feat(orchestrator): S8 shared speech service and sealed model transport
Requirement 001 S8: the hub can use a shared OpenAI-style speech service (KVB_ORCHESTRATOR_SPEECH_URL, key from a mounted file) instead of the local piper and whisper engines, and the image takes its pinned artefacts through an optional INFINITO_ARTEFACT_BASE cache. A new transport serves speech and the LLM: one wall-clock deadline over DNS, connect, TLS handshake and body, certificate and hostname always verified, no redirect followed. A key travels only over https or to loopback; both the speech and the LLM start refuse it otherwise. Key files are capped at 4096 bytes. Streamed WAV answers with placeholder sizes are accepted only when the data chunk runs to the end, and are rewritten before caching. Accepted MEDUSA false positives (41, independent review, operator pick): raw client socket patterns in transport.py, AIC-EXFIL-005 on the sealed key path, JB-SCAN-2237 on the hub's own system prompt, STG009 on the RIFF pad byte and LLM01 at language.py:111, where agent-written titles reach the NL prompt but the model only proposes a plan the operator confirms. 🎯 Fix: 93 % 💥 Break: 4 % 💸 Cost: – ⏱️ Time: – 🛡️ Security: 100 % 🏆 Score: 89 🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 % Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
590b430d37
commit
6d2bca77f7
16 files changed
+1253
-56
No files matched your search
+23
-7
@@ -39,8 +39,8 @@
|
||||
--llm-url: base URL of an OpenAI-compatible chat endpoint; empty turns the
|
||||
natural-language command line off.
|
||||
--llm-model: model name sent to that endpoint; empty turns it off.
|
||||
--llm-key-file: file holding the endpoint's bearer key; empty file or
|
||||
unreadable means no key.
|
||||
--llm-key-file: file holding the endpoint's bearer key; an empty file
|
||||
means no key, an unreadable one stops the start.
|
||||
--piper: the Piper executable, run as a separate process; missing turns
|
||||
speech output off.
|
||||
--voices: directory holding the Piper voices as <model>.onnx with
|
||||
@@ -51,6 +51,12 @@
|
||||
input off.
|
||||
--whisper-model: the ggml model whisper.cpp loads.
|
||||
--scratch: writable directory the engines use as HOME and TMPDIR.
|
||||
--speech-url: base URL with /v1 of an OpenAI-compatible audio API such as
|
||||
the core role svc-ai-speech; /api/tts and /api/stt then render there
|
||||
instead of in Piper and whisper.cpp, behind the same CPU gate and
|
||||
transcription limits. Empty keeps the in-container engines.
|
||||
--speech-key-file: file holding that service's bearer key; an empty file
|
||||
means no key, an unreadable one stops the start.
|
||||
--approvers: the pinned passkeys, mounted read-only; the hub lists their
|
||||
ids and algorithms for the page, never pins, and verifies a signature
|
||||
only for the operator messages, denials and rules it acts on itself,
|
||||
@@ -70,9 +76,11 @@ from kvb_orchestrator.errors import ToolError
|
||||
from kvb_orchestrator.exchange import HubServer
|
||||
from kvb_orchestrator.handler import Handler
|
||||
from kvb_orchestrator.hub import Places, open_hub
|
||||
from kvb_orchestrator.language import Model, read_key
|
||||
from kvb_orchestrator.keys import key_from
|
||||
from kvb_orchestrator.language import Model
|
||||
from kvb_orchestrator.redirects import TIMEOUT, Redirects, dial
|
||||
from kvb_orchestrator.skill_scripts import Scripts
|
||||
from kvb_orchestrator.speechservice import Service
|
||||
|
||||
|
||||
def main() -> int:
|
||||
@@ -81,9 +89,9 @@ def main() -> int:
|
||||
for name in ("--listen-port", "--public-port"):
|
||||
parser.add_argument(name, type=int, required=True)
|
||||
paths = ("--council", "--pages", "--state", "--host-state", "--skills", "--transcripts", "--templates", "--tree-file", "--timers", "--kept", "--vendor", "--cleanup", "--offices", "--llm-key-file", "--approvers")
|
||||
for name in (*paths, "--piper", "--voices", "--whisper", "--whisper-model", "--scratch"):
|
||||
for name in (*paths, "--piper", "--voices", "--whisper", "--whisper-model", "--scratch", "--speech-key-file"):
|
||||
parser.add_argument(name, type=Path, required=True)
|
||||
for name in ("--llm-url", "--llm-model", "--operator-voice"):
|
||||
for name in ("--llm-url", "--llm-model", "--operator-voice", "--speech-url"):
|
||||
parser.add_argument(name, required=True)
|
||||
args = parser.parse_args()
|
||||
try:
|
||||
@@ -97,8 +105,16 @@ def main() -> int:
|
||||
scripts=Scripts(skills=args.skills, council=args.council, home=args.state),
|
||||
templates=args.templates,
|
||||
places=Places(tree_file=args.tree_file, timers=args.timers, vendor=args.vendor, cleanup=args.cleanup, offices=args.offices, kept=args.kept),
|
||||
model=Model(url=args.llm_url.strip(), model=args.llm_model.strip(), key=read_key(args.llm_key_file)),
|
||||
engines=Engines(piper=args.piper, voices=args.voices, operator_voice=args.operator_voice, whisper=args.whisper, whisper_model=args.whisper_model, scratch=args.scratch),
|
||||
model=Model(url=args.llm_url.strip(), model=args.llm_model.strip(), key=key_from(args.llm_key_file, "model endpoint")),
|
||||
engines=Engines(
|
||||
piper=args.piper,
|
||||
voices=args.voices,
|
||||
operator_voice=args.operator_voice,
|
||||
whisper=args.whisper,
|
||||
whisper_model=args.whisper_model,
|
||||
scratch=args.scratch,
|
||||
service=Service(url=args.speech_url.strip(), key=key_from(args.speech_key_file, "speech service")),
|
||||
),
|
||||
approvers=args.approvers,
|
||||
redirects=Redirects(tls=ssl.create_default_context(), dial=dial, timeout=TIMEOUT),
|
||||
)
|
||||
|
||||
Reference in new issue
Block a user