forcedotcom/sf-skills / plugins/builder/agentforce-adlc/skills/agentforce-d360-analyze
agentforce-d360-analyze
VerifiedData Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID `019d…` or MessagingSession id `0Mw…`). Also triggers on session discovery — find/list/search sessions by time, agent, channel, outcome, or conversation text — when the user has no session id yet. DO NOT TRIGGER for design-time architecture questions (use agentforce-architecture-analyze instead) or for runtime perf/latency/SLO questions that require platform telemetry beyond Data Cloud.
scripts/tests/test_session_shape.py
View on GitHub"""Tests for ``fetch_dc._classify_session_shape``.
Covers all 5 shapes with a parameterized table:
- session_not_found — sessions.json returned 0 rows
- interactions_not_materialized_yet — gw_reqs > 0 AND steps == 0 (STDM lag)
- abandoned_before_llm — steps > 0, LLM_STEP == 0, gw_reqs == 0
- planner_ran_no_gateway_logs — LLM_STEP > 0 with generation ids, gw_reqs == 0
- complete — the happy path
Order matters — the gateway-direct rule sits BEFORE abandoned_before_llm
because ``gw_req_count > 0`` is a stronger positive signal than
``steps_total > 0``. Verified here by including a case with both signals
disjointly (steps==0 on the gateway-direct path).
"""
from __future__ import annotations
import unittest
from . import _bootstrap # noqa: F401 — sys.path setup
from fetch_dc import _classify_session_shape # type: ignore
_CASES = [
# (label, kwargs, expected)
(
"session_not_found when sessions.json is empty",
dict(sessions_count=0, steps_total=0, llm_step_count=0,
steps_with_generation_id=0, gw_req_count=0),
"session_not_found",
),
(
"session_not_found wins even when gw_reqs > 0 (sessions gate runs first)",
dict(sessions_count=0, steps_total=0, llm_step_count=0,
steps_with_generation_id=0, gw_req_count=5),
"session_not_found",
),
(
"interactions_not_materialized_yet — fresh session, gateway populated, STDM lagging",
dict(sessions_count=1, steps_total=0, llm_step_count=0,
steps_with_generation_id=0, gw_req_count=3),
"interactions_not_materialized_yet",
),
(
"abandoned_before_llm — steps created but no LLM step, no gateway calls",
dict(sessions_count=1, steps_total=2, llm_step_count=0,
steps_with_generation_id=0, gw_req_count=0),
"abandoned_before_llm",
),
(
"planner_ran_no_gateway_logs — LLM steps + gen ids but gateway empty",
dict(sessions_count=1, steps_total=3, llm_step_count=2,
steps_with_generation_id=2, gw_req_count=0),
"planner_ran_no_gateway_logs",
),
(
"complete — the normal bucket",
dict(sessions_count=1, steps_total=5, llm_step_count=3,
steps_with_generation_id=3, gw_req_count=4),
"complete",
),
]
class ClassifySessionShapeTests(unittest.TestCase):
"""Parametric truth-table for the 5-way enum."""
def test_all_shapes(self):
for label, kwargs, expected in _CASES:
with self.subTest(label=label):
self.assertEqual(_classify_session_shape(**kwargs), expected)
def test_gateway_direct_precedes_abandoned(self):
"""Regression guard: the new rule must fire before abandoned_before_llm.
If someone reorders the checks, a session with gw_reqs > 0 AND
steps > 0 AND LLM_STEP == 0 (edge case — happens when Step rows
land while Interaction parent rows are still lagging) could fall
through incorrectly. Today the rules' inputs are disjoint
(gateway-direct needs steps==0), so the guard case uses steps==0
to exercise the ordering directly.
"""
shape = _classify_session_shape(
sessions_count=1,
steps_total=0,
llm_step_count=0,
steps_with_generation_id=0,
gw_req_count=1,
)
self.assertEqual(shape, "interactions_not_materialized_yet")
if __name__ == "__main__":
unittest.main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |