mirror of
https://github.com/forcedotcom/afv-library.git
synced 2026-08-10 09:41:17 +08:00
20ae436442
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.
46 lines
1.8 KiB
Python
46 lines
1.8 KiB
Python
"""Shared constants for investigating-agentforce-d360.
|
|
|
|
Values that don't vary per environment or user live here. If a value
|
|
needs to be overridable at runtime in the future, swap this module for
|
|
a loader — callers won't notice.
|
|
|
|
Path layout::
|
|
|
|
~/.claude/data/investigating-agentforce-d360/
|
|
└── <org_id_15>/
|
|
└── <agent_api_name>__<agent_version>/
|
|
└── <session_id>/ ← session artifacts
|
|
|
|
``DATA_ROOT`` is re-exported from the canonical helper in
|
|
``scripts/_shared/paths.py`` (sibling module, inlined at the skill
|
|
boundary). All session-dir composition MUST go through
|
|
``paths.session_dir(...)`` — never compose ``DATA_ROOT / <sid>``
|
|
directly, because that bypasses the 4-segment regex validation.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
# Data Cloud Query API — the instance_url prefix is resolved at runtime
|
|
# via `sf org display --target-org <alias> --json` (Claude does that,
|
|
# not python). Python only owns the path.
|
|
DC_API_PATH = "/services/data/v66.0/ssot/query"
|
|
|
|
|
|
# -----------------------------------------------------------------------------
|
|
# Shared path helpers — sibling _shared/ package
|
|
# -----------------------------------------------------------------------------
|
|
|
|
_SCRIPTS_DIR = Path(__file__).resolve().parent
|
|
if str(_SCRIPTS_DIR) not in sys.path:
|
|
sys.path.insert(0, str(_SCRIPTS_DIR))
|
|
|
|
from _shared import paths # type: ignore # noqa: E402,F401 — re-export
|
|
from _shared import sql # type: ignore # noqa: E402,F401 — re-export
|
|
|
|
# One persistent tree per session. Writes land directly here — no
|
|
# ephemeral /tmp staging. Re-running the same session id finds prior
|
|
# results, which later enables per-artifact caching.
|
|
DATA_ROOT = paths.DATA_ROOT
|