Merge origin/main into task/14: CLAUDE.md became the AGENTS.md pointer

Rename-vs-edit conflict: task 13 (landed) moved the workflow brief to
AGENTS.md leaving CLAUDE.md as a pointer, while this branch had edited
the brief's work-launch section in place. Resolution: CLAUDE.md keeps
main's pointer form; this branch's documentation of the
branch-from-origin behaviour moved verbatim into AGENTS.md where that
text now lives. agents.py and the rest auto-merged; 103 tests green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
istos
2026-07-30 07:46:26 +02:00
co-authored by Claude Fable 5
32 changed files with 1672 additions and 531 deletions
+19 -1
View File
@@ -15,13 +15,31 @@ BOARD_AGENT_ADAPTER=claude
BOARD_CLAUDE_BIN=claude
BOARD_OPENCODE_BIN=opencode
# The model headless agents run on — an opaque vendor-native name the
# adapter passes through untranslated (claude: a model name or alias for
# --model; opencode: the "provider/model-id" config key). Empty = inherit
# the vendor's own default, i.e. whatever the CLI on this machine would
# pick anyway. The per-intent settings beat the general one for their
# intent only; _REVIEW covers both PR reviews and relevance checks. Work
# agents write code; reviews just read and judge — they can ride a
# cheaper, faster model.
BOARD_AGENT_MODEL=
BOARD_AGENT_MODEL_WORK=
BOARD_AGENT_MODEL_ACT_PR=
BOARD_AGENT_MODEL_REVIEW=
# Command prefixes headless agents may run in their worktree — the
# project's test/check commands, comma-separated, in plain neutral form
# (each adapter renders them into its vendor's permission rules; the
# git/gh grants per launch intent are built in). Headless runs have no
# human at a permission prompt, so a test runner missing from this list
# is a test the work agent cannot run.
BOARD_AGENT_COMMANDS=python3 -m unittest,python3 -m pytest
BOARD_AGENT_COMMANDS=python3 -m unittest
# What counts as a definition-of-done check (the Focus view's CHECKS
# panel) is a file, not an env var: core/checks ships a generic default,
# and a `checks` file in manager/local/ replaces it wholesale. Format
# (`<label>: <command regex>`) is documented in the default file itself.
# Where work-agent worktrees are created, relative to the repo root.
BOARD_WORKTREES=.worktrees
+19 -3
View File
@@ -15,14 +15,19 @@ An adapter is a directory with two executables:
- env in: `AGENT_PROMPT` (the full prompt), `AGENT_MODE` (the launch
intent, below), `AGENT_COMMANDS` (the project's allowed command
prefixes, below), `AGENT_CWD`, and the `BOARD_*` passthrough
(`BOARD_AGENT_ID`, `BOARD_TASK`, `BOARD_PORT`) which your event bridge
must forward with every event.
prefixes, below), `AGENT_MODEL` (optional, below), `AGENT_CWD`, and
the `BOARD_*` passthrough (`BOARD_AGENT_ID`, `BOARD_TASK`,
`BOARD_PORT`) which your event bridge must forward with every event.
- stdout is captured by the board as the job log. The prompts instruct the
agent to end with marker lines (`NOT READY:`, `RELEVANCE REVIEW:`,
`PR REVIEW:`, `ADDRESSED:`) — the board parses them from this output, so
the agent's final text must reach stdout.
- exit 0 = completed; anything else = failed.
- The workflow brief the prompts point agents at is `AGENTS.md` at the
repo root (`CLAUDE.md` beside it is only a compatibility pointer).
Vendors that read `AGENTS.md` from the working directory's tree
natively — opencode does, as does current Claude Code — pick it up in
every worktree with no adapter work; `run` never needs to inject it.
### Launch intents (`AGENT_MODE`)
@@ -57,6 +62,17 @@ prefix-pattern based, so the translation is mechanical:
"allow"}}` in a generated config, wildcard rules, last match wins
(`opencode/permission_config.py`)
### The model (`AGENT_MODEL`) — optional
Absent = the vendor's own default: launch without any model argument and
let your CLI resolve it however it normally would. When set, it is an
opaque vendor-native model name — a claude alias, an opencode
`provider/model-id` — that core never validates or interprets; pass it
through untranslated (claude → `--model "$AGENT_MODEL"`, opencode → the
generated config's `model` key). Never send your vendor an empty value:
the board only sets the variable when a model is actually configured
(`BOARD_AGENT_MODEL` and its per-intent overrides in `local/.env`).
### `wire` — wire live-session visibility into the host project
Called by `install.py` with the project root as argv[1] (plus `--dry-run`).
+93 -46
View File
@@ -25,6 +25,10 @@ from pathlib import Path
EDIT_TOOLS = {"Edit", "Write", "MultiEdit", "NotebookEdit"}
# manager/ — the same distance up from core/adapters/claude/ as from a
# local/adapters/claude/ override, so both copies resolve the same files.
MANAGER = Path(__file__).resolve().parents[3]
def _txt(value, cap=600):
return value[:cap] if isinstance(value, str) else ""
@@ -51,6 +55,56 @@ def _resp_text(resp):
return ""
def check_defs():
"""The project's definition-of-done checks: `<label>: <command regex>`
per line, local/checks replacing core/checks wholesale — the same file
the board serves to the Focus panel, read here for classification so
the two never drift. (Core's config.py mirrors this parser; the bridge
stays standalone.) Read fresh per event; must never raise."""
for base in (MANAGER / "local", MANAGER / "core"):
try:
text = (base / "checks").read_text(encoding="utf-8")
except OSError:
continue
defs = []
for line in text.splitlines():
line = line.strip()
if not line or line.startswith("#"):
continue
label, sep, pattern = line.partition(":")
label, pattern = label.strip(), pattern.strip()
if not sep or not label or not pattern:
continue
try:
defs.append((label, re.compile(pattern)))
except re.error:
continue
return defs
return []
def judge(out):
"""Generic pass/fail from a check's output — the hook payload carries
no exit status (stdout/stderr/interrupted only), so judgment rests on
the summaries test tools print: counted results ('3 passed',
'1 failed', '2 errors'), lint-style broken totals, and OK/FAILED
verdict lines. Returns (ok, summary bit); (None, '') when the output
says nothing recognizable either way."""
failed = re.search(r"\b\d+ (?:failed|errors?)\b", out)
passed = re.search(r"\b\d+ passed\b", out)
if failed:
return False, failed.group(0) + (f", {passed.group(0)}" if passed else "")
if passed:
return True, passed.group(0)
broken = re.search(r"\b(\d+) broken\b", out)
if broken:
return broken.group(1) == "0", broken.group(0)
verdict = re.search(r"^(OK|FAILED)\b.*", out, re.M)
if verdict:
return verdict.group(1) == "OK", verdict.group(0)[:60]
return None, ""
def classify(hook, tool, tool_input, resp):
if hook == "SessionStart":
return {"kind": "session", "summary": "session started"}
@@ -88,31 +142,19 @@ def classify(hook, tool, tool_input, resp):
cmd = _txt(tool_input.get("command"), 240)
running = hook == "PreToolUse"
out = "" if running else _resp_text(resp)[:1200]
kind, ok = "command", None
if re.search(r"\bpytest\b", cmd):
kind = "test"
elif "lint-imports" in cmd or re.search(r"type-check|vue-tsc|\bnpm (run )?test\b|\bvitest\b", cmd):
kind = "check"
elif re.match(r"\s*git (commit|add|push|checkout|switch|merge|worktree)", cmd):
kind, ok, label = "command", None, None
for name, pattern in check_defs():
if pattern.search(cmd):
kind, label = "check", name
break
if kind == "command" and re.match(r"\s*git (commit|add|push|checkout|switch|merge|worktree)", cmd):
kind = "git"
if running:
summary = f"running: {cmd[:90]}"
elif kind == "test":
passed = re.search(r"(\d+) passed", out)
failed = re.search(r"(\d+) failed", out) or re.search(r"(\d+) error", out)
if failed:
ok = False
summary = f"pytest — {failed.group(0)}" + (f", {passed.group(0)}" if passed else "")
elif passed:
ok = True
summary = f"pytest — {passed.group(0)}"
else:
summary = f"ran: {cmd[:90]}"
elif kind == "check":
if "broken" in out:
ok = not re.search(r"[1-9]\d* broken", out)
summary = f"ran: {cmd[:90]}"
ok, bits = judge(out)
summary = f"{label} — {bits}" if bits else f"ran: {cmd[:90]}"
elif kind == "git":
m = re.search(r"""-m ["']([^"']{1,90})""", cmd)
summary = f"git: {m.group(1) if m else cmd[:80]}"
@@ -129,7 +171,7 @@ def board_port():
if port:
return port
try:
env_file = Path(__file__).resolve().parents[3] / "local" / ".env"
env_file = MANAGER / "local" / ".env"
for line in env_file.read_text().splitlines():
key, _, value = line.strip().partition("=")
if key.strip() == "BOARD_PORT":
@@ -139,31 +181,36 @@ def board_port():
return port or "26071"
try:
payload = json.load(sys.stdin)
except Exception:
payload = {}
def main():
try:
payload = json.load(sys.stdin)
except Exception:
payload = {}
tool_input = payload.get("tool_input")
event = {
"v": 1,
"session": payload.get("session_id") or "unknown",
"agent": os.environ.get("BOARD_AGENT_ID"),
"task": os.environ.get("BOARD_TASK"),
**classify(payload.get("hook_event_name") or "?",
payload.get("tool_name") or "",
tool_input if isinstance(tool_input, dict) else {},
payload.get("tool_response")),
}
tool_input = payload.get("tool_input")
event = {
"v": 1,
"session": payload.get("session_id") or "unknown",
"agent": os.environ.get("BOARD_AGENT_ID"),
"task": os.environ.get("BOARD_TASK"),
**classify(payload.get("hook_event_name") or "?",
payload.get("tool_name") or "",
tool_input if isinstance(tool_input, dict) else {},
payload.get("tool_response")),
}
try:
request = urllib.request.Request(
f"http://127.0.0.1:{board_port()}/api/events",
data=json.dumps(event).encode("utf-8"),
headers={"Content-Type": "application/json"},
)
urllib.request.urlopen(request, timeout=1).read()
except Exception:
pass
try:
request = urllib.request.Request(
f"http://127.0.0.1:{board_port()}/api/events",
data=json.dumps(event).encode("utf-8"),
headers={"Content-Type": "application/json"},
)
urllib.request.urlopen(request, timeout=1).read()
except Exception:
pass
sys.exit(0)
sys.exit(0)
if __name__ == "__main__":
main()
+11
View File
@@ -7,6 +7,9 @@
# (see core/adapters/README.md)
# AGENT_COMMANDS comma-separated neutral command prefixes the
# project lets agents run (tests/checks)
# AGENT_MODEL optional; a claude model name/alias passed
# through as --model. Absent = the CLI's own
# resolution (user settings), untouched.
# AGENT_CWD working directory (already set as cwd by the board)
# BOARD_* passthrough for the event bridge
# stdout: captured by the board as the job log; the closing report's
@@ -25,12 +28,20 @@ BIN="${BOARD_CLAUDE_BIN:-claude}"
MODE="${AGENT_MODE:-work}"
SETTINGS="$(python3 "$HERE/hook_settings.py" "$MODE")"
# The ${arr[@]+...} expansion keeps set -u happy on bash 3.2 when unset.
MODEL_ARGS=()
if [ -n "${AGENT_MODEL:-}" ]; then
MODEL_ARGS=(--model "$AGENT_MODEL")
fi
if [ "$MODE" = "review" ]; then
exec "$BIN" -p "$AGENT_PROMPT" --settings "$SETTINGS" \
${MODEL_ARGS[@]+"${MODEL_ARGS[@]}"} \
--permission-mode default \
--disallowedTools Edit Write NotebookEdit
else
# work and act-pr both mutate the worktree; the allowlist differs.
exec "$BIN" -p "$AGENT_PROMPT" --settings "$SETTINGS" \
${MODEL_ARGS[@]+"${MODEL_ARGS[@]}"} \
--permission-mode acceptEdits
fi
@@ -1,6 +1,6 @@
#!/usr/bin/env python3
"""Print the opencode config JSON for one headless launch: the permission
rules for the launch's intent.
rules for the launch's intent, plus the model when the board configured one.
Usage: permission_config.py [work|act-pr|review]
@@ -21,6 +21,10 @@ and never a blanket allow: the worktree is isolated, the shell is not.
The project's test/check commands arrive in AGENT_COMMANDS as comma-
separated neutral command prefixes (set BOARD_AGENT_COMMANDS in
local/.env); here each becomes "<prefix>" and "<prefix> *" allow rules.
AGENT_MODEL, when set, becomes the config's top-level "model" key —
opencode's "provider/model-id" form (opencode.ai/docs/config), passed
through untranslated. Absent = no key, opencode's own resolution applies.
"""
import json
import os
@@ -56,17 +60,21 @@ def bash_rules(mode: str, commands: list[str]) -> dict:
return rules
def build_config(mode: str, commands: list[str]) -> dict:
return {
def build_config(mode: str, commands: list[str], model: str = "") -> dict:
config = {
"$schema": "https://opencode.ai/config.json",
"permission": {
"edit": "deny" if mode == "review" else "allow",
"bash": bash_rules(mode, commands),
},
}
if model:
config["model"] = model
return config
if __name__ == "__main__":
mode = sys.argv[1] if len(sys.argv) > 1 else "work"
commands = split_commands(os.environ.get("AGENT_COMMANDS", ""))
print(json.dumps(build_config(mode, commands)))
model = os.environ.get("AGENT_MODEL", "").strip()
print(json.dumps(build_config(mode, commands, model)))
+3
View File
@@ -7,6 +7,9 @@
# (see core/adapters/README.md)
# AGENT_COMMANDS comma-separated neutral command prefixes the
# project lets agents run (tests/checks)
# AGENT_MODEL optional; opencode's "provider/model-id" form,
# set as the generated config's model key.
# Absent = opencode's own resolution, untouched.
# AGENT_CWD working directory (already set as cwd by the board)
# BOARD_* passthrough for the event bridge
# stdout: captured by the board as the job log; `opencode run` prints
+24 -12
View File
@@ -81,6 +81,9 @@ def _agent_public(record: dict) -> dict:
("id", "task", "branch", "worktree", "status", "rc", "started", "session")}
public["mode"] = record.get("mode", "work")
public["name"] = record.get("name")
# The model the launch was actually given; None = inherited the
# vendor's own default. Honesty for the Sessions/Focus views.
public["model"] = record.get("model")
return public
@@ -111,9 +114,11 @@ def _launch(mode: str, prompt: str, cwd: Path, agent_id: str, filename: str, log
The adapter contract: `run` gets AGENT_PROMPT, AGENT_MODE (the intent:
work = mutate and commit, act-pr = work + push, review = read-only +
post PR verdicts) and AGENT_COMMANDS (the project's runnable command
prefixes) plus the BOARD_* passthrough for its event bridge; its
stdout is the job log; exit 0 = completed.
post PR verdicts), AGENT_COMMANDS (the project's runnable command
prefixes) and AGENT_MODEL (the configured model, when there is one)
plus the BOARD_* passthrough for its event bridge; its stdout is the
job log; exit 0 = completed. Returns (proc, log_file, model) with
model = '' when the launch inherits the vendor default.
"""
adapter = config.adapter_dir()
if adapter is None:
@@ -130,6 +135,13 @@ def _launch(mode: str, prompt: str, cwd: Path, agent_id: str, filename: str, log
"BOARD_TASK": filename,
"BOARD_PORT": str(state.serve_port),
})
model = config.agent_model(mode)
if model:
env["AGENT_MODEL"] = model
else:
# Inherit = the variable is simply absent. Popping also stops a
# stray AGENT_MODEL in the board's own environment leaking through.
env.pop("AGENT_MODEL", None)
log_file = log_path.open("wb")
try:
proc = subprocess.Popen(
@@ -138,7 +150,7 @@ def _launch(mode: str, prompt: str, cwd: Path, agent_id: str, filename: str, log
except OSError as exc:
log_file.close()
raise ValueError(f"could not launch adapter {adapter}: {exc}")
return proc, log_file
return proc, log_file, model
def _fresh_branch_point() -> tuple[str | None, str | None]:
@@ -229,7 +241,7 @@ def start_agent(filename: str, stage: str) -> dict:
prompt = config.prompt("work.md").format(
branch=branch, filename=filename, body=task["body"])
proc, log_file = _launch("work", prompt, worktree, agent_id, filename, log_path)
proc, log_file, model = _launch("work", prompt, worktree, agent_id, filename, log_path)
name = _pick_name(stem)
record = {
@@ -237,7 +249,7 @@ def start_agent(filename: str, stage: str) -> dict:
"worktree": str(worktree), "base": base, "status": "running",
"rc": None, "started": time.time(), "session": None,
"log": str(log_path), "proc": proc, "origin": stage, "mode": "work",
"name": name,
"name": name, "model": model or None,
}
with state.LOCK:
state.AGENTS[agent_id] = record
@@ -266,14 +278,14 @@ def start_review(filename: str, stage: str) -> dict:
prompt = config.prompt("review.md").format(
stage=stage, filename=filename, body=task["body"])
proc, log_file = _launch("review", prompt, config.REPO, agent_id, filename, log_path)
proc, log_file, model = _launch("review", prompt, config.REPO, agent_id, filename, log_path)
name = _pick_name(filename)
record = {
"id": agent_id, "task": filename, "branch": None, "worktree": None,
"base": None, "status": "running", "rc": None, "started": time.time(),
"session": None, "log": str(log_path), "proc": proc,
"origin": stage, "mode": "review", "name": name,
"origin": stage, "mode": "review", "name": name, "model": model or None,
}
with state.LOCK:
state.AGENTS[agent_id] = record
@@ -399,13 +411,13 @@ def start_pr_review(filename: str, stage: str) -> dict:
prompt = config.prompt("review-pr.md").format(
filename=filename, pr=task["pr"], branch=branch, body=task["body"])
proc, log_file = _launch("review", prompt, config.REPO, agent_id, filename, log_path)
proc, log_file, model = _launch("review", prompt, config.REPO, agent_id, filename, log_path)
record = {
"id": agent_id, "task": filename, "branch": branch, "worktree": None,
"base": None, "status": "running", "rc": None, "started": time.time(),
"session": None, "log": str(log_path), "proc": proc,
"origin": stage, "mode": "review", "name": name,
"origin": stage, "mode": "review", "name": name, "model": model or None,
}
with state.LOCK:
state.AGENTS[agent_id] = record
@@ -450,14 +462,14 @@ def start_pr_fix(filename: str, stage: str) -> dict:
prompt = config.prompt("act-pr.md").format(
filename=filename, branch=branch, pr=task["pr"], body=task["body"])
# act-pr is the one intent allowed to push: the PR must update.
proc, log_file = _launch("act-pr", prompt, worktree, agent_id, filename, log_path)
proc, log_file, model = _launch("act-pr", prompt, worktree, agent_id, filename, log_path)
record = {
"id": agent_id, "task": filename, "branch": branch,
"worktree": str(worktree), "base": None, "status": "running",
"rc": None, "started": time.time(), "session": None,
"log": str(log_path), "proc": proc, "origin": stage, "mode": "work",
"name": name,
"name": name, "model": model or None,
}
with state.LOCK:
state.AGENTS[agent_id] = record
+24 -12
View File
@@ -20,7 +20,7 @@
--accent:#56c2d8; --calm:#a6c96f; --alarm:#e08a63; --idle:#5d757b;
--on-accent:#0a161b; --on-calm:#141a10;
--shadow:0 10px 24px -18px rgba(0,0,0,.9);
--pad:14px; --gap:10px; --radius:10px; --col:296px;
--pad:14px; --gap:10px; --radius:10px; --col:296px; --col-min:240px;
--sans:'IBM Plex Sans',system-ui,sans-serif;
--mono:'IBM Plex Mono',ui-monospace,SFMono-Regular,Menlo,monospace;
}
@@ -91,7 +91,7 @@
.view.on{display:flex}
#view-board{flex-direction:column}
#board{flex:1;display:flex;gap:var(--gap);align-items:stretch;padding:14px 18px;overflow-x:auto;min-height:0}
.kcol{flex:0 0 var(--col);width:var(--col);display:flex;flex-direction:column;gap:8px;min-height:0}
.kcol{flex:1 1 0;min-width:var(--col-min);max-width:var(--col);display:flex;flex-direction:column;gap:8px;min-height:0}
.kcol > h2{
margin:0;display:flex;align-items:center;gap:8px;padding:0 4px 2px;
font-size:11px;font-weight:600;letter-spacing:.09em;text-transform:uppercase;color:var(--muted);
@@ -1295,17 +1295,20 @@ function renderFlight() {
}
const events = S.events[sid] || [];
const files = new Set(events.filter(e => e.file && e.kind === 'edit').map(e => e.file));
const tests = events.filter(e => e.kind === 'test').length;
const checks = events.filter(e => e.kind === 'test' || e.kind === 'check').length;
const agent = agentFor(sid);
const stopBtn = agent && agent.status === 'running'
? `<button id="stopagent" class="stopbtn" data-aid="${esc(agent.id)}">Hold</button>` : '';
const branch = agent && agent.branch ? ` · <span class="mono">${esc(agent.branch)}</span>` : '';
// Honesty about what the run actually rode: the configured model, or
// the vendor default it inherited. Interactive sessions say nothing.
const model = agent ? ` · <span class="mono">${agent.model ? esc(agent.model) : 'model inherited'}</span>` : '';
$('#fsession').innerHTML =
`<div><div class="s-title">${esc((meta.label || sid).split(' · ')[0])}` +
`<span class="sid">${esc(sid.slice(0, 8))}</span></div>` +
`<div class="s-line">${meta.task ? 'on ' + esc(meta.task) + ' · ' : ''}` +
`started ${fmtShort(meta.started)} · ${meta.count || 0} events · ` +
`${files.size} files edited · ${tests} test runs${branch}</div></div>` +
`${files.size} files edited · ${checks} check runs${branch}${model}</div></div>` +
stopBtn + spark(events, meta);
const stop = $('#stopagent');
if (stop) stop.addEventListener('click', () => stopAgent(stop.dataset.aid));
@@ -1490,6 +1493,7 @@ function renderFocus() {
refBits.push(task.number ? '#' + esc(task.number) : esc(task.file));
refBits.push(`<span class="acc">${esc((meta.label || '').split(' · ')[0])}</span>`);
if (agent && agent.branch) refBits.push('worktree ' + esc(agent.branch));
if (agent) refBits.push(agent.model ? esc(agent.model) : 'model inherited');
refBits.push(esc(task.stage) + '/' + esc(task.file));
} else {
refBits.push(esc(sid.slice(0, 8)), 'no task attached');
@@ -1504,19 +1508,27 @@ function renderFocus() {
steps + act + `</div>`;
const rev = [...events].reverse();
const lastTest = rev.find(e => e.kind === 'test' && !e.running);
const lastLint = rev.find(e => e.kind === 'check' && (e.cmd || '').includes('lint-imports'));
const lastFront = rev.find(e => e.kind === 'check' && /type-check|vitest|npm/.test(e.cmd || ''));
const checkRow = (name, ev) => {
if (!ev) return `<div class="check-row none"><span class="glyph">—</span><span class="name">${name}</span><span class="state">not run</span></div>`;
if (!ev) return `<div class="check-row none"><span class="glyph">—</span><span class="name">${esc(name)}</span><span class="state">not run</span></div>`;
const cls = ev.ok === false ? 'fail' : ev.ok === true ? 'pass' : 'none';
const glyph = ev.ok === false ? '✕' : ev.ok === true ? '✓' : '·';
const state = esc(ev.summary.replace(/^pytest — /, '').replace(/^ran: /, '')) + ' · ' + fmtShort(ev.ts);
return `<div class="check-row ${cls}"><span class="glyph">${glyph}</span><span class="name">${name}</span><span class="state">${state}</span></div>`;
const text = ev.summary.startsWith(name + ' — ')
? ev.summary.slice(name.length + 3) : ev.summary.replace(/^ran: /, '');
const state = esc(text) + ' · ' + fmtShort(ev.ts);
return `<div class="check-row ${cls}"><span class="glyph">${glyph}</span><span class="name">${esc(name)}</span><span class="state">${state}</span></div>`;
};
// One row per project-defined check — labels and command patterns come
// from the served checks definition (local/checks over core/checks),
// the same file the adapter classifies against.
