||
headers["x-demo-session"] = settings.S2S_APIPILOT_API_KEY
|
||||
final_auth: str | None = f"Bearer {settings.S2S_APIPILOT_API_KEY}"
|
||||
else:
|
||||
# Authentication priority: service-token override, then caller auth_header
|
||||
# from phone login/discovery/pass-2 fallback, then no authentication.
|
||||
if settings.S2S_APIPILOT_SERVICE_TOKEN:
|
||||
_svc = settings.S2S_APIPILOT_SERVICE_TOKEN.strip()
|
||||
final_auth = (f"Bearer {_svc}" if (not _svc.lower().startswith("bearer ")) else _svc) if _svc else None
|
||||
else:
|
||||
final_auth = auth_header if isinstance(auth_header, str) and auth_header.strip() else None
|
||||
if final_auth:
|
||||
headers["Authorization"] = final_auth
|
||||
if demo_session:
|
||||
headers["x-demo-session"] = demo_session
|
||||
payload = {"name": name_clean, "arguments": cleaned_args}
|
||||
removed = sorted(list(set(arguments) - set(cleaned_args))) if isinstance(arguments, dict) else []
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-EXEC] → POST %s name=%s argsKeys=%s removedKeys=%s auth=%s demo=%s",
|
||||
url,
|
||||
name_clean,
|
||||
sorted(cleaned_args.keys()),
|
||||
removed,
|
||||
("APIKEY" if settings.S2S_APIPILOT_API_KEY else ("Y" if final_auth else "-")),
|
||||
("APIKEY" if settings.S2S_APIPILOT_API_KEY else ("Y" if demo_session else "-")),
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=settings.APIPILOT_HTTP_TIMEOUT, follow_redirects=True) as http:
|
||||
resp = await http.post(url, json=payload, headers=headers)
|
||||
except Exception as exc:
|
||||
app_logging.logger.error("[APIPILOT-EXEC] ✗ network error: %s", exc)
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "EXECUTION_ERROR",
|
||||
"message": f"Error de red al ejecutar «{name_clean}»: {exc}",
|
||||
"status_code": 502,
|
||||
"raw": None,
|
||||
},
|
||||
}
|
||||
# Parse a standard envelope; construct a matching error for non-JSON/5xx responses.
|
||||
raw_text = resp.text
|
||||
# Detailed diagnostics are always enabled for HTTP >= 400: request payload,
|
||||
# unmasked demo session, response status and bounded raw response body.
|
||||
if resp.status_code >= 400:
|
||||
try:
|
||||
payload_dump = __import__("json").dumps(payload, ensure_ascii=False)
|
||||
except Exception: # noqa: BLE001
|
||||
payload_dump = str(payload)
|
||||
app_logging.logger.warning(
|
||||
"[APIPILOT-EXEC][DIAGNOSTIC 4xx] HTTP=%d url=%s name=%s demoSession=%.60s AUTH=%s requestPAYLOAD=%s |RAW RESPONSE BODY (max 1800 chars)=|%s|",
|
||||
resp.status_code,
|
||||
url,
|
||||
name_clean,
|
||||
(demo_session if isinstance(demo_session, str) else "?"),
|
||||
("YES len=" + str(len(final_auth)) if isinstance(final_auth, str) and final_auth.strip() else "-"),
|
||||
payload_dump,
|
||||
(raw_text or "")[:1800],
|
||||
)
|
||||
try:
|
||||
parsed = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.error("[APIPILOT-EXEC] ✗ non-JSON body HTTP %s: %s", resp.status_code, raw_text[:500])
|
||||
return {
|
||||
"success": False,
|
||||
"data": None,
|
||||
"error": {
|
||||
"code": "EXECUTION_ERROR",
|
||||
"message": f"La respuesta de ejecución «{name_clean}» no es JSON válido (HTTP {resp.status_code}).",
|
||||
"status_code": resp.status_code,
|
||||
"raw": raw_text[:2000] if raw_text else None,
|
||||
},
|
||||
}
|
||||
# Return standard {success,data,error} envelopes unchanged.
|
||||
if isinstance(parsed, dict) and "success" in parsed and isinstance(parsed.get("success"), bool):
|
||||
envelope_ok = parsed["success"] and parsed.get("error") in (None, {})
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-EXEC] ← %s name=%s success=%s http=%s dataKeys=%s",
|
||||
"OK" if envelope_ok else "FAIL",
|
||||
name_clean,
|
||||
bool(parsed.get("success")),
|
||||
resp.status_code,
|
||||
sorted(list(cast(dict, parsed.get("data")).keys())) if isinstance(parsed.get("data"), dict) else "-",
|
||||
)
|
||||
if (not envelope_ok) and isinstance(parsed.get("error"), dict):
|
||||
err = parsed["error"]
|
||||
app_logging.logger.warning(
|
||||
"[APIPILOT-EXEC] ERROR: code=%s status=%s msg=%s",
|
||||
err.get("code"),
|
||||
err.get("status_code"),
|
||||
(str(err.get("message"))[:200] if err.get("message") is not None else "-"),
|
||||
)
|
||||
return parsed
|
||||
# Wrap raw backend data in the required envelope (guide §2.2) for stable
|
||||
# downstream behavior when an upstream response omits the wrapper.
|
||||
app_logging.logger.warning(
|
||||
"[APIPILOT-EXEC] backend omitted standard envelope → wrapping response http=%s", resp.status_code
|
||||
)
|
||||
return {
|
||||
"success": 200 <= resp.status_code < 300,
|
||||
"data": parsed if (200 <= resp.status_code < 300) else None,
|
||||
"error": None
|
||||
if (200 <= resp.status_code < 300)
|
||||
else {
|
||||
"code": "EXECUTION_ERROR",
|
||||
"message": (f"Ejecución «{name_clean}» devolvió HTTP {resp.status_code} sin envelope estándar."),
|
||||
"status_code": resp.status_code,
|
||||
"raw": (raw_text[:2000] if raw_text else None),
|
||||
},
|
||||
}
|
||||
@@ -0,0 +1,558 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any
|
||||
from urllib.parse import urlencode
|
||||
|
||||
import httpx
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
|
||||
|
||||
async def _fetch_reports_list(phone_number: str | None = None, auth_token: str | None = None) -> list | dict | None:
|
||||
"""Fetch scheduled reports list from S2S_REPORT_LIST.
|
||||
|
||||
Completely generic / deploy-agnostic: performs GET ${S2S_REPORT_LIST} and appends
|
||||
?phoneNumber=<x> if a phone is provided. Accepts JSON (optional {"result": [...]}
|
||||
wrapper) and returns the list or unwrapped list. On any error logs and returns None
|
||||
(never fails the proxy / reasoning tunnel).
|
||||
|
||||
USER FIX 2026-09-11: remove mass injection of scheduled reports.
|
||||
• If S2S_INJECT_REPORTS is FALSE (DEFAULT) we short-circuit to None at the
|
||||
very top — NO HTTP call is made to S2S_REPORT_LIST at all. The upstream
|
||||
endpoint is never hit, not even for a "cheap empty list"; combined with
|
||||
_resolve_reports_context → "" above, this guarantees ZERO scheduled-report
|
||||
contents reach any LLM prompt anywhere (WS session instructions patch,
|
||||
/api/reasoning user_context, NODE_RED instructions augment, quick reports
|
||||
lookup response).
|
||||
• S2S_INJECT_REPORTS=true restores prior behaviour (both the HTTP fetch AND
|
||||
the full injection into every prompt path).
|
||||
"""
|
||||
# ── MASS-INJECTION KILL SWITCH (user request) ─────────────────────────
|
||||
if not settings.S2S_INJECT_REPORTS:
|
||||
return None
|
||||
# ───────────────────────────────────────────────────────────────────────
|
||||
if not settings.S2S_REPORT_LIST:
|
||||
return None
|
||||
if phone_number:
|
||||
sep = "&" if "?" in settings.S2S_REPORT_LIST else "?"
|
||||
target_url = f"{settings.S2S_REPORT_LIST}{sep}{urlencode({'phoneNumber': phone_number})}"
|
||||
else:
|
||||
target_url = settings.S2S_REPORT_LIST
|
||||
app_logging.logger.info(
|
||||
"[INJECT-REPORTS] fetch upstream URL=%s phoneLen=%s bearer=%s",
|
||||
settings.S2S_REPORT_LIST,
|
||||
len(phone_number) if phone_number else "none",
|
||||
"yes" if auth_token else "no",
|
||||
)
|
||||
try:
|
||||
headers = {}
|
||||
if auth_token:
|
||||
headers["Authorization"] = f"Bearer {auth_token}"
|
||||
async with httpx.AsyncClient(timeout=15.0, follow_redirects=True) as http:
|
||||
resp = await http.get(target_url, headers=headers or None)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-REPORTS] ⛔ upstream HTTP %s response=%.250s",
|
||||
resp.status_code,
|
||||
resp.text,
|
||||
)
|
||||
return None
|
||||
text = (resp.text or "").strip()
|
||||
if not text:
|
||||
app_logging.logger.info("[INJECT-REPORTS] ⏭️ upstream returned empty body.")
|
||||
return None
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-REPORTS] ⛔ upstream returned non-JSON body len=%d; cannot parse list. response=%.250s",
|
||||
len(text),
|
||||
text,
|
||||
)
|
||||
return None
|
||||
except Exception as exc:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-REPORTS] ⛔ fetch unreachable error=%r",
|
||||
exc,
|
||||
)
|
||||
return None
|
||||
# Unwrap {"result": [...]} or other common list-wrapping dict keys
|
||||
# (e.g. {"data": [...], "reports": [...], "items": [...], "content": [...], "value": [...]}).
|
||||
unwrapped: object = payload
|
||||
if isinstance(payload, dict):
|
||||
# Log full structure for debugging if enabled
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
try:
|
||||
keys_preview = ",".join(sorted(str(k) for k in payload.keys()))
|
||||
preview = json.dumps(payload, ensure_ascii=False)
|
||||
preview = preview[:4000]
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-REPORTS][fetch] upstream response dict keys=[%s] full PREVIEW (len=%d):\n%s\n",
|
||||
keys_preview,
|
||||
len(preview),
|
||||
preview,
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
# Preferred explicit "result" key first
|
||||
if "result" in payload and isinstance(payload["result"], list):
|
||||
unwrapped = payload["result"]
|
||||
else:
|
||||
# Scan all common list-wrapper keys (case-insensitive match on the key)
|
||||
wrapper_keys = {
|
||||
k.lower()
|
||||
for k in (
|
||||
"data",
|
||||
"reports",
|
||||
"reportList",
|
||||
"report_list",
|
||||
"report",
|
||||
"items",
|
||||
"itemList",
|
||||
"item_list",
|
||||
"list",
|
||||
"content",
|
||||
"scheduled",
|
||||
"scheduledReports",
|
||||
"scheduled_reports",
|
||||
"podcastList",
|
||||
"podcast_list",
|
||||
"podcasts",
|
||||
"entries",
|
||||
"records",
|
||||
"rows",
|
||||
"pageContent",
|
||||
"page_content",
|
||||
"value",
|
||||
)
|
||||
}
|
||||
for k, v in payload.items():
|
||||
if isinstance(k, str) and isinstance(v, list) and k.lower() in wrapper_keys:
|
||||
unwrapped = v
|
||||
break
|
||||
# Fallback: if it's still a dict with only ONE list-valued key,
|
||||
# assume that's the list (common pattern like {"data": [...]} with
|
||||
# unusual key name we don't hardcode).
|
||||
if not isinstance(unwrapped, list):
|
||||
list_valued_keys = [k for k, v in payload.items() if isinstance(v, list) and len(v) > 0]
|
||||
if len(list_valued_keys) == 1:
|
||||
unwrapped = payload[list_valued_keys[0]]
|
||||
# Validate array shape
|
||||
if isinstance(unwrapped, list):
|
||||
n_items = len(unwrapped)
|
||||
n_dict = sum(1 for x in unwrapped if isinstance(x, dict))
|
||||
app_logging.logger.info(
|
||||
"[INJECT-REPORTS] ✅ reports list loaded OK (list len=%d dictItems=%d)",
|
||||
n_items,
|
||||
n_dict,
|
||||
)
|
||||
return unwrapped
|
||||
app_logging.logger.info(
|
||||
"[INJECT-REPORTS] ⏭️ upstream returned type=%s (not list); nothing to inject.",
|
||||
type(unwrapped).__name__,
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and isinstance(payload, dict):
|
||||
# Log final top-level keys to help diagnose wrapper shape
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-REPORTS][fetch] wrapper not detected — top-level keys of dict response: [%s] "
|
||||
"(list values under keys: %s)",
|
||||
",".join(sorted(str(k) for k in payload.keys())),
|
||||
",".join(sorted(str(k) + "=list[" + str(len(v)) + "]" for k, v in payload.items() if isinstance(v, list)))
|
||||
or "none",
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
def _extract_login_token(login_payload: dict | None) -> str | None:
|
||||
"""Given the parsed response from the S2S_LOGIN_BY_PHONE endpoint (already
|
||||
{"result":…}-unwrapped), try to extract an auth / session token.
|
||||
Looks under common names (case-insensitive). Returns None if nothing found.
|
||||
"""
|
||||
if not login_payload or not isinstance(login_payload, dict):
|
||||
return None
|
||||
# Unwrap one level of nesting if result is still an dict: handled by caller already.
|
||||
candidates = {
|
||||
c.lower()
|
||||
for c in (
|
||||
"token",
|
||||
"jwt",
|
||||
"access_token",
|
||||
"accessToken",
|
||||
"auth_token",
|
||||
"authToken",
|
||||
"session_token",
|
||||
"sessionToken",
|
||||
"id_token",
|
||||
"idToken",
|
||||
"bearer",
|
||||
"bearer_token",
|
||||
"bearerToken",
|
||||
"authentication_token",
|
||||
)
|
||||
}
|
||||
for k, v in login_payload.items():
|
||||
if isinstance(k, str) and k.lower() in candidates and isinstance(v, str) and v.strip():
|
||||
return v.strip()
|
||||
# Second pass: nested dict {"data": {"token": …}} or {"auth": {"jwt": …}}
|
||||
for _k, v in login_payload.items():
|
||||
if isinstance(v, dict):
|
||||
nested = _extract_login_token(v)
|
||||
if nested:
|
||||
return nested
|
||||
# Third pass: list like [{"token": ...}] (uncommon but safe)
|
||||
for _k, v in login_payload.items():
|
||||
if isinstance(v, list) and v:
|
||||
for elem in v:
|
||||
if isinstance(elem, dict):
|
||||
nested = _extract_login_token(elem)
|
||||
if nested:
|
||||
return nested
|
||||
return None
|
||||
|
||||
|
||||
async def _login_by_phone(phone_number: str) -> tuple[str | None, dict | None]:
|
||||
"""Perform login-by-phone: POST S2S_LOGIN_BY_PHONE with JSON
|
||||
{"phoneNumber": phone_number}. Returns (bearer_token_or_None, response_obj_or_None).
|
||||
|
||||
Never fails: on any HTTP/parse error logs a warning and returns (None, None)
|
||||
so subsequent profile/summary calls simply proceed without a Bearer token.
|
||||
"""
|
||||
if not settings.S2S_LOGIN_BY_PHONE or not phone_number:
|
||||
return None, None
|
||||
body = {"phoneNumber": phone_number}
|
||||
app_logging.logger.info(
|
||||
"[INJECT-LOGIN] POST upstream URL=%s phoneLen=%d",
|
||||
settings.S2S_LOGIN_BY_PHONE,
|
||||
len(phone_number),
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=10.0, follow_redirects=True) as http:
|
||||
resp = await http.post(
|
||||
settings.S2S_LOGIN_BY_PHONE,
|
||||
json=body,
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-LOGIN] ⛔ upstream HTTP %s phoneLen=%d response=%.250s",
|
||||
resp.status_code,
|
||||
len(phone_number),
|
||||
resp.text,
|
||||
)
|
||||
return None, None
|
||||
text = (resp.text or "").strip()
|
||||
if not text:
|
||||
app_logging.logger.info("[INJECT-LOGIN] ⏭️ upstream returned empty body; no login token available.")
|
||||
return None, None
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-LOGIN] ⛔ upstream returned non-JSON body len=%d; cannot extract token. response=%.250s",
|
||||
len(text),
|
||||
text,
|
||||
)
|
||||
return None, None
|
||||
except Exception as exc:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-LOGIN] ⛔ fetch unreachable phoneLen=%d error=%r",
|
||||
len(phone_number),
|
||||
exc,
|
||||
)
|
||||
return None, None
|
||||
|
||||
# Unwrap {"result": …} OR {"data": …} if present (common wrapper conventions).
|
||||
unwrapped: dict | None = None
|
||||
if isinstance(payload, dict):
|
||||
for _wrap_key in ("result", "data", "payload"):
|
||||
if isinstance(payload.get(_wrap_key), dict):
|
||||
unwrapped = payload[_wrap_key]
|
||||
break
|
||||
if unwrapped is None:
|
||||
unwrapped = payload
|
||||
token = (
|
||||
_extract_login_token(unwrapped)
|
||||
if isinstance(unwrapped, dict)
|
||||
else _extract_login_token(payload if isinstance(payload, dict) else None)
|
||||
)
|
||||
# Always log login-token diagnostics, even without S2S_DEBUG_PROMPT:
|
||||
# token length, first eight characters, response keys and wrapper layer.
|
||||
_all_keys: list[str] = []
|
||||
if isinstance(payload, dict):
|
||||
_all_keys.extend(str(k) for k in payload.keys())
|
||||
_unwrap_keys: list[str] = []
|
||||
if isinstance(unwrapped, dict):
|
||||
_unwrap_keys.extend(str(k) for k in unwrapped.keys())
|
||||
if isinstance(unwrapped, dict):
|
||||
_t_preview = ""
|
||||
_t_len = 0
|
||||
if isinstance(token, str) and token.strip():
|
||||
_t_len = len(token.strip())
|
||||
if _t_len > 8:
|
||||
_t_preview = token.strip()[:8] + "..."
