mirror of
https://github.com/forcedotcom/afv-library.git
synced 2026-08-07 16:04:41 +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.
65 lines
2.6 KiB
SQL
65 lines
2.6 KiB
SQL
-- Planner steps — reusable for any WHERE filter.
|
|
-- DMO: ssot__AIAgentInteractionStep__dlm
|
|
--
|
|
-- Placeholders (substituted by scripts/dc.py.load_sql):
|
|
-- WHERE_CLAUSE — the filter expression, no "WHERE" keyword
|
|
-- ORDER_BY — full "ORDER BY <col>" or empty string
|
|
--
|
|
-- One row per planner step within an interaction. Type enum (verified live):
|
|
-- LLM_STEP | ACTION_STEP | TOPIC_STEP | TRUST_GUARDRAILS_STEP | SESSION_END.
|
|
--
|
|
-- NOTE: InputValueText__c / OutputValueText__c are HTML-escaped JSON.
|
|
-- Callers should `html.unescape()` then `json.loads()` after fetch.
|
|
-- No direct session FK — scope forward via ssot__AiAgentInteractionId__c
|
|
-- (harvested from the session's Interaction rows).
|
|
--
|
|
-- ssot__GenAiGatewayRequestId__c / ssot__GenAiGatewayResponseId__c are
|
|
-- included in the SELECT for completeness but are NOT used as join keys
|
|
-- anywhere in the waterfall. Gateway audit rows are fetched forward from
|
|
-- Session → GatewayRequest (via sessionId__c) — see gateway_requests.sql.
|
|
-- ssot__ErrorMessageText__c uses the sentinel 'NOT_SET' (never NULL) to
|
|
-- mean "no error"; filter with `!= 'NOT_SET'`, not `IS NOT NULL`.
|
|
|
|
SELECT
|
|
ssot__Id__c,
|
|
ssot__AiAgentInteractionId__c,
|
|
ssot__AiAgentInteractionStepType__c,
|
|
ssot__Name__c,
|
|
ssot__InputValueText__c,
|
|
ssot__OutputValueText__c,
|
|
ssot__PreStepVariableText__c,
|
|
ssot__PostStepVariableText__c,
|
|
ssot__GenerationId__c,
|
|
ssot__ErrorMessageText__c,
|
|
ssot__StartTimestamp__c,
|
|
ssot__EndTimestamp__c,
|
|
ssot__PrevStepId__c,
|
|
ssot__InternalOrganizationId__c,
|
|
ssot__TelemetryTraceSpanId__c,
|
|
ssot__AttributeText__c,
|
|
ssot__GenAiGatewayRequestId__c,
|
|
ssot__GenAiGatewayResponseId__c
|
|
FROM ssot__AIAgentInteractionStep__dlm
|
|
WHERE {{WHERE_CLAUSE}}
|
|
{{ORDER_BY}};
|
|
|
|
|
|
-- ============================================================================
|
|
-- EXAMPLE WHERE clauses (pass via where_clause=)
|
|
-- ============================================================================
|
|
|
|
-- Steps for a specific interaction
|
|
-- WHERE → ssot__AiAgentInteractionId__c = '<interaction_id>'
|
|
-- ORDER BY → ORDER BY ssot__StartTimestamp__c
|
|
|
|
-- Steps for a session (via interaction id IN list)
|
|
-- WHERE → ssot__AiAgentInteractionId__c IN ('<id1>','<id2>',...)
|
|
|
|
-- Only action steps (exclude LLM + topic planning)
|
|
-- WHERE → ssot__AiAgentInteractionId__c IN ('<id1>','<id2>')
|
|
-- AND ssot__AiAgentInteractionStepType__c = 'ACTION_STEP'
|
|
|
|
-- Steps with errors (sentinel value; NOT null)
|
|
-- WHERE → ssot__AiAgentInteractionId__c IN ('<id1>','<id2>')
|
|
-- AND ssot__ErrorMessageText__c != 'NOT_SET'
|