Brings the branch up to the current base (executor settings, project
skills, Chinese run messages, cloud IDE removal, wish attachments) and
resolves the ten conflicted files, keeping both sides:
- wish-refiner: the tenant's executor settings pick the models first,
then the Copilot model setting; the tenant credential still goes
before the operator's login
- worker providers: executor settings apply, and a run with its own
credential still gets an empty home
- main.ts: Copilot screenshot uploads and wish attachments each keep
their own body limit
- contracts, http, web types: default budget and skill auto-activation,
Copilot and attachment entity kinds, ./text and ./attachments exports
- globals.css: Copilot styles and attachment styles, one after the other
- tests: the canceled-release reason is Chinese; the refiner's default
models have no [1m] suffix, as this branch names them
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Raw stderr never streamed into a run because it may carry credentials, but discarding it
left a stalled CLI completely silent — there was no way to tell "cannot reach the gateway"
from "still thinking".
The tail of stderr now goes to the worker log when a run fails, is canceled or never saw a
success, with both the CLI's credential values and the usual key/token shapes removed.
Resolved against the IDE removal and the lessons-to-skills merge; the
pitfall skills, their events and repair notes are written in Chinese too.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The run page mixed English stage events and agent summaries into the
Chinese console. Messages are now written in Simplified Chinese at their
source (control plane, dispatcher, worker, POC build), keeping commands,
SHAs, branches and error codes verbatim; raw runtime errors get a Chinese
prefix. The agent prompt asks for the plan, summary and questions in
Chinese. File-change parsing accepts old and new messages, and the event
label table covers every event kind written.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A per-tenant, per-executor settings record (GET /executor-settings,
GET/PUT /executor-settings/:provider, owner/admin, idempotent replace) with
baseUrl, defaultModel, smallFastModel, fallbackModel, timeoutMinutes, askModel
and askFallbackModel. Unset fields keep the operator's configuration.
- defaultModel is pinned at submission below the wish and bundle models.
- smallFastModel, fallbackModel and timeoutMinutes travel in the run context
to the worker; Claude Code gets ANTHROPIC_SMALL_FAST_MODEL /
ANTHROPIC_DEFAULT_HAIKU_MODEL and --fallback-model, CodeBuddy the limit.
- baseUrl goes only with the tenant's own key, over HTTPS (plain HTTP only
where plainHttpAllowed), never in production, behind the model proxy or
with the deployment's native Claude account.
- The wish refiner tries the tenant's ask models first.
- The 执行器 page gets an 执行器设置 dialog, also in native-account mode;
model fields (and the agent page's) accept gateway names like
deepseek-flash@latest[1m].
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
AI optimization called Claude CLI with no --model, so it used
deepseek-pro and hit the 120 s limit. It now uses flash by default,
with 140 s, and WF_CLAUDE_ASK_MODEL can override it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Wide wishes made Claude Code write more than 16 MiB of stream-json and
stopped at "executor failed". The limit is now maxOutputBytes, 256 MiB
by default.
Co-Authored-By: Claude Haiku 4.5 (1M context) <noreply@anthropic.com>
- Checks run in a repository of their own holding only the commit (and
the commit the run started from, as refs/wishforge/base), so code that
asks Git which commit it is gets the true answer; the verifier's
repository and configuration stay out of reach
- A frontend test gets two minutes before it fails, instead of one that
never settles holding the whole suite until the check is killed
- When frontend or Go tests fail, the same tests run at the commit the
run started from; only failures that were not there before fail the
change
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Profiles pin each environment: POC (branch poc) and Fanyu (branch dev,
180.76.138.88, droboticflow-fanyu), with their Deployments by UID
- Releases expect every Deployment of their profile; Fanyu's api image
also runs its annotation processor and validator, each rolled back to
its own image
- Bindings may list several projects; each Runner has its own settings
- fanyu-access: least-privilege identity and build-Pod admission policy in
Fanyu's cluster, its token only in the executor and Fanyu's Runner
- projects --replace: delete every project with all it holds, then create
the POC and Fanyu projects, their environments and Runners
- Ship the Runner's public keys in the ConfigMap, not a Mac path
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- cluster-poc.mjs: image (in-cluster Kaniko), bootstrap, secrets, apply,
migrate --rehearsal|--final, public HTTPS entry, backup and restore
- One restricted Pod (platform, executor, Runner, PostgreSQL, Temporal,
MinIO, Caddy, backup) listening only on loopback except Caddy
- Protected checks run in per-workspace check Pods; cancellation during
start-up now always removes them
- Daily snapshots on the node (consistent dump with row counts, Temporal
online backup), copied to the Mac by launchd with SHA-256 checks and a
notification on failure; restore verified on the rehearsal copy
- Downloads and uploads survive the Mac's lossy link to the cluster
- Local public entry, evidence isolation labels, acceptance records
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Each wish says whether it may change backend code. A frontend-only wish is told
which paths it must leave alone; a change to them goes back before any check runs,
the platform puts those files back before the repair round, and the control plane
never integrates them. A wish that may change backend code integrates directly for
people with backend permission and waits for a code review otherwise.
