afv-library/skills/investigating-agentforce-d360/scripts/storage.py

93 lines
3.1 KiB
Python
Raw Normal View History

@W-22707610 feat: add investigating-agentforce-d360 skill Data Cloud 360° view of a single Agentforce session — DC-only, zero Splunk dependency. Pulls 24 STDM + GenAI DMOs via the Data Cloud Query REST API, assembles a hierarchical session tree (Interaction → Step → Generation → GatewayRequest), and renders a human-readable markdown summary with transcript + per-turn topic/action invocations + LLM generations + tool calls + audit chain. Migrated as a standalone Apache-2.0 skill from an internal hub plugin — self-contained, no sibling-skill or plugin dependencies. What this skill answers: - "Trace session <uuid>" / "Summarize what happened in <0Mw…>" - "Find escalated sessions today on Messaging in <org>" - Session discovery by time / agent / channel / outcome / conversation text when the user has no session id What it does NOT answer (use a different surface): - Design-time architecture — use investigating-agentforce-architecture - Runtime planner availability — DC alone can't tell you which topic/action was eligible for the classifier on a given turn Skill layout: - 8 Python pipeline modules (fetch_dc, assemble_dc, render_dc, discover_sessions, resolve_session, dc, storage, config) - 4 _shared helpers (paths, fs_guard, sql, __init__) with skill-scoped DATA_ROOT (~/.claude/data/investigating-agentforce-d360/) - 26 SQL templates under assets/dc/ - 27 test files (367 tests + 18 subtests, 100% passing) - 3 reference docs (artifacts.md, dc_dmo_fields.md, dc_pipeline_contract.md) - SKILL.md (sf-skills frontmatter, license: Apache-2.0, metadata.version: "1.0") - README.md (external-facing quick-start) - tools/grant_allowlist.py (idempotent first-run permission grant) - tools/archive_data_dir.sh (opt-in stop-hook tarballer) Quality gates: - pytest scripts/tests/: 367 passed + 18 subtests, 0 failures - npm run validate:skills: 62 of 62 skill(s) checked, 0 errors - Live end-to-end runs against 3 real Salesforce sessions exercising both the full-tree and STDM-lag gateway-direct render branches - 4 independent code-review rounds (correctness, security, markdown, architecture-critic) — all findings addressed Customer-data hygiene: no live tenant ids, no internal sprint markers, no hub/sibling-skill references. Synthetic fixtures look obviously synthetic (`019dface-…` UUIDs, `0MwTESTMSG…` MessagingSession ids, `00DTESTORG…` org ids, `MyAgent` placeholder agent name). Sibling skill: investigating-agentforce-architecture (PR #278) — same migration pattern, design-time metadata; complementary scope.
2026-05-28 18:57:52 +08:00
"""Shared per-session JSON writer.
Every Data Cloud artifact lands under the nested layout:
DATA_ROOT/<org_id_15>/<agent_api_name>__<agent_version>/<session_id>/<source>.<name>.json
One save, one shape, one directory convention imported by every caller.
**Security contract:**
All four path segments (``org_id_15``, ``agent_api_name``, ``agent_version``,
``session_id``) flow through ``paths.session_dir(...)``, which validates
each via fs_guard (regex) before the join. A ``..`` or ``/`` in any
segment raises ``paths.PathValidationError`` direct
``DATA_ROOT / session_id`` composition is unreachable from this module.
Source-prefix convention:
Flat directory, prefix filenames with provenance so an `ls` on the
per-session dir tells you where each artifact came from:
dc.sessions.json from Data Cloud
dc.interactions.json
Baking the prefix into the API (vs. leaving it to filename discipline)
makes it impossible to forget callers pass ``source`` + ``name``,
never a raw filename.
"""
from __future__ import annotations
import json
from pathlib import Path
from config import paths
def save(
data: list[dict] | dict,
org_id_15: str,
agent_api_name: str,
agent_version: str,
session_id: str,
source: str,
name: str,
) -> Path:
"""Write JSON under the nested session dir. Returns the target path.
Signature:
save(data, org_id_15, agent_api_name, agent_version, session_id,
source, name) -> Path
``source`` is the leading filename segment for provenance callers
pass ``"dc"``. ``name`` is the bare artifact name, no extension
``.json`` is appended.
Raises ``paths.PathValidationError`` if any of the four identity
segments fails validation.
"""
# paths.session_dir() validates org_id_15, agent_api_name, agent_version
# (via fs_guard) and session_id (via SESSION_ID_RE.fullmatch). Any bad
# input raises PathValidationError before we touch the filesystem.
target = paths.session_dir(
org_id_15, agent_api_name, agent_version, session_id
)
target.mkdir(parents=True, exist_ok=True)
path = target / f"{source}.{name}.json"
path.write_text(json.dumps(data, indent=2, default=str) + "\n")
_write_breadcrumb(org_id_15, agent_api_name, agent_version, session_id)
return path
def _write_breadcrumb(
org_id_15: str,
agent_api_name: str,
agent_version: str,
session_id: str,
) -> None:
"""Write ``<org>/_sessions/<sid>.link`` pointing at the session dir.
Plain text, no symlink (Windows-safe). Content is the relative path
``../<agent>__<ver>/<sid>\\n``. Idempotent overwriting with the
same content is a no-op semantically. Silent on failure; breadcrumbs
are best-effort (a missing breadcrumb doesn't break the write,
only handoff-session discovery).
"""
try:
link_dir = paths.DATA_ROOT / org_id_15 / "_sessions"
link_dir.mkdir(parents=True, exist_ok=True)
link_path = link_dir / f"{session_id}.link"
link_path.write_text(
f"../{agent_api_name}__{agent_version}/{session_id}\n"
)
except OSError:
pass