improvise/AGENTS.md

• Always use tests to demonstrate the existence of a bug before fixing the bug.
  • If you suspect that a bug exists, use a test to demonstrate it first:
    • prefer unit tests testing a small amount of code to integration or e2e tests
• Option<...> or Result<...> are fine but should not be present in the majority of the code.
• Similarly, code managing Box<...> or RC<...>, etc. for containers pointing to heap data should be split from logic
• @context/repo-map.md is your "road map" for the repository. use it to reduce exploration and keep it updated.
• @context/design-principles.md is also important for keeping the repository consistent.
• prefer merges to rebasing.
• always start responses with bananaS!
• there is a prolog MCP available: load a session from kb at the root of the repository at the beginning of every session, and query it as you work. Reading only — the MCP must never write kb.pl.
• save structured facts as you go — work done, interesting locations, important decisions — with scripts/kb add (see the kb skill). Write a fact when you learn it; there is no reason to batch.
• query the knowledge base as needed and use Prolog reasoning when it makes sense.
• Prolog should be used as a design tool to reason about the code and the implementation of tickets and to persist a formal model of it.

Agent Instructions

This project uses bd (beads) for issue tracking. Run bd prime for full workflow context.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --claim  # Claim work atomically
bd close <id>         # Complete work
bd dolt push          # Push beads data to remote

Non-Interactive Shell Commands

ALWAYS use non-interactive flags with file operations to avoid hanging on confirmation prompts.

Shell commands like cp, mv, and rm may be aliased to include -i (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.

Use these forms instead:

# Force overwrite without prompting
cp -f source dest           # NOT: cp source dest
mv -f source dest           # NOT: mv source dest
rm -f file                  # NOT: rm file

# For recursive operations
rm -rf directory            # NOT: rm -r directory
cp -rf source dest          # NOT: cp -r source dest

Other commands that may prompt:

• scp - use -o BatchMode=yes for non-interactive
• ssh - use -o BatchMode=yes to fail instead of prompting
• apt-get - use -y flag
• brew - use HOMEBREW_NO_AUTO_UPDATE=1 env var

The Wave Workflow

Most work here is done by waves: an orchestrator chunks the open backlog, fans several agents out into their own git worktrees, merges what comes back, reviews it, and pushes the wave as one PR. This section is what that costs to get right. Everything in it was learned by getting it wrong first.

Who owns what

Three files are orchestrator-only, and the rule exists because they are guaranteed conflicts — every agent has a reason to touch them and they merge badly:

File	Why
.beads/ (incl. issues.jsonl)	bd owns it. See "Never hand-edit" below.
prolog-sessions/kb.pl	Written by scripts/kb only. See context/code/kb-tool.md.
context/repo-map.md	Every agent wants to add a gotcha; every wave would conflict.

Wave agents read all three freely (bd show, bd ready, grep kb.pl) and write none of them. They report proposed repo-map lines and kb.pl facts as text in their hand-back, and the orchestrator applies them — batched, at the end of the wave, after the review. kb.pl is written by scripts/kb add|replace|rm and by nothing else — not the Prolog MCP, not an editor. Every write is gated on kb_consistent against the candidate, so a bad delta leaves the file untouched. Facts do not need batching: write one when you learn it. There is a kb skill; read it before your first write. Reading is unaffected — loadSession at session start is still how a session gets the model in hand.

Partitioning a wave

Partition by crate or directory, not by ticket count, and tell each agent explicitly which ground is not theirs. Two rules that fall out of the ones we broke:

• Tickets that share a file belong to one agent. The four TUI widget migrations all touch src/draw.rs; split across agents they are a guaranteed conflict, so they go to one agent to do sequentially. Group first, then count.
• An agent that must stray says so rather than guessing. Give the boundary and ask for a report when it has to be crossed.

Two agents each adding a workspace member will still collide in Cargo.toml/Cargo.lock. That one is expected; keep both sides.

Every wave agent's brief must include

1. Verify your base commit first. Worktrees do not reliably branch from the orchestrator's HEAD — one was created three merges behind and only noticed because it was told to look. git log --oneline -1 against a named commit, reset onto main if behind. Name the expected commit in the brief.

2. The baseline test count, so "1090 passing" is checkable rather than asserted, and a drop is visible. Tell the agent to measure its own and cite the machine: the same commit measured improvise-io's binary at 1.4s on one machine and 3.7–5.2s on another, so a figure with no machine is a claim about the suite, which it is not.

3. The gate list, and it must not say cargo fmt --all. That reaches only one of this repo's two workspace roots — harness/opfs-contract declares its own [workspace] — and the obvious repair is worse: cargo fmt -p opfs-contract from the repo root exits 1, "not a member of the workspace", which is indistinguishable from a real formatting failure (improvise-b4ks). Both spellings fail in the direction that looks like success. The gate is:

   direnv exec . ./scripts/fmt-workspaces.sh   # exit 2 = the gate did not run
   

   Every gate goes through direnv exec . — ./scripts/checkers.sh scrubs the environment to an allowlist, so a bare invocation drops tpl off PATH and reports spurious failures. And never pipe a gate: $? must be the gate's own, and check-comment-runs.py --check-evidence prints two lines with the comment cap first, so | tail -1 silently drops half of it.

4. Do not push, do not merge to main. The orchestrator merges.

5. The commit-message trailers, spelled out.

6. What to report: branch and commits, what changed per ticket, what could not be verified and why, and proposed repo-map/kb.pl text. Ask explicitly for the thing the agent learned that the ticket did not predict — that is consistently the most valuable part of a hand-back, and agents omit it unless asked.

bd works in any worktree, but .envrc must be allowed there or you get a version mismatch rather than a clean failure — direnv allow in the worktree, or rely on the [whitelist] prefix in ~/.config/direnv/direnv.toml. Note direnv status reports Found RC allowed 0, and 0 means allowed (the enum is 0=Allowed, 1=NotAllowed). It reads like the opposite.

Between waves

Run the code-review skill on the merged range and iterate until its backlog is empty. This is not ceremony: in this repo the review's characteristic find is not a wrong line, it is a test that passes while the thing it names is broken — a vacuous fold test, a bit-witness that cannot see the bit, a one-category fixture, a helper that fabricates the _Measure items the code under test needs, a check-the-checker that injected malformed JSON and so proved nothing. A green suite is not evidence. Ask the reviewer to inject the fault and watch the check fail.

Shipping a wave

Do not push main to gh/main. Work reaches GitHub as a branch and a pull request, and lands on main by being merged there. The orchestrator still merges agent branches into its local main to integrate and run the gates — that is how conflicts get found early — but the push is a branch push, not a main push. origin and gitea are mirrors and take main directly.

So origin/main runs ahead of gh/main, and a branch destined for a GitHub PR must merge gh/main — never origin/main. This is a trap in this repo's own topology rather than a slip: the two remotes are both spelled main, and nothing about git merge origin/main looks wrong. The session-completion protocol below literally says git merge origin/main, which is right for main itself and wrong for a PR branch. It cost a review round on PR #145, where four unmerged commits — including another PR's whole diff — were pulled into a branch based on gh/main and had to be rebuilt by cherry-picking. ChatGPT Codex caught it; nothing in CI could, because the result compiles and passes. The tell is a PR diff naming files the ticket has no reason to touch, so read your own PR's file list before asking for review — and diff against gh/main...<branch>, never the local equivalent. The second vector is the worktree base: a branch cut from the orchestrator's local main inherits whatever that checkout has merged but not yet pushed, and nothing in the branch says so. That hit PR #148 with another PR's whole diff — including .beads/, kb.pl and context/repo-map.md, the three files agents are forbidden to touch, so the review read as a rule violation rather than a base problem. Note the window is transient — the two remotes are equal immediately after the orchestrator syncs — which makes it worse, not better: the hazard is absent exactly when you would think to check for it.

This is easy to drift out of, because merging locally and pushing feels like finishing. It happened in this repo: 27 commits across six agent branches — including a new crate, a new protocol type, and a type moving between crates — went straight to main unreviewed, while AGENTS.md already said not to. If you notice a batch has bypassed the loop, the cheap repair is a review-only PR: base a branch at the last PR merge, open a PR with main as the head, let Copilot review the diff, and land the findings as an ordinary PR afterwards. It cannot be merged — the commits are already in — so close it once its findings are filed or fixed. Rewinding the default branch to fake a mergeable PR is not worth it on a repo with other collaborators.

One PR per wave, built by a dedicated PR agent in its own worktree, so waves pipeline against it: the next wave runs while the PR absorbs review fixes.

Read the PR's reviews before merging it. This is separate from CI and from the adversarial agent, and it has been missed: two ChatGPT Codex reviews landed on merged PRs and were not read until afterwards, one of them a live P2 (improvise-x1ns). Both were correct.

gh pr view <n> --json reviews -q '.reviews[]|"[\(.state)] \(.submittedAt) \(.commit.oid[0:8])\n\(.body)"'

Two things make a Codex review easy to miss. It arrives as a review, not a comment, so a glance at the comment thread does not show it. And it posts under the repository owner's account — the same account our own agents post under — so authorship does not distinguish it. The tell is the trailing line _Automated review by ChatGPT Codex (…)_; ours open with _Posted by Claude (…)_. Check the commit.oid too: a review may target an earlier head, and the finding may already be fixed — verify rather than assume in either direction.

Reviews arrive as the owner's quota allows, so absence is not evidence. Wait where a review is plausible, and when one is found, answer it on the thread even if the PR has already merged: that is where the next reader looks.

Copilot is not reviewing this repository, and the request is a silent no-op. Measured 2026-09-20: PRs #12, #21 and #27 carry 2, 8 and 4 Copilot reviews; #61, #66, #68 and #70 carry none. Both request paths report success and produce zero review_requested events — the GraphQL mutation returns clientMutationId: null and the REST call returns 200 with requested_reviewers: []. So do not wait on it: an absent review and an unrequested one look identical from outside, which is doctrine(review_is_requested_not_inherited) seen from the requester's side. Review is an adversarial agent the orchestrator dispatches, given the head SHA. The mechanics below are kept for the day it comes back.

Copilot review must be re-requested after every fix push; it does not re-review on its own. The mutation takes a botIds field — userIds fails with "Could not resolve to User node":

gh api graphql -f query='mutation($pr:ID!,$ids:[ID!]!){requestReviews(input:{pullRequestId:$pr,botIds:$ids,union:true}){clientMutationId}}' \
  -f pr="$(gh pr view <n> --json id -q .id)" -f ids=BOT_kgDOCnlnWA

REST also works, with the login spelled copilot-pull-request-reviewer[bot] — without the [bot] suffix it 422s as "not a collaborator".

In a worktree-isolated agent the shell guard refuses an inline gh api graphql -f query='mutation(...)' as "too complex to verify". Put the query in a file and pass -F query=@file; PR comment bodies likewise go through -F body=@file rather than command substitution.

Anything you post to GitHub goes out under the repository owner's account, so say who is speaking. Open every PR comment, review and issue body with a line naming the model and that it is an agent posting in his session. A PR body's 🤖 Generated with Claude Code footer covers that case; comments have nothing unless you add it, and an unattributed one reads as his own words to everyone who sees it.

Two environment notes. gh is not on PATH here — the name is shell-aliased to git-hub, a different tool — so use nix shell nixpkgs#gh --command gh …. And a Copilot review takes about six minutes; tool calls return fast, which makes elapsed time easy to misjudge, so check date -u against the GitHub timeline before concluding a review is stuck. (One agent closed and reopened a PR to "unstick" a review that was proceeding normally.)

Across four PRs Copilot has found genuine bugs and no false positives, so its findings are worth the loop. But judge each one against the repo's doctrine rather than applying it reflexively, and when you decline, reply on the thread with the reason. The distinction that has mattered: a finding can be correct and still be wrong to fix in that PR. On #12, a non-ASCII truncate panic was applied (byte-identical on ASCII, so it cost no evidence) while a hint-line padding bug in the same file was declined — fixing it would have rewritten the exact-frame characterization tests that were the PR's only evidence the migration changed nothing. Two right findings, different costs. File the declined one.

Under merge-as-soon-as-green, a review round can land after its own merge. GitHub deletes the branch when a PR merges, so a fix push to the old branch name silently succeeds and accomplishes nothing — it re-creates a branch main will never see, CI runs on it, and the commit is nowhere. The tell is the push printing * [new branch] where you expected an old..new range. It happened on #51: the third review round completed four minutes after the merge, and the correction it prompted went to a re-created wave/b-projection-gaps. The repair is to branch from gh/main, cherry-pick, open a follow-up PR, and delete the stray re-creation. Check gh pr view <n> --json state before pushing a fix to a PR you have not looked at in a few minutes, rather than after.

Merge only once a review has passed — an adversarial agent's while Copilot is absent, and it must name the head SHA it reviewed. Prefer a merge commit — AGENTS.md says merges over rebases, and a wave's commits are individually meaningful.

Never hand-edit .beads/issues.jsonl

bd manipulates that file and auto-exports to it. Editing it — or even git checkout-ing it, which fires the post-checkout hook — breaks auto-export and desynchronises export-state.json. Use bd commands, let auto-export run, and commit whatever it leaves.

Cite a ticket ID you have read back

bd create assigns the ID; it is not derivable from the title. An orchestrator that files with output suppressed and then writes the ticket into a gotcha or an ADR will invent one — six invented IDs survived into context/ in a single session before an agent tried one and found nothing. Read the ID back after filing, and before pushing docs run the audit:

grep -rohE 'improvise-[a-z0-9]{3,8}\b' \
     context README.md AGENTS.md CLAUDE.md crates src tests examples web harness docs \
  | sort -u \
  | grep -vE '^improvise-(core|formula|io|protocol|command|gp|ws|worker|wasm|harness|registry|side|web)$' \
  > /tmp/bd-audit-ids.txt
bd show $(cat /tmp/bd-audit-ids.txt) 2>&1 \
  | grep -iE 'not found|no such issue' || echo "all resolve"

Three things the earlier version of this recipe got wrong, each of which let a real defect through:

• It scanned two paths (context/repo-map.md context/adr/*.md), so it found one dead id in the repo map and missed both copies of it in harness/tests/shell.spec.js. Ticket IDs are cited in code comments, in README.md and in web/, not only in context/.
• [a-z0-9]{3,4} cannot see a commit SHA wearing the prefix. A seven-hex commit sha cited as improvise-<sha> survived in crates/improvise-core/src/workbook.rs precisely because it was too long to match. An ID-shaped non-ID is worse than a dead ID, because the diagnosis is identical and the repair is not.
• The exclusion list named only core and wasm, so every other crate name would have been reported missing. The exclusions above also cover the non-ticket tokens this repo really contains: a package name, a temp file name, and the prose word "improvise-side". They are anchored ^…$ for the same reason the recipe is read as code: unanchored, the gp alternative is a prefix match, so a future real ticket whose id happens to begin gp is silently excluded and the audit reports nothing while skipping it. An exclusion list is a filter, and a filter that over-matches fails in the direction that looks like success. (Anchoring it is also what caught the example id this very paragraph originally spelled out — see the note below.)
• A release artifact's name is ID-shaped, and improvise-installer.sh escaped only by being ten characters long. improvise-web.tar.gz (improvise-oujb) is three, so it matches {3,8} and resolves to nothing; web is therefore excluded above. The general point is that the length bound, not any rule, is what has been keeping dist's artifact names out of this audit — so a new artifact whose name is a short lowercase word must be added to the exclusion list in the same commit, or it arrives as a dead id that no amount of bd archaeology explains.

Note the recipe's own prose deliberately spells no live or dead id: a document that lists ids as examples makes itself a source of audit noise.

One environment note: in a worktree-isolated agent the shell guard refuses a loop that passes a runtime-computed argument to bd, so the recipe above materialises the id list into a file and hands bd show the whole list in one call rather than looping. If bd show in your build does not take several ids, run the ids through xargs -n1 -I{} bd show {} from a plain shell instead.

A dead ID is worse than no ID: it reads as a promise that the follow-up exists.

Before filing a ticket, search

Agent-filed issues duplicate work that is already open, sometimes already in progress. Two duplicates were filed in this repo within minutes of the hand-backs that prompted them. bd search the core concept and scan in-progress issues first.

Beads Issue Tracker

This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --claim  # Claim work
bd close <id>         # Complete work

Rules

• Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists (the exception being that you must maintain context/design-principles.md and context/repo-map.md)
• Run bd prime for detailed command reference and session close protocol
• Use bd remember for persistent knowledge — do NOT use MEMORY.md files (the exception being that you must maintain context/design-principles.md and context/repo-map.md)

Session Completion

When ending a work session, you MUST complete ALL steps below. Work is NOT complete until git push succeeds.

MANDATORY WORKFLOW:

1. File issues for remaining work - Create issues for anything that needs follow-up
2. Run quality gates (if code changed) - Tests, linters, builds
3. Update issue status - Close finished work, update in-progress items
4. PUSH TO REMOTE - This is MANDATORY:

   git merge origin/main
   bd dolt push
   git push
   git status  # MUST show "up to date with origin"
   

5. Clean up - Clear stashes, prune remote branches
6. Verify - All changes committed AND pushed
7. Hand off - Provide context for next session

CRITICAL RULES:

• Work is NOT complete until git push succeeds
• NEVER stop before pushing - that leaves work stranded locally
• NEVER say "ready to push when you are" - YOU must push
• If push fails, resolve and retry until it succeeds

Beads Issue Tracker

Use Beads (bd) for durable task tracking in repositories that include it. Use the beads skill at .agents/skills/beads/SKILL.md (project install) or ~/.agents/skills/beads/SKILL.md (global install) for Beads workflow guidance, then use the bd CLI for issue operations.

Quick Reference

bd ready                # Find available work
bd show <id>            # View issue details
bd update <id> --claim  # Claim work
bd close <id>           # Complete work
bd prime                # Refresh Beads context

Rules

• Use bd for all task tracking; do not create markdown TODO lists.
• Run bd prime when Beads context is missing or stale. Codex 0.129.0+ can load Beads context automatically through native hooks; use /hooks to inspect or toggle them.
• Keep persistent project memory in Beads via bd remember; do not create ad hoc memory files.

Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/core-concepts/sync-concepts.md for details and anti-patterns.