- Owners and admins grant backend permission per person on the members page as well
as per project in the project settings.
- AI optimization has its own button for the wish and for the criteria. It writes a
wish of at most three lines (goal, scope, limits), keeps the details in checkable
criteria, and asks only what the person must decide, as choices whose answers join
the wish; suggested criteria are taken one by one.
- Lists, run titles, Feishu cards and pull request titles show a wish's first line;
the run details show the rest.
- Changed paths no longer follow renames, so moving backend code into a frontend
directory counts at both places for code review and for the frontend-only scope.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Someone deployed the POC api and worker outside WishForge by mutable tags,
and every build then stopped with a raw validation error: the cluster
snapshot only accepted digest-pinned images.
A component running a tag is now of unknown source, as one set by hand
already was: the timeline names the component and its tag, the build makes
it again, and the release needs a person's approval. A release still deploys
digests only; what it replaces may be a tag of the same repository, and such
a release never declares itself rollback-compatible, since what the tag
pointed at may be gone. An image neither pinned nor tagged, or not of the
component's repository, stops the build with a message naming it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
What the pilot asked for, from its meeting:
- Code review: a project names the paths changes to which a person reviews
before they reach the target branch (globs, with exceptions). After the
checks pass, the verifier asks the control plane, and the run waits at
integration until an owner or admin approves the exact commit; approving
integrates it without repeating the checks, rejecting hands the comment to
the agent as a new requirement. Continuing cannot get around it: the
verifier asks again before every integration.
- Undo: "take back this change" starts a run that reverses what a run
integrated on the current target branch, three-way, keeping later commits;
only lines later commits changed too go to the agent. It then verifies,
integrates and delivers like any run. Releases get a rollback button for the
version live in their environment.
- Wish optimization: the local Claude account rewrites a draft wish and its
acceptance criteria by built-in and project rules, with no tools at all;
the person compares and decides, nothing is submitted for them.
- Release confirmation: an environment can make every release wait for a
person, not only those the risk rules flag.
- Feishu notifications: a group bot is told of releases awaiting approval and
changes awaiting review (mentioning the decision makers), runs that need a
person, finished runs and failed releases; each once, signed when a secret
is set, with text from runs never acting as card markup.
- Reviewers see the agent's change summary and who submitted the wish, and
whether the checks ran in the macOS sandbox; the wish form offers only the
executors this deployment can run.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A POC release counted, besides what the target branch gained, the
changes since the commit every component runs. Worker and coordinator
keep their images while only web files changed, so they lag behind the
api, and every later release counted again the changes of releases the
api had long deployed: on the POC a run's classification listed the
previous run's test file, and an earlier change to a protected web file
would have asked for approval on every api-only release after it.
A component that keeps its image does not change; the release now
counts the changes since what the api and each component built again
run. pocComponentsToBuild says which commits those are.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every POC build left its source archive, about 30 MB, under
~/.local/share/wishforge/poc/builds, and nothing ever removed them;
nothing reads one once its build has ended either.
After a successful build, the archives of other builds older than an
hour are removed. Their build and release records and logs stay, a
build still uploading keeps its archive, and the newest archive remains
for the operator's sandbox check, which uses it by default.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
When a run's change passed its checks but failed one once merged onto
a target branch that moved meanwhile, the agent got a repair round for
it, even when the failure came from commits other people had pushed:
it would change their code, and spend rounds and tokens doing so.
The verifier now runs that check, recording no evidence, on the target
branch alone. If the branch passes, combining the two caused the
failure, and the agent repairