Repository navigation
The first release of aloop (Aladdin's Loop), the plugin formerly published as agentic-agile.
It carries the 0.11.0 rename (below: Upgrading from agentic-agile) and everything the roadmap
shipped since v0.10.1: the intent contract and the aladdin.event/1 stream with events trace
(a commit on main answers with its task, gates, plan, intent and approver), sprint budget and
admission control, the planning feedback lifecycle, frozen ids, semantic targets, the stuck
release, the impact-provider seam, the portable host core (Claude Code, Codex, OpenCode), run
data under .aladdin/ with a .agentic/ fallback, and seventeen measured live runs of the
north-star loop (make e2e-live), each of which fixed a gate false positive or a dead path.
Upgrading from agentic-agile: uninstall agentic-agile@agentic-agile-marketplace, install
aloop@aloop-marketplace; agentic … commands keep working as aliases and existing .agentic/
project data is read as before (see 0.11.0 → Compatibility, and README → Upgrading).
Changed
- The README is tested (
scripts/test/readme.test.py, inmake test-hosts): the §4.11 section
order, everyaloop <tool>/aladdin <sub>it names exists, the install lines name this
repo's plugin and marketplace, every relative link resolves, and every demo time/cost figure
is one ROADMAP §0 records. Reason: the README was the last §4.11 row without a test. - Run data moves to
.aladdin/(ROADMAP M1). Fresh projects keep transcripts, budgets,
the ledger, logs, state, host records and task worktrees under.aladdin/, next to
config.yaml;.aladdin/.gitignore(written by the plugin) keeps everything but
config.yamlout of git. A project that already has.agentic/keeps using it until
aloop layout migratemoves it (refused while worker worktrees are live);aloop layout showsays which dir is live andaloop layout checkfails unless the run data is
git-ignored. EveryAGENTIC_<KEY>env var and settings key acceptsALADDIN_<KEY>
(AGENTIC_wins when both are set). The gates andbudgetfind the task contract in
either dir, so a supervisor that writes the old literal path is still understood. The
worktree-local markers (task.envcopy,budget-exceeded,scaffold-symbols) move with
it: written to the worker worktree's.aladdin/(guarded), read from.agentic/too.
Test:scripts/test/layout.test.py; every suite runs on the new layout. - Workers append their
output.mdblock beforeselfcheck(RED/SCAFFOLD/GREEN personas,
agents and pipeline sources). Reason: the soft-limit line said "run selfcheck, append your
report", so workers self-checked first and were blocked for a missing report block: 4 of
run 16's 9 blocks, 3 of run 15's 6. - The supervisor never commits on main (SKILL.md): every commit on main arrives through
task-worktree merge. Reason: live run 16's one untraceable commit was the supervisor's own
Track Cargo.lock; the e2e fixture now commits the lockfile in its seed. - A wave with one dispatchable task runs in the foreground (SKILL.md orchestrator loop).
Reason: live run 15 dispatched every single-task wave in the background and woke 16 times,
each wake re-reading the supervisor's context (5.5M cached tokens, $1.26 of $1.42); run 14,
foreground, woke twice for $0.75. Background dispatch +budget watchstays the rule for
parallel waves. The host table's "merge a passed task" row namestask-worktree merge. - The soft token limit is telemetry only (ROADMAP §3.1). Crossing it no longer tells
the worker to wrap up;budgetrecordstask.token_soft_limitonce per attempt in
.agentic/logs/events.jsonl,stats.mdcounts it, andNEXT.mdlists those tasks as
planner input. The soft time limit still warns. - No post-kill narration (ROADMAP §3.5). At the hard limit the worker is stopped on
the crossing call instead of being given a last call to write its report. The harness
appends the gate-validstatus: re-planblock to output.md itself (limits, worktree
diff, transcript path) and recordstask.token_hard_limit/task.time_hard_timeout.
