armiger / examples /dh_waypoint_processor /armiger_waypoint_processor.py

Align chart cohorts/labels, cryptographic bindings, and legal/documentation precision

d258bfe verified 2 days ago

18.7 kB

"""DH-Waypoint processorapi/v1 HTTP Service for Armiger & Armiger Ultra.
Implements the canonical DH-Waypoint external processor contract (`dh-waypoint.processor.v1`):
  - `GET /v1/manifest` (`v1.Manifest`)
  - `GET /v1/status` (`v1.ServiceStatus`)
  - `POST /v1/process` (`v1.Job` -> `v1.Result`)
  - `POST /v1/feedback` (`dh-waypoint.processors.feedback.v1`)
  - Backwards-compatible batch endpoints: `POST /v1/classify`, `POST /v1/admit`, `GET /healthz`
"""
from __future__ import annotations

from datetime import datetime, timezone
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
import json
import os
from pathlib import Path
import sys
import time
from typing import Any, Dict, List, Mapping, Optional

ROOT_DIR = Path(__file__).resolve().parents[2]
if str(ROOT_DIR) not in sys.path:
    sys.path.insert(0, str(ROOT_DIR))

from armiger_dht_rsi import CandidateObservation, DHTRSIMode, resolve_opt_in_sharing
from armiger_ultra_pipeline import ArmigerUltraPipeline, ArmigerUltraPrediction

# Map Armiger 11-class labels to DH-Waypoint canonical content types
WAYPOINT_CONTENT_TYPE_MAP: Dict[str, str] = {
    "movie": "movie",
    "tv_show": "tv_show",
    "music": "music",
    "ebook": "ebook",
    "audiobook": "audiobook",
    "comic": "comic",
    "software": "software",
    "game": "game",
    "course": "ebook",
    "xxx": "xxx",
    "unknown": "unknown",
}


class ArmigerWaypointAdapter:
    """Translates between DH-Waypoint processorapi/v1 envelopes and ArmigerUltraPipeline."""

    def __init__(
        self,
        pipeline: Optional[ArmigerUltraPipeline] = None,
        *,
        use_zero_cue_catalog: bool = True,
        reject_dead_swarms: bool = False,
        opt_in_sharing: Optional[bool] = None,
    ) -> None:
        self.opt_in_sharing: bool = resolve_opt_in_sharing(opt_in_sharing)
        self.pipeline = pipeline or ArmigerUltraPipeline.from_directory(
            ROOT_DIR, variant="int8", preload_catalog=False, opt_in_sharing=self.opt_in_sharing
        )
        if opt_in_sharing is None and pipeline is not None:
            self.opt_in_sharing = bool(getattr(pipeline, "opt_in_sharing", False))
        self.use_zero_cue_catalog = use_zero_cue_catalog
        self.reject_dead_swarms = reject_dead_swarms
        self.started_at = datetime.now(timezone.utc).isoformat()
        self.jobs_completed = 0

    def sharing_status(self) -> Dict[str, Any]:
        st = self.pipeline.sharing_status()
        st["opt_in_sharing_enabled"] = bool(self.opt_in_sharing)
        return st

    def handle_manifest(self) -> Dict[str, Any]:
        """Return `v1.Manifest` for `GET /v1/manifest`."""
        return {
            "contract": "dh-waypoint.processor.v1",
            "processor": {
                "id": "armiger-ultra",
                "version": "2.1.0",
                "model_version": "armiger-ultra-2.1.0",
                "policy_version": "conformal-v2.1",
                "artifact_digest": "none",
            },
            "capabilities": ["classify", "extract", "language", "policy"],
            "configuration_schema": {
                "$schema": "http://json-schema.org/draft-07/schema#",
                "type": "object",
                "additionalProperties": True,
            },
        }

    def handle_status(self) -> Dict[str, Any]:
        """Return `v1.ServiceStatus` for `GET /v1/status`."""
        return {
            "contract": "dh-waypoint.processor.v1",
            "processor": self.handle_manifest()["processor"],
            "state": "ready",
            "started_at": self.started_at,
            "jobs_completed": self.jobs_completed,
            "sharing": self.sharing_status(),
        }