const checkRows = (S.state?.checks || []).map(c => {
let re = null;
try { re = new RegExp(c.pattern); } catch { /* skip unparseable */ }
const ev = re && rev.find(e => !e.running && e.cmd && re.test(e.cmd));
return checkRow(c.label, ev);
}).join('');
const checksPanel = `<div class="panel"><div class="phead"><span class="label">Checks</span></div>` +
checkRow('pytest', lastTest) + checkRow('lint-imports', lastLint) +
checkRow('frontend', lastFront) + `</div>`;
(checkRows || `<div class="check-row none"><span class="glyph">—</span><span class="name">no checks defined</span><span class="state"></span></div>`) +
`</div>`;
let fileRows = '', fileHead = '';
const diff = agent && S.diffCache[agent.id];
+1 -1
View File
@@ -6,7 +6,7 @@
The manager sits cleanly on top of the tasks/ directory: it reads and moves
task files, but the tasks work as a plain folder kanban without it. See
../CLAUDE.md for the workflow and the module map:
../AGENTS.md for the workflow and the module map:
config.py paths, stages, launch configuration
state.py shared registries, event persistence, SSE fan-out
+18
View File
@@ -0,0 +1,18 @@
# Definition-of-done checks — the project half of the Focus view's
# CHECKS panel. One check per line:
#
# <label>: <regex matched against the commands agents run>
#
# The board never runs anything: the agent adapter classifies each
# command an agent runs against these patterns, and Focus shows the last
# matching run per row, judged pass/fail from the command's own output.
#
# Core ships this default; a file named `checks` in manager/local/
# replaces it WHOLESALE (same resolution as prompts — the local file
# wins by filename). The adapter and the browser read the same file, so
# a label edited here flows to classification and rendering alike; keep
# patterns in the regex dialect Python and JavaScript share. Read fresh
# on every event and request — edits apply without a restart.
pytest: \bpytest\b
lint-imports: \blint-imports\b
frontend: type-check|vue-tsc|\bnpm (run )?test\b|\bvitest\b
+50 -2
View File
@@ -9,6 +9,7 @@ things are* lives here. No state, no behaviour.
from __future__ import annotations
import os
import re
import subprocess
from pathlib import Path
@@ -92,8 +93,25 @@ ADAPTER = setting("BOARD_AGENT_ADAPTER", "claude")
# test/check commands) — neutral, comma-separated; each adapter renders
# them in its own permission-rule syntax. The universal git/gh grants are
# the adapter's own knowledge; this list is the project's half.
AGENT_COMMANDS = setting("BOARD_AGENT_COMMANDS",
"python3 -m unittest,python3 -m pytest")
AGENT_COMMANDS = setting("BOARD_AGENT_COMMANDS", "python3 -m unittest")
# Model per launch intent — an opaque vendor-native name core passes to the
# adapter untranslated (what names mean anything is vendor knowledge). Empty
# = inherit the vendor's own default, exactly today's behaviour. A per-intent
# setting beats the general one; review covers PR reviews and relevance
# checks (they share the review intent).
AGENT_MODEL = setting("BOARD_AGENT_MODEL", "")
AGENT_MODELS = {
"work": setting("BOARD_AGENT_MODEL_WORK", ""),
"act-pr": setting("BOARD_AGENT_MODEL_ACT_PR", ""),
"review": setting("BOARD_AGENT_MODEL_REVIEW", ""),
}
def agent_model(mode: str) -> str:
"""The model one launch intent rides — '' means inherit."""