|
||||
else:
|
||||
_t_preview = token.strip()
|
||||
_fmt_note = ""
|
||||
if _t_len >= 120:
|
||||
_fmt_note = " [JWT-like]"
|
||||
elif _t_len > 0:
|
||||
_fmt_note = " [SHORT]"
|
||||
_wrap_layer = "ROOT"
|
||||
if isinstance(payload, dict):
|
||||
for _wk in ("result", "data", "payload"):
|
||||
if isinstance(payload.get(_wk), dict):
|
||||
_wrap_layer = "result/data/payload"
|
||||
break
|
||||
_all_keys_s = ",".join(sorted(_all_keys)) if _all_keys else "-"
|
||||
_unwrap_keys_s = ",".join(sorted(_unwrap_keys)) if _unwrap_keys else "-"
|
||||
_t_info = "MISSING"
|
||||
if _t_len:
|
||||
_t_info = "YES len=" + str(_t_len) + " head=" + _t_preview
|
||||
msg = f"[INJECT-LOGIN] ✅ login OK: wrapLayer={_wrap_layer} topKeys={_all_keys_s} unwrappedKeys={_unwrap_keys_s} token={_t_info}{_fmt_note}"
|
||||
app_logging.logger.info("%s", msg)
|
||||
return token, unwrapped
|
||||
# Fallback: non-dict payload (string/list/number) — still log it, but no token expected.
|
||||
app_logging.logger.info(
|
||||
"[INJECT-LOGIN] ⏭️ login response parsed but type=%s (not dict); no token extracted.",
|
||||
type(payload).__name__,
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-LOGIN][response] FULL login payload (len=%d):\n%s\n",
|
||||
len(str(payload)),
|
||||
payload,
|
||||
)
|
||||
return None, None
|
||||
|
||||
|
||||
async def _fetch_latest_summary_for_phone(phone_number: str, auth_token: str | None = None) -> Any:
|
||||
"""Fetch the latest caller summary via S2S_LATEST_SUMMARY URL.
|
||||
|
||||
Generic / completely deploy-agnostic: plain GET
|
||||
S2S_LATEST_SUMMARY?phoneNumber=<phone>; accepts JSON (optional {"result": …}
|
||||
wrapper) or plain text. Never fails the proxy / reasoning; returns None on
|
||||
any error and logs it. If `auth_token` is provided it is sent as
|
||||
Authorization: Bearer <auth_token>.
|
||||
|
||||
OVERRIDE (2026-09-23): when S2S_LATEST_SUMMARY_TEXT is set (non-empty) it
|
||||
takes absolute priority over S2S_LATEST_SUMMARY. No HTTP call is made at all;
|
||||
the raw plain-text value is returned directly. Designed for operators who want
|
||||
a clean, pre-curated, essential summary snippet without any upstream API
|
||||
dependency. Works even without a phone_number (static snippet).
|
||||
"""
|
||||
if settings.S2S_LATEST_SUMMARY_TEXT:
|
||||
override_len = len(settings.S2S_LATEST_SUMMARY_TEXT)
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] S2S_LATEST_SUMMARY_TEXT OVERRIDE active (len=%d chars). Skipping HTTP fetch; injecting raw static plain-text summary directly.",
|
||||
override_len,
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] [DEBUG-PROMPT] S2S_LATEST_SUMMARY_TEXT raw value (first 800 chars):\n%s",
|
||||
settings.S2S_LATEST_SUMMARY_TEXT[:800],
|
||||
)
|
||||
return settings.S2S_LATEST_SUMMARY_TEXT
|
||||
if not settings.S2S_LATEST_SUMMARY or not phone_number:
|
||||
return None
|
||||
target_url = f"{settings.S2S_LATEST_SUMMARY}?{urlencode({'phoneNumber': phone_number})}"
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] fetch upstream URL=%s phoneLen=%d bearer=%s",
|
||||
settings.S2S_LATEST_SUMMARY,
|
||||
len(phone_number),
|
||||
"yes" if auth_token else "no",
|
||||
)
|
||||
try:
|
||||
headers = {}
|
||||
if auth_token:
|
||||
headers["Authorization"] = f"Bearer {auth_token}"
|
||||
async with httpx.AsyncClient(timeout=10.0, follow_redirects=True) as http:
|
||||
resp = await http.get(target_url, headers=headers or None)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-SUMMARY] ⛔ upstream HTTP %s phoneLen=%d response=%.200s",
|
||||
resp.status_code,
|
||||
len(phone_number),
|
||||
resp.text,
|
||||
)
|
||||
return None
|
||||
# Accept JSON first, then fall back to plain text (some summary APIs
|
||||
# return text/plain).
|
||||
text = (resp.text or "").strip()
|
||||
if not text:
|
||||
return ""
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] upstream returned non-JSON response (len=%d); treating as plain string summary.",
|
||||
len(text),
|
||||
)
|
||||
return text
|
||||
except Exception as exc:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-SUMMARY] ⛔ fetch unreachable phoneLen=%d error=%r",
|
||||
len(phone_number),
|
||||
exc,
|
||||
)
|
||||
return None
|
||||
# Unwrap {"result": …} just like profile fetch (common wrapper pattern).
|
||||
if isinstance(payload, dict) and "result" in payload:
|
||||
payload = payload["result"]
|
||||
# Filter out empty dict/list / empty string after unwrap.
|
||||
empty = (
|
||||
payload is None
|
||||
or (isinstance(payload, str) and not payload.strip())
|
||||
or (isinstance(payload, dict) and len(payload) == 0)
|
||||
or (isinstance(payload, list) and len(payload) == 0)
|
||||
)
|
||||
if empty:
|
||||
app_logging.logger.info("[INJECT-SUMMARY] ⏭️ upstream returned empty summary; nothing to inject.")
|
||||
return None
|
||||
if isinstance(payload, dict):
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] ✅ summary loaded OK (object) keys=%s",
|
||||
",".join(sorted(str(k) for k in payload.keys())),
|
||||
)
|
||||
elif isinstance(payload, list):
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] ✅ summary loaded OK (list) len=%d",
|
||||
len(payload),
|
||||
)
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] ✅ summary loaded OK (string) len=%d",
|
||||
len(str(payload)),
|
||||
)
|
||||
return payload
|
||||
|
||||
|
||||
async def _fetch_podcast_episode(episode_id: str) -> Any:
|
||||
"""Fetch a single podcast episode by ID from the Aquachile AzurianLab API.
|
||||
|
||||
Completely generic / deploy-agnostic: plain GET
|
||||
https://aquachile.azurianlab.com/api/v1/podcast/episodes/<episode_id>
|
||||
Accepts JSON (optional {"result": …} wrapper) or plain text. Never fails
|
||||
the proxy / reasoning; returns None on any error and logs it.
|
||||
"""
|
||||
if not episode_id:
|
||||
return None
|
||||
target_url = f"https://aquachile.azurianlab.com/api/v1/podcast/episodes/{episode_id}"
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] fetch upstream URL=%s episodeId=%.80s",
|
||||
target_url,
|
||||
episode_id,
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=15.0, follow_redirects=True) as http:
|
||||
resp = await http.get(target_url)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-EPISODE] ⛔ upstream HTTP %s episodeId=%.80s response=%.200s",
|
||||
resp.status_code,
|
||||
episode_id,
|
||||
resp.text,
|
||||
)
|
||||
return None
|
||||
text = (resp.text or "").strip()
|
||||
if not text:
|
||||
return ""
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] upstream returned non-JSON response (len=%d); treating as plain string.",
|
||||
len(text),
|
||||
)
|
||||
return text
|
||||
except Exception as exc:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-EPISODE] ⛔ fetch unreachable episodeId=%.80s error=%r",
|
||||
episode_id,
|
||||
exc,
|
||||
)
|
||||
return None
|
||||
if isinstance(payload, dict) and "result" in payload:
|
||||
payload = payload["result"]
|
||||
empty = (
|
||||
payload is None
|
||||
or (isinstance(payload, str) and not payload.strip())
|
||||
or (isinstance(payload, dict) and len(payload) == 0)
|
||||
or (isinstance(payload, list) and len(payload) == 0)
|
||||
)
|
||||
if empty:
|
||||
app_logging.logger.info("[INJECT-EPISODE] ⏭️ upstream returned empty episode; nothing to inject.")
|
||||
return None
|
||||
if isinstance(payload, dict):
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] ✅ episode loaded OK (object) keys=%s",
|
||||
",".join(sorted(str(k) for k in payload.keys())),
|
||||
)
|
||||
elif isinstance(payload, list):
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] ✅ episode loaded OK (list) len=%d",
|
||||
len(payload),
|
||||
)
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] ✅ episode loaded OK (string) len=%d",
|
||||
len(str(payload)),
|
||||
)
|
||||
return payload
|
||||
|
||||
|
||||
async def _fetch_user_profile_for_phone(phone_number: str, auth_token: str | None = None) -> dict | None:
|
||||
"""Fetch the profile JSON from VOCERO_USER_PHONE_AUTH_URL for a phone.
|
||||
Returns the raw {"result": ...}-unwrapped object or None. Errors are logged
|
||||
then suppressed (never fail the proxy / reasoning because of this).
|
||||
|
||||
When `auth_token` is provided it is forwarded as Authorization: Bearer <auth_token>
|
||||
to the upstream profile endpoint.
|
||||
"""
|
||||
if not settings.VOCERO_USER_PHONE_AUTH_URL or not phone_number:
|
||||
return None
|
||||
target_url = f"{settings.VOCERO_USER_PHONE_AUTH_URL}?{urlencode({'phoneNumber': phone_number})}"
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] fetch upstream URL=%s phoneLen=%d bearer=%s",
|
||||
settings.VOCERO_USER_PHONE_AUTH_URL,
|
||||
len(phone_number),
|
||||
"yes" if auth_token else "no",
|
||||
)
|
||||
try:
|
||||
headers = {}
|
||||
if auth_token:
|
||||
headers["Authorization"] = f"Bearer {auth_token}"
|
||||
async with httpx.AsyncClient(timeout=10.0, follow_redirects=True) as http:
|
||||
resp = await http.get(target_url, headers=headers or None)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ⛔ upstream HTTP %s phoneLen=%d response=%.200s",
|
||||
resp.status_code,
|
||||
len(phone_number),
|
||||
resp.text,
|
||||
)
|
||||
return None
|
||||
payload = resp.json()
|
||||
except Exception as exc:
|
||||
app_logging.logger.warning(
|
||||
"[INJECT-PROFILE] ⛔ fetch unreachable phoneLen=%d error=%r",
|
||||
len(phone_number),
|
||||
exc,
|
||||
)
|
||||
return None
|
||||
if isinstance(payload, dict) and "result" in payload and isinstance(payload["result"], dict):
|
||||
profile_obj = payload["result"]
|
||||
elif isinstance(payload, dict) and not isinstance(payload, list):
|
||||
profile_obj = payload
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ⛔ upstream returned non-object JSON type=%s keys=?",
|
||||
type(payload).__name__,
|
||||
)
|
||||
return None
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ✅ profile loaded OK keys=%s",
|
||||
",".join(sorted(profile_obj.keys())),
|
||||
)
|
||||
return profile_obj
|
||||
@@ -0,0 +1,461 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import re
|
||||
from typing import Any, cast
|
||||
|
||||
from s2s_client.core import logging as app_logging
|
||||
from s2s_client.services import context as services_context
|
||||
from s2s_client.services import tool_context as services_tool_context
|
||||
|
||||
|
||||
async def _report_server_debug(hypothesis_id: str, location: str, msg: str, data: dict | None = None) -> None:
|
||||
return
|
||||
|
||||
|
||||
def _realtime_event_summary(raw: str) -> dict | None:
|
||||
try:
|
||||
payload = json.loads(raw)
|
||||
except Exception:
|
||||
return None
|
||||
if not isinstance(payload, dict):
|
||||
return None
|
||||
event_type = payload.get("type")
|
||||
if not isinstance(event_type, str):
|
||||
return None
|
||||
summary: dict[str, Any] = {"type": event_type}
|
||||
if event_type == "session.update":
|
||||
session = cast(dict[str, Any], payload.get("session")) if isinstance(payload.get("session"), dict) else {}
|
||||
tools = cast(list[Any], session.get("tools")) if isinstance(session.get("tools"), list) else []
|
||||
summary["toolCount"] = len(tools)
|
||||
summary["toolNames"] = [tool.get("name") for tool in tools if isinstance(tool, dict)]
|
||||
summary["toolChoice"] = session.get("tool_choice")
|
||||
summary["instructionLength"] = len(session.get("instructions") or "")
|
||||
elif event_type in {"response.function_call_arguments.done", "error", "session.updated"}:
|
||||
for key in ("name", "call_id", "code", "message", "response_id"):
|
||||
if key in payload:
|
||||
summary[key] = payload.get(key)
|
||||
# --- INPUT (user speech → STT transcript) ---
|
||||
# Can arrive from upstream (server-side STT) — match either direction.
|
||||
elif event_type == "conversation.item.input_audio_transcription.completed":
|
||||
summary["transcript"] = payload.get("transcript", "")
|
||||
summary["item_id"] = payload.get("item_id")
|
||||
elif event_type == "conversation.item.created":
|
||||
item = payload.get("item") if isinstance(payload.get("item"), dict) else None
|
||||
if isinstance(item, dict):
|
||||
summary["item_id"] = item.get("id")
|
||||
summary["role"] = item.get("role")
|
||||
summary["item_type"] = item.get("type")
|
||||
summary["status"] = item.get("status")
|
||||
content_parts = []
|
||||
for c in item.get("content") or []:
|
||||
if isinstance(c, dict):
|
||||
if c.get("type") in {"input_text", "text"} and isinstance(c.get("text"), str):
|
||||
content_parts.append(c["text"])
|
||||
elif c.get("type") == "transcript" and isinstance(c.get("transcript"), str):
|
||||
content_parts.append(c["transcript"])
|
||||
if content_parts:
|
||||
summary["text"] = " ".join(content_parts)
|
||||
# --- OUTPUT (agent text/speech generation) ---
|
||||
elif event_type == "response.output_item.done":
|
||||
item = payload.get("item") if isinstance(payload.get("item"), dict) else None
|
||||
if isinstance(item, dict):
|
||||
summary["item_id"] = item.get("id")
|
||||
summary["role"] = item.get("role")
|
||||
summary["status"] = item.get("status")
|
||||
content_parts = []
|
||||
for c in item.get("content") or []:
|
||||
if isinstance(c, dict):
|
||||
if c.get("type") == "text" and isinstance(c.get("text"), str) and c["text"]:
|
||||
content_parts.append(c["text"])
|
||||
elif c.get("type") == "audio" and isinstance(c.get("transcript"), str) and c["transcript"]:
|
||||
content_parts.append(c["transcript"])
|
||||
if content_parts:
|
||||
summary["text"] = " ".join(content_parts)
|
||||
elif event_type == "response.content_part.done":
|
||||
part = payload.get("part") if isinstance(payload.get("part"), dict) else None
|
||||
if isinstance(part, dict):
|
||||
summary["response_id"] = payload.get("response_id")
|
||||
summary["item_id"] = payload.get("item_id")
|
||||
summary["output_index"] = payload.get("output_index")
|
||||
summary["content_index"] = payload.get("content_index")
|
||||
if part.get("type") == "text":
|
||||
summary["text"] = part.get("text", "")
|
||||
elif part.get("type") == "audio":
|
||||
if isinstance(part.get("transcript"), str) and part["transcript"]:
|
||||
summary["text"] = part["transcript"]
|
||||
# Standard OpenAI variant:
|
||||
elif event_type == "response.audio_transcript.done":
|
||||
summary["response_id"] = payload.get("response_id")
|
||||
summary["item_id"] = payload.get("item_id")
|
||||
summary["text"] = payload.get("transcript", "")
|
||||
# Custom upstream variant observed in user logs:
|
||||
elif event_type == "response.output_audio_transcript.done":
|
||||
summary["response_id"] = payload.get("response_id")
|
||||
summary["item_id"] = payload.get("item_id")
|
||||
summary["output_index"] = payload.get("output_index")
|
||||
# Try field names in order of likelihood
|
||||
text = ""
|
||||
for key in (
|
||||
"transcript",
|
||||
"text",
|
||||
"output_text",
|
||||
"audio_text",
|
||||
"output_transcript",
|
||||
"final_transcript",
|
||||
"output_audio_text",
|
||||
"content",
|
||||
"message",
|
||||
"utterance",
|
||||
):
|
||||
v = payload.get(key)
|
||||
if isinstance(v, str) and v.strip():
|
||||
text = v.strip()