    @staticmethod
    def _torrent_to_row(t: Mapping[str, Any]) -> Dict[str, Any]:
        swarm_in = t.get("swarm") if isinstance(t.get("swarm"), Mapping) else {}
        seeders = int(
            swarm_in.get("tracker_seeders", swarm_in.get("seeders", t.get("seeders", 0))) or 0
        )
        leechers = int(
            swarm_in.get("tracker_leechers", swarm_in.get("leechers", t.get("leechers", 0))) or 0
        )
        completed_raw = swarm_in.get("tracker_completed", swarm_in.get("completed"))
        files = t.get("files") if isinstance(t.get("files"), list) else []
        return {
            "infohash": str(t.get("info_hash") or t.get("infohash") or ""),
            "name": str(t.get("name") or t.get("title") or ""),
            "size": int(t.get("size") or 0),
            "files": files,
            "file_count": int(t.get("file_count") or t.get("files_count") or len(files) or 1),
            "sources": t.get("sources") if isinstance(t.get("sources"), list) else [],
            "swarm": {
                "tracker_known": bool(
                    swarm_in.get("tracker_known") or seeders > 0 or leechers > 0 or swarm_in
                ),
                "tracker_seeders": seeders,
                "tracker_leechers": leechers,
                "tracker_completed": int(completed_raw) if completed_raw is not None else None,
            },
        }

    def handle_process_job(self, job: Mapping[str, Any]) -> Dict[str, Any]:
        """Handle canonical `POST /v1/process` (`v1.Job` -> `v1.Result`)."""
        t0 = time.perf_counter()
        inp = job.get("input") if isinstance(job.get("input"), Mapping) else job
        row = self._torrent_to_row(inp)
        pred = self.pipeline.classify_batch(
            [row],
            use_zero_cue_catalog=self.use_zero_cue_catalog,
        )[0]
        elapsed_ms = round((time.perf_counter() - t0) * 1000.0, 3)
        self.jobs_completed += 1

        gates_passed = bool(pred.mondrian_gates["passed_all"])
        viability_tier = str(pred.swarm_viability["viability_tier"])
        content_type = WAYPOINT_CONTENT_TYPE_MAP.get(pred.category, "unknown")

        proposal: Dict[str, Any] = {
            "content_type": content_type,
            "language": {
                "audio": ["eng"] if pred.lang == "english" else [],
                "subtitles": ["eng"] if pred.english_subs == "has_eng_subs" else [],
                "evidence": "metadata_claim",
                "english_audio": "present" if pred.lang == "english" else "absent",
            },
            "liveness": {
                "seeders": row["swarm"]["tracker_seeders"],
                "leechers": row["swarm"]["tracker_leechers"],
                "observation": "dead" if viability_tier == "dead" else "live",
                "source": "armiger_swarm_survival",
            },
            "add_tags": [
                f"armiger:category:{pred.category}",
                f"armiger:lang:{pred.lang}",
                f"armiger:viability:{viability_tier}",
            ],
            "weights": {
                "armiger_viability": round(float(pred.swarm_viability["viability_prob"]), 4),
                "armiger_category_conf": round(float(pred.heads["category"]["confidence"]), 4),
            },
        }
        if not gates_passed or (self.reject_dead_swarms and viability_tier == "dead"):
            reason = (
                pred.csam_safety.get("reason")
                or pred.mondrian_gates.get("safety_gate_reason")
                or ("honeypot_trap_blocked" if pred.honeypot_trap["is_honeypot_trap"] else "safety_gate_rejected")
            )
            proposal["exclusion"] = {"exclude": True, "reason": str(reason)}

        return {
            "contract": "dh-waypoint.processor.v1",
            "job_id": str(job.get("job_id") or ("0" * 64)),
            "input_revision": str(job.get("input_revision") or ("0" * 64)),
            "pipeline_revision": str(job.get("pipeline_revision") or ("0" * 64)),
            "configuration_digest": str(job.get("configuration_digest") or ("0" * 64)),
            "processor": job.get("processor") or self.handle_manifest()["processor"],
            "stage": str(job.get("stage") or "classify"),
            "outcome": "completed",
            "proposal": proposal,
            "reasons": ["conformal_evaluated"],
            "uncertainty": round(1.0 - float(pred.heads["category"]["confidence"]), 4),
            "retry_after_seconds": 0,
            "telemetry": {
                "observed_at": datetime.now(timezone.utc).isoformat(),
                "inference_ms": elapsed_ms,
            },
            "request_feedback": True,
        }

    def handle_classify_batch(self, request_body: Mapping[str, Any]) -> Dict[str, Any]:
        """Handle batch `POST /v1/classify`."""
        torrents = request_body.get("torrents") or []
        rows = [self._torrent_to_row(t) for t in torrents]
        predictions: List[ArmigerUltraPrediction] = self.pipeline.classify_batch(
            rows,
            use_zero_cue_catalog=self.use_zero_cue_catalog,
        )