return AGENT_MODELS.get(mode, "") or AGENT_MODEL
# GitHub plumbing: the gh CLI (stub-able for tests) and the git remote PRs
# go to. Empty remote = auto-detect the first remote; no remote = no PRs.
@@ -120,6 +138,36 @@ def prompt(name: str) -> str:
return (CORE / "prompts" / name).read_text(encoding="utf-8")
def checks() -> list[dict]:
"""Definition-of-done checks for the Focus panel: core ships a default
(core/checks); a local/checks replaces it wholesale, like prompts. Each
line is `<label>: <command regex>`; invalid regexes are skipped. The
agent adapter reads the same file to classify commands (the claude
adapter's emit.py is standalone, so the parser is mirrored there), and
the browser matches with the served patterns — keep them in the regex
dialect Python and JavaScript share. Read fresh on every request."""
for base in (LOCAL, CORE):
path = base / "checks"
if not path.is_file():
continue
entries = []
for line in path.read_text(encoding="utf-8").splitlines():
line = line.strip()
if not line or line.startswith("#"):
continue
label, sep, pattern = line.partition(":")
label, pattern = label.strip(), pattern.strip()
if not sep or not label or not pattern:
continue
try:
re.compile(pattern)
except re.error:
continue
entries.append({"label": label, "pattern": pattern})
return entries
return []
def adapter_dir() -> Path | None:
"""The configured agent adapter's directory — local overrides core."""
for base in (LOCAL / "adapters", CORE / "adapters"):
+1
View File
@@ -35,6 +35,7 @@ def state_payload() -> dict:
"branches": github.task_branches(),
"commands": config.commands(),
"commandRuns": commands.public(),
"checks": config.checks(),
"archivedCount": taskfiles.archived_count(),
"boardEvents": board_events,
"now": time.time(),
+1 -1
View File
@@ -14,7 +14,7 @@ Do this properly:
repos/{{owner}}/{{repo}}/pulls/<number>/comments`.
- Address each point in the code. If you disagree with a point, do not
silently ignore it — leave it unchanged and say why in your summary.
- Follow repo CLAUDE.md: layering rules, definition of done. Run the tests
- Follow repo AGENTS.md: layering rules, definition of done. Run the tests
that cover what you changed until they pass.
- Commit in clear, reviewable commits and push the branch (`git push`) so
the PR updates.
+1 -1
View File
@@ -14,7 +14,7 @@ Review the PR properly:
context, not in isolation.
- Check the work against the task: does it do what the task asked? Is
anything missing, wrong, or beyond scope?
- Check it against CLAUDE.md at the repo root: layering rules, definition of
- Check it against AGENTS.md at the repo root: layering rules, definition of
done, testing expectations.
You are read-only on the working tree: make NO edits, NO commits, move
+1 -1
View File
@@ -14,7 +14,7 @@ written? Specifically:
written (renamed modules, replaced approaches, merged tasks)?
- Is anything in it now wrong or misleading?
You are read-only: make NO edits, NO commits, move nothing. Read CLAUDE.md
You are read-only: make NO edits, NO commits, move nothing. Read AGENTS.md
and the code; run read-only commands (grep, git log) as needed.
End with a report whose FIRST line is exactly
+2 -2
View File
@@ -4,7 +4,7 @@ You are in an isolated git worktree on branch `{branch}` created for this task.
All your work happens here: commit to this branch, do not push, do not merge,
and do not switch branches.
Read CLAUDE.md at the repo root first and follow it, including its
Read AGENTS.md at the repo root first and follow it, including its
definition of done — run whatever checks it names until they pass.
The task is `{filename}`. Its content:
@@ -24,7 +24,7 @@ NOT READY: <one-line reason>
followed by a bullet list of the specific questions that block the task.
The board treats that marker as "send the task back for refinement". Only
questions that change what should be built count — implementation details
you can decide yourself by reading the codebase and CLAUDE.md do not.
you can decide yourself by reading the codebase and AGENTS.md do not.
Rules:
- Do NOT move, rename or edit the task file itself — the board manages its
+1 -1
View File
@@ -1,6 +1,6 @@
"""Reading and moving task files — the only module that touches tasks/.
The directory a task file sits in *is* its status (see ../CLAUDE.md). Nothing
The directory a task file sits in *is* its status (see ../AGENTS.md). Nothing
here knows about agents or HTTP; it is the same folder kanban you could drive
by hand with mv.
"""