|
||||
break
|
||||
# If text is still empty, search known nested objects.
|
||||
if not text:
|
||||
for container in ("item", "part", "content", "output", "delta", "audio"):
|
||||
sub = payload.get(container)
|
||||
if isinstance(sub, dict):
|
||||
for key in ("transcript", "text", "output_text"):
|
||||
v = sub.get(key)
|
||||
if isinstance(v, str) and v.strip():
|
||||
text = v.strip()
|
||||
break
|
||||
if text:
|
||||
break
|
||||
if not text:
|
||||
# Last resort: the content[] array.
|
||||
arr = payload.get("content")
|
||||
if isinstance(arr, list):
|
||||
parts = []
|
||||
for c in arr:
|
||||
if isinstance(c, dict):
|
||||
for key in ("transcript", "text"):
|
||||
v = c.get(key)
|
||||
if isinstance(v, str) and v.strip():
|
||||
parts.append(v.strip())
|
||||
if parts:
|
||||
text = " ".join(parts)
|
||||
summary["text"] = text
|
||||
# If no text was found, retain a raw preview to inspect the custom format.
|
||||
if not text:
|
||||
preview = raw[:800]
|
||||
try:
|
||||
pretty = json.dumps(payload, ensure_ascii=True)[:800]
|
||||
except Exception:
|
||||
pretty = preview
|
||||
summary["_raw_preview"] = pretty
|
||||
elif event_type == "response.function_call_arguments.done":
|
||||
summary["arguments"] = payload.get("arguments")
|
||||
# This event confirms strategy B: ai-server accepted native tools[].
|
||||
_tool_name = payload.get("name") if isinstance(payload.get("name"), str) else ""
|
||||
_call_id = payload.get("call_id") if isinstance(payload.get("call_id"), str) else ""
|
||||
_args_json = cast(str, payload.get("arguments")) if isinstance(payload.get("arguments"), str) else "{}"
|
||||
app_logging.logger.info(
|
||||
"[TOOLCALL] ✓ UPSTREAM emitted response.function_call_arguments.done! "
|
||||
"tool=%s callId=%s argsLen=%d argsPreview=%s",
|
||||
_tool_name or "(empty)",
|
||||
_call_id or "-",
|
||||
len(_args_json),
|
||||
_args_json[:200],
|
||||
)
|
||||
try:
|
||||
_args_parsed = json.loads(_args_json or "{}")
|
||||
app_logging.logger.info(
|
||||
"[TOOLCALL] ✓ Tool call parsed argsKeys=%s",
|
||||
sorted(_args_parsed.keys()) if isinstance(_args_parsed, dict) else "N/A",
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
return summary
|
||||
|
||||
|
||||
# Suppress noisy high-frequency events in detailed logs. Internal debug
|
||||
# reporting still tracks them when enabled.
|
||||
_NOISY_REALTIME_EVENT_TYPES = frozenset(
|
||||
{
|
||||
"response.output_audio.delta",
|
||||
"response.audio.delta",
|
||||
"conversation.item.input_audio_transcription.delta",
|
||||
"response.text.delta",
|
||||
"response.output_text.delta",
|
||||
"rate_limits.updated",
|
||||
}
|
||||
)
|
||||
|
||||
# Suppress client-side high-frequency events such as input_audio_buffer.append.
|
||||
_NOISY_CLIENT_EVENT_TYPES = frozenset(
|
||||
{
|
||||
"input_audio_buffer.append",
|
||||
"input_audio_buffer.commit",
|
||||
"input_audio_buffer.clear",
|
||||
"input_audio_buffer.speech_started",
|
||||
"input_audio_buffer.speech_stopped",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def _extract_profile_for_session(session_ctx: dict) -> dict:
|
||||
"""Return the profile dict stored in session_ctx (phone auth result)."""
|
||||
p = session_ctx.get("profile_obj") or session_ctx.get("user_profile") or {}
|
||||
if isinstance(p, dict) and isinstance(p.get("user"), dict):
|
||||
return cast(dict[str, Any], p["user"])
|
||||
if isinstance(p, dict):
|
||||
return p
|
||||
return {}
|
||||
|
||||
|
||||
def _sanitize_agent_output(text: Any, session_ctx: dict[str, Any] | None = None) -> str:
|
||||
"""Server-side FINAL filter applied to ALL assistant output text.
|
||||
|
||||
Guarantees (belt-and-suspenders over the 6 prompt layers):
|
||||
1. No [...][xxx] bracket markers of any kind.
|
||||
2. No inline { ... } JSON / dict literals.
|
||||
3. No [-]: <internal action name> pseudo-markers.
|
||||
4. No name anglicization: Alessandro → restored to Alessandro.
|
||||
5. Trim + collapse multiple spaces.
|
||||
"""
|
||||
s = str(text or "")
|
||||
if not s:
|
||||
return s
|
||||
# (0) Remove "action line" pseudo-markers FIRST, BEFORE stripping all
|
||||
# other brackets, because the pattern uses the literal "[-]" prefix
|
||||
# which would get silently swallowed by step (1) otherwise. Match:
|
||||
# [-]: checking_podcast_report (bracket literal then colon)
|
||||
# []: action_name (empty bracket variant)
|
||||
# [ - ] : do_stuff (spaces inside & around)
|
||||
# Pattern is intentionally TIGHT: after the colon we only take up to 6
|
||||
# underscore/hyphen words so we cannot accidentally eat the following
|
||||
# real user speech (bug: greedy class with ,. and 200-char upper bound ate
|
||||
# the entire "Claro, revisaré el reporte." clause on 2026-09-11).
|
||||
s = re.sub(
|
||||
r"\[[\s\-]{0,6}\]\s*:\s*[a-z0-9_\-]+(?:[ \t]+[a-z0-9_\-]+){0,5}",
|
||||
" ",
|
||||
s,
|
||||
)
|
||||
# Also catch dangling residual patterns if brackets got normalized to a
|
||||
# single char already — handles cases where upstream writes the "colon"
|
||||
# action marker without explicit brackets.
|
||||
s = re.sub(r"(?<!\w):\s*checking_[A-Za-z0-9_\-]{1,120}", " ", s)
|
||||
# (1) Remove ALL bracket-markers — [rightspeak], [endspeak], [thinking],
|
||||
# [anything_else01]. We also remove stray [ / ] that don't form a
|
||||
# complete pair (e.g. leftover "hello] there").
|
||||
s = re.sub(r"\[[^\]\n]{0,80}\]", " ", s)
|
||||
# (2) Remove inline dict / JSON literals. Pattern: { ... }, possibly
|
||||
# split across a few \n (not greedy). Conservative: matches balanced
|
||||
# pairs up to a reasonable length, otherwise fallback.
|
||||
_max_iter = 5
|
||||
for _ in range(_max_iter):
|
||||
new_s = re.sub(r"\{[^{}]{0,1600}\}", " ", s)
|
||||
if new_s == s:
|
||||
break
|
||||
s = new_s
|
||||
# (3) Name anglicization. Iterate profile name's known variants →
|
||||
# replace with original (case-insensitive match).
|
||||
if session_ctx is not None and isinstance(session_ctx, dict):
|
||||
profile = _extract_profile_for_session(session_ctx)
|
||||
if profile:
|
||||
full_name = str(profile.get("name") or "").strip()
|
||||
if full_name:
|
||||
# Split into parts and check each
|
||||
parts = [p for p in re.split(r"[\s\-_]+", full_name) if p]
|
||||
for part in parts:
|
||||
variants = services_context._common_name_variants(part)
|
||||
orig_cap = part[0].upper() + part[1:] if part else part
|
||||
for variant in variants:
|
||||
# Case-insensitive global replace → original case
|
||||
s = re.sub(
|
||||
r"\b" + re.escape(variant) + r"\b",
|
||||
orig_cap,
|
||||
s,
|
||||
flags=re.IGNORECASE,
|
||||
)
|
||||
# Also try full-name variants (combined)
|
||||
combined = full_name.replace(" ", "") # noqa: F841
|
||||
# (5) Collapse whitespace. Re-punctuation cleanup: avoid normalizing
|
||||
# legitimate terminal "?" / "!" into nothing; only collapse doubled
|
||||
# or space-separated punctuation that resulted from earlier deletes.
|
||||
s = re.sub(r"[ \t\u00a0]+", " ", s)
|
||||
s = re.sub(r"\n{3,}", "\n\n", s)
|
||||
# Interior punctuation: normalize spaces, but keep the char itself.
|
||||
# Example: "hello , world" → "hello, world"
|
||||
s = re.sub(r"\s+([,.;:])\s+", r"\1 ", s)
|
||||
# Terminal / exclamation / interrogation: only fix spacing, never strip.
|
||||
s = re.sub(r"\s+([!?])", r"\1", s)
|
||||
s = re.sub(r"([!?])\s{2,}", r"\1 ", s)
|
||||
# Strip leftover whitespace. Do NOT strip the legitimate terminal
|
||||
# punctuation chars ?, !, ., because they are part of the real speech.
|
||||
# Only strip repeated trailing commas / semicolons that appear because
|
||||
# we deleted bracket/JSON fragments that separated clauses.
|
||||
s = s.strip()
|
||||
# Strip 2+ identical terminal punctuation chars (e.g. "hello.." → "hello.")
|
||||
s = re.sub(r"([,.;:!?])\1{1,}$", r"\1", s)
|
||||
# Strip terminal comma / semicolon / colon that now dangle (clause joins)
|
||||
# but preserve ., ?, !.
|
||||
s = re.sub(r"[,;:]$", "", s).strip()
|
||||
return s
|
||||
|
||||
|
||||
def _sanitize_realtime_event_raw(raw_message: str, session_ctx: dict[str, Any] | None = None) -> tuple[str, bool]:
|
||||
"""If the raw upstream event contains assistant OUTPUT text, sanitize it
|
||||
in-place and return (new_json_str, True) — otherwise return (raw, False).
|
||||
|
||||
Mirrors exactly the same traversal used by _realtime_event_summary so we
|
||||
touch every field that would become summary["text"].
|
||||
"""
|
||||
import json as _json
|
||||
|
||||
if not isinstance(raw_message, str) or not raw_message.strip():
|
||||
return raw_message, False
|
||||
try:
|
||||
payload = _json.loads(raw_message)
|
||||
except Exception:
|
||||
return raw_message, False
|
||||
if not isinstance(payload, dict):
|
||||
return raw_message, False
|
||||
event_type = payload.get("type")
|
||||
if not isinstance(event_type, str):
|
||||
return raw_message, False
|
||||
|
||||
changed = False
|
||||
|
||||
def _sanitize_value(v: Any) -> Any:
|
||||
nonlocal changed
|
||||
if isinstance(v, str) and v.strip():
|
||||
cleaned = _sanitize_agent_output(v, session_ctx)
|
||||
# Layer 8 removes internal ApiPilot CALL markers before UI/TTS.
|
||||
# The pass-2 accumulator retains the original transcript so
|
||||
# execution can still be triggered by its marker.
|
||||
cleaned = services_tool_context._sanitize_text_strip_apipilot_markers(cleaned)
|
||||
if cleaned != v:
|
||||
changed = True
|
||||
return cleaned
|
||||
return v
|
||||
|
||||
# --- Event dispatch (same shape as _realtime_event_summary) -------------
|
||||
# Sanitize streaming deltas as well as .done events. Qwen3-TTS reads deltas
|
||||
# before generating binary audio and could otherwise pronounce the marker.
|
||||
if event_type in {"response.audio_transcript.done", "response.audio_transcript.delta"}:
|
||||
if "transcript" in payload:
|
||||
payload["transcript"] = _sanitize_value(payload["transcript"])
|
||||
if "delta" in payload and isinstance(payload.get("delta"), str):
|
||||
payload["delta"] = _sanitize_value(payload["delta"])
|
||||
for container in ("item", "part", "content", "output", "audio"):
|
||||
sub = payload.get(container)
|
||||
if isinstance(sub, dict):
|
||||
for key in ("transcript", "text", "delta"):
|
||||
if key in sub and isinstance(sub.get(key), str):
|
||||
sub[key] = _sanitize_value(sub[key])
|
||||
elif event_type in {"response.output_audio_transcript.done", "response.output_audio_transcript.delta"}:
|
||||
# Top-level keys
|
||||
for key in (
|
||||
"transcript",
|
||||
"text",
|
||||
"output_text",
|
||||
"audio_text",
|
||||
"output_transcript",
|
||||
"final_transcript",
|
||||
"output_audio_text",
|
||||
"content",
|
||||
"message",
|
||||
"utterance",
|
||||
"delta",
|
||||
):
|
||||
if key in payload and isinstance(payload.get(key), str):
|
||||
payload[key] = _sanitize_value(payload[key])
|
||||
# Sub-containers
|
||||
for container in ("item", "part", "content", "output", "delta", "audio"):
|
||||
sub = payload.get(container)
|
||||
if isinstance(sub, dict):
|
||||
for key in ("transcript", "text", "output_text", "delta"):
|
||||
if key in sub and isinstance(sub.get(key), str):
|
||||
sub[key] = _sanitize_value(sub[key])
|
||||
# content[] array
|
||||
if isinstance(sub.get("content"), list):
|
||||
for c in sub["content"]:
|
||||
if isinstance(c, dict):
|
||||
for k2 in ("transcript", "text", "delta"):
|
||||
if k2 in c and isinstance(c.get(k2), str):
|
||||
c[k2] = _sanitize_value(c[k2])
|
||||
if isinstance(payload.get("content"), list):
|
||||
for c in payload["content"]:
|
||||
if isinstance(c, dict):
|
||||
for k2 in ("transcript", "text", "delta"):
|
||||
if k2 in c and isinstance(c.get(k2), str):
|
||||
c[k2] = _sanitize_value(c[k2])
|
||||
elif event_type in {
|
||||
"response.text.delta",
|
||||
"response.text.done",
|
||||
"response.output_text.delta",
|
||||
"response.output_text.done",
|
||||
}:
|
||||
for key in ("text", "output_text", "delta", "final_text", "content"):
|
||||
if key in payload and isinstance(payload.get(key), str):
|
||||
payload[key] = _sanitize_value(payload[key])
|
||||
for container in ("item", "part", "output", "content", "text"):
|
||||
sub = payload.get(container)
|
||||
if isinstance(sub, dict):
|
||||
for key in ("text", "output_text", "delta"):
|
||||
if key in sub and isinstance(sub.get(key), str):
|
||||
sub[key] = _sanitize_value(sub[key])
|
||||
if isinstance(sub.get("content"), list):
|
||||
for c in sub["content"]:
|
||||
if isinstance(c, dict):
|
||||
for k2 in ("text", "transcript", "delta"):
|
||||
if k2 in c and isinstance(c.get(k2), str):
|
||||
c[k2] = _sanitize_value(c[k2])
|
||||
if isinstance(payload.get("content"), list):
|
||||
for c in payload["content"]:
|
||||
if isinstance(c, dict):
|
||||
for k2 in ("text", "transcript", "delta"):
|
||||
if k2 in c and isinstance(c.get(k2), str):
|
||||
c[k2] = _sanitize_value(c[k2])
|
||||
elif event_type == "response.content_part.done":
|
||||
part = payload.get("part")
|
||||
if isinstance(part, dict):
|
||||
if "text" in part and isinstance(part.get("text"), str):
|
||||
part["text"] = _sanitize_value(part["text"])
|
||||
if "transcript" in part and isinstance(part.get("transcript"), str):
|
||||
part["transcript"] = _sanitize_value(part["transcript"])
|
||||
elif event_type == "response.content_part.added":
|
||||
part = payload.get("part")
|
||||
if isinstance(part, dict):
|
||||
if "text" in part and isinstance(part.get("text"), str):
|
||||
part["text"] = _sanitize_value(part["text"])
|
||||
if "transcript" in part and isinstance(part.get("transcript"), str):
|
||||
part["transcript"] = _sanitize_value(part["transcript"])
|
||||
elif event_type in {
|
||||
"response.content_part.text.delta",
|
||||
"response.output_content.text.delta",
|
||||
"response.content.text.delta",
|
||||
}:
|
||||
for key in ("text", "delta"):
|
||||
if key in payload and isinstance(payload.get(key), str):
|
||||
payload[key] = _sanitize_value(payload[key])
|
||||
elif event_type in {"response.output_item.done", "response.output_item.added"}:
|
||||
item = payload.get("item")
|
||||
if isinstance(item, dict):
|
||||
for c in item.get("content") or []:
|
||||
if isinstance(c, dict):
|
||||
if "text" in c and isinstance(c["text"], str):
|
||||
c["text"] = _sanitize_value(c["text"])
|
||||
if "transcript" in c and isinstance(c["transcript"], str):
|
||||
c["transcript"] = _sanitize_value(c["transcript"])
|
||||
elif event_type == "conversation.item.created":
|
||||
item = payload.get("item")
|
||||
if isinstance(item, dict) and item.get("role") == "assistant":
|
||||
for c in item.get("content") or []:
|
||||
if isinstance(c, dict):
|
||||
if c.get("type") in {"input_text", "text"} and isinstance(c.get("text"), str):
|
||||
c["text"] = _sanitize_value(c["text"])
|
||||
if c.get("type") == "transcript" and isinstance(c.get("transcript"), str):
|
||||
c["transcript"] = _sanitize_value(c["transcript"])
|
||||
|
||||
if not changed:
|
||||
return raw_message, False
|
||||
try:
|
||||
new_raw = _json.dumps(payload, ensure_ascii=False)
|
||||
except Exception:
|
||||
return raw_message, False
|
||||
return new_raw, True
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,960 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
from fastapi import HTTPException
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from s2s_client.core import config as settings
|
||||
from s2s_client.core import logging as app_logging
|
||||
from s2s_client.models import requests as models_requests
|
||||
from s2s_client.providers import apipilot as providers_apipilot
|
||||
from s2s_client.providers import caller as providers_caller
|
||||
from s2s_client.services import context as services_context
|
||||
from s2s_client.services import tool_context as services_tool_context
|
||||
|
||||
|
||||
def _openai_headers() -> dict[str, str]:
|
||||
if not settings.OPENAI_API_KEY:
|
||||
raise RuntimeError("OPENAI_API_KEY is not configured.")
|
||||
headers = {
|
||||
"Authorization": f"Bearer {settings.OPENAI_API_KEY}",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
if settings.OPENAI_ORGANIZATION:
|
||||
headers["OpenAI-Organization"] = settings.OPENAI_ORGANIZATION
|
||||
if settings.OPENAI_PROJECT:
|
||||
headers["OpenAI-Project"] = settings.OPENAI_PROJECT
|
||||
return headers
|
||||
|
||||
|
||||
async def reasoning(req: models_requests.ReasoningRequest) -> JSONResponse:
|
||||
if settings.S2S_REASONING_TYPE == "PROXY":
|
||||
raise HTTPException(status_code=409, detail="El servicio de razonamiento está deshabilitado en el modo PROXY.")
|
||||
transcript = (req.transcript or "").strip()
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=400, detail="Se requiere el campo transcript.")
|
||||
|
||||
# ── S2S_INJECT_PROFILE: resolve podcast episode + caller profile + reports list + latest summary ──
|
||||
# (When S2S_INJECT_PROFILE=false this entire block is a no-op; user_context
|
||||
# and instructions are taken verbatim from the request body.)
|
||||
inject_episode_text = ""
|
||||
inject_profile_text = ""
|
||||
inject_reports_text = ""
|
||||
inject_summary_text = ""
|
||||
phone = (req.phoneNumber or "").strip()
|
||||
episode_id = (req.episode_id or "").strip()
|
||||
if not settings.S2S_INJECT_PROFILE:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ⏭️ REASONING: skipped (S2S_INJECT_PROFILE=false). "
|
||||
"Using verbatim request body; no fetch, no augmentation."
|
||||
)
|
||||
else:
|
||||
needs_phone_authed = bool(settings.VOCERO_USER_PHONE_AUTH_URL.strip())
|
||||
# 2026-09-11 user fix: remove mass injection of scheduled reports.
|
||||
# treats S2S_REPORT_LIST as "need to fetch reports" ONLY when BOTH the URL is
|
||||
# configured AND the new opt-in S2S_INJECT_REPORTS flag is true. When
|
||||
# S2S_INJECT_REPORTS=false (default) needs_reports stays False here → we skip
|
||||
# the branch entirely, no HTTP call, no context string, no prompt bloat.
|
||||
needs_reports = bool(settings.S2S_REPORT_LIST.strip()) and settings.S2S_INJECT_REPORTS
|
||||
needs_summary = bool(settings.S2S_LATEST_SUMMARY.strip()) or bool(settings.S2S_LATEST_SUMMARY_TEXT)
|
||||
needs_login = bool(settings.S2S_LOGIN_BY_PHONE.strip())
|
||||
can_inject = needs_phone_authed or needs_reports or needs_summary or needs_login or bool(episode_id)
|
||||
if (
|
||||
(not needs_phone_authed)
|
||||
and (not needs_reports)
|
||||
and (not needs_summary)
|
||||
and (not needs_login)
|
||||
and (not episode_id)
|
||||
):
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ⏭️ REASONING: skipped (VOCERO_USER_PHONE_AUTH_URL, S2S_REPORT_LIST, S2S_LATEST_SUMMARY/S2S_LATEST_SUMMARY_TEXT and S2S_LOGIN_BY_PHONE all empty, AND no episode_id in request; OR S2S_INJECT_REPORTS is false so reports injection is globally disabled). "
|
||||
"Set at least one AND set S2S_INJECT_REPORTS=true (if you want scheduled reports) to enable login / fetch episode/profile/reports/summary for REASONING endpoint."
|
||||
)
|
||||
elif (not phone) and (not needs_reports) and (not episode_id) and (not settings.S2S_LATEST_SUMMARY_TEXT):
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ⏭️ REASONING: skipped (phoneNumber missing from request body AND no episode_id). "
|
||||
"Browser-side issue: check VoiceController passes phoneNumber and/or episode_id in the JSON body. (Note: S2S_REPORT_LIST fetch works even without phone.)"
|
||||
)
|
||||
elif not can_inject:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ⏭️ REASONING: skipped (env for phone empty and no reports/summary/login API and no episode_id)."
|
||||
)
|
||||
else:
|
||||
# ###################################################################
|
||||
# 0) Login-by-phone (optional — only if S2S_LOGIN_BY_PHONE env set)
|
||||
# Obtains a bearer token that will be forwarded for profile/reports/summary fetches.
|
||||
# ###################################################################
|
||||
login_token = None
|
||||
if settings.S2S_LOGIN_BY_PHONE and phone:
|
||||
login_token, _login_resp = await providers_caller._login_by_phone(phone)
|
||||
# ###################################################################
|
||||
# 0.5) Podcast episode fetch (independent of phone — uses req.episode_id)
|
||||
# ###################################################################
|
||||
if episode_id:
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] starting REASONING fetch podcast episode episodeId=%.80s...",
|
||||
episode_id,
|
||||
)
|
||||
episode_raw = await providers_caller._fetch_podcast_episode(episode_id)
|
||||
inject_episode_text = services_context._resolve_episode_context(episode_raw)
|
||||
if inject_episode_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] ✅ REASONING: PODCAST EPISODE READY episodeId=%.80s wrappedLen=%d -> augmenting instructions + user_context before sending upstream.",
|
||||
episode_id,
|
||||
len(inject_episode_text),
|
||||
)
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-EPISODE] ⏭️ REASONING: episode skipped (context empty / upstream returned empty / fetch failed)."
|
||||
)
|
||||
# ###################################################################
|
||||
# 1) Profile fetch (optional — only if env is configured)
|
||||
# ###################################################################
|
||||
if needs_phone_authed and phone:
|
||||
profile_obj = await providers_caller._fetch_user_profile_for_phone(phone, auth_token=login_token)
|
||||
inject_profile_text = services_context._resolve_user_context_text(phone, profile_obj, loaded=True)
|
||||
if inject_profile_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ✅ REASONING: profile READY phoneLen=%d contextLen=%d -> augmenting instructions + user_context before sending upstream.",
|
||||
len(phone),
|
||||
len(inject_profile_text),
|
||||
)
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] ⏭️ REASONING: profile fetch OK but resolved context empty."
|
||||
)
|
||||
# ###################################################################
|
||||
# 1.5) Scheduled reports / podcast scripts list (optional — S2S_REPORT_LIST)
|
||||
# ###################################################################
|
||||
if needs_reports:
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-REPORTS] starting REASONING fetch S2S_REPORT_LIST (phoneLen=%s, bearer=%s)...",
|
||||
len(phone) if phone else "none",
|
||||
"yes" if login_token else "no",
|
||||
)
|
||||
reports_raw = await providers_caller._fetch_reports_list(
|
||||
phone_number=phone if phone else None, auth_token=login_token
|
||||
)
|
||||
inject_reports_text = services_context._resolve_reports_context(reports_raw)
|
||||
if inject_reports_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[INJECT-REPORTS] ✅ REASONING: reports list READY wrappedLen=%d -> augmenting instructions + user_context before sending upstream.",
|
||||
len(inject_reports_text),
|
||||
)
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-REPORTS] ⏭️ REASONING: reports list skipped (context empty / upstream returned empty list / fetch failed)."
|
||||
)
|
||||
# ###################################################################
|
||||
# 2) Latest summary fetch (optional — only if env is configured)
|
||||
# ###################################################################
|
||||
if needs_summary and (phone or settings.S2S_LATEST_SUMMARY_TEXT):
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] starting REASONING fetch (reasoning summary... S2S_LATEST_SUMMARY=%s S2S_LATEST_SUMMARY_TEXT=%s phoneLen=%s.",
|
||||
bool(settings.S2S_LATEST_SUMMARY),
|
||||
bool(settings.S2S_LATEST_SUMMARY_TEXT),
|
||||
len(phone) if phone else "none",
|
||||
)
|
||||
latest_summary_raw = await providers_caller._fetch_latest_summary_for_phone(
|
||||
phone, auth_token=login_token
|
||||
)
|
||||
inject_summary_text = services_context._resolve_latest_summary_context(latest_summary_raw)
|
||||
if inject_summary_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] ✅ REASONING: latest summary READY phoneLen=%s summaryTextOverride=%s wrappedLen=%d -> augmenting instructions + user_context before sending upstream.",
|
||||
len(phone) if phone else "none",
|
||||
bool(settings.S2S_LATEST_SUMMARY_TEXT),
|
||||
len(inject_summary_text),
|
||||
)
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-SUMMARY] ⏭️ REASONING: latest summary skipped (context empty / upstream returned empty summary / fetch failed.)"
|
||||
)
|
||||
# Load dynamic ApiPilot tools before building context, independently of
|
||||
# S2S_INJECT_PROFILE.
|
||||
needs_apipilot = bool(settings.S2S_APIPILOT_TOOLS_URL) or bool(settings.S2S_APIPILOT_TOOLS_EXECUTE_URL)
|
||||
apipilot_tools_pass1: list[dict] = []
|
||||
apipilot_auth_header: str | None = None
|
||||
if isinstance(login_token, str) and login_token.strip():
|
||||
tk = login_token.strip()
|
||||
if tk.lower().startswith("bearer "):
|
||||
apipilot_auth_header = tk
|
||||
else:
|
||||
apipilot_auth_header = f"Bearer {tk}"
|
||||
# S2S_LOGIN_BY_PHONE resolves an AquaPortal JWT, used for requires_auth=true
|
||||
# execution. S2S_APIPILOT_SERVICE_TOKEN overrides it when configured.
|
||||
if settings.S2S_APIPILOT_SERVICE_TOKEN:
|
||||
_svc = settings.S2S_APIPILOT_SERVICE_TOKEN.strip()
|
||||
if _svc:
|
||||
apipilot_auth_header = f"Bearer {_svc}" if not _svc.lower().startswith("bearer ") else _svc
|
||||
if needs_apipilot:
|
||||
try:
|
||||
apipilot_t0 = providers_apipilot._monotonic_now()
|
||||
apipilot_tools_pass1 = await providers_apipilot._apipilot_fetch_tools(
|
||||
auth_header=apipilot_auth_header,
|
||||
demo_session=None,
|
||||
force_refresh=False,
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT] REASONING PASS-1: tool list ready N=%d t=%dms auth=%s",
|
||||
len(apipilot_tools_pass1),
|
||||
int((providers_apipilot._monotonic_now() - apipilot_t0) * 1000),
|
||||
"Y" if apipilot_auth_header else "-",
|
||||
)
|
||||
except Exception as exc:
|
||||
app_logging.logger.warning("[APIPILOT] REASONING: tool-list fetch failed, ignoring: %s", exc)
|
||||
apipilot_tools_pass1 = []
|
||||
inject_apipilot_text_pass1 = services_tool_context._resolve_apipilot_reasoning_context_block(
|
||||
apipilot_tools_pass1,
|
||||
call_result=None,
|
||||
)
|
||||
|
||||
user_context_parts: list[str] = []
|
||||
# ─── USER FIX BUG 3: TODAY fixed context block → PREPEND to user_context too
|
||||
# (the same anti-hallucination block gets prefixed in the SYSTEM instructions
|
||||
# path via _augment_instructions_with_profile; we also prepend here so the
|
||||
# OPENAI/ANYSCALE messages[] array (where caller context is user_message[0])
|
||||
# ALSO gets the same guard.)
|
||||
# ─── USER FIX 2026-09-11 HALLUCINATION: voice_lock_block FIRST position
|
||||
voice_lock_block = services_context._build_voice_rules_head_lock_block(profile=profile_obj)
|
||||
if voice_lock_block.strip():
|
||||
user_context_parts.append(voice_lock_block)
|
||||
today_block = services_context._build_today_fixed_context_block()
|
||||
if today_block.strip():
|
||||
user_context_parts.append(today_block)
|
||||
if inject_episode_text:
|
||||
user_context_parts.append(inject_episode_text)
|
||||
if inject_profile_text:
|
||||
user_context_parts.append(inject_profile_text)
|
||||
if inject_reports_text:
|
||||
user_context_parts.append(inject_reports_text)
|
||||
if inject_summary_text:
|
||||
user_context_parts.append(inject_summary_text)
|
||||
if inject_apipilot_text_pass1:
|
||||
user_context_parts.append(inject_apipilot_text_pass1)
|
||||
original_user_context = (req.user_context or "").strip()
|
||||
if original_user_context:
|
||||
user_context_parts.append(original_user_context)
|
||||
user_context_parts = services_context._dedup_context_blocks_by_type(user_context_parts)
|
||||
if original_user_context:
|
||||
server_injected_types_in_client_ctx: set = set()
|
||||
for part in user_context_parts:
|
||||
if original_user_context and (part or "").strip() == original_user_context:
|
||||
continue
|
||||
tid = services_context._classify_context_block(part)
|
||||
if tid is None:
|
||||
continue
|
||||
for marker_tid, marker in services_context._CONTEXT_DEDUPE_MARKERS:
|
||||
if marker_tid == tid and marker and marker in original_user_context:
|
||||
server_injected_types_in_client_ctx.add(tid)
|
||||
break
|
||||
if server_injected_types_in_client_ctx:
|
||||
new_parts: list[str] = []
|
||||
for part in user_context_parts:
|
||||
if (part or "").strip() == original_user_context:
|
||||
new_parts.append(part)
|
||||
continue
|
||||
tid = services_context._classify_context_block(part)
|
||||
if tid in server_injected_types_in_client_ctx:
|
||||
continue
|
||||
new_parts.append(part)
|
||||
if settings.S2S_DEBUG_PROMPT and new_parts != user_context_parts:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-DEDUPE] dropped server-injected profile/episode/reports/summary because the same block type was already present in req.user_context client-side context=%s kept=%d",
|
||||
", ".join(sorted(server_injected_types_in_client_ctx)),
|
||||
len(new_parts),
|
||||
)