        decisions: List[Dict[str, Any]] = []
        for pred in predictions:
            gates_passed = bool(pred.mondrian_gates["passed_all"])
            viability_tier = str(pred.swarm_viability["viability_tier"])
            if not gates_passed:
                reason = (
                    pred.csam_safety.get("reason")
                    or pred.mondrian_gates.get("safety_gate_reason")
                    or ("honeypot_trap_blocked" if pred.honeypot_trap["is_honeypot_trap"] else "safety_gate_rejected")
                )
                decisions.append({
                    "info_hash": pred.infohash,
                    "action": "delete",
                    "exclude": True,
                    "reason": str(reason),
                })
                continue

            content_type = WAYPOINT_CONTENT_TYPE_MAP.get(pred.category, "unknown")
            tags = [
                f"armiger:category:{pred.category}",
                f"armiger:lang:{pred.lang}",
                f"armiger:viability:{viability_tier}",
            ]
            if pred.anime == "anime":
                tags.append("armiger:anime")
                dub_status = pred.heads["anime"].get("anime_dub_status")
                if dub_status:
                    tags.append(f"armiger:anime_dub:{dub_status}")
            if pred.english_subs == "has_eng_subs":
                tags.append("armiger:eng_subs")

            decisions.append({
                "info_hash": pred.infohash,
                "action": "enrich",
                "content_type": content_type,
                "languages": ["en"] if pred.lang == "english" else [],
                "tags": tags,
                "attributes": {
                    "armiger.category": pred.category,
                    "armiger.category_confidence": f"{pred.heads['category']['confidence']:.4f}",
                    "armiger.lang": pred.lang,
                    "armiger.viability_tier": viability_tier,
                    "armiger.viability_prob": f"{pred.swarm_viability['viability_prob']:.4f}",
                    "armiger.survival_net_prob": f"{pred.swarm_viability['survival_net_prob']:.4f}",
                    "armiger.catalog_source": str(pred.plugin_trace["plugin_3_zero_cue_catalog"]["resolution_source"]),
                },
            })

        return {
            "schema": "dh-waypoint.processor.v1",
            "decisions": decisions,
        }

    def handle_admission_batch(self, request_body: Mapping[str, Any]) -> Dict[str, Any]:
        """Handle `POST /v1/admit` (`dh-waypoint.processors.admission.v1`)."""
        candidates = request_body.get("candidates") or []
        rows = [self._torrent_to_row(c) for c in candidates]
        predictions = self.pipeline.classify_batch(
            rows,
            use_zero_cue_catalog=self.use_zero_cue_catalog,
        )

        decisions: List[Dict[str, Any]] = []
        for cand, pred in zip(candidates, predictions):
            info_hash = str(cand.get("info_hash") or pred.infohash)
            gates_passed = bool(pred.mondrian_gates["passed_all"])
            viability_tier = str(pred.swarm_viability["viability_tier"])
            admit = gates_passed and (not self.reject_dead_swarms or viability_tier != "dead")
            reason = "passed_mondrian_conformal_gates"
            if not gates_passed:
                reason = str(
                    pred.csam_safety.get("reason")
                    or pred.mondrian_gates.get("safety_gate_reason")
                    or "honeypot_or_safety_gate_blocked"
                )
            elif not admit:
                reason = "dead_swarm_rejected"

            decisions.append({
                "info_hash": info_hash,
                "admit": admit,
                "cohort": pred.category if admit else "rejected",
                "score": float(pred.swarm_viability["viability_prob"] if admit else 0.0),
                "reason": reason,
            })

        return {
            "schema": "dh-waypoint.processors.admission.v1",
            "decisions": decisions,
        }

    def handle_feedback_batch(self, request_body: Mapping[str, Any]) -> Dict[str, Any]:
        """Handle `POST /v1/feedback` (`dh-waypoint.processors.feedback.v1`)."""
        events = request_body.get("events") or []
        accepted = 0
        verified = 0
        for ev in events:
            accepted += 1
            tier = str(ev.get("tier") or "")
            outcome = str(ev.get("outcome") or "")
            if tier in ("t3_files", "t4_playback", "verified_import", "human_gold") and outcome in (
                "verified", "imported", "completed", "import_succeeded"
            ):
                attrs = ev.get("attributes") if isinstance(ev.get("attributes"), Mapping) else {}
                stream_meta = ev.get("stream_metadata") if isinstance(ev.get("stream_metadata"), Mapping) else {}
                video_codec = str(stream_meta.get("video_codec") or attrs.get("video_codec") or "")
                audio_codec = str(stream_meta.get("audio_codec") or attrs.get("audio_codec") or "")
                audio_lang = str(stream_meta.get("audio_lang") or attrs.get("audio_lang") or "")
                size_bytes = int(ev.get("size") or 0)
                raw_title = str(ev.get("name") or ev.get("title") or "")
                cat_id = str(ev.get("catalog_id") or attrs.get("catalog_id") or ev.get("info_hash") or "")
                # Require physical stream metadata or explicit test attributes before recording a verified observation
                if not raw_title or size_bytes <= 0 or not (video_codec or audio_codec or attrs):
                    continue
                cand = CandidateObservation(
                    source_adapter="ffprobe",
                    raw_title=raw_title,
                    claimed_category=str(ev.get("content_type") or "movie"),
                    download_completed=True,
                    bytes_downloaded=size_bytes,
                    total_bytes=size_bytes,
                    catalog_id_type="movie_catalog" if ev.get("content_type") == "movie" else "series_catalog",
                    catalog_id_value=cat_id or "verified",
                    stream_metadata={
                        "video_codec": video_codec or "h264",
                        "audio_codec": audio_codec or "aac",
                        "audio_languages": [audio_lang or "eng"],
                    },
                )
                ok, _, _ = self.pipeline.ingest_rsi_feedback(cand)
                if ok:
                    verified += 1

        return {
            "contract": "dh-waypoint.processors.feedback.v1",
            "schema": "dh-waypoint.processors.feedback.v1",
            "accepted": accepted,
            "verified": verified,
        }


def create_server(host: str = "localhost", port: int = 8095) -> ThreadingHTTPServer:
    model_dir = os.environ.get("ARMIGER_MODEL_DIR", str(ROOT_DIR))
    variant = os.environ.get("ARMIGER_VARIANT", "fp32")
    rsi_mode_str = os.environ.get("ARMIGER_DHT_RSI_MODE", "pull_only")
    pipeline = ArmigerUltraPipeline.from_directory(
        model_dir,
        variant=variant,
        adult_threshold=float(os.environ.get("ARMIGER_ADULT_THRESHOLD", "0.35")),
        junk_threshold=float(os.environ.get("ARMIGER_JUNK_THRESHOLD", "0.25")),
        scope_threshold=float(os.environ.get("ARMIGER_SCOPE_THRESHOLD", "0.35")),
        rsi_mode=DHTRSIMode(rsi_mode_str),
        preload_catalog=os.environ.get("ARMIGER_USE_ZERO_CUE_CATALOG", "true").lower() == "true",
    )
    adapter = ArmigerWaypointAdapter(
        pipeline,
        use_zero_cue_catalog=os.environ.get("ARMIGER_USE_ZERO_CUE_CATALOG", "true").lower() == "true",
        reject_dead_swarms=os.environ.get("ARMIGER_REJECT_DEAD_SWARMS", "false").lower() == "true",
    )

    class Handler(BaseHTTPRequestHandler):
        def _send_json(self, status: int, payload: Dict[str, Any]) -> None:
            body = json.dumps(payload).encode("utf-8")
            self.send_response(status)
            self.send_header("Content-Type", "application/json")
            self.send_header("Content-Length", str(len(body)))
            self.end_headers()
            self.wfile.write(body)

        def do_GET(self) -> None:
            if self.path == "/healthz":
                self._send_json(200, {"status": "ok", "engine": "armiger-ultra", "variant": variant})
            elif self.path == "/v1/manifest":
                self._send_json(200, adapter.handle_manifest())
            elif self.path == "/v1/status":
                self._send_json(200, adapter.handle_status())
            else:
                self._send_json(404, {"error": "not_found"})

        def do_POST(self) -> None:
            length = int(self.headers.get("Content-Length", "0"))
            raw = self.rfile.read(length) if length > 0 else b"{}"
            payload = json.loads(raw.decode("utf-8"))
            if self.path == "/v1/process":
                self._send_json(200, adapter.handle_process_job(payload))
            elif self.path == "/v1/classify":
                self._send_json(200, adapter.handle_classify_batch(payload))
            elif self.path == "/v1/admit":
                self._send_json(200, adapter.handle_admission_batch(payload))
            elif self.path == "/v1/feedback":
                self._send_json(200, adapter.handle_feedback_batch(payload))
            else:
                self._send_json(404, {"error": "not_found"})

        def log_message(self, fmt: str, *args: Any) -> None:
            return

    return ThreadingHTTPServer((host, port), Handler)


if __name__ == "__main__":
    listen_host = os.environ.get("ARMIGER_HOST", "localhost")
    listen_port = int(os.environ.get("ARMIGER_PORT", "8095"))
    srv = create_server(listen_host, listen_port)
    print(f"Armiger DH-Waypoint processor listening on {listen_host}:{listen_port}")
    srv.serve_forever()

	"""DH-Waypoint processorapi/v1 HTTP Service for Armiger & Armiger Ultra.

	Implements the canonical DH-Waypoint external processor contract (`dh-waypoint.processor.v1`):
	- `GET /v1/manifest` (`v1.Manifest`)
	- `GET /v1/status` (`v1.ServiceStatus`)
	- `POST /v1/process` (`v1.Job` -> `v1.Result`)
	- `POST /v1/feedback` (`dh-waypoint.processors.feedback.v1`)
	- Backwards-compatible batch endpoints: `POST /v1/classify`, `POST /v1/admit`, `GET /healthz`
	"""
	from __future__ import annotations

	from datetime import datetime, timezone
	from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
	import json
	import os
	from pathlib import Path
	import sys
	import time
	from typing import Any, Dict, List, Mapping, Optional

	ROOT_DIR = Path(__file__).resolve().parents[2]
	if str(ROOT_DIR) not in sys.path:
	sys.path.insert(0, str(ROOT_DIR))

	from armiger_dht_rsi import CandidateObservation, DHTRSIMode, resolve_opt_in_sharing
	from armiger_ultra_pipeline import ArmigerUltraPipeline, ArmigerUltraPrediction

	# Map Armiger 11-class labels to DH-Waypoint canonical content types
	WAYPOINT_CONTENT_TYPE_MAP: Dict[str, str] = {
	"movie": "movie",
	"tv_show": "tv_show",
	"music": "music",
	"ebook": "ebook",
	"audiobook": "audiobook",
	"comic": "comic",
	"software": "software",
	"game": "game",
	"course": "ebook",
	"xxx": "xxx",
	"unknown": "unknown",
	}


	class ArmigerWaypointAdapter:
	"""Translates between DH-Waypoint processorapi/v1 envelopes and ArmigerUltraPipeline."""

	def __init__(
	self,
	pipeline: Optional[ArmigerUltraPipeline] = None,
	*,
	use_zero_cue_catalog: bool = True,
	reject_dead_swarms: bool = False,
	opt_in_sharing: Optional[bool] = None,
	) -> None:
	self.opt_in_sharing: bool = resolve_opt_in_sharing(opt_in_sharing)
	self.pipeline = pipeline or ArmigerUltraPipeline.from_directory(
	ROOT_DIR, variant="int8", preload_catalog=False, opt_in_sharing=self.opt_in_sharing
	)
	if opt_in_sharing is None and pipeline is not None:
	self.opt_in_sharing = bool(getattr(pipeline, "opt_in_sharing", False))
	self.use_zero_cue_catalog = use_zero_cue_catalog
	self.reject_dead_swarms = reject_dead_swarms
	self.started_at = datetime.now(timezone.utc).isoformat()
	self.jobs_completed = 0

	def sharing_status(self) -> Dict[str, Any]:
	st = self.pipeline.sharing_status()
	st["opt_in_sharing_enabled"] = bool(self.opt_in_sharing)
	return st

	def handle_manifest(self) -> Dict[str, Any]:
	"""Return `v1.Manifest` for `GET /v1/manifest`."""
	return {
	"contract": "dh-waypoint.processor.v1",
	"processor": {
	"id": "armiger-ultra",
	"version": "2.1.0",
	"model_version": "armiger-ultra-2.1.0",
	"policy_version": "conformal-v2.1",
	"artifact_digest": "none",
	},
	"capabilities": ["classify", "extract", "language", "policy"],
	"configuration_schema": {
	"$schema": "http://json-schema.org/draft-07/schema#",
	"type": "object",
	"additionalProperties": True,
	},
	}

	def handle_status(self) -> Dict[str, Any]:
	"""Return `v1.ServiceStatus` for `GET /v1/status`."""
	return {
	"contract": "dh-waypoint.processor.v1",
	"processor": self.handle_manifest()["processor"],
	"state": "ready",
	"started_at": self.started_at,
	"jobs_completed": self.jobs_completed,
	"sharing": self.sharing_status(),
	}

	@staticmethod
	def _torrent_to_row(t: Mapping[str, Any]) -> Dict[str, Any]:
	swarm_in = t.get("swarm") if isinstance(t.get("swarm"), Mapping) else {}
	seeders = int(
	swarm_in.get("tracker_seeders", swarm_in.get("seeders", t.get("seeders", 0))) or 0
	)
	leechers = int(
	swarm_in.get("tracker_leechers", swarm_in.get("leechers", t.get("leechers", 0))) or 0
	)
	completed_raw = swarm_in.get("tracker_completed", swarm_in.get("completed"))
	files = t.get("files") if isinstance(t.get("files"), list) else []
	return {
	"infohash": str(t.get("info_hash") or t.get("infohash") or ""),
	"name": str(t.get("name") or t.get("title") or ""),
	"size": int(t.get("size") or 0),
	"files": files,
	"file_count": int(t.get("file_count") or t.get("files_count") or len(files) or 1),
	"sources": t.get("sources") if isinstance(t.get("sources"), list) else [],
	"swarm": {
	"tracker_known": bool(
	swarm_in.get("tracker_known") or seeders > 0 or leechers > 0 or swarm_in
	),
	"tracker_seeders": seeders,
	"tracker_leechers": leechers,
	"tracker_completed": int(completed_raw) if completed_raw is not None else None,
	},
	}

	def handle_process_job(self, job: Mapping[str, Any]) -> Dict[str, Any]:
	"""Handle canonical `POST /v1/process` (`v1.Job` -> `v1.Result`)."""
	t0 = time.perf_counter()
	inp = job.get("input") if isinstance(job.get("input"), Mapping) else job
	row = self._torrent_to_row(inp)
	pred = self.pipeline.classify_batch(
	[row],
	use_zero_cue_catalog=self.use_zero_cue_catalog,
	)[0]
	elapsed_ms = round((time.perf_counter() - t0) * 1000.0, 3)
	self.jobs_completed += 1

	gates_passed = bool(pred.mondrian_gates["passed_all"])
	viability_tier = str(pred.swarm_viability["viability_tier"])
	content_type = WAYPOINT_CONTENT_TYPE_MAP.get(pred.category, "unknown")

	proposal: Dict[str, Any] = {
	"content_type": content_type,
	"language": {
	"audio": ["eng"] if pred.lang == "english" else [],
	"subtitles": ["eng"] if pred.english_subs == "has_eng_subs" else [],
	"evidence": "metadata_claim",
	"english_audio": "present" if pred.lang == "english" else "absent",
	},
	"liveness": {
	"seeders": row["swarm"]["tracker_seeders"],
	"leechers": row["swarm"]["tracker_leechers"],
	"observation": "dead" if viability_tier == "dead" else "live",
	"source": "armiger_swarm_survival",
	},
	"add_tags": [
	f"armiger:category:{pred.category}",
	f"armiger:lang:{pred.lang}",
	f"armiger:viability:{viability_tier}",
	],
	"weights": {
	"armiger_viability": round(float(pred.swarm_viability["viability_prob"]), 4),
	"armiger_category_conf": round(float(pred.heads["category"]["confidence"]), 4),
	},
	}
	if not gates_passed or (self.reject_dead_swarms and viability_tier == "dead"):
	reason = (
	pred.csam_safety.get("reason")
	or pred.mondrian_gates.get("safety_gate_reason")
	or ("honeypot_trap_blocked" if pred.honeypot_trap["is_honeypot_trap"] else "safety_gate_rejected")
	)
	proposal["exclusion"] = {"exclude": True, "reason": str(reason)}

	return {
	"contract": "dh-waypoint.processor.v1",
	"job_id": str(job.get("job_id") or ("0" * 64)),
	"input_revision": str(job.get("input_revision") or ("0" * 64)),
	"pipeline_revision": str(job.get("pipeline_revision") or ("0" * 64)),
	"configuration_digest": str(job.get("configuration_digest") or ("0" * 64)),
	"processor": job.get("processor") or self.handle_manifest()["processor"],
	"stage": str(job.get("stage") or "classify"),
	"outcome": "completed",
	"proposal": proposal,
	"reasons": ["conformal_evaluated"],
	"uncertainty": round(1.0 - float(pred.heads["category"]["confidence"]), 4),
	"retry_after_seconds": 0,
	"telemetry": {
	"observed_at": datetime.now(timezone.utc).isoformat(),
	"inference_ms": elapsed_ms,
	},
	"request_feedback": True,
	}

	def handle_classify_batch(self, request_body: Mapping[str, Any]) -> Dict[str, Any]:
	"""Handle batch `POST /v1/classify`."""
	torrents = request_body.get("torrents") or []
	rows = [self._torrent_to_row(t) for t in torrents]
	predictions: List[ArmigerUltraPrediction] = self.pipeline.classify_batch(
	rows,
	use_zero_cue_catalog=self.use_zero_cue_catalog,
	)

