docs(prd): Mosaic Stack PRD draft 0.1 from PRDY round 1; lead decision 45
Round 1 answers fill users, problems, hard limits, hosting and the v1 done measure. Decision 45 raises Sage's seat limit to 4 Opus 5.5 and 4 Sonnet 5.5 sessions. Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
Claude Opus 5.5
@@ -466,3 +466,5 @@ are never rewritten or removed; corrections are new entries.
|
||||
2026-10-04T18:52:41Z | Sage (T3 Claude Code, thread 1ef1e4f8) | row 5 r1 routing (#1507) | pushed darkwing's queue commit 5a5013c4 (verify rev 53 ok); woke Dewey (84fb346c, stopped) with B1/B2 rework under decision 42, and Filbert's session restarted on my INFO; Sage-launched sessions running: 2 of 2 (dewey, filbert); one round 2 to both reviewers after rework
|
||||
2026-10-04T19:00:33Z | Filbert (T3 Claude Code, thread 9cb9731e) | row 5 CHAT-03 I1 review round 1 (#1507) | candidate 1404341e (27 files) verified frozen in a scratch clone and an export; §10 suites green (conductor 17/17 needs a git clone, queue 27 + 2 canonical-only skips); changes requested: B1 terminal Enter concatenation, B2 split paste-start ESC, B3 parallel force-stop escalations corrupt claim phaseStarted, B4 no test kills decision 34, B5 K12 freeze unproven (no-freeze mutant 18/18), B6 K15 missing-path case absent (ENOENT mutant 18/18); 20 notes; comment 26683, recorded rev 54 (filbert-5-r1-changes), committed f0b13a2f via queue-commit.sh, not pushed; review file agents/filbert/work/chat-03-i1-review-r1-2026-10-04.md (0444, uncommitted); REVIEW-RESULT to Dewey, copy to Sage; Darkwing's 26681 is on #1508, not the round's #1507 (flagged to Sage); rev 55 (jason park row 32) left uncommitted
|
||||
2026-10-04T19:01:37Z | Sage (T3 Claude Code, thread 1ef1e4f8) | foundation ratified, row 32 parked, row 5 r1 records | Jason ratified the foundation direction (lead decision 44; goals page superseded in part); row 32 parked on Jason's word (rev 55, 3270cc4e); row 5 r1 closed with both reviewers requesting changes (darkwing 26681, filbert 26683), both review files committed; pointer comment 26685 on #1507 for darkwing's verdict that landed on #1508; DEFERRED item for review record not checking the comment's issue
|
||||
2026-10-04T19:12:27Z | Filbert (T3 Claude Code, thread 9cb9731e) | meta-harness survey started (slice 1 step 8, Sage ASSIGNMENT) | research only in agents/filbert/work/; no commits; row 5 round 2 takes priority
|
||||
2026-10-04T19:12:38Z | Sage (T3 Claude Code, thread 1ef1e4f8) | PRDY round 1, seat launches (decision 45) | PRD draft 0.1 at docs/prd/mosaic-stack.md; launched Researcher (T3 Sonnet 5.5, thread 9bac0794) for the Vikunja and Pocket ID report; assigned Darkwing the slice 1 data model note and Filbert the meta-harness survey (both T3 Opus 5.5, existing threads); Dewey on the row 5 rework; running under the new limits: Opus 3 of 4 (dewey, darkwing, filbert), Sonnet 1 of 4 (researcher)
|
||||
|
||||
@@ -665,3 +665,30 @@ which stay with him. Each item names who decided it and what happened.
|
||||
write-once files (canon invariant 5). The decision and message
|
||||
tables are append-only: a correction is a new row, never an update.
|
||||
That keeps invariant 9's rule for logs.
|
||||
45. **PRDY round 1 answers and more seat sessions (2026-10-04).** Jason,
|
||||
thread 1ef1e4f8. The answers fill `docs/prd/mosaic-stack.md`
|
||||
(draft 0.1):
|
||||
1. Users: "D". Jason alone for now, built so outside users can
|
||||
install it later.
|
||||
2. Problems, in order: "A, C, B". Admin falls on Jason; he can't see
|
||||
what agents are doing or what's waiting on him; agents drift.
|
||||
3. Hard limits: "all five". No spend without Jason. No speaking
|
||||
externally as Jason without approval. No founder credentials in
|
||||
agents. Not a multi-tenant SaaS in v1. It wraps the harnesses and
|
||||
doesn't replace them.
|
||||
4. Hosting: "A first". Self-hosted, with cloud not ruled out later.
|
||||
5. v1 done: "A". Mosaic Stack builds pieces of itself from
|
||||
one-sentence CLI requests, five in a row, with only gated
|
||||
decisions reaching Jason and a full trail.
|
||||
Session limit: "You are now permitted to run more than 2 agent
|
||||
sessions. ... Opus 5.5 and Sonnet 5.5 should be able to run as many as
|
||||
4 sessions each." This replaces decision 42's limit of two. Sage may
|
||||
run up to 4 Opus 5.5 and up to 4 Sonnet 5.5 roster-seat sessions at
|
||||
once, in T3, in the mosaic-stack project. Sage's own thread isn't
|
||||
counted. Every other limit from decision 42 stands: roster seats only,
|
||||
each launch logged in SESSIONS, revocable with one word, and no new
|
||||
roles, credentials, push or merge. The roster lists Pi for Darkwing,
|
||||
Dewey, Filbert and Researcher, but their T3 sessions run on Claude
|
||||
Code. Sage reads Jason's ruling as covering those T3 Claude sessions.
