afv-library/skills/investigating-agentforce-d360/assets/dc/sessions.sql

79 lines
3.0 KiB
MySQL
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
-- Sessions from Data Cloud — reusable for any WHERE filter.
-- DMO: ssot__AIAgentSession__dlm
--
-- Placeholders (substituted by scripts/dc.py._load):
-- WHERE_CLAUSE — the filter expression, no "WHERE" keyword
-- ORDER_BY — full "ORDER BY <col>" or empty string
--
-- See EXAMPLE QUERIES below for common WHERE patterns.
--
-- This query extracts session-level data including:
-- - Session ID and timestamps
-- - Channel type (how user connected)
-- - How the session ended (Completed, Abandoned, Escalated, etc.)
-- - Related messaging session (if applicable)
--
-- NOTE: Agent name is NOT on Session table. Join with Moment to get agent info.
SELECT
ssot__Id__c,
ssot__AiAgentChannelType__c,
ssot__StartTimestamp__c,
ssot__EndTimestamp__c,
ssot__AiAgentSessionEndType__c,
ssot__RelatedMessagingSessionId__c,
ssot__RelatedVoiceCallId__c,
ssot__InternalOrganizationId__c,
ssot__SessionOwnerId__c,
ssot__SessionOwnerObject__c,
ssot__IndividualId__c,
ssot__PreviousSessionId__c,
ssot__VariableText__c
FROM ssot__AIAgentSession__dlm
WHERE {{WHERE_CLAUSE}}
{{ORDER_BY}};
-- ============================================================================
-- EXAMPLE QUERIES (pass to sessions_sql via where_clause= / order_by=)
-- ============================================================================
-- One session by id (this skill's primary use case)
-- WHERE → ssot__Id__c = '<session_uuid>'
-- ORDER BY → ORDER BY ssot__StartTimestamp__c
-- Last 7 days of sessions
-- WHERE → ssot__StartTimestamp__c >= '<iso_cutoff_7d_ago>'
-- ORDER BY → ORDER BY ssot__StartTimestamp__c
-- Date range
-- WHERE → ssot__StartTimestamp__c >= '2026-01-01T00:00:00.000Z'
-- AND ssot__StartTimestamp__c < '2026-02-01T00:00:00.000Z'
-- ORDER BY → ORDER BY ssot__StartTimestamp__c
-- Failed / escalated sessions only
-- WHERE → ssot__AiAgentSessionEndType__c IN ('Escalated', 'Abandoned', 'Failed')
-- AND ssot__StartTimestamp__c >= '2026-01-01T00:00:00.000Z'
-- ORDER BY → ORDER BY ssot__StartTimestamp__c
-- Sessions by channel (e.g. embedded messaging only)
-- WHERE → ssot__AiAgentChannelType__c = 'SCRT2 - EmbeddedMessaging'
-- AND ssot__StartTimestamp__c >= '2026-01-01T00:00:00.000Z'
-- ORDER BY → ORDER BY ssot__StartTimestamp__c
-- Session count by end type (aggregate — SELECT list changes too; separate template)
-- SELECT
-- ssot__AiAgentSessionEndType__c,
-- COUNT(*) as session_count
-- FROM ssot__AIAgentSession__dlm
-- WHERE ssot__StartTimestamp__c >= '2026-01-01T00:00:00.000Z'
-- GROUP BY ssot__AiAgentSessionEndType__c;
-- Sessions by agent (requires Moment join — separate query shape, not this template)
-- SELECT DISTINCT s.*
-- FROM ssot__AIAgentSession__dlm s
-- JOIN ssot__AiAgentMoment__dlm m
-- ON m.ssot__AiAgentSessionId__c = s.ssot__Id__c
-- WHERE m.ssot__AiAgentApiName__c = 'MyAgent'
-- AND s.ssot__StartTimestamp__c >= '2026-01-01T00:00:00.000Z';