A verdict reached before the worker's worktree is known still gets one call to find it. - The token meter counts classes separately (ROADMAP §3.2). The budget charge is now
fresh (uncached) input + output by default. Cache read and cache write are kept as
their own classes in each attempt's state (usage), and context size is the latest
call's, never cumulative cache traffic.TOKEN_METER=contextin defaults.md (or
BUDGET_TOKEN_METER=contextin a task.env) keeps the previous context + output charge;
budget resolve/statusshow the meter in force. - Budgets cover every model role (ROADMAP §3.3). Intake, standards, planner,
archivist, structural-reviewer and final-gate are metered against per-role profiles
(overridable withAGENTIC_BUDGET_<ROLE>in defaults.md). They are observe-only:
crossings are recorded as events, and the agent is never told or stopped. - Hard breaches are classified, not always split (ROADMAP §3.4). The hook makes a
deterministic first call (TASK_TOO_LARGE,AGENT_LOOPING,EXTERNAL_SERVICE,
TEST_SUITE_SLOW,ENVIRONMENT_SLOW,CONTEXT_PATHOLOGY,HOST_FAILURE,UNKNOWN)
from usage classes, tool calls and results, with its evidence in the output.md block,
the event,budget watchand the newbudget classify. The planner confirms or
overrides it (breach:line) and acts per class (SKILL.md "Breach classes").
Added
-
log-execution --help, a default ledger (the latestdocs/agents/sprintN/execution.log) and
exit 64 with the usage on a wrong call. Reason: it had no usage, so the supervisor read its
source twice per live run to learn that the last argument is the file. SKILL.md now gives the
exact call and says the init-block section list is the whole shape (the supervisor also read
init.template.mdfour times per run).make e2e-livecounts plugin-source reads precisely
(tool calls naming a plugin path,--schema …/schemas/…excluded): runs 13–15 were 9, 8, 6. -
task-worktree merge <TASK_ID> <BRANCH>records the §4.7 lineage on Claude Code, where the
host makes the worktree and the supervisor merges it (sotask-worktree removenever runs): a
--no-ffmerge, thenworktree.merged+ onecommit.createdper merged commit. SKILL.md tells the
supervisor to merge with it (a rawgit mergeleft live runs 11–14 with no traceable commits), and
make e2e-livenow checks every merged commit answersevents trace. -
Stuck release: a worker that hits the same gate block 3 times in a row (one gate, task,
attempt and worktree;AGENTIC_STUCK_BLOCKS) is released unverified instead of
looping until its time box (live run 10 lost 29 minutes to a RED worker that stopped 29
times on one unchanged reason). The release is not a pass: the gate leaves
.agentic/state/stuck/<task>.<attempt>with the reason,budget watchprints aSTUCK
line once, and the supervisor re-dispatches with feedback or re-plans. A different reason
or a new attempt resets the count; a self-check never releases. Every gate verdict now
logs its worktree and a checksum of the block reason. 7 conformance checks (§6.9). -
Portable project config (ROADMAP §4.9).
.aladdin/config.yaml(budgets, context,
semantic, models, provenance, memory, git, plus per-role budget profiles) replaces
docs/agents/defaults.mdas the human's file.aloop config migratewrites it from the
current settings; when it exists it is authoritative and defaults.md is rendered from it
(config sync, run by SessionStart andaloop-init --apply), so the bash gates read the
same values.config checkrefuses unknown sections, keys, bad numbers and schema. -
The
HostAdapterinterface (ROADMAP §4.9)._host.pynames, per host, the one place
the harness does each thing: capabilities, the dispatch vocabulary (spawn / wait / send /
cancel / subscribe), model and transcript resolution, usage and context pressure,
compact / rotate, the worktree seam, gate install and enforcement, tool policy. Claude
Code is the reference; Codex and OpenCode are adapters.aloop host describeprints the
contract,host check(inmake test-hosts) fails if an adapter is incomplete or would
enforce a gate as a warning. What a host lacks raisesUnsupported; nothing is faked. -
Abstract model routes (ROADMAP §3.6). Roles map to
strongest | strong | economical
and each host resolves the route to its own id (plugin/hosts/routes.json; Codex: the
session's model).AGENTIC_MODEL_PLANNING/AGENTIC_MODEL_WORKERdefault to
strongest/strong; a pinned id still passes through.aloop models resolveis what
the supervisor passes on dispatch and whataloop installrenders;--jsonmakes the
route observable (conformance 18). -
Sprint token envelope and admission control (ROADMAP §4.2).
budget admit <task>
runs before each dispatch. AtSPRINT_TOKENS_SOFTit prints one rollover warning, and
atSPRINT_TOKENS_HARDadmission closes (exit 3). Refused tasks are carried over in
sprintN/rollover.mdwith the reason, gate-final accepts unticked boxes only for those
tasks (budget rollover-check), and NEXT.md lists them for the next planning cycle.
Events:sprint.token_soft_limit,sprint.admission_closed,sprint.rolled_over. -
Planning feedback lifecycle (ROADMAP §4.3).
budget envelope <task>prints the
minimal failure envelope: limit, observed value, breach class, last gate, changed files
and references, with nothing inlined. NEXT.md gains a "Planner feedback" section that
applies the grace rule (0–1 failed or hard-breached tasks → no nudge; 2+ → one "plan
smaller" nudge for the next cycle only) with a calibration verdict derived from the
breach classes (plan-smaller,raise-time,raise-tokens,reduce-context,
fix-environment). -
The
aladdin.event/1stream (ROADMAP §4.7)._events.pyandbin/eventsgive
every harness event one envelope (ids,parent_event_id/caused_by, role, host,
model, authority, decision, refs, data) and refuse unknown event types. Budget events,
every real gate verdict (gate.passed/gate.failed) and the worktree lifecycle
(worktree.created/merged/discarded) are emitted into it.events queryand
events lineage <task>answer from the stream, with references only and no transcripts.
events authorityrecords the run's authority (who approved it, the mode, the scope and
any overrides).events deciderecords one-line decisions with evidence refs, linked to
that authority. A decision without an authority, with a multi-line reason or with an
unknown kind is refused. -
The Intent Contract and the clarification policy (ROADMAP §4.1).
bin/intent new
issues a canonical, time-orderedintent_id, which is never model text, and the
contract skeleton with provenance.intent checkvalidates every field. It requires a
class for each open question (assume/default/spikemust record their
resolution) and stops BOTH modes on an unansweredask(exit 3).intent summary
surfaces defaults and assumptions for approval. gate-intake runs the check. Autonomous
mode is explicit (events authority --mode autonomous) and skips approval unless an
escalation class is hit. -
Host capability matrix and the context-boundary rule (ROADMAP §4.4, §4.9).
plugin/hosts/capabilities.json+bin/capabilitiesstate what each host advertises
(unknowncounts as not advertised). At a sprint boundary the harness rotates (the host's
own/clearor/new, named in the sprint-close message) unless
AGENTIC_CONTEXT_BOUNDARY=compactand the host advertises compaction; keeping a session
needs a recorded reason. SessionStart recordscontext.rotated/context.compacted,
and stats.md counts them. -
Usage accuracy is explicit (ROADMAP §4.9, conformance 12). Each attempt's usage
carriesaccuracy: exactand names any class the host never reports (Codex has no cache
write) instead of a silent zero; stats.md shows it in the Metrics table. -
The site (ROADMAP §4.11):
docs/index.html, one self-contained page for GitHub Pages (from
/docs): an original lamp mark, the RED explainer ("Give the agent something to make false."),
the gates table and the audit tree;scripts/test/site.test.pychecks it is self-contained and
that every time/cost number on it is one ROADMAP §0 records. -
README reordered product-first (ROADMAP §4.11): intent, demo (the measured §0 runs), test-driven
agents, how the loop works, why failing first matters, gates, install, hosts, evidence, audit,
architecture, limitations. ROADMAP §0 milestone statuses now match the code (M1–M7 done, M8 in progress). -
aladdinentry point (ROADMAP §4.11).aladdin "<intent>"records the Intent Contract
(plus the raw words) and says how to start the run;aladdin status|resume|reportread the
harness files (sweep, the resume rule, NEXT.md, stats.md);aladdin target|context|refs|…
are the semantic queries; every aloop tool answers under the new name. A/aladdinskill
defers to/aloop; installs link~/.local/bin/aladdinand copy the skill. The stray
bin/aloop-init.origleft by the rename merge is gone. -
Context-window share (ROADMAP §4.10). stats.md divides the context peak by the new
AGENTIC_CONTEXT_WINDOWsetting (context.windowin.aladdin/config.yaml, default 200000):
hosts do not report the window, so the human states it instead of the harness guessing. -
Host swap (ROADMAP §4.9).