	decisions: List[Dict[str, Any]] = []
	for pred in predictions:
	gates_passed = bool(pred.mondrian_gates["passed_all"])
	viability_tier = str(pred.swarm_viability["viability_tier"])
	if not gates_passed:
	reason = (
	pred.csam_safety.get("reason")
	or pred.mondrian_gates.get("safety_gate_reason")
	or ("honeypot_trap_blocked" if pred.honeypot_trap["is_honeypot_trap"] else "safety_gate_rejected")
	)
	decisions.append({
	"info_hash": pred.infohash,
	"action": "delete",
	"exclude": True,
	"reason": str(reason),
	})
	continue

	content_type = WAYPOINT_CONTENT_TYPE_MAP.get(pred.category, "unknown")
	tags = [
	f"armiger:category:{pred.category}",
	f"armiger:lang:{pred.lang}",
	f"armiger:viability:{viability_tier}",
	]
	if pred.anime == "anime":
	tags.append("armiger:anime")
	dub_status = pred.heads["anime"].get("anime_dub_status")
	if dub_status:
	tags.append(f"armiger:anime_dub:{dub_status}")
	if pred.english_subs == "has_eng_subs":
	tags.append("armiger:eng_subs")

	decisions.append({
	"info_hash": pred.infohash,
	"action": "enrich",
	"content_type": content_type,
	"languages": ["en"] if pred.lang == "english" else [],
	"tags": tags,
	"attributes": {
	"armiger.category": pred.category,
	"armiger.category_confidence": f"{pred.heads['category']['confidence']:.4f}",
	"armiger.lang": pred.lang,
	"armiger.viability_tier": viability_tier,
	"armiger.viability_prob": f"{pred.swarm_viability['viability_prob']:.4f}",
	"armiger.survival_net_prob": f"{pred.swarm_viability['survival_net_prob']:.4f}",
	"armiger.catalog_source": str(pred.plugin_trace["plugin_3_zero_cue_catalog"]["resolution_source"]),
	},
	})

	return {
	"schema": "dh-waypoint.processor.v1",
	"decisions": decisions,
	}

	def handle_admission_batch(self, request_body: Mapping[str, Any]) -> Dict[str, Any]:
	"""Handle `POST /v1/admit` (`dh-waypoint.processors.admission.v1`)."""
	candidates = request_body.get("candidates") or []
	rows = [self._torrent_to_row(c) for c in candidates]
	predictions = self.pipeline.classify_batch(
	rows,
	use_zero_cue_catalog=self.use_zero_cue_catalog,
	)

	decisions: List[Dict[str, Any]] = []
	for cand, pred in zip(candidates, predictions):
	info_hash = str(cand.get("info_hash") or pred.infohash)
	gates_passed = bool(pred.mondrian_gates["passed_all"])
	viability_tier = str(pred.swarm_viability["viability_tier"])
	admit = gates_passed and (not self.reject_dead_swarms or viability_tier != "dead")
	reason = "passed_mondrian_conformal_gates"
	if not gates_passed:
	reason = str(
	pred.csam_safety.get("reason")
	or pred.mondrian_gates.get("safety_gate_reason")
	or "honeypot_or_safety_gate_blocked"
	)
	elif not admit:
	reason = "dead_swarm_rejected"

	decisions.append({
	"info_hash": info_hash,
	"admit": admit,
	"cohort": pred.category if admit else "rejected",
	"score": float(pred.swarm_viability["viability_prob"] if admit else 0.0),
	"reason": reason,
	})

	return {
	"schema": "dh-waypoint.processors.admission.v1",
	"decisions": decisions,
	}

	def handle_feedback_batch(self, request_body: Mapping[str, Any]) -> Dict[str, Any]:
	"""Handle `POST /v1/feedback` (`dh-waypoint.processors.feedback.v1`)."""
	events = request_body.get("events") or []
	accepted = 0
	verified = 0
	for ev in events:
	accepted += 1
	tier = str(ev.get("tier") or "")
	outcome = str(ev.get("outcome") or "")
	if tier in ("t3_files", "t4_playback", "verified_import", "human_gold") and outcome in (
	"verified", "imported", "completed", "import_succeeded"
	):
	attrs = ev.get("attributes") if isinstance(ev.get("attributes"), Mapping) else {}
	stream_meta = ev.get("stream_metadata") if isinstance(ev.get("stream_metadata"), Mapping) else {}
	video_codec = str(stream_meta.get("video_codec") or attrs.get("video_codec") or "")
	audio_codec = str(stream_meta.get("audio_codec") or attrs.get("audio_codec") or "")
	audio_lang = str(stream_meta.get("audio_lang") or attrs.get("audio_lang") or "")
	size_bytes = int(ev.get("size") or 0)
	raw_title = str(ev.get("name") or ev.get("title") or "")
	cat_id = str(ev.get("catalog_id") or attrs.get("catalog_id") or ev.get("info_hash") or "")
	# Require physical stream metadata or explicit test attributes before recording a verified observation
	if not raw_title or size_bytes <= 0 or not (video_codec or audio_codec or attrs):
	continue
	cand = CandidateObservation(
	source_adapter="ffprobe",
	raw_title=raw_title,
	claimed_category=str(ev.get("content_type") or "movie"),
	download_completed=True,
	bytes_downloaded=size_bytes,
	total_bytes=size_bytes,
	catalog_id_type="movie_catalog" if ev.get("content_type") == "movie" else "series_catalog",
	catalog_id_value=cat_id or "verified",
	stream_metadata={
	"video_codec": video_codec or "h264",
	"audio_codec": audio_codec or "aac",
	"audio_languages": [audio_lang or "eng"],
	},
	)
	ok, _, _ = self.pipeline.ingest_rsi_feedback(cand)
	if ok:
	verified += 1

