fluid-core/workplans/FLUID-WP-0005-fluid-insight.md
repo-manager 0aab793a3a repo.work.assign_missing_identifiers
source: repo-manager
reason: deterministic projection registration

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1116572@bnt-lap001
Assistant-Session: 8ba9bb93-a72a-4883-b189-2499cce5c400
2026-09-04 01:52:06 +02:00

132 lines
3.1 KiB
Markdown

---
id: FLUID-WP-0005
type: workplan
title: "FLUID Insight - observation plane (Blueprint Phase B)"
domain: infotech
repo: fluid-core
status: active
owner: worsch
topic_slug: fluid-core
created: "2026-09-04"
updated: "2026-09-04"
planning_priority: high
planning_order: 4
depends_on:
- FLUID-WP-0004
state_hub_workstream_id: "06661687-9a1b-5f11-b900-7b086c9c2975"
---
# FLUID-WP-0005 - FLUID Insight
Turn traffic into evidence. Deterministic heuristics only at this stage — no
model inference anywhere in this workplan.
## T01 - Telemetry ingest and normalizer
```task
id: FLUID-WP-0005-T01
status: todo
priority: high
state_hub_task_id: "0c074022-031b-5049-832f-1fa8b1ff8b4f"
```
Request, error, sequence, adoption and explicit-feedback events into one
normalized interaction event (Blueprint §6.1).
## T02 - Redaction and privacy filter
```task
id: FLUID-WP-0005-T02
status: todo
priority: high
state_hub_task_id: "13086f4a-217c-5999-a039-90f5d84fb53b"
```
Field exclusion, pseudonymization, tenant isolation, retention, cohort minimum
sizes (§6.2). Raw payload capture is off by default and must stay that way —
FLUID learns about the interface, not about people.
## T03 - Cohort engine
```task
id: FLUID-WP-0005-T03
status: todo
priority: medium
state_hub_task_id: "815765d4-8d20-5c6f-87ac-e085778cd58c"
```
Coarse, stable, comparable over time (§6.3). Resist granularity: cohorts should
not be more specific than the analysis requires.
## T04 - Interaction topology analyzer
```task
id: FLUID-WP-0005-T04
status: todo
priority: high
state_hub_task_id: "27726efa-e054-56c2-a6b8-3cce8f2e85e7"
```
Recurring call-sequence detection (§6.4) — the signal that makes FLUID more than
error counting.
## T05 - Pressure classifier
```task
id: FLUID-WP-0005-T05
status: todo
priority: high
state_hub_task_id: "d2e4f2df-809f-5817-9b74-e1533f8f71d9"
```
The ten pressure classes from §6.5. Classification retains evidence references
in every case.
## T06 - Pressure registry
```task
id: FLUID-WP-0005-T06
status: todo
priority: high
state_hub_task_id: "50bd30a6-ae29-5e2b-9618-a3efe6a362b3"
```
Deduplication, aggregation, frequency, severity, confidence, and the §9
lifecycle. Pressure may remain unresolved on purpose — not every mismatch
deserves adaptation.
## T07 - Fitness engine
```task
id: FLUID-WP-0005-T07
status: todo
priority: high
state_hub_task_id: "ebecef59-2ff8-59c0-8cff-cde53030d0c8"
```
Blueprint §18: primary metrics, guardrails, secondary and learning metrics kept
distinct. Baseline and measurement window are retained, never recomputed.
## T08 - Explicit feedback collector
```task
id: FLUID-WP-0005-T08
status: todo
priority: medium
state_hub_task_id: "48f6bbce-2ae8-5b72-8fdc-e962c6ea1f54"
```
API Standards §15. Accepted over the wire, stored as evidence, and never
treated as authority to change anything.
## T09 - CLI and pressure API
```task
id: FLUID-WP-0005-T09
status: todo
priority: medium
state_hub_task_id: "ba413808-346b-5026-bfce-aec0eae0c410"
```
Blueprint §44.2 plus `fluid pressure list|show|dismiss`, `fluid cohort list`,
`fluid fitness compare`.