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>
Add optional second TOKEN parameter to codeberg_api_all in lib/env.sh,
defaulting to $CODEBERG_TOKEN. Pass $REVIEW_BOT_TOKEN at the dismiss
block in review-pr.sh so reviews are fetched as the review bot account.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Look up the backlog label ID via the Gitea labels API (with fallback to
1300815) and replace '{"labels":["backlog"]}' with the integer ID form
at both call sites (cleanup() line 135 and idle_timeout handler line 713).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
phase-handler.sh does not source agent-session.sh directly — dev-agent.sh
sources agent-session.sh first, then sources phase-handler.sh. Correct
the Sourced-by entry to: dev-agent.sh, gardener-agent.sh.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Look up backlog label ID via Codeberg API at the start of the PHASE:failed
branch and replace '{"labels":["backlog"]}' at lines 547 and 628 with
the numeric ID, matching the pattern already used in gardener.
python3 is used directly by dev/dev-poll.sh (JSON CI-fix tracker),
lib/load-project.sh (TOML parsing via tomllib), and gardener/gardener-poll.sh
(recipe-matching engine). Add it to the dependency list and rephrase the
runtime constraint to reflect what is actually true.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
BusyBox grep (Alpine CI) does not treat \( as a literal paren in -E mode,
causing inject_formula to appear undefined even though it is defined in
lib/agent-session.sh. Using [(][)] is unambiguous in both GNU grep and
BusyBox grep.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add optional 4th parameter to monitor_phase_loop for SESSION_NAME,
falling back to the $SESSION_NAME global for backwards-compatibility.
Document the full function signature in both the file header and inline comment.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Fix set -e bug: use `_merge_rc=0; do_merge ... || _merge_rc=$?` so non-zero
returns don't kill the agent before _merge_rc is captured
- Fix sentinel path: skip sentinel break for APPROVE so do_merge() always runs,
even when review-poll.sh injected the verdict first
- Fix fragile grep: match HTTP 405 alone instead of `grep -qi "not enough"` —
any 405 from the merge endpoint is a structural block (approvals, branch
protection), not a transient error
- Fix stale comment/status in PHASE:done handler: "orchestrator or Claude"
instead of "agent"
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Before posting an APPROVED formal review, fetch all prior reviews by
the review bot on this PR and dismiss any with state REQUEST_CHANGES.
This unblocks merges when branch protection has dismiss_stale_approvals
and the bot has prior REQUEST_CHANGES reviews from earlier rounds.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The APPROVE injection previously told the dev-agent to write PHASE:done
and let the orchestrator merge. Now the dev-agent merges directly, so the
injection includes the full merge + issue-close curl commands matching the
pattern already in the dev-agent.sh prompt.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- phase-handler.sh: remove do_merge(); on APPROVAL inject exact API
commands for agent to merge+close directly; PHASE:done now only
does local cleanup (tmux, worktree, labels) — merge already done
- dev-agent.sh: update PHASE_PROTOCOL_INSTRUCTIONS — Approved means
merge via API, close issue, then write PHASE:done
- dev-poll.sh: remove try_merge_or_rebase(); for approved+CI-green
orphaned PRs, spawn dev-agent (recovery mode) to merge instead
- .env.example: document new token roles (CODEBERG_TOKEN = bot for
push/PR/merge; REVIEW_BOT_TOKEN = human account for approvals)
- AGENTS.md: update token descriptions to match new roles
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Export LAST_PHASE_MTIME from monitor_phase_loop before invoking the callback
so that phase-handler.sh can compare phase file mtimes inside the awaiting_review
inner poll loop without hitting an unbound variable error under set -u.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Lost during #160 refactor. These are dev-agent specific (reference
$ISSUE, $THREAD_FILE, $LOGFILE) so they belong in the agent script,
not the shared library.
Library functions need explicit session name argument — they no longer
have closure over $SESSION_NAME from the parent script.
- agent_kill_session: add $SESSION_NAME to all 11 call sites
- agent_inject_into_session: add $SESSION_NAME to all call sites in
phase-handler.sh and gardener-agent.sh
- agent_kill_session: guard against missing arg (defensive)
Both dev-agent.sh and gardener-agent.sh call these functions but they
were never implemented during the #158 extraction. Adds:
- create_agent_session(session, workdir) — tmux + claude + wait for ready
- inject_formula(session, text) — alias for agent_inject_into_session
kill_tmux_session → agent_kill_session
inject_into_session → agent_inject_into_session
wait_for_claude_ready → agent_wait_for_claude_ready
Also restore status() function lost during #160 refactor.
Fixes dev-agent and gardener-agent crash on startup:
line 149: status: command not found
line 280: kill_tmux_session: command not found
