The Telegram channel publishes posts written from hall entries, not the
entries themselves, so the handover's pressure, competition and
guardrails are rebuilt around that. Composition sits outside the
interface because Blueprint 48.1 forbids an LLM in the mandatory request
path, and because a post about a named person's work deserves a human
read that a request-path step would never get.
Adds FLUID-WP-0009 for the pr- campaign repository convention and for
reducing the Hall of Helix case from the thing this framework is for to
an example of using it. The prefix deliberately includes "propaganda":
a campaign repository that cannot name what it is doing will not govern
it well.
The workplan starts only after the loop has closed once on real traffic.
Extracting a seam before using it is how you learn you cut it in the
wrong place.
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
Completes FLUID-WP-0008's deliverable in this repository. The handover
records the measured pressure that motivates the interface -- 80 of 94
hall entries exceed Telegram's 4096-character limit -- and names the
three places this workload will strain the framework honestly, so the
strain reads as information rather than as a surprise.
A conformance test asserts the handover's contract compiles with
fluid-core's own validator and stays within the intent's complexity
budget, so a change on either side that broke the handover fails CI
rather than failing at the first publication.
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
