Artemis-Eapil/apps/admin_console/services/task_inspection.py

"""Bounded, read-only task diagnostics shared by MCP and HTTP clients."""

import os
import re

from apps.admin_console.database.repositories.session_repository import session_repo
from apps.admin_console.services import evidence_service, report_export
from apps.admin_console.services.automation_store import identifier, store
from apps.admin_console.services.request_diagnostics import request_diagnostics


_SECRET = re.compile(
    r"(?i)^(api[_-]?key|access[_-]?token|refresh[_-]?token|authorization|password|secret|client_secret|token_key)$"
)


def public_value(value, *, max_chars: int = 60000):
    """Remove common credential forms and bound text without inventing missing evidence."""
    remaining = max_chars
    remaining_nodes = 2000
    truncated = False
    secrets = [
        v
        for k, v in os.environ.items()
        if len(v) >= 8 and re.search(r"(?i)(api_?key|password|secret|token)$", k)
    ]

    def clean(item, depth=0):
        nonlocal remaining, remaining_nodes, truncated
        remaining_nodes -= 1
        if depth > 12:
            truncated = True
            return "[嵌套内容已截断]"
        if isinstance(item, dict):
            result = {}
            for k, v in item.items():
                if remaining_nodes <= 0 or len(result) >= 100:
                    truncated = True
                    break
                key = clean(str(k), depth + 1)
                result[key] = "[REDACTED]" if _SECRET.fullmatch(str(k)) else clean(v, depth + 1)
            return result
        if isinstance(item, list):
            result = []
            for v in item:
                if remaining_nodes <= 0 or len(result) >= 100:
                    truncated = True
                    break
                result.append(clean(v, depth + 1))
            return result
        if not isinstance(item, str):
            return item
        for secret in secrets:
            item = item.replace(secret, "[REDACTED]")
        item = re.sub(r"(?i)\bBearer\s+[^\s\"',;]+", "Bearer [REDACTED]", item)
        item = re.sub(r"\bsk-[A-Za-z0-9_-]+", "[REDACTED]", item)
        item = re.sub(r"(https?://)[^\s/@]+:[^\s/@]+@", r"\1[REDACTED]@", item)
        item = re.sub(
            r"""(?ix)((?:api[_-]?key|access[_-]?token|refresh[_-]?token|authorization|password|secret|token_key)["']?\s*[:=]\s*)("[^"]*"|'[^']*'|[^\s&,;]+)""",
            r"\1[REDACTED]",
            item,
        )
        allowance = min(8000, remaining)
        if len(item) > allowance:
            truncated = True
            item = item[:allowance] + "…[已截断；按步骤或关键词缩小范围]"
        remaining = max(0, remaining - min(len(item), allowance))
        return item

    result = clean(value)
    return {**result, "text_truncated": truncated, "content_truncated": truncated}


def page(items: list, offset: int, limit: int) -> dict:
    return {
        "items": items[offset : offset + limit],
        "total": len(items),
        "offset": offset,
        "limit": limit,
        "next_offset": offset + limit if offset + limit < len(items) else None,
    }


def inspect_task(session_id: str, view: str, *, offset: int = 0, limit: int = 20) -> dict:
    identifier(session_id)
    if offset < 0 or not 1 <= limit <= 100:
        raise ValueError("offset 必须非负，limit 必须在 1–100 之间")
    if not session_repo.get_session_by_id(session_id) and not store.job(session_id):
        raise LookupError("任务记录不存在")
    if view == "usage":
        result = session_repo.get_session_usage(session_id)
        result["cache_hit_rate"] = (
            result["cached_tokens"] / result["prompt_tokens"] if result["prompt_tokens"] else None
        )
        result["note"] = (
            "缓存率=已记录 cached_tokens / prompt_tokens；无用量不等于零消耗，未上报的请求无法补推。"
        )
    elif view == "requests":
        result = request_diagnostics(session_id, limit=limit, offset=offset)
    elif view == "logs":
        root = evidence_service.task_root(session_id)
        result = {"logs": []}
        for name in ("stdout.log", "stderr.log"):
            path = evidence_service.evidence_file(root, name)
            if path is None:
                result["logs"].append({"name": name, "available": False})
                continue
            with path.open("rb") as stream:
                size = path.stat().st_size
                start = max(0, size - 128 * 1024)
                stream.seek(start)
                raw = stream.read(128 * 1024)
            lines = raw.decode("utf-8", errors="replace").splitlines()
            if start and lines:
                lines = lines[1:]
            # Offset counts backward from the newest line within the bounded tail.
            end = max(0, len(lines) - offset)
            result["logs"].append(
                {
                    "name": name,
                    "available": True,
                    "bytes": size,
                    "lines": lines[max(0, end - limit) : end],
                    "offset": offset,
                    "next_offset": offset + limit if end > limit else None,
                    "older_bytes_omitted": start,
                    "order": "oldest_to_newest",
                }
            )
    elif view in {"report", "evidence"}:
        report = report_export.session_report(session_id)
        if view == "report":
            result = {**report, "steps": page(report.get("steps", []), offset, limit)}
        else:
            index = evidence_service.export_index(
                session_id, report, report_export.session_videos(report)
            )
            result = {
                **index,
                **{
                    key: page(index.get(key, []), offset, limit)
                    for key in ("steps", "calls", "recordings", "android_videos", "files")
                },
            }
    else:
        raise ValueError("view 需为 report / usage / requests / logs / evidence")
    return public_value({"session_id": session_id, **result})