Commit graph

8 commits

Author SHA1 Message Date
openhands
eedb3c7045 fix: Resolve 'formula' terminology conflict between AGENTS.md and EVIDENCE-ARCHITECTURE.md (#228)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 16:50:58 +00:00
openhands
8ddfbfe492 fix: address review — reword banner, mark partial items (#227)
- Reword banner to avoid false 'not yet implemented' absolute claim
- Change document-level label from 'Planned Architecture' to 'Partially Implemented'
- Mark Protocol and User experience rows as **Partial** (upstream scripts exist but no evidence output yet)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 15:44:40 +00:00
openhands
9505f0b825 fix: Add 'Status: Planned Architecture' banner to EVIDENCE-ARCHITECTURE.md (#227)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 15:40:38 +00:00
johba
b9ba5c9250 docs: agent design principles — determinism/judgment split (#240)
Design principle for all disinto agents.

## Core idea
Split every agent into two layers:
- **Bash orchestrator (thin, deterministic):** session lifecycle, worktrees, locks, phase monitoring
- **Claude via formula (fat, judgment):** understand task, implement, handle reviews/CI/merge, adapt to novel situations

## Why
Agent scripts grow by accretion — every lesson becomes another if/else in bash. Formulas are refineable, learnable, and generalizable. Bash state machines are not.

## Includes
- Design principle with clear split criteria
- "When reviewing, ask these questions" checklist
- Current state assessment for all 5 agent types
- Risk mitigations (phase protocol as safety net)

Reviewers and planner should be aware of this principle when assessing PRs and planning work.

Co-authored-by: openhands <openhands@all-hands.dev>
Reviewed-on: https://codeberg.org/johba/disinto/pulls/240
Reviewed-by: Disinto_bot <disinto_bot@noreply.codeberg.org>
2026-03-19 09:56:37 +01:00
johba
e782119a15 docs: evidence architecture — sensing, integration, deployment gates (#207)
Captures design decisions from 2026-03-18 session with Johann.

## Key decisions
- **Evidence as integration layer**: formulas adapt external platforms (Analytics, Ponder, DigitalOcean) into structured JSON in `evidence/`; planner reads evidence, not platforms
- **Process types**: sense (holdout, user-test, measure-*) vs mutation (evolution, red-team)
- **Evidence-gated deployment**: no human "ship it" — all dimensions green = deploy
- **Resource allocation**: planner reads evidence staleness + current box load, decides what to run
- **Scope**: disinto is not a general company OS — it is finetuned for money → software → customer → knowledge → market fit

## New file
- `docs/EVIDENCE-ARCHITECTURE.md`

Co-authored-by: openhands <openhands@all-hands.dev>
Reviewed-on: https://codeberg.org/johba/disinto/pulls/207
Reviewed-by: Disinto_bot <disinto_bot@noreply.codeberg.org>
2026-03-19 07:55:21 +01:00
openhands
48683e508c fix: feat: supervisor-poll.sh and gardener-poll.sh inject human replies into needs_human dev sessions (#81)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-17 22:33:28 +00:00
openhands
275b92e8b5 fix: address review findings from issue #79 phase protocol
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-17 19:21:01 +00:00
openhands
d87b7db8f3 fix: feat: define phase-signaling protocol for persistent Claude sessions (#79)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-17 18:53:15 +00:00