|
||||
user_context_parts = new_parts
|
||||
# ─── 2026-09-11 MARKER LEAK GUARD: strip invisible internal sentinels from EACH part.
|
||||
stripped_parts: list[str] = []
|
||||
for p in user_context_parts:
|
||||
sp = services_context._strip_internal_markers(p)
|
||||
if sp:
|
||||
stripped_parts.append(sp)
|
||||
user_context_parts = stripped_parts
|
||||
effective_user_context = "\n\n".join(user_context_parts)
|
||||
if settings.S2S_INJECT_PROFILE:
|
||||
any_injected = bool(inject_episode_text or inject_profile_text or inject_reports_text or inject_summary_text)
|
||||
if any_injected:
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] REASONING user_context final parts=%d serverEpisodeLen=%d serverProfileLen=%d serverReportsLen=%d serverSummaryLen=%d browserUserCtxLen=%d joinedLen=%d",
|
||||
len(user_context_parts),
|
||||
len(inject_episode_text),
|
||||
len(inject_profile_text),
|
||||
len(inject_reports_text),
|
||||
len(inject_summary_text),
|
||||
len(original_user_context),
|
||||
len(effective_user_context),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and voice_lock_block.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-VOICELOCK][REASONING augment] FULL voice lock block (len=%d):\n%s\n",
|
||||
len(voice_lock_block),
|
||||
services_context._strip_internal_markers(voice_lock_block),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and inject_episode_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-EPISODE][REASONING augment] FULL podcast episode block (len=%d):\n%s\n",
|
||||
len(inject_episode_text),
|
||||
services_context._strip_internal_markers(inject_episode_text),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and today_block.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-TODAY][REASONING augment] FULL today block (len=%d):\n%s\n",
|
||||
len(today_block),
|
||||
services_context._strip_internal_markers(today_block),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and inject_reports_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-REPORTS][REASONING augment] FULL reports list block (len=%d):\n%s\n",
|
||||
len(inject_reports_text),
|
||||
services_context._strip_internal_markers(inject_reports_text),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and inject_summary_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-SUMMARY][REASONING augment] FULL latest summary block (len=%d):\n%s\n",
|
||||
len(inject_summary_text),
|
||||
services_context._strip_internal_markers(inject_summary_text),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and inject_profile_text.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-PROFILE][REASONING augment] FULL profile block (len=%d):\n%s\n",
|
||||
len(inject_profile_text),
|
||||
services_context._strip_internal_markers(inject_profile_text),
|
||||
)
|
||||
if settings.S2S_DEBUG_PROMPT and inject_apipilot_text_pass1.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-APIPILOT][REASONING augment] FULL ApiPilot tools list block (len=%d):\n%s\n",
|
||||
len(inject_apipilot_text_pass1),
|
||||
services_context._strip_internal_markers(inject_apipilot_text_pass1),
|
||||
)
|
||||
if needs_apipilot and inject_apipilot_text_pass1.strip():
|
||||
app_logging.logger.info(
|
||||
"[INJECT-APIPILOT] REASONING PASS-1: inject tool list (len=%d, Ntools=%d) into instructions and user_context.",
|
||||
len(inject_apipilot_text_pass1),
|
||||
len(apipilot_tools_pass1),
|
||||
)
|
||||
effective_instructions = services_context._augment_instructions_with_profile(
|
||||
req.instructions or "",
|
||||
inject_profile_text,
|
||||
inject_reports_text,
|
||||
inject_summary_text,
|
||||
inject_episode_text,
|
||||
profile_obj=profile_obj,
|
||||
)
|
||||
if inject_apipilot_text_pass1.strip():
|
||||
effective_instructions = (
|
||||
effective_instructions + "\n\n" if effective_instructions else ""
|
||||
) + inject_apipilot_text_pass1
|
||||
else:
|
||||
effective_instructions = (req.instructions or "").strip()
|
||||
if inject_apipilot_text_pass1.strip():
|
||||
app_logging.logger.info(
|
||||
"[INJECT-APIPILOT] REASONING PASS-1: inject tool list (len=%d, Ntools=%d) into instructions (inject_profile=false).",
|
||||
len(inject_apipilot_text_pass1),
|
||||
len(apipilot_tools_pass1),
|
||||
)
|
||||
effective_instructions = (
|
||||
effective_instructions + "\n\n" if effective_instructions else ""
|
||||
) + inject_apipilot_text_pass1
|
||||
if settings.S2S_DEBUG_PROMPT and inject_apipilot_text_pass1.strip():
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-APIPILOT][REASONING augment] FULL ApiPilot tools list block (len=%d):\n%s\n",
|
||||
len(inject_apipilot_text_pass1),
|
||||
services_context._strip_internal_markers(inject_apipilot_text_pass1),
|
||||
)
|
||||
|
||||
# ────────────────────────────────────────────────────────────────────
|
||||
# Mode A: NODE_RED forwards the complete payload; the flow decides behavior.
|
||||
# Stage 1 (log-only) returns {answer: "", log_only: true}, allowing the browser
|
||||
# to leave speech generation to the S2S backend. Later stages can return
|
||||
# {answer: "...", log_only: false}. Expected response fields include answer,
|
||||
# log_only, usage, debug and latency_ms.
|
||||
# ────────────────────────────────────────────────────────────────────
|
||||
if settings.S2S_REASONING_TYPE == "NODE_RED":
|
||||
if not settings.NODE_RED_REASONING_URL:
|
||||
raise HTTPException(
|
||||
status_code=503,
|
||||
detail="S2S_REASONING_NODE_RED_URL no está configurado. Configure esta variable de entorno con la dirección de Node-RED (por ejemplo, http://localhost:1881).",
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] REASONING->NODE_RED body fields. instructionsLen=%d userCtxLen=%d phoneLen=%d episodeIdLen=%d",
|
||||
len(effective_instructions),
|
||||
len(effective_user_context),
|
||||
len(phone),
|
||||
len(episode_id),
|
||||
)
|
||||
upstream_body = {
|
||||
"transcript": transcript,
|
||||
"instructions": effective_instructions,
|
||||
"language": (req.language or "").strip(),
|
||||
"user_context": effective_user_context,
|
||||
}
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-PROMPT][REASONING → NODE_RED] FULL upstream_body JSON:\n%s\n",
|
||||
json.dumps(upstream_body, ensure_ascii=False, indent=2),
|
||||
)
|
||||
app_logging.logger.debug(
|
||||
"[EXT][NODE_RED] reasoning POST %s/api/reasoning lang=%s transcriptLen=%d",
|
||||
settings.NODE_RED_REASONING_URL,
|
||||
(req.language or "")[:20] or "auto",
|
||||
len(transcript),
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=120.0) as http:
|
||||
resp = await http.post(
|
||||
f"{settings.NODE_RED_REASONING_URL}/api/reasoning",
|
||||
json=upstream_body,
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
"X-S2S-Caller": "demo-server",
|
||||
},
|
||||
)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("[EXT][NODE_RED] unreachable: %r", exc)
|
||||
raise HTTPException( # noqa: B904
|
||||
status_code=502, detail="No se puede conectar con el motor de razonamiento de Node-RED."
|
||||
)
|
||||
app_logging.logger.debug(
|
||||
"[EXT][NODE_RED] reasoning RESP status=%s len=%dB",
|
||||
resp.status_code,
|
||||
len(resp.content or b""),
|
||||
)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.warning("[EXT][NODE_RED] failed %s: %s", resp.status_code, resp.text[:500])
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail=f"El razonamiento de Node-RED falló (HTTP {resp.status_code}).",
|
||||
)
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.warning("[EXT][NODE_RED] invalid JSON: %s", resp.text[:500])
|
||||
raise HTTPException(status_code=502, detail="Node-RED devolvió un JSON no válido.") # noqa: B904
|
||||
answer = payload.get("answer") if isinstance(payload, dict) else None
|
||||
log_only = bool(isinstance(payload, dict) and payload.get("log_only") is True)
|
||||
if not isinstance(answer, str):
|
||||
app_logging.logger.warning(
|
||||
"[EXT][NODE_RED] invalid answer type: %s", json.dumps(payload, ensure_ascii=True)[:800]
|
||||
)
|
||||
raise HTTPException(status_code=502, detail="Node-RED devolvió un campo answer no válido.")
|
||||
answer_stripped = answer.strip()
|
||||
# An empty answer is intentional in log-only mode; forward the flag.
|
||||
if not answer_stripped and not log_only:
|
||||
app_logging.logger.warning(
|
||||
"[EXT][NODE_RED] empty answer and !log_only: %s", json.dumps(payload, ensure_ascii=True)[:800]
|
||||
)
|
||||
raise HTTPException(status_code=502, detail="Node-RED no devolvió una respuesta ni la marca log_only.")
|
||||
usage = payload.get("usage") if isinstance(payload, dict) else None
|
||||
if isinstance(usage, dict):
|
||||
app_logging.logger.debug(
|
||||
"[EXT][NODE_RED] reasoning USAGE prompt=%d completion=%d total=%d",
|
||||
usage.get("prompt_tokens", 0),
|
||||
usage.get("completion_tokens", 0),
|
||||
usage.get("total_tokens", 0),
|
||||
)
|
||||
extra = {}
|
||||
for key in ("latency_ms", "intent", "caller_profile_keys", "debug"):
|
||||
if isinstance(payload, dict) and key in payload:
|
||||
extra[key] = payload[key]
|
||||
if log_only:
|
||||
app_logging.logger.info(
|
||||
"[Vocero REASONING] engine=NODE_RED mode=LOG_ONLY transcript=%s extra=%s",
|
||||
transcript[:300],
|
||||
json.dumps({k: v for k, v in extra.items() if k != "debug"}, ensure_ascii=True)[:400],
|
||||
)
|
||||
else:
|
||||
app_logging.logger.info(
|
||||
"[Vocero REASONING] engine=NODE_RED transcript=%s answer=%s extra=%s",
|
||||
transcript[:300],
|
||||
answer_stripped[:500],
|
||||
json.dumps({k: v for k, v in extra.items() if k != "debug"}, ensure_ascii=True)[:400],
|
||||
)
|
||||
out: dict[str, Any] = {"answer": answer_stripped}
|
||||
if log_only:
|
||||
out["log_only"] = True
|
||||
if usage:
|
||||
out["usage"] = usage
|
||||
out.update({k: v for k, v in extra.items() if k != "debug" or app_logging.logger.level <= logging.DEBUG})
|
||||
# Capture the ApiPilot marker, execute its tool and run reasoning pass 2.
|
||||
tool_name_p1, tool_args_p1 = services_tool_context._apipilot_parse_call_marker(answer_stripped)
|
||||
if tool_name_p1:
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=NODE_RED_PASS2_TRIGGER name=%r argsKeys=%s",
|
||||
tool_name_p1,
|
||||
sorted(list((tool_args_p1 or {}).keys())),
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT] REASONING PASS-2 trigger NODE_RED marker name=%s args=%s",
|
||||
tool_name_p1,
|
||||
json.dumps(tool_args_p1 or {}, ensure_ascii=True)[:300],
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=NODE_RED_PASS2_EXEC_HELPER name=%r → forward to _apipilot_execute_tool",
|
||||
tool_name_p1,
|
||||
)
|
||||
tool_env_p1 = await providers_apipilot._apipilot_execute_tool(
|
||||
auth_header=apipilot_auth_header,
|
||||
demo_session=None,
|
||||
name=tool_name_p1,
|
||||
arguments=tool_args_p1 or {},
|
||||
)
|
||||
is_tool_err = not bool(tool_env_p1.get("success"))
|
||||
tool_data = tool_env_p1.get("data")
|
||||
if isinstance(tool_data, str):
|
||||
tool_text_p1 = tool_data
|
||||
elif tool_data is None:
|
||||
tool_text_p1 = ""
|
||||
else:
|
||||
try:
|
||||
tool_text_p1 = json.dumps(tool_data, ensure_ascii=False, indent=2)
|
||||
except Exception:
|
||||
tool_text_p1 = str(tool_data)
|
||||
if is_tool_err and isinstance(tool_env_p1.get("error"), dict):
|
||||
err = tool_env_p1["error"]
|
||||
err_head = f"[{err.get('code')}] {err.get('message')}"
|
||||
tool_text_p1 = (err_head + ("\n" + tool_text_p1 if tool_text_p1.strip() else "")).strip()
|
||||
inject_apipilot_text_pass2 = services_tool_context._resolve_apipilot_reasoning_context_block(
|
||||
[],
|
||||
call_result={
|
||||
"name": tool_name_p1,
|
||||
"text": tool_text_p1,
|
||||
"error": is_tool_err,
|
||||
},
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT] REASONING PASS-2 execute name=%s success=%s httpResultLen=%d trigger second Node-RED call",
|
||||
tool_name_p1,
|
||||
str(not is_tool_err).lower(),
|
||||
len(tool_text_p1),
|
||||
)
|
||||
# Pass-2 context replaces the tool list with the execution result,
|
||||
# preserving voice/date/profile context.
|
||||
user_ctx_parts_2: list[str] = []
|
||||
if voice_lock_block.strip():
|
||||
user_ctx_parts_2.append(voice_lock_block)
|
||||
if today_block.strip():
|
||||
user_ctx_parts_2.append(today_block)
|
||||
if inject_episode_text:
|
||||
user_ctx_parts_2.append(inject_episode_text)
|
||||
if inject_profile_text:
|
||||
user_ctx_parts_2.append(inject_profile_text)
|
||||
if inject_reports_text:
|
||||
user_ctx_parts_2.append(inject_reports_text)
|
||||
if inject_summary_text:
|
||||
user_ctx_parts_2.append(inject_summary_text)
|
||||
if inject_apipilot_text_pass2:
|
||||
user_ctx_parts_2.append(inject_apipilot_text_pass2)
|
||||
if original_user_context:
|
||||
user_ctx_parts_2.append(original_user_context)
|
||||
user_ctx_parts_2 = services_context._dedup_context_blocks_by_type(user_ctx_parts_2)
|
||||
stripped_2: list[str] = []
|
||||
for p in user_ctx_parts_2:
|
||||
sp = services_context._strip_internal_markers(p)
|
||||
if sp:
|
||||
stripped_2.append(sp)
|
||||
user_ctx_parts_2 = stripped_2
|
||||
effective_user_ctx_2 = "\n\n".join(user_ctx_parts_2)
|
||||
# Preserve augmentation without CALL-marker instructions; the result
|
||||
# block supplies the pass-2 response instructions.
|
||||
if settings.S2S_INJECT_PROFILE:
|
||||
eff_inst_2 = services_context._augment_instructions_with_profile(
|
||||
req.instructions or "",
|
||||
inject_profile_text,
|
||||
inject_reports_text,
|
||||
inject_summary_text,
|
||||
inject_episode_text,
|
||||
profile_obj=profile_obj,
|
||||
)
|
||||
else:
|
||||
eff_inst_2 = (req.instructions or "").strip()
|
||||
if inject_apipilot_text_pass2.strip():
|
||||
eff_inst_2 = (eff_inst_2 + "\n\n" if eff_inst_2 else "") + inject_apipilot_text_pass2
|
||||
upstream_body_2 = {
|
||||
"transcript": transcript,
|
||||
"instructions": eff_inst_2,
|
||||
"language": (req.language or "").strip(),
|
||||
"user_context": effective_user_ctx_2,
|
||||
}
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-PROMPT][REASONING → NODE_RED PASS-2] FULL upstream_body_2 JSON:\n%s\n",
|
||||
json.dumps(upstream_body_2, ensure_ascii=False, indent=2),
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=120.0) as http2:
|
||||
resp2 = await http2.post(
|
||||
f"{settings.NODE_RED_REASONING_URL}/api/reasoning",
|
||||
json=upstream_body_2,
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
"X-S2S-Caller": "demo-server-pass2",
|
||||
},
|
||||
)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("[EXT][NODE_RED PASS-2] unreachable: %r", exc)
|
||||
raise HTTPException( # noqa: B904
|
||||
status_code=502,
|
||||
detail="No se puede conectar con el motor de razonamiento de Node-RED (segunda pasada).",
|
||||
)
|
||||
if resp2.status_code != 200:
|
||||
app_logging.logger.warning("[EXT][NODE_RED PASS-2] failed %s: %s", resp2.status_code, resp2.text[:500])
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail=f"La segunda pasada del razonamiento de Node-RED falló (HTTP {resp2.status_code}).",
|
||||
)
|
||||
try:
|
||||
payload2 = resp2.json()
|
||||
except Exception:
|
||||
app_logging.logger.warning("[EXT][NODE_RED PASS-2] invalid JSON: %s", resp2.text[:500])
|
||||
raise HTTPException(status_code=502, detail="Node-RED devolvió un JSON no válido (segunda pasada).") # noqa: B904
|
||||
final_ans = payload2.get("answer") if isinstance(payload2, dict) else None
|
||||
if not isinstance(final_ans, str):
|
||||
# Fallback: the first message and raw result.
|
||||
app_logging.logger.warning("[EXT][NODE_RED PASS-2] invalid answer, falling back to raw result text")
|
||||
final_ans = tool_text_p1 or answer_stripped
|
||||
final_stripped = final_ans.strip()
|
||||
# Pass 2 always sets log_only=False: its final answer is ready for speech.
|
||||
out2: dict = {"answer": final_stripped}
|
||||
usage2 = payload2.get("usage") if isinstance(payload2, dict) else None
|
||||
if usage2:
|
||||
out2["usage_pass2"] = usage2
|
||||
out2["apipilot_invoked"] = {
|
||||
"name": tool_name_p1,
|
||||
"success": not is_tool_err,
|
||||
"result_length": len(tool_text_p1),
|
||||
}
|
||||
app_logging.logger.info(
|
||||
"[Vocero REASONING] engine=NODE_RED PASS-2 transcript=%s finalAnswer=%s apipilot=%s",
|
||||
transcript[:300],
|
||||
final_stripped[:500],
|
||||
json.dumps(out2["apipilot_invoked"], ensure_ascii=True),
|
||||
)
|
||||
return JSONResponse(out2)
|
||||
# Without a marker, return the original pass-1 answer.
|
||||
return JSONResponse(out)
|
||||
|
||||
# ────────────────────────────────────────────────────────────────────
|
||||
# Mode B: OPENAI calls OpenAI Chat Completions directly.
|
||||
# ────────────────────────────────────────────────────────────────────
|
||||
if not settings.OPENAI_API_KEY:
|
||||
raise HTTPException(status_code=503, detail="OPENAI_API_KEY no está configurado.")
|
||||
system_parts = []
|
||||
instructions = effective_instructions or ((req.instructions or "").strip())
|
||||
if instructions:
|
||||
system_parts.append(instructions)
|
||||
if effective_user_context.strip():
|
||||
system_parts.append(f"User context:\n{effective_user_context.strip()}")
|
||||
if inject_apipilot_text_pass1:
|
||||
system_parts.append(inject_apipilot_text_pass1)
|
||||
if req.language.strip():
|
||||
system_parts.append(
|
||||
"Reply only with the final assistant answer text. "
|
||||
f"Keep the answer natural and concise in this language: {req.language.strip()}."
|
||||
)
|
||||
else:
|
||||
system_parts.append("Reply only with the final assistant answer text. Keep the answer natural and concise.")
