fluid-core/INTENT.md
tegwick c2cfe86d88 Establish fluid-core scaffold, intent, and phased workplans
Adds the repository structure, INTENT.md declaring the wire-contract
boundary, and seven workplans covering Blueprint Phases A-C plus the
fluid-telegram handover.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014KmVxhJ35tCo7rE7UnLwWu

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1116572@bnt-lap001
Assistant-Session: 8ba9bb93-a72a-4883-b189-2499cce5c400
2026-09-04 01:49:12 +02:00

85 lines
3.3 KiB
Markdown

---
project: fluid-core
product: FLUID
status: draft
intent_version: 0.1.0
date: 2026-09-04
standard: FluidAPIStandards
standard_version: 0.1.0
---
# INTENT.md — fluid-core
> **FLUID envisions interfaces that learn when they should change, why, how to
> test the change, and whether the result deserves to become part of their
> evolving contract.**
## 1. Repository intent
`fluid-core` exists to make FLUID — *Flow Utilizing Interface Daimon*
executable. It is the reference framework for operating deterministic service
interfaces inside a governed evolutionary control loop.
The framework's defining commitment is stated in `spec/FluidAPIStandards.md` §3:
> **Deterministic execution, adaptive evolution.**
The production request path stays deterministic and auditable. Observation,
analysis, hypothesis formation, experimentation and promotion happen *around*
the interface, never inside the request path.
## 2. What this repository owns
- the deterministic data plane: gateway, revision resolver, revision router,
contract validation, backend connectors, response policy, telemetry emission;
- the observation plane: telemetry ingest, redaction, cohorts, interaction
topology, pressure classification;
- the evolution control plane through Blueprint Phase C: pressure registry,
hypothesis records, experiment control, fitness evaluation, promotion
decisions;
- the evidence, artifact and intent stores;
- the wire contract by which any interface, in any language, becomes FLUID.
## 3. What this repository does not own
- the interfaces themselves — those live in consumer repositories
(`fluid-telegram`, `fluid-x`, `fluid-substack`);
- backend systems reached through connectors;
- the Daimon's generative capability (Blueprint Phase D), deliberately deferred
until real telemetry exists for it to learn from.
## 4. The boundary is a wire contract
fluid-core is integrated **out of process**. A target API contributes no code,
imports no library, and may be written in any stack. Integration happens through
four artifacts:
1. the revision descriptor (Blueprint §36);
2. the routing policy (Blueprint §17);
3. the telemetry envelope;
4. the control APIs (Blueprint §44).
Any change that leaks Go types across this boundary is a design failure. This
constraint is what allows adapters, Daimons and future gateways to be written in
whatever language suits them.
## 5. Governing invariants
The sixteen architectural invariants in `spec/ArchitectureBlueprint.md` §55 are
constitutional for this repository. The four that most often get eroded and must
be defended hardest:
- **Runtime behavior remains deterministic.** No LLM in the mandatory request path.
- **Evolution can stop without stopping the API.** Every control-plane component
must be killable in production with no runtime effect.
- **AI-generated artifacts are untrusted until verified.** The deterministic
policy gate is not advisory.
- **Backend authority does not leak into the interface Daimon.** Missing backend
capability is escalated as a structured requirement, never taken.
## 6. Success
`fluid-core` succeeds when an interface owner can put an existing API behind it
without modifying that API, and then answer — from evidence, months later — the
eleven auditability questions in `spec/FluidAPIStandards.md` §25 about any change
the interface underwent.