|
||||
The first launch under it is a Researcher thread on Sonnet 5.5
|
||||
(9bac0794), researching Vikunja and Pocket ID.
|
||||
|
||||
@@ -0,0 +1,108 @@
|
||||
# PRD: Mosaic Stack
|
||||
|
||||
- Status: draft, version 0.1. Jason approves it, and once approved it is
|
||||
never edited in place. Changes after approval are a new version.
|
||||
- Owner: Jason. Sage writes it from the PRDY interview.
|
||||
- Template: PRDY "software" (`v1/packages/prdy/src/templates.ts`), filled
|
||||
by hand until PRDY is ported.
|
||||
- Interview record: Sage's thread 1ef1e4f8. Round 1 was answered on
|
||||
2026-10-04 and is recorded as lead decision 45.
|
||||
|
||||
## Introduction
|
||||
|
||||
### Objective
|
||||
|
||||
Working north star, ratified as lead decision 44: "Jason declares
|
||||
businesses, projects and roles. Agents in those roles carry the work end
|
||||
to end under declared policy, and only gated decisions reach him."
|
||||
|
||||
### Context
|
||||
|
||||
See `docs/plans/2026-10-04_foundation-direction.md`. Agents can already do
|
||||
real work here, but a person has to launch them, relay between them, hand
|
||||
them credentials and correct them. There's no CLI or complete WebUI for
|
||||
Jason, and no place where outstanding decisions collect.
|
||||
|
||||
## Users
|
||||
|
||||
Jason alone for now. The stack must be built so outside users can install
|
||||
it later: an installer, no paths or names specific to Jason, and
|
||||
configuration through the variable layers (round 1, answer D).
|
||||
|
||||
## Problem statement
|
||||
|
||||
In priority order (round 1):
|
||||
1. **Admin falls on Jason.** He launches seats, relays between them,
|
||||
finds credentials and corrects them.
|
||||
2. **Jason can't see what the agents are doing or what's waiting on
|
||||
him.**
|
||||
3. **Agents drift from what the business needs.** Nothing ties a piece of
|
||||
work to a stated goal.
|
||||
|
||||
Credential sprawl wasn't picked as a top problem. The roles work and hard
|
||||
limit C cover it.
|
||||
|
||||
## Scope and non-goals
|
||||
|
||||
### Hard limits
|
||||
|
||||
Every one of these is a gated decision, or simply not done (round 1,
|
||||
"all five"):
|
||||
- A. The stack never spends money without Jason.
|
||||
- B. It never speaks externally as Jason without his approval.
|
||||
- C. Agents never hold Jason's personal credentials. Each role gets its own.
|
||||
- D. It is not a multi-tenant SaaS in v1.
|
||||
- E. It doesn't replace Claude Code, Codex or Pi. It wraps them.
|
||||
|
||||
### Where it runs
|
||||
|
||||
Self-hosted first, on Jason's machines and homelab (round 1, "A first").
|
||||
Cloud workers aren't ruled out later.
|
||||
|
||||
### In scope for v1
|
||||
|
||||
Slice 1 of the foundation direction:
|
||||
- roles, variables and credentials per role;
|
||||
- decision records and messages addressed by role;
|
||||
- tasks in Vikunja through its API;
|
||||
- the `mosaic` CLI, then the WebUI;
|
||||
- the meta-harness.
|
||||
|
||||
### Out of scope for v1
|
||||
|
||||
To be set in round 2.
|
||||
|
||||
## Requirements
|
||||
|
||||
To be set in rounds 2 and 3. Each requirement gets a stable id
|
||||
(`REQ-<area>-<n>`). Every task the stack creates must cite one.
|
||||
|
||||
## Acceptance criteria and success measures
|
||||
|
||||
v1 is done when Jason gives one-sentence requests in the CLI and Mosaic
|
||||
Stack builds pieces of itself from them, five pieces in a row. For each
|
||||
piece:
|
||||
- only gated decisions reach Jason;
|
||||
- every step leaves a trail in the CLI and the WebUI.
|
||||
|
||||
(Round 1, answer A.)
|
||||
|
||||
## Technical considerations
|
||||
|
||||
Ratified as lead decision 44:
|
||||
- Vikunja is integrated through its API, never annexed. Mosaic Stack's
|
||||
own work uses a dedicated local instance. The installer offers an
|
||||
existing instance or the bundled one.
|
||||
- Decisions and messages live in SQLite, in append-only tables. Run
|
||||
records stay as write-once files.
|
||||
- People sign in through Pocket ID, wired in after slice 1. Agents use
|
||||
service tokens per role.
|
||||
|
||||
## Risks and open questions
|
||||
|
||||
To be set in round 3.
|
||||
|
||||
## Milestones
|
||||
|
||||
Slice 1 first, in the order on the foundation direction page. The
|
||||
milestones get set once the requirements exist.
|
||||
Reference in New Issue
Block a user