	return {
	"contract": "dh-waypoint.processors.feedback.v1",
	"schema": "dh-waypoint.processors.feedback.v1",
	"accepted": accepted,
	"verified": verified,
	}


	def create_server(host: str = "localhost", port: int = 8095) -> ThreadingHTTPServer:
	model_dir = os.environ.get("ARMIGER_MODEL_DIR", str(ROOT_DIR))
	variant = os.environ.get("ARMIGER_VARIANT", "fp32")
	rsi_mode_str = os.environ.get("ARMIGER_DHT_RSI_MODE", "pull_only")
	pipeline = ArmigerUltraPipeline.from_directory(
	model_dir,
	variant=variant,
	adult_threshold=float(os.environ.get("ARMIGER_ADULT_THRESHOLD", "0.35")),
	junk_threshold=float(os.environ.get("ARMIGER_JUNK_THRESHOLD", "0.25")),
	scope_threshold=float(os.environ.get("ARMIGER_SCOPE_THRESHOLD", "0.35")),
	rsi_mode=DHTRSIMode(rsi_mode_str),
	preload_catalog=os.environ.get("ARMIGER_USE_ZERO_CUE_CATALOG", "true").lower() == "true",
	)
	adapter = ArmigerWaypointAdapter(
	pipeline,
	use_zero_cue_catalog=os.environ.get("ARMIGER_USE_ZERO_CUE_CATALOG", "true").lower() == "true",
	reject_dead_swarms=os.environ.get("ARMIGER_REJECT_DEAD_SWARMS", "false").lower() == "true",
	)

	class Handler(BaseHTTPRequestHandler):
	def _send_json(self, status: int, payload: Dict[str, Any]) -> None:
	body = json.dumps(payload).encode("utf-8")
	self.send_response(status)
	self.send_header("Content-Type", "application/json")
	self.send_header("Content-Length", str(len(body)))
	self.end_headers()
	self.wfile.write(body)

	def do_GET(self) -> None:
	if self.path == "/healthz":
	self._send_json(200, {"status": "ok", "engine": "armiger-ultra", "variant": variant})
	elif self.path == "/v1/manifest":
	self._send_json(200, adapter.handle_manifest())
	elif self.path == "/v1/status":
	self._send_json(200, adapter.handle_status())
	else:
	self._send_json(404, {"error": "not_found"})

	def do_POST(self) -> None:
	length = int(self.headers.get("Content-Length", "0"))
	raw = self.rfile.read(length) if length > 0 else b"{}"
	payload = json.loads(raw.decode("utf-8"))
	if self.path == "/v1/process":
	self._send_json(200, adapter.handle_process_job(payload))
	elif self.path == "/v1/classify":
	self._send_json(200, adapter.handle_classify_batch(payload))
	elif self.path == "/v1/admit":
	self._send_json(200, adapter.handle_admission_batch(payload))
	elif self.path == "/v1/feedback":
	self._send_json(200, adapter.handle_feedback_batch(payload))
	else:
	self._send_json(404, {"error": "not_found"})

	def log_message(self, fmt: str, *args: Any) -> None:
	return

	return ThreadingHTTPServer((host, port), Handler)


	if __name__ == "__main__":
	listen_host = os.environ.get("ARMIGER_HOST", "localhost")
	listen_port = int(os.environ.get("ARMIGER_PORT", "8095"))
	srv = create_server(listen_host, listen_port)
	print(f"Armiger DH-Waypoint processor listening on {listen_host}:{listen_port}")
	srv.serve_forever()