aloop host swap --to codex|opencode|claudehands a sprint to
another host from portable state only: the sprint dir (handoff.json / plan-ready.md),
.aladdin/config.yamland.agentic/logs. A missing piece or a live worker worktree blocks;
the target's capability gaps are named; SessionStart on the new host resumes the sprint under
the same resume rule and records the rotation. Test:scripts/test/host-swap.test.py. -
The semantic plan as the execution source (ROADMAP §4.6). With
tasksin a story's
targets.json,targets renderwrites tasks.md, validate.md and plan.md as deterministic
views over it, andtargets check(gate-stage2-complete) refuses a hand-edited view, so the
md files cannot fork from the plan. Test:scripts/test/plan-render.test.py. -
Diff scope derived from change targets (ROADMAP §4.6). When the supervisor gives no
SCOPE_GLOBSand the story hastargets.json, gate-green-verify enforces the task's
target paths (targets scope) instead of skipping the scope check. -
LSP adapter seam (ROADMAP §4.6).
targets refs|callers|calleesask the language
server named byAGENTIC_LSP_COMMAND(_lsp.py: references and the call hierarchy only).
No server, or a server without the capability, is reported with exit 4; planned targets
answer "none yet" without touching any server. -
The orchestrator's inspect step (ROADMAP §4.2).
bin/sweepprints one action per
planned task (DONE, ROLLOVER, WAIT, REPLAN, ACCEPT, RETRY, ESCALATE, SPAWN), decided from
the event stream, attempt states and rollover.md.sweep waitis a token-free sleep
that wakes on the next event or state change. -
Time budget
automode (ROADMAP §4.2). WithAGENTIC_TIME_MODE=auto,bin/timebox proposerecords one stable task duration per project (with min/max) andbudgetuses
it (soft = 2/3).timebox revisechanges it only within range and only with evidence
that exists; each change is adecision.recorded. Task overrides still win. -
Cross-project impact provider seam (ROADMAP §4.8).
bin/impact queryasks an optional
provider (AGENTIC_IMPACT_PROVIDER, any command speakingaladdin.impact/1) for downstream
consumers, rationale, migration order or standards. Results without a source ref are
dropped; answers are saved underdocs/agents/impact/and recorded as planning
provenance. An unavailable provider is reported and planning continues. -
More run metrics (ROADMAP §4.10). The Metrics table adds commits produced and test
files added (fromcommit.created), time soft limits reached, and semantic context
served (targets target|contextemitsemantic_target.resolved). -
Commit → intent trace (ROADMAP §4.7, milestone 7). gate-stage2-complete emits
plan.created/plan.revised, caused by the intent;events authorityemits
plan.approvedfor the latest plan;task-worktree removeemitscommit.createdper
merged commit.events trace SHAwalks commit → task → gates → plan → intent → approver
from the event stream alone.events commit-msg TASKbuilds the commit message from the
task title, recorded decisions and ids;events graphexports the stream as a
rebuildable graph (JSON or DOT). -
Semantic change targets, first slice (ROADMAP §4.6). The planner may write
<story>/targets.json(change_ref / operation / path / symbol | planned_symbol / reason / evidence_refs / constraints).bin/targets checkproves each target against tasks.md and
the real tree, and gate-stage2-complete runs it. Workers start fromtargets targetand
targets context --budget N, including for files that do not exist yet; planned files
form a shadow workspace and no stub is created.refs/callers/calleesreport the missing
LSP backend (exit 4) instead of guessing. -
Canonical ids and referential integrity (ROADMAP §4.5).
bin/ids freezechecks the
structured references between planning artifacts, never prose, and issues each story and
task alias a frozen UUIDv7 insprintN/ids.json. A split task's original is retired and
its number can never be reused. gate-stage2-complete runs it, and events for a frozen
task carrystory_uidandtask_uid. -
Planner lesson candidates (ROADMAP §4.3).
bin/lessons addrecords a candidate with
symptom / cause / change / applies_to / evidence_refsand emitsmemory.candidate.
It refuses empty fields, missing evidence and any change that would weaken a gate.
lessons recurringhands the archivist the groups seen in two or more tasks, as
memory.md rows. gate-memory blocks a row that promotes a one-off without a humankeep.
There is no second memory system. -
Canonical sprint handoff and the resume rule (ROADMAP §4.4). sprint-close writes
sprintN/handoff.json(aladdin.handoff/1) from accepted state: completed tasks with
their gate verdict and merge event, unverified, open and carried tasks, the nudge and
evidence refs. NEXT.md renders it.stats resume-checknames every task that
plan-ready.md shows as done but that has no passing gate verdict, and SessionStart
appends that live check to the loaded handoff. -
Sprint metrics (ROADMAP §4.10). stats.md gains a Metrics table: p50/p90/p95 attempt
duration and tokens, hard breaches by role and class, hard-breach waste, tokens per
accepted task, first-pass rate by gate, re-plan rate, cache-hit and churn ratios,
context peak, and admission closures. All of it is derived from harness files, with no
model calls. -
Second live e2e intent:
make e2e-live YES=1 INTENT=wordfreqruns two dependent stories
(word counting, then top-N ranking). -
gate-finalchecks every planned test is on main: eachpath::fnbullet in a story's
plan.mdmust exist at its path.plan-ready.mdlists only what RED wrote, so a test a
re-plan dropped used to vanish unnoticed (e2e run 6). -
aloop initseedsdocs/agents/memory.mdas a schema-valid empty table, and
gate-memoryprints a valid skeleton when it blocks. e2e run 7's archivist guessed
type: agent-memoryand the supervisor's stop was blocked 15 times. -
gate-dispatch(PreToolUse on Agent/Task): the supervisor's dispatch of an execution
worker is refused until its prompt opens withTASK_ID: <id>and the contract exists.
e2e run 6 dispatched the structural reviewer before writing its contract, and its gate
blocked 25 times on aSTORY_DIRthe worker could not supply.scripts/test/dispatch.test.py. -
End-to-end live run (north star).
make e2e-live YES=1turns a one-line intent
(a semver parser) into planned, tested, merged code in a real Claude Code session with
the plugin, then checks the artifacts, gate verdicts, merge, tests and cost. First run:
done end to end in 19 min for $1.15 (sonnet supervisor, haiku workers), 22 tests on main;
it found the gate-matcher, selfcheck and copy-merge bugs fixed below. -
Conformance fixtures (ROADMAP §6, M1 slice 1).
make conformanceruns the real RED
and GREEN gates on a fixture crate in linked worktrees: 16 checks over §6.3–6.9 (RED that
passes or editssrc/is rejected, suppressions and out-of-scope diffs are blocked,
shared-tree workers are blocked, an accepted GREEN merges, a hard breach is released as
"not a pass"). Items not covered yet are printed with the reason. Runs in CI's rust job.
§6.2 adds 4 schema checks through the real md-db; task.env tampering adds 6 more (26 in all). -
Live smoke test (M0).
make smoke-live YES=1runs one short real Claude Code
session with the plugin and checks the handoff injection, the supervisor-scope block,
transcripts and the token ledger (~$0.004 on haiku). Not run in CI (needs tokens). -
Gates fail closed (M0.6). A gate that crashes (exit other than 0 or 2) now blocks
with "the gate itself failed … failing closed" instead of being a non-blocking hook error
that lets the action through. Covers every sub-agent gate, andgate-supervisor-scope
once the repo has a sprint lock.scripts/test/fail-closed.test.py.
Security
- No role gate ran on Claude Code plugin installs. Claude Code names a plugin's
sub-agentsaloop:<agent>, and a plain-name hook matcher is an exact list, so the
red-worker,green-worker, … SubagentStop/SubagentStart matchers never matched: every
"gate" verdict came from the workers' own optional self-checks. Found by the first live
end-to-end run (all 7 verdicts were self-checks) and confirmed with a probe plugin.
Matchers now list both<role>andaloop:<role>;scripts/test/hook-matchers.test.py
failed before. - A worker could pass its own gate by editing
task.env. The gate library sourced
.agentic/task.env, which sits in the worker's worktree: appendingexit 0passed a
failing GREEN, andGATE_RUN_MATRIX=0orSKIP_HOOKS=1switched checks off. The file
is now parsed as data and only the contract keys are read (selfchecktoo). Four new
conformance cases cover it; they failed before the fix. Remaining exposure (a worker
rewriting its contract keys) is ROADMAP M0.7. - A worker could relabel its own role.
AGENT_ROLEcame fromtask.env, so a RED
worker claimingplannerskipped the worktree-isolation check. Gates now take the role
from the host's hook payload (agent_type) and block iftask.envcontradicts it.
2 conformance cases (26 in all) failed before. - The task contract is the supervisor's (M0.7). The playbook told the supervisor to
writetask.envinto the worker's worktree before dispatch, but on Claude Code
isolation: "worktree"creates that worktree (.claude/worktrees/agent-<id>) at
dispatch (measured with a live probe), so the contract could only be missing or
worker-written. The supervisor now writes.agentic/state/tasks/<TASK_ID>.envin the main
tree and putsTASK_ID: <id>on the dispatch prompt's first line; gates and the time box
find the contract from that line in the host's transcript. A worktree copy that disagrees
with the contract blocks the gate, andgate-supervisor-scopestops sub-agents writing
.agentic/state/or.agentic/task.env. 4 conformance cases (30 in all) and 4 unit
checks failed before. - Workers could rewrite the contract through Bash.
gate-supervisor-scopenow also
sees a sub-agent's Bash calls and blocks a command that names.agentic/state/or
.agentic/task.envtogether with a write (redirect,tee,sed -i,cp,mv, …);
reading it stays allowed. 2 checks failed before.
Fixed
- Reviewers and the final gate get the task-contract copy in their host worktree (
budget hook).
Reason: only the three workers did, so every structural reviewer's firstselfcheckon Claude
Code blocked "STORY_DIR unset" (runs 15–17: 2, 1 and 3 blocks) until it guessed the contract.
The observed role's state now names its task and story dir too. - The planner persona states
targets check's rules ({"targets": [...]},symbolonly for code
that exists,planned_symbolwithcreate/extendfor new code), so its firsttargets.json
passes (live runs 12–14: 2–3 blocks each). - The planner persona lists the exact frontmatter and
##sectionsplanning-artifacts.kdl
requires, so its first write passes (every live run so far wrote each artifact twice: 8–12
write blocks per run). ctx-symbols(and the gate's grep fallback) no longer scan a host's worktree checkouts
inside the main tree (.claude/worktrees/agent-<id>/), nor.agentic/or.transcripts/:
a stale checkout duplicated every symbol of main and the structural review halted on a
false HIGH finding 20 times (live e2e run 12). The exclusion applies below the walk root, so a
reviewer whose own worktree is such a checkout is still scanned. 3 conformance checks (§6.7),
2 unit tests.- The stuck release also covers the structural reviewer and the final gate, whose blocks can name
a defect only the supervisor can act on (run 12: 10 identical blocks). 1 conformance check. gate-validate-artifact's block now carries md-db's diagnostics (the missing section or field
and its hint): a PostToolUse block hands the model only stderr, and the bare "failed the
schema" made the planner guess (live e2e run 11: every planning artifact was written twice,
12 of 25 gate verdicts).gate-dispatchrefuses a task contract with noSTORY_DIR, or one naming a dir that does
not exist, and tells a whole-wave structural review to use the sprint dir
docs/agents/sprintN/(run 11: the reviewer's contract had none, 2 blocks the worker could
not fix). 5 new dispatch checks.- OpenCode: a stuck release (exit 0 with
STUCK … NOT verified) is reported to the supervisor
as "released UNVERIFIED, do not merge", never as a silent pass; 2 new checks. make test-hostsmasked a failing OpenCode test as "node not found".- The host tests (Codex hooks, OpenCode plugin, rename-compat, budget, fail-closed, scope,
dispatch) each leaked a temp dir, and the Codex and OpenCode ones started a real background
cargo build over their fake tools (~500MB per run; 57 leaked dirs filled the disk and killed
e2e run 11 with ENOSPC). They now remove their temp dir on exit and set
AGENTIC_NO_AUTOINSTALL=1;e2e-livedrops its cargo target dirs after the run. - The comms gate's "no output.md" block now says HOW to append the report: a shell heredoc
from the worktree, because Claude Code's Write/Edit refuse a path outside it and
docs/agents/lives only in the main tree (e2e run 10: a RED worker stopped 29 times on
it). The worker personas say the same. - A worktree
task.envcopy OLDER than the supervisor's contract (a re-dispatch bumped
ATTEMPT) is stale and is ignored, not reported as tampering (e2e run 10: 3 blocks). ensure-toolsrebuilds the bundled md-db / ctx-symbols when their sources change, not
only on a version bump; e2e run 9 ran a stale ctx-symbols that still had the duplicate bug.gate-stage2-completenames the expectedsN-NN-<slug>/story dir (and a misnamed one it
found); the planner prompt states the naming. e2e run 9: 56 planner retries onS1-01/.- Scope globs are no longer expanded against the worktree:
tests/**became the files that
happened to exist, so GREEN was blocked for an in-scopetests/common/mod.rs(e2e run 8: 29 blocks). ctx-symbols conflictsno longer reports the same name in two integration-test files
(mod common;, a local helper) as a HIGH duplicate; eachtests/*.rsis its own crate.
e2e run 8's structural review halted 57 times on it. The grep fallback skipstests/too.gate-scaffold-verify's grep fallback (no ctx-symbols) located a test fn instead of the stub,
depending on directory order; it now uses the same name-anchored match assymbol_count.gate-red-verifyno longer blocks a RED report that lists a test already on the base as
PASS (an earlier task's test, for context); only a NEW test may not pass. e2e run 7: 22 blocks.make shellcheckno longer reports a lint error as "shellcheck not installed" and passes.gate-scaffold-verifyskips asymbol path kindheader row andTrait for Typeimpl
lines in.agentic/scaffold-symbols.- Annotated
scaffold-symbolslines were split into fake symbols ((enum),@, …), each
"defined 0 times". The first token of a line is the symbol; non-identifiers are dropped. - Sub-agents read the plugin's own source (19–30 commands per e2e run) to work out
formatsselfcheckalready reports. The agent prompts now say not to; run 6 had 2, and
cost its lowest yet: $0.65 in 11 min. - A Claude Code worker could get another task's budget. With no
task.envin its own
worktree, the time box guessed "the only green-worker worktree" and applied that task's
limits. It now takes the worker's own worktree from its cwd first. - A worker's
selfcheck <role>crashed on good work (AGENT_ROLE: unbound variable)
when the role came only from the argument; selfcheck now exports it. Found by the e2e run. - The supervisor merged by copying files out of worktrees. Workers never committed, so
their branches were empty and the supervisorcp'd files into main, past the gate's
diff. RED/SCAFFOLD/GREEN gates now block uncommitted work, the worker prompts say to
commit, and the playbook says togit merge --no-ffthe worktree branch. Found by the
e2e run. - Gates looped on the supervisor's own contract slips. A comma-separated
SCOPE_GLOBS
(34 blocks in e2e run 2) or a mistypedAGENT_ROLEin the main-tree contract blocked a
worker that cannot edit the contract, so it retried until it gave up. Lists now accept
commas, and the host's role wins over the contract's with a WARN (a contradicting
worktree copy still blocks). - A worker's
selfcheckcould not find its task on Claude Code (STORY_DIR unset, once
per role in e2e run 2): the worktree is made at dispatch and has notask.env. The time
box's first tool-call hook now copies the supervisor's contract into the worktree (the
dispatch prompt'sTASK_IDpicks it); the gates still compare the copy to the contract. - GREEN looped on RED's formatting (19 blocks in e2e run 3): RED's test file failed
cargo fmt --check, and GREEN may not touch tests. RED and SCAFFOLD gates now run the
matrix's format check, so the file is fixed by the role that wrote it. - False "isolation dropped" blocks (27 in e2e run 5): a worker that
cds to the main
tree to read its story left the hook's cwd there. Gates now check the worktree Claude
Code made for that agent (.claude/worktrees/agent-<agent_id>) first. The Bash contract
guard is per simple command now (run 5 blocked a read-only probe), and RED's
out-of-scope message says how to undo the change. - The supervisor could write source mid-sprint on Linux.
gate-supervisor-scope's
"recently refreshed lock" arm calledstat -f %mfirst; on Linux that prints a
filesystem report instead of failing, the arithmetic crashed underset -u, and a
crashed hook does not block. GNUstat -c %Ynow goes first and the value is checked.
Found by the live smoke test;scripts/test/supervisor-scope.test.pycovers it. - Valid planner artifacts were blocked by the schema gate.
gate-validate-artifact,
gate-intakeandgate-memoryran md-db on the written file's whole directory, and
gate-stage2-completeon the whole sprint tree. Those directories also hold the
init.md/output.mdcomms (andstats.md), which the schema does not know, so every
validtasks.md/validate.md/stories.mdwrite in a story that had comms was blocked.
They now validate only the written file (stage-2: only the planning artifacts). Found by
the new §6.2 fixture.