valenti/vocero-client
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(vocero): remove the legacy ApiPilot integration (#3)

Browse Source 
Vocero now retrieves AquaPortal content through authenticated MCP. This removes the obsolete ApiPilot integration from the API and browser while preserving the separately deployed speech pipeline.

Release notes:

- Removed ApiPilot endpoints, configuration, credential overrides, and HTTP/realtime tool execution.
- Removed browser ApiPilot catalog loading and prompt generation while retaining authenticated MCP discovery.
- Updated regression coverage and operating documentation for the retired routes and settings.

Reviewed-on: AquaPortal/s2s#3
This commit is contained in:
alvaro
2026-10-08 11:23:41 -04:00
parent 0311d3f1ff
commit dfed03ac7c
39 changed files with 198 additions and 3314 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vocero-api/vocero_api/services/reasoning.py
-256
View File
@@ -11,11 +11,9 @@ from vocero_api.core import config as settings
from vocero_api.core import logging as app_logging
from vocero_api.models import requests as models_requests
from vocero_api.models.responses import ReasoningResponse
from vocero_api.providers import apipilot as providers_apipilot
from vocero_api.providers import caller as providers_caller
from vocero_api.services import context as services_context
from vocero_api.services import mcp_reasoning
from vocero_api.services import tool_context as services_tool_context
def _openai_headers() -> dict[str, str]:
@@ -182,45 +180,6 @@ async def reasoning(req: models_requests.ReasoningRequest, request: Request) ->
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
@@ -242,8 +201,6 @@ async def reasoning(req: models_requests.ReasoningRequest, request: Request) ->
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)
@@ -334,18 +291,6 @@ async def reasoning(req: models_requests.ReasoningRequest, request: Request) ->
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,
@@ -354,28 +299,8 @@ async def reasoning(req: models_requests.ReasoningRequest, request: Request) ->
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),
)
# Call the OpenAI-compatible Chat Completions provider.
if not settings.OPENAI_API_KEY:
raise HTTPException(status_code=503, detail="OPENAI_API_KEY no está configurado.")
@@ -385,8 +310,6 @@ async def reasoning(req: models_requests.ReasoningRequest, request: Request) ->
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. "
@@ -474,183 +397,4 @@ async def reasoning(req: models_requests.ReasoningRequest, request: Request) ->
)
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 validated_json_response(final_out_oai, ReasoningResponse)
# Without a marker, return the original pass-1 answer.
return validated_json_response({"answer": answer}, ReasoningResponse)