|
||||
app_logging.logger.info(
|
||||
"[INJECT-PROFILE] REASONING->OPENAI system message parts=%d instructionsLen=%d userCtxLen=%d phoneLen=%d episodeIdLen=%d",
|
||||
len(system_parts),
|
||||
len(effective_instructions),
|
||||
len(effective_user_context),
|
||||
len(phone),
|
||||
len(episode_id),
|
||||
)
|
||||
system_msg = "\n\n".join(system_parts)
|
||||
body = {
|
||||
"model": settings.OPENAI_REASONING_MODEL,
|
||||
"messages": [
|
||||
{"role": "system", "content": system_msg},
|
||||
{"role": "user", "content": transcript},
|
||||
],
|
||||
}
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-PROMPT][REASONING → OPENAI] FULL SYSTEM message (len=%d):\n%s\n",
|
||||
len(system_msg),
|
||||
system_msg,
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-PROMPT][REASONING → OPENAI] USER transcript (len=%d):\n%s\n",
|
||||
len(transcript),
|
||||
transcript,
|
||||
)
|
||||
app_logging.logger.debug(
|
||||
"[EXT][OPENAI] reasoning POST %s/chat/completions model=%s systemLen=%d transcriptLen=%d language=%s",
|
||||
settings.OPENAI_BASE_URL,
|
||||
settings.OPENAI_REASONING_MODEL,
|
||||
len(system_parts[0]) if system_parts else 0,
|
||||
len(transcript),
|
||||
(req.language or "")[:20] or "auto",
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=30.0) as http:
|
||||
resp = await http.post(
|
||||
f"{settings.OPENAI_BASE_URL}/chat/completions",
|
||||
headers=_openai_headers(),
|
||||
json=body,
|
||||
)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("OpenAI reasoning unreachable: %r", exc)
|
||||
raise HTTPException(status_code=502, detail="No se puede conectar con el servicio de razonamiento de OpenAI.") # noqa: B904
|
||||
app_logging.logger.debug(
|
||||
"[EXT][OPENAI] reasoning RESP status=%s len=%dB",
|
||||
resp.status_code,
|
||||
len(resp.content or b""),
|
||||
)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.warning("OpenAI reasoning failed %s: %s", resp.status_code, resp.text[:400])
|
||||
raise HTTPException(status_code=502, detail=f"El razonamiento de OpenAI falló ({resp.status_code}).")
|
||||
try:
|
||||
payload = resp.json()
|
||||
except Exception:
|
||||
app_logging.logger.warning("OpenAI reasoning returned invalid JSON: %s", resp.text[:400])
|
||||
raise HTTPException(status_code=502, detail="El servicio de razonamiento de OpenAI devolvió un JSON no válido.") # noqa: B904
|
||||
answer = ""
|
||||
choices = payload.get("choices")
|
||||
if isinstance(choices, list) and choices:
|
||||
message = choices[0].get("message") if isinstance(choices[0], dict) else None
|
||||
if isinstance(message, dict):
|
||||
content = message.get("content")
|
||||
if isinstance(content, str):
|
||||
answer = content.strip()
|
||||
usage = payload.get("usage")
|
||||
if isinstance(usage, dict):
|
||||
app_logging.logger.debug(
|
||||
"[EXT][OPENAI] reasoning USAGE prompt=%d completion=%d total=%d",
|
||||
usage.get("prompt_tokens", 0),
|
||||
usage.get("completion_tokens", 0),
|
||||
usage.get("total_tokens", 0),
|
||||
)
|
||||
if not answer:
|
||||
app_logging.logger.warning(
|
||||
"OpenAI reasoning returned empty answer: %s", json.dumps(payload, ensure_ascii=True)[:800]
|
||||
)
|
||||
raise HTTPException(status_code=502, detail="El servicio de razonamiento de OpenAI no devolvió una respuesta.")
|
||||
app_logging.logger.info("[Vocero REASONING] engine=OPENAI transcript=%s answer=%s", transcript[:300], answer[:500])
|
||||
# Capture the ApiPilot marker, execute its tool and run OpenAI pass 2.
|
||||
tool_name_p1_oai, tool_args_p1_oai = services_tool_context._apipilot_parse_call_marker(answer)
|
||||
if tool_name_p1_oai:
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=OPENAI_PASS2_TRIGGER name=%r argsKeys=%s",
|
||||
tool_name_p1_oai,
|
||||
sorted(list((tool_args_p1_oai or {}).keys())),
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT] REASONING PASS-2 trigger OPENAI marker name=%s args=%s",
|
||||
tool_name_p1_oai,
|
||||
json.dumps(tool_args_p1_oai or {}, ensure_ascii=True)[:300],
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=OPENAI_PASS2_EXEC_HELPER name=%r → forward to _apipilot_execute_tool",
|
||||
tool_name_p1_oai,
|
||||
)
|
||||
tool_env_oai_p1 = await providers_apipilot._apipilot_execute_tool(
|
||||
auth_header=apipilot_auth_header,
|
||||
demo_session=None,
|
||||
name=tool_name_p1_oai,
|
||||
arguments=tool_args_p1_oai or {},
|
||||
)
|
||||
is_tool_err_oai = not bool(tool_env_oai_p1.get("success"))
|
||||
tool_data_oai = tool_env_oai_p1.get("data")
|
||||
if isinstance(tool_data_oai, str):
|
||||
tool_text_oai = tool_data_oai
|
||||
elif tool_data_oai is None:
|
||||
tool_text_oai = ""
|
||||
else:
|
||||
try:
|
||||
tool_text_oai = json.dumps(tool_data_oai, ensure_ascii=False, indent=2)
|
||||
except Exception:
|
||||
tool_text_oai = str(tool_data_oai)
|
||||
if is_tool_err_oai and isinstance(tool_env_oai_p1.get("error"), dict):
|
||||
err_oai = tool_env_oai_p1["error"]
|
||||
err_oai_head = f"[{err_oai.get('code')}] {err_oai.get('message')}"
|
||||
tool_text_oai = (err_oai_head + ("\n" + tool_text_oai if tool_text_oai.strip() else "")).strip()
|
||||
inject_apipilot_pass2_oai = services_tool_context._resolve_apipilot_reasoning_context_block(
|
||||
[],
|
||||
call_result={
|
||||
"name": tool_name_p1_oai,
|
||||
"text": tool_text_oai,
|
||||
"error": is_tool_err_oai,
|
||||
},
|
||||
)
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT] REASONING PASS-2 OPENAI execute name=%s success=%s resultLen=%d → second chat/completions call",
|
||||
tool_name_p1_oai,
|
||||
str(not is_tool_err_oai).lower(),
|
||||
len(tool_text_oai),
|
||||
)
|
||||
# Build pass 2 with the same instructions/context structure, replacing
|
||||
# inject_apipilot_text_pass1 with the result block inject_apipilot_pass2_oai.
|
||||
user_ctx_oai_2: list[str] = []
|
||||
if voice_lock_block.strip():
|
||||
user_ctx_oai_2.append(voice_lock_block)
|
||||
if today_block.strip():
|
||||
user_ctx_oai_2.append(today_block)
|
||||
if inject_episode_text:
|
||||
user_ctx_oai_2.append(inject_episode_text)
|
||||
if inject_profile_text:
|
||||
user_ctx_oai_2.append(inject_profile_text)
|
||||
if inject_reports_text:
|
||||
user_ctx_oai_2.append(inject_reports_text)
|
||||
if inject_summary_text:
|
||||
user_ctx_oai_2.append(inject_summary_text)
|
||||
if inject_apipilot_pass2_oai:
|
||||
user_ctx_oai_2.append(inject_apipilot_pass2_oai)
|
||||
if original_user_context:
|
||||
user_ctx_oai_2.append(original_user_context)
|
||||
user_ctx_oai_2 = services_context._dedup_context_blocks_by_type(user_ctx_oai_2)
|
||||
stripped_oai_2: list[str] = []
|
||||
for p in user_ctx_oai_2:
|
||||
sp = services_context._strip_internal_markers(p)
|
||||
if sp:
|
||||
stripped_oai_2.append(sp)
|
||||
user_ctx_oai_2 = stripped_oai_2
|
||||
eff_user_ctx_oai_2 = "\n\n".join(user_ctx_oai_2)
|
||||
if settings.S2S_INJECT_PROFILE:
|
||||
eff_inst_oai_2 = services_context._augment_instructions_with_profile(
|
||||
req.instructions or "",
|
||||
inject_profile_text,
|
||||
inject_reports_text,
|
||||
inject_summary_text,
|
||||
inject_episode_text,
|
||||
profile_obj=profile_obj,
|
||||
)
|
||||
else:
|
||||
eff_inst_oai_2 = (req.instructions or "").strip()
|
||||
sys_parts_oai_2: list[str] = []
|
||||
instr_oai_2 = eff_inst_oai_2 or ((req.instructions or "").strip())
|
||||
if instr_oai_2:
|
||||
sys_parts_oai_2.append(instr_oai_2)
|
||||
if eff_user_ctx_oai_2.strip():
|
||||
sys_parts_oai_2.append(f"User context:\n{eff_user_ctx_oai_2.strip()}")
|
||||
if inject_apipilot_pass2_oai:
|
||||
sys_parts_oai_2.append(inject_apipilot_pass2_oai)
|
||||
if req.language.strip():
|
||||
sys_parts_oai_2.append(
|
||||
"Reply only with the final assistant answer text. "
|
||||
f"Keep the answer natural and concise in this language: {req.language.strip()}."
|
||||
)
|
||||
else:
|
||||
sys_parts_oai_2.append(
|
||||
"Reply only with the final assistant answer text. Keep the answer natural and concise."
|
||||
)
|
||||
system_msg_oai_2 = "\n\n".join(sys_parts_oai_2)
|
||||
body_oai_2 = {
|
||||
"model": settings.OPENAI_REASONING_MODEL,
|
||||
"messages": [
|
||||
{"role": "system", "content": system_msg_oai_2},
|
||||
{"role": "user", "content": transcript},
|
||||
],
|
||||
}
|
||||
if settings.S2S_DEBUG_PROMPT:
|
||||
app_logging.logger.info(
|
||||
"[DEBUG-PROMPT][REASONING → OPENAI PASS-2] FULL SYSTEM message (len=%d):\n%s\n",
|
||||
len(system_msg_oai_2),
|
||||
system_msg_oai_2,
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=30.0) as http_oai2:
|
||||
resp_oai_2 = await http_oai2.post(
|
||||
f"{settings.OPENAI_BASE_URL}/chat/completions",
|
||||
headers=_openai_headers(),
|
||||
json=body_oai_2,
|
||||
)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.warning("[EXT][OPENAI PASS-2] unreachable: %r", exc)
|
||||
raise HTTPException( # noqa: B904
|
||||
status_code=502,
|
||||
detail="No se puede conectar con el servicio de razonamiento de OpenAI (segunda pasada).",
|
||||
)
|
||||
if resp_oai_2.status_code != 200:
|
||||
app_logging.logger.warning(
|
||||
"[EXT][OPENAI PASS-2] failed %s: %s", resp_oai_2.status_code, resp_oai_2.text[:400]
|
||||
)
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail=f"La segunda pasada del razonamiento de OpenAI falló ({resp_oai_2.status_code}).",
|
||||
)
|
||||
try:
|
||||
payload_oai_2 = resp_oai_2.json()
|
||||
except Exception:
|
||||
app_logging.logger.warning("[EXT][OPENAI PASS-2] invalid JSON: %s", resp_oai_2.text[:400])
|
||||
raise HTTPException( # noqa: B904
|
||||
status_code=502,
|
||||
detail="El servicio de razonamiento de OpenAI devolvió un JSON no válido (segunda pasada).",
|
||||
)
|
||||
final_oai_ans = ""
|
||||
choices_oai_2 = payload_oai_2.get("choices")
|
||||
if isinstance(choices_oai_2, list) and choices_oai_2:
|
||||
msg_oai_2 = choices_oai_2[0].get("message") if isinstance(choices_oai_2[0], dict) else None
|
||||
if isinstance(msg_oai_2, dict):
|
||||
content_oai_2 = msg_oai_2.get("content")
|
||||
if isinstance(content_oai_2, str):
|
||||
final_oai_ans = content_oai_2.strip()
|
||||
usage_oai_2 = payload_oai_2.get("usage")
|
||||
if not final_oai_ans:
|
||||
# Last-resort fallback: raw tool-result text.
|
||||
app_logging.logger.warning("[EXT][OPENAI PASS-2] empty answer, falling back to raw tool-result text")
|
||||
final_oai_ans = (tool_text_oai or answer).strip()
|
||||
final_out_oai: dict = {"answer": final_oai_ans}
|
||||
if usage_oai_2:
|
||||
final_out_oai["usage_pass2"] = usage_oai_2
|
||||
final_out_oai["apipilot_invoked"] = {
|
||||
"name": tool_name_p1_oai,
|
||||
"success": not is_tool_err_oai,
|
||||
"result_length": len(tool_text_oai),
|
||||
}
|
||||
app_logging.logger.info(
|
||||
"[Vocero REASONING] engine=OPENAI PASS-2 transcript=%s finalAnswer=%s apipilot=%s",
|
||||
transcript[:300],
|
||||
final_oai_ans[:500],
|
||||
json.dumps(final_out_oai["apipilot_invoked"], ensure_ascii=True),
|
||||
)
|
||||
return JSONResponse(final_out_oai)
|
||||
# Without a marker, return the original pass-1 answer.
|
||||
return JSONResponse({"answer": answer})
|
||||
|
||||
|
||||
async def _forward_agent_text_to_nodered(payload: dict) -> None:
|
||||
"""Forward native-backend TTS responses to Node-RED's stage-1 logging endpoint.
|
||||
|
||||
Ignore unavailable or unconfigured Node-RED so the realtime loop continues.
|
||||
"""
|
||||
if settings.S2S_REASONING_TYPE != "NODE_RED" or not settings.NODE_RED_REASONING_URL:
|
||||
return
|
||||
url = f"{settings.NODE_RED_REASONING_URL}/api/log/system-response"
|
||||
app_logging.logger.debug(
|
||||
"[EXT][NODE_RED] forward system-response POST %s len=%d source=%s",
|
||||
settings.NODE_RED_REASONING_URL,
|
||||
len(str(payload.get("tts", "")) or 0), # type: ignore[arg-type] # Preserve the legacy empty-TTS failure.
|
||||
payload.get("source_event") or "-",
|
||||
)
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=5.0) as http:
|
||||
resp = await http.post(
|
||||
url,
|
||||
json=payload,
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
"X-S2S-Caller": "demo-server",
|
||||
},
|
||||
)
|
||||
if resp.status_code != 200:
|
||||
app_logging.logger.debug(
|
||||
"[EXT][NODE_RED] forward system-response non-200 status=%s body=%s",
|
||||
resp.status_code,
|
||||
(resp.text or "")[:300],
|
||||
)
|
||||
except httpx.RequestError as exc:
|
||||
app_logging.logger.debug("[EXT][NODE_RED] forward system-response unreachable: %r", exc)
|
||||
except Exception as exc: # noqa: BLE001 — never interrupt the realtime loop
|
||||
app_logging.logger.debug("[EXT][NODE_RED] forward system-response unexpected: %r", exc)
|
||||
@@ -0,0 +1,629 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import re
|
||||
from typing import cast
|
||||
|
||||
from s2s_client.core import logging as app_logging
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# APIPILOT — Reasoning engine integration (two passes)
|
||||
# ---------------------------------------------------------------------------
|
||||
# Deduplication/start/end markers used by _classify_context_block to avoid
|
||||
# injecting a block already supplied by the client or found in base_instructions.
|
||||
APIPILOT_PASS1_LIST_MARKER = "<<<APIPILOT_TOOLS_LIST_BEGIN>>>"
|
||||
APIPILOT_PASS2_RESULT_MARKER = "<<<APIPILOT_RESULT:"
|
||||
|
||||
# Flow:
|
||||
# PASS 1: inject {name,description,required,parameters} and marker rules.
|
||||
# The model matches descriptions and emits the CALL marker.
|
||||
# PASS 2: capture the marker, execute through S2S_APIPILOT_TOOLS_EXECUTE_URL,
|
||||
# inject the result text, and request a natural spoken response.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_APIPILOT_CALL_MARKER_RE = re.compile(
|
||||
r"[<]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[>]{1,3}",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
# 2026-09-25: observed inverted marker (incorrect LLM syntax):
|
||||
# >>>APIPILOT_CALL:NAME=tool,ARGUMENTS=json<<<
|
||||
_APIPILOT_CALL_MARKER_INVERTED_RE = re.compile(
|
||||
r"[>]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[<]{1,3}",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
|
||||
|
||||
def _apipilot_parse_call_marker(answer_text: str, *, defaults: dict | None = None) -> tuple[str | None, dict | None]:
|
||||
"""Parse the mandatory CALL marker emitted by the LLM in pass 1.
|
||||
|
||||
Returns (tool_name, arguments_dict), or (None, None) when no marker exists.
|
||||
|
||||
Supports:
|
||||
(1) ARGUMENTS={"key":"val"}, valid JSON.
|
||||
(2) ARGUMENTS={}, a valid empty object.
|
||||
(3) ARGUMENTS= without braces, observed on realtime WebSocket sessions.
|
||||
(4) key=val,key2=val2 strings through a manual parsing fallback.
|
||||
(5) After parsing, fill missing required arguments from defaults such as
|
||||
phone and episode_id.
|
||||
"""
|
||||
if not isinstance(answer_text, str) or not answer_text.strip():
|
||||
app_logging.logger.info("[APIPILOT-CALL-NAME] USE=PARSE_EMPTY_INPUT name=None markerFound=N")
|
||||
return None, None
|
||||
m = _APIPILOT_CALL_MARKER_RE.search(answer_text.strip())
|
||||
inverted = False
|
||||
if not m:
|
||||
m = _APIPILOT_CALL_MARKER_INVERTED_RE.search(answer_text.strip())
|
||||
inverted = bool(m)
|
||||
if not m:
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=PARSE_NO_MATCH name=None markerFound=N textHead=%r", answer_text.strip()[:80]
|
||||
)
|
||||
return None, None
|
||||
name_raw = m.group(1).strip()
|
||||
args_raw = (m.group(2) if m.lastindex and m.lastindex >= 2 and isinstance(m.group(2), str) else "").strip()
|
||||
if not name_raw:
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=PARSE_EMPTY_NAME name=None markerFound=Y argsRawHead=%r inverted=%s",
|
||||
args_raw[:60],
|
||||
("Y" if inverted else "N"),
|
||||
)
|
||||
return None, None
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=PARSE_MARKER_OK name=%r argsRawLen=%d markerFound=Y inverted=%s",
|
||||
name_raw,
|
||||
len(args_raw),
|
||||
("Y" if inverted else "N"),
|
||||
)
|
||||
args: dict = {}
|
||||
# Parse args_raw into a dict, tolerating common formatting variations.
|
||||
if args_raw == "" or args_raw in {"{}", "null", "None"}:
|
||||
args = {}
|
||||
else:
|
||||
# Attempt 1: standard JSON, with or without braces.
|
||||
_candidate = args_raw
|
||||
try:
|
||||
args = json.loads(_candidate)
|
||||
except Exception:
|
||||
try:
|
||||
# Attempt 2: supply missing outer braces.
|
||||
args = json.loads("{" + _candidate + "}")
|
||||
except Exception:
|
||||
try:
|
||||
# Attempt 3: replace single quotes with double quotes.
|
||||
args = json.loads(_candidate.replace("'", '"'))
|
||||
except Exception:
|
||||
try:
|
||||
# Attempt 4: supply braces and replace single quotes.
|
||||
args = json.loads("{" + _candidate.replace("'", '"') + "}")
|
||||
except Exception:
|
||||
# Manual fallback 5: equals signs and commas.
|
||||
# Example: args_raw="phone=+56,name=Mario" → dict.
|
||||
args = {}
|
||||
for piece in args_raw.split(","):
|
||||
kv = piece.strip()
|
||||
if not kv or "=" not in kv:
|
||||
continue
|
||||
k, v = kv.split("=", 1)
|
||||
k = k.strip().strip('"').strip("'")
|
||||
v = v.strip().strip('"').strip("'")
|
||||
if k:
|
||||
args[k] = v
|
||||
if not isinstance(args, dict):
|
||||
args = {}
|
||||
# Stage 2: fill missing arguments from defaults (phone, etc.).
|
||||
if isinstance(defaults, dict) and defaults:
|
||||
for dk, dv in defaults.items():
|
||||
if dk not in args or args[dk] in (None, "", []):
|
||||
if dv not in (None, "", []):
|
||||
args[dk] = dv
|
||||
app_logging.logger.info(
|
||||
"[APIPILOT-CALL-NAME] USE=PARSE_RETURN_FINAL name=%r finalArgsKeys=%s defaultsApplied=%s",
|
||||
name_raw,
|
||||
sorted(list(args.keys())),
|
||||
("Y" if isinstance(defaults, dict) and defaults else "N"),
|
||||
)
|
||||
return name_raw, args
|
||||
|
||||
|
||||
def _resolve_apipilot_reasoning_context_block(
|
||||
tools_list: list[dict] | None,
|
||||
*,
|
||||
call_result: dict | None = None,
|
||||
context_defaults: dict | None = None,
|
||||
) -> str:
|
||||
"""Build the ApiPilot context block for the reasoning prompt.
|
||||
|
||||
With call_result=None, pass 1 supplies the tool list and marker syntax
|
||||
the model must emit when a description matches.
|
||||
|
||||
With call_result={'name':str, 'text':str, 'error':bool}, pass 2 injects the
|
||||
execution result and requests a final spoken/text response for the user.
|
||||
|
||||
The optional context_defaults dict adds known default values to pass 1.
|
||||
The model must use these exact values for required arguments rather than
|
||||
inventing them. Usually contains {"phone": "+56..."} from inject_phone.
|
||||
"""
|
||||
# Pass 2: the tool result is already available.
|
||||
if isinstance(call_result, dict) and call_result.get("name"):
|
||||
name = call_result.get("name") or "?"
|
||||
text = (call_result.get("text") if isinstance(call_result.get("text"), str) else "") or ""
|
||||
is_err = bool(call_result.get("error"))
|
||||
status_label = "ERROR" if is_err else "OK"
|
||||
title = f"<<<APIPILOT_RESULT:STATUS={status_label},NAME={name}>>>"
|
||||
trailer = (
|
||||
"Now reinterpret THE RESULT TEXT (above) in clear, concise natural language, "
|
||||
"exclusively in the user's language (language field; Spanish by default). "
|
||||
"Do not mention the internal tool or technical details. "
|
||||
"Respond ONLY with the final content intended for the user."
|
||||
)
|
||||
return (
|
||||
f"{APIPILOT_PASS2_RESULT_MARKER}PASS2>>>\n"
|
||||
"### Invoked ApiPilot tool result\n"
|
||||
f"{title}\n"
|
||||
f"\n```tool-output\n"
|
||||
f"{text.rstrip() if text.strip() else '(empty output)'}\n"
|
||||
f"```\n\n"
|
||||
f"{trailer}\n"
|
||||
)
|
||||
# Pass 1: available tools and marker rules.
|
||||
tools = tools_list if isinstance(tools_list, list) else []
|
||||
# Limit to 100 tools, although the guide specifies at most 50 for the demo.
|
||||
tools_cap = tools[:100]
|
||||
if not tools_cap:
|
||||
return ""
|
||||
entries: list[str] = []
|
||||
for t in tools_cap:
|
||||
if not isinstance(t, dict):
|
||||
continue
|
||||
name = t.get("name") if isinstance(t.get("name"), str) else ""
|
||||
if not name:
|
||||
continue
|
||||
desc = cast(str, t.get("description")) if isinstance(t.get("description"), str) else ""
|
||||
params = t.get("parameters") if isinstance(t.get("parameters"), dict) else None
|
||||
requires_auth = bool(t.get("requires_auth"))
|
||||
required_fields: list[str] = []
|
||||
if isinstance(params, dict) and isinstance(params.get("required"), list):
|
||||
required_fields = [str(x) for x in cast(list, params.get("required")) if isinstance(x, str)]
|
||||
# Limit descriptions to about 500 characters to control prompt size.
|
||||
desc_cut = desc[:500].rstrip()
|
||||
if len(desc) > 500:
|
||||
desc_cut += "…"
|
||||
snippet = f"- name: {name}\n requires_auth: {('true' if requires_auth else 'false')}"
|
||||
if required_fields:
|
||||
snippet += f"\n required_parameters: [{', '.join(required_fields[:40])}]"
|
||||
if desc_cut:
|
||||
snippet += f"\n description: {desc_cut}"
|
||||
entries.append(snippet)
|
||||
if not entries:
|
||||
return ""
|
||||
rule = (
|
||||
f"{APIPILOT_PASS1_LIST_MARKER}\n"
|
||||
"### Available dynamic tools (ApiPilot AquaPortal)\n"
|
||||
"\n"
|
||||
"Each tool has a `name` field (a unique identifier: do NOT modify it, "
|
||||
"use camelCase, or translate it) and a `description` describing its use case.\n"
|
||||
"\n"
|
||||
"MANDATORY EXECUTION RULES:\n"
|
||||
"1. If the USER REQUEST (transcript) clearly matches the `description` of "
|
||||
"EXACTLY one tool below, emit ONLY one line as the FIRST line of YOUR RESPONSE, "
|
||||
"with this exact syntax:\n"
|
||||
' <<<APIPILOT_CALL:NAME=tool_name,ARGUMENTS={"parameter1":"value1","parameter2":"value2"}>>>\n'
|
||||
"2. ARGUMENTS={…} MUST be valid JSON (double quotes, commas, no comments). "
|
||||
"Include ONLY fields listed in `required_parameters:`, if present.\n"
|
||||
"3. Add NO text after the marker line: no explanations or previews. The engine "
|
||||
"will execute the tool and supply its result in a second call.\n"
|
||||
"4. If NO description matches, emit NO marker and respond normally in Spanish.\n"
|
||||
"5. If multiple descriptions match, choose the most specific one and use the marker.\n"
|
||||
"6. 🔴 EXCLUSIVE RESPONSE MODE (HIGHEST priority, mandatory): when using a CALL "
|
||||
"marker, YOUR ENTIRE RESPONSE MUST CONTAIN ONLY THE MARKER LINE. "
|
||||
"Write NOTHING BEFORE it: no 'Claro que sí', 'Voy a revisar', "
|
||||
"'Voy a generar tu briefing', greeting, or transition. "
|
||||
"Write NOTHING AFTER it: no comments, previews, or explanations. "
|
||||
"Exactly one line containing the marker. Additional text prevents the engine "
|
||||
"from recognizing the marker and executing the tool.\n"
|
||||
"8. INCORRECT examples (NEVER do this):\n"
|
||||
" 'Claro que sí, ahora ejecuto'\n"
|
||||
" 'Voy a generar tu briefing ejecutivo personal.'\n"
|
||||
" 'Claro que sí.\\n<<<APIPILOT_CALL:...>>>'\n"
|
||||
" '<<<APIPILOT_CALL:...>>>\\nAhora proceso el resultado.'\n"
|
||||
"9. 🔴 TTS ANTI-LEAK RULES (mandatory, HIGHEST audio priority):\n"
|
||||
" <<<APIPILOT_CALL:...>>> IS AN INTERNAL SYSTEM SIGNAL and MUST NEVER be spoken,\n"
|
||||
" read aloud, or synthesized by TTS. When emitting the marker:\n"
|
||||
" - INTERNAL REASONING (text/transcript) MUST contain the exact marker line.\n"
|
||||
" - FINAL TTS AUDIO heard by the user MUST contain ONLY this placeholder:\n"
|
||||
' "Voy a consultar tus datos, un momento por favor."\n'
|
||||
" - NEVER speak any of these technical terms in final TTS audio:\n"
|
||||
" APIPILOT, CALL, ARGUMENTS, tool, herramienta, ejecutar, function, function call,\n"
|
||||
" marcador, marker, even to explain or describe the call.\n"
|
||||
"\n"
|
||||
)
|
||||
# 2026-09-25 known defaults: inject values already resolved from the URL or
|
||||
# profile, such as phoneNumber, so tool arguments use those exact values.
|
||||
if isinstance(context_defaults, dict) and context_defaults:
|
||||
defaults_lines = []
|
||||
for dk, dv in context_defaults.items():
|
||||
if dv in (None, "", []):
|
||||
continue
|
||||
if isinstance(dv, (dict, list)):
|
||||
try:
|
||||
dv_repr = json.dumps(dv, ensure_ascii=False)
|
||||
except Exception:
|
||||
dv_repr = str(dv)
|
||||
else:
|
||||
dv_repr = str(dv)
|
||||
defaults_lines.append(f'- {dk} = "{dv_repr}"')
|
||||
if defaults_lines:
|
||||
rule += (
|
||||
"KNOWN DEFAULT VALUES (use these exact values in ARGUMENTS={…} when "
|
||||
"the corresponding tool lists these names in required_parameters; "
|
||||
"do not invent, translate, or normalize them):\n"
|
||||
f"{chr(10).join(defaults_lines)}\n"
|
||||
"\n"
|
||||
)
|
||||
rule += f"Tool list (name / description):\n{chr(10).join(entries)}\n<<<APIPILOT_TOOLS_LIST_END>>>"
|
||||
return rule
|
||||
|
||||
|
||||
def _sanitize_pass2_internal_context(text: str) -> str:
|
||||
"""Lightly sanitize the pass-2 block injected into the upstream model.
|
||||
|
||||
Unlike _sanitize_text_strip_apipilot_markers, preserve the pass-2 wrapper:
|
||||
the model needs it to recognize tool data. Limit sanitation to filesystem
|
||||
path leaks, fragmented marker tokens, and contextual phone leaks.
|
||||
"""
|
||||
if not isinstance(text, str) or not text.strip():
|
||||
return text
|
||||
# Block 3: Unix/Windows/TRAE path leaks, matching the user-output sanitizer.
|
||||
import re as _re_pass2
|
||||
|
||||
text = _re_pass2.sub(
|
||||
r"(?i)(?:/[A-Za-z0-9_.\-@~]+){2,}/(?:\.trae[^\s\"']*|workspaceStorage[^\s\"']*|User[^\s\"']*|home[^\s\"']*)",
|
||||
" ",
|
||||
text,
|
||||
)
|
||||
text = _re_pass2.sub(r"(?i)(?:[A-Z]:)?[\\/](?:Users|home|root|tmp|var|mnt|opt|srv)[\\/][^\s\"']{5,}", " ", text)
|
||||
text = _re_pass2.sub(r"(?i)(?:\.trae-server|\.trae[^\s\"']{0,40}|workspaceStorage[0-9a-f]+)", " ", text)
|
||||
text = _re_pass2.sub(r"\s{2,}", " ", text)
|
||||
# Block 4: fragmented marker leaks, tier 4.
|
||||
tier4_out_parts: list[str] = []
|
||||
for _line in text.splitlines(keepends=True):
|
||||
_orig = _line
|
||||
_low = _line.lower()
|
||||
if "apipilot" in _low and (
|
||||
("call" in _low and "name=" in _low) or ("arguments=" in _low) or ("result" in _low and "pass" in _low)
|
||||
):
|
||||
if "<<<" in _line or ">>>" in _line:
|
||||
_line = _re_pass2.sub(
|
||||
r"[<]{1,3}\s*APIPILOT_(?:CALL|RESULT)[^<>\n]{0,500}[>]{1,3}",
|
||||
" ",
|
||||
_line,
|
||||
flags=_re_pass2.IGNORECASE,
|
||||
)
|
||||
if "apipilot" in _line.lower():
|
||||
_line = _re_pass2.sub(
|
||||
r"(?i)\bAPIPILOT(?:_CALL|_RESULT)?\b",
|
||||
" ",
|
||||
_line,
|
||||
)
|
||||
_line = _re_pass2.sub(
|
||||
r"(?i)\b(?:NAME|ARGUMENTS|STATUS|REV|PASS2)\s*[:=]",
|
||||
" ",
|
||||
_line,
|
||||
)
|
||||
tier4_out_parts.append(_line if _line.strip() else _orig)
|
||||
text = "".join(tier4_out_parts)
|
||||
text = _re_pass2.sub(r"\s{2,}", " ", text)
|
||||
return text.strip() if isinstance(text, str) else text
|
||||
|
||||
|
||||
def _sanitize_text_strip_apipilot_markers(
|
||||
text: str,
|
||||
*,
|
||||
placeholder: str | None = None,
|
||||
) -> str:
|
||||
"""Remove all internal ApiPilot markers from user-visible chat and TTS text.
|
||||
|
||||
Replace pass-1 CALL markers with a Spanish placeholder. Silently remove
|
||||
pass-2 RESULT markers, their heading, tool-output block and instruction
|
||||
trailer. These server-only signals must never reach the user.
|
||||
|
||||
Args:
|
||||
text: Text to sanitize.
|
||||
placeholder: Optional replacement; defaults to the Spanish UI/voice message.
|
||||
"""
|
||||
if not isinstance(text, str) or not text:
|
||||
return text
|
||||
if placeholder is None:
|
||||
placeholder = "Voy a consultar tus datos, un momento por favor."
|
||||
|
||||
# ================================================================
|
||||
# Block 1: silently remove pass-2 RESULT markers and wrappers from TTS/UI.
|
||||
# ================================================================
|
||||
# (1a) Full pass-2 wrapper first: marker, heading, status, output, trailer.
|
||||
pass2_full_block_pattern = re.compile(
|
||||
r"[ \t]*(?:\r?\n|\r)?[ \t]*"
|
||||
r"<<<APIPILOT_RESULT:PASS2>>>[ \t]*(?:\r?\n|\r)+"
|
||||
r"###[ \t]+(?:Resultado de la herramienta ApiPilot invocada|Invoked ApiPilot tool result)[ \t]*(?:\r?\n|\r)+"
|
||||
r"<<<APIPILOT_RESULT:STATUS=[A-Za-z_]+,NAME=[A-Za-z0-9_.-]+>>>[ \t]*(?:\r?\n|\r)*"
|
||||
r"(?:\r?\n|\r)?"
|
||||
r"```tool-output[ \t]*(?:\r?\n|\r)?"
|
||||
r"(?P<tool_body>.*?)"
|
||||
r"(?:\r?\n|\r)?```[ \t]*(?:\r?\n|\r){0,3}"
|
||||
r"(?:"
|
||||
r"(?:Ahora debes reinterpretar EL TEXTO RESULTADO|Now reinterpret THE RESULT TEXT)[\s\S]{0,1200}?"
|
||||
r"(?:\r?\n|\r){0,2}"
|
||||
r")?"
|
||||
r"[ \t]*",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
text = pass2_full_block_pattern.sub("", text)
|
||||
|
||||
# (1b) Standalone PASS2 markers when the wrapper is incomplete or fragmented.
|
||||
pass2_marker_pattern = re.compile(
|
||||
r"[ \t]*(?:\r?\n|\r)?[ \t]*<<<APIPILOT_RESULT(?::PASS2|:STATUS=[A-Za-z_]+,NAME=[A-Za-z0-9_.-]+)?>>>[ \t]*(?:\r?\n|\r)?[ \t]*",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = pass2_marker_pattern.sub("", text)
|
||||
|
||||
# (1c) Residual Markdown heading after the marker has been removed.
|
||||
pass2_title_pattern = re.compile(
|
||||
r"[ \t]*(?:\r?\n|\r)?[ \t]*###[ \t]+(?:Resultado de la herramienta ApiPilot invocada|Invoked ApiPilot tool result)[ \t]*(?:\r?\n|\r)?[ \t]*",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = pass2_title_pattern.sub("", text)
|
||||
|
||||
# (1d) Standalone tool-output blocks without a PASS2 wrapper.
|
||||
pass2_codeblock_pattern = re.compile(
|
||||
r"```tool-output[ \t]*(?:\r?\n|\r)?.*?(?:\r?\n|\r)?```",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
text = pass2_codeblock_pattern.sub("", text)
|
||||
|
||||
# (1e) Residual instruction trailers missed by the full-wrapper pattern.
|
||||
pass2_trailer_pattern = re.compile(
|
||||
r"(?:Ahora debes reinterpretar EL TEXTO RESULTADO[\s\S]{0,1200}?contenido final que le quieres transmitir al usuario|Now reinterpret THE RESULT TEXT[\s\S]{0,1200}?final content intended for the user)\.",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
text = pass2_trailer_pattern.sub("", text)
|
||||
# Broader fallback also handles trailers truncated before their closing text.
|
||||
pass2_trailer_fallback = re.compile(
|
||||
r"(?:Ahora debes reinterpretar[\s\S]{0,1500}?(?:al usuario\.|$)|Now reinterpret THE RESULT TEXT[\s\S]{0,1500}?(?:for the user\.|$))",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
text = pass2_trailer_fallback.sub("", text)
|
||||
# Handle residual middle fragments after the trailer's opening was removed.
|
||||
pass2_trailer_broad = re.compile(
|
||||
r"(?:en lenguaje natural[\s\S]{0,800}?contenido final que le quieres transmitir al usuario|in clear, concise natural language[\s\S]{0,800}?final content intended for the user)\.?",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
text = pass2_trailer_broad.sub("", text)
|
||||
|
||||
# ================================================================
|
||||
# Block 2: pass-1 CALL marker replacement with a Spanish placeholder.
|
||||
# ================================================================
|
||||
marker_full_pattern = re.compile(
|
||||
r"<<<APIPILOT_CALL:NAME=[A-Za-z0-9_.-]+,ARGUMENTS=.*?>>>",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
line_wrapped_pattern = re.compile(
|
||||
r"[ \t]*(?:\r?\n|\r)?[ \t]*<<<APIPILOT_CALL:NAME=[A-Za-z0-9_.-]+,ARGUMENTS=.*?>>>[ \t]*(?:\r?\n|\r)?[ \t]*",
|
||||
re.IGNORECASE | re.DOTALL,
|
||||
)
|
||||
|
||||
def _replacement_full(_m: re.Match) -> str:
|
||||
"""Replace standalone or inline markers with the spoken placeholder."""
|
||||
return placeholder
|
||||
|
||||
text = line_wrapped_pattern.sub(_replacement_full, text)
|
||||
text = marker_full_pattern.sub(_replacement_full, text)
|
||||
|
||||
# Remove truncated CALL markers such as <<<APIPILOT_CALL:NAME=tool,ARGS….
|
||||
trunc_call_pattern = re.compile(
|
||||
r"<<<APIPILOT_CALL(?::NAME=[A-Za-z0-9_.-]+,?[^>\n]{0,500}?)?>>*",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = trunc_call_pattern.sub(_replacement_full, text)
|
||||
|
||||
# Make closing brackets optional to remove RESULT markers truncated by TTS,
|
||||
# such as <<<APIPILOT_RESULT:STATUS=OK,NAM without closing >>>.
|
||||
trunc_result_pattern = re.compile(
|
||||
r"<<<APIPILOT_RESULT(?::[A-Za-z0-9_=,:.\- ]{0,800}?)?>?>?>?",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = trunc_result_pattern.sub("", text)
|
||||
# Remove remaining APIPILOT_RESULT fragments after partial sanitation.
|
||||
trunc_result_residual = re.compile(
|
||||
r"<{0,3}APIPILOT_RESULT(?::[^\s<]{0,800})?<{0,3}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = trunc_result_residual.sub("", text)
|
||||
|
||||
# Collapse whitespace left by pass-2 block removal.
|
||||
text = re.sub(r"[ \t]{2,}", " ", text)
|
||||
text = re.sub(r"\n{3,}", "\n\n", text)
|
||||
# Remove residual trailer fragments and empty parentheses before TTS.
|
||||
text = re.sub(r"\s*\((?:arriba|above)\)\s*", " ", text, flags=re.IGNORECASE)
|
||||
text = re.sub(r"\(\s*\)", "", text)
|
||||
# ================================================================
|
||||
# Block 3: remove filesystem paths and host information leaked into TTS.
|
||||
# Match long absolute Unix/Windows/mixed paths and known workspace tokens.
|
||||
# ================================================================
|
||||
# (3a) Absolute Unix paths and nested paths with multiple separators.
|
||||
unix_path_pattern = re.compile(
|
||||
r"\b(?:/(?:home|tmp|var|root|opt|mnt|media|srv|proc|sys|etc|usr|Users|trae)[/\w@.+\-:#$%^&()[\]{}!~=,]*){2,}[A-Za-z0-9_./\-+@#$%^&()[\]{}!~=,:]*\.(?:txt|md|log|json|csv|pdf|doc|docx|py|js|ts|html|css|sh|yaml|yml|env|conf|cfg|ini|mp3|wav|ogg|png|jpg|jpeg|gif)\b"
|
||||
r"|"
|
||||
# Broad fallback for long absolute Unix paths under known directories,
|
||||
# including paths without extensions; avoid short URLs such as /api/v1.
|
||||
r"(?:^|\s+|\(|[,.;:!?])(/(?:home|tmp|var|root|opt|mnt|media|srv|proc|sys|etc|usr|Users|trae)[/A-Za-z0-9_\-+@#$%^&()[\]{}!~=,.]{10,})(?=$|\s|\)|[,.;:!?])",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = unix_path_pattern.sub("", text)
|
||||
# (3b) Windows paths with single/double backslashes and mixed separators.
|
||||
win_path_pattern = re.compile(
|
||||
r"(?:^|\s|\(|[,.;:])"
|
||||
r"([A-Za-z]:[\\/]"
|
||||
r"|(?:[\\/]{1,2}(?:home|Users|Windows|Program|Program\sFiles|ProgramData|Users|trae|AppData)[\\/])"
|
||||
r"|(?:[\\/]{1,2}\.(?:trae|trae-server|vscode|config|cache)[\\/])"
|
||||
r")"
|
||||
r"[A-Za-z0-9_@.+\-:#$%^&()[\]{}!~=,\\/\s]{10,}"
|
||||
r"(?:\.(?:txt|md|log|json|csv|pdf|doc|docx|py|js|ts|html|css|sh|yaml|yml|env|conf|cfg|ini|mp3|wav|ogg|png|jpg|jpeg|gif))?"
|
||||
r"(?=$|\s|\)|[,.;:!?])",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = win_path_pattern.sub("", text)
|
||||
# (3c) TRAE workspace tokens, including fragments without complete paths.
|
||||
trae_leak_tokens = re.compile(
|
||||
r"\b(?:workspaceStorage|long-text|\.trae-server|\.trae|ckg_server|ai-agent)\b[^\s()'\"`,.]{0,80}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = trae_leak_tokens.sub("", text)
|
||||
# (3d) Remove long tokens containing mixed separators or many path segments.
|
||||
mixed_path_pattern = re.compile(
|
||||
r"(?=\S{0,200})"
|
||||
r"(?=\S*(?:[/\\].*){5,})"
|
||||
r"(?:\S{10,})",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
def _mixed_safe(m: re.Match[str]) -> str:
|
||||
s = m.group(0)
|
||||
has_slash = "/" in s
|
||||
has_back = "\\" in s
|
||||
if (has_slash and has_back) or s.count("/") + s.count("\\") >= 6:
|
||||
return ""
|
||||
return s
|
||||
|
||||
text = mixed_path_pattern.sub(_mixed_safe, text)
|
||||
# ================================================================
|
||||
# Block 4: remove fragmented APIPILOT CALL text from TTS. The upstream
|
||||
# pipeline (start_pipeline_rag / Qwen3-TTS) can remove <<< >>> and read:
|
||||
# "APIPILOT CALL name get_user_briefing arguments phone +56912345678"
|
||||
# The bracketed patterns cannot catch this, so use contextual fallback tiers.
|
||||
# ================================================================
|
||||
# Tier 1: full normalized form without braces, through the sentence ending.
|
||||
call_normalized_full = re.compile(
|
||||
r"(?:^|\s+|\(|[,.;:!?\"\'])\s*"
|
||||
r"(?:"
|
||||
r"APIPILOT[\s_\-]+CALL\s+(?:marker\s+)?(?:de\s+)?(?:señal\s+)?(?:herramienta\s+)?(?:funci[oó]n\s+)?"
|
||||
r"|marcador\s+APIPILOT(?:\s+CALL)?\s*"
|
||||
r"|señal\s+de\s+llamada\s+APIPILOT\s*"
|
||||
r"|llamada\s+(?:a\s+)?(?:la\s+)?(?:herramienta|funci[oó]n)\s+APIPILOT\s*"
|
||||
r")"
|
||||
r"(?:\s*(?:con\s+)?(?:identificador|ID|name|nombre)\s*[:=]?\s*[A-Za-z0-9_.-]+)?"
|
||||
r"(?:\s*(?:y\s+)?(?:con\s+)?(?:argumentos|ARGUMENTS|params|par[áa]metros)\s*[:=]?\s*(?:\{[^{}]{0,800}\}|[\"'][^\"']{0,200}[\"']|[^\s.!,?;]{3,100}(?:\s*[,:]\s*[^\s.!,?;]{3,100})*\s*)?)?"
|
||||
r"(?:\s*(?:phone|tel[ée]fono|correo|email)\s*[:=]?\s*[+0-9A-Za-z._@\-]{6,50})?"
|
||||
r"(?=$|\s+|\)|[,.;:!?\"\'])",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = call_normalized_full.sub(placeholder, text)
|
||||
# Tier 2: shortened forms with APIPILOT_CALL or adjacent APIPILOT and CALL.
|
||||
apipilot_call_token = re.compile(
|
||||
r"(?:^|\s|\(|[,.;:!?\"\'])\s*"
|
||||
r"APIPILOT(?:[\s_\-]+CALL|_CALL|\s+llamada|\s+marker)"
|
||||
r"(?:[^.!,?;\n]{0,600})?"
|
||||
r"(?=$|\s|\)|[,.;:!?\"\'])",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = apipilot_call_token.sub(placeholder, text)
|
||||
# Tier 3: standalone service tokens in call/name/argument contexts.
|
||||
service_token_context = re.compile(
|
||||
r"(?:"
|
||||
r"ARGUMENTS\s*[:=]\s*(?:\{[^{}]{0,800}\}|[^\s,.;!?]{3,100})"
|
||||
r"|\barguments\s+(?:de\s+)?(?:la\s+)?(?:llamada|herramienta|funci[oó]n)\b[^\n.]{0,200}"
|
||||
r")",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = service_token_context.sub("", text)
|
||||
|
||||
# Tier 4: remove sentences containing APIPILOT with technical call context.
|
||||
def _apipilot_sentence(m: re.Match[str]) -> str:
|
||||
sentence = m.group(0)
|
||||
lowered = sentence.lower()
|
||||
# Preserve a sentence already containing the Spanish CALL placeholder,
|
||||
# including any natural text surrounding it.
|
||||
if "voy a consultar tus datos" in lowered:
|
||||
return sentence
|
||||
ctx_kw = (
|
||||
"name",
|
||||
"argument",
|
||||
"arg",
|
||||
"herramienta",
|
||||
"tool",
|
||||
"funci",
|
||||
"phone",
|
||||
"tel",
|
||||
"+56",
|
||||
"+44",
|
||||
"marker",
|
||||
"call",
|
||||
"llamada",
|
||||
"señal",
|
||||
"marcador",
|
||||
)
|
||||
if any(k in lowered for k in ctx_kw) and "apipilot" in lowered:
|
||||
return ""
|
||||
return sentence
|
||||
|
||||
catchall_sentence = re.compile(
|
||||
r"[^.?!;\n]{0,600}APIPILOT[^.?!;\n]{0,600}[.?!;\n]{0,1}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = catchall_sentence.sub(_apipilot_sentence, text)
|
||||
# Tier 5: replace any remaining APIPILOT CALL tokens, even without context.
|
||||
final_apipilot_leak = re.compile(
|
||||
r"\bAPIPILOT[\s_\-]+CALL\b|\bAPIPILOT_CALL\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
text = final_apipilot_leak.sub(placeholder, text)
|
||||
# Tier 6: remove residual fake/real phone numbers from internal call text.
|
||||
# Match compact and spaced forms to tolerate TTS normalization.
|
||||
fake_phone_pattern = re.compile(
|
||||
r"("
|
||||
# Compact forms without spaces:
|
||||
r"\+56912345678"
|
||||
r"|\+1234567890"
|
||||
r"|\+447432477433"
|
||||
r"|56912345678"
|
||||
r"|1234567890"
|
||||
r"|447432477433"
|
||||
# Spaced forms with punctuation:
|
||||
r"|\+?\s*56\s*[\s\-()]?9\s*[\s\-()]?1\s*[\s\-()]?2\s*[\s\-()]?3\s*[\s\-()]?4\s*[\s\-()]?5\s*[\s\-()]?6\s*[\s\-()]?7\s*[\s\-()]?8"
|
||||
r"|\+?\s*1\s*[\s\-()]?2\s*[\s\-()]?3\s*[\s\-()]?4\s*[\s\-()]?5\s*[\s\-()]?6\s*[\s\-()]?7\s*[\s\-()]?8\s*[\s\-()]?9\s*[\s\-()]?0"
|
||||
r"|\+?\s*44\s*[\s\-()]?7\s*[\s\-()]?4\s*[\s\-()]?3\s*[\s\-()]?2\s*[\s\-()]?4\s*[\s\-()]?7\s*[\s\-()]?7\s*[\s\-()]?4\s*[\s\-()]?3\s*[\s\-()]?3"
|
||||
# Generic labeled forms (English or Spanish phone labels):
|
||||
r"|phone\s*[:=]\s*[+()\-\s]*[0-9][+()\-\s0-9]{6,}"
|
||||
r"|tel(?:éfono|efono)?\s*[:=]\s*[+()\-\s]*[0-9][+()\-\s0-9]{6,}"
|
||||
r")",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
# Strip numbers only from lines with technical call context or the Spanish
|
||||
# placeholder, indicating that the number belongs to a replaced CALL marker.
|
||||
lines = text.splitlines(keepends=True)
|
||||
_phone_ctx = (
|
||||
"apipilot",
|
||||
"call",
|
||||
"arguments",
|
||||
"marker",
|
||||
"herramienta",
|
||||
"funcion",
|
||||
"función",
|
||||
"ejecutar",
|
||||
"llamada",
|
||||
"marcador",
|
||||
"señal",
|
||||
"voy a consultar tus datos",
|
||||
)
|
||||
|
||||
def _phone_line_safe(line: str) -> str:
|
||||
lowered = line.lower()
|
||||
has_ctx = any(c in lowered for c in _phone_ctx)
|
||||
if has_ctx:
|
||||
# Remove phone numbers in this line (strip also surrounding space)
|
||||
return fake_phone_pattern.sub(" ", line)
|
||||
return line
|
||||
|
||||
text = "".join(_phone_line_safe(line) for line in lines)
|
||||
# Collapse whitespace left by marker and path removal.
|
||||
text = re.sub(r"[ \t]{2,}", " ", text)
|
||||
text = re.sub(r"\n{3,}", "\n\n", text)
|
||||
return text.strip()
|
||||
Reference in New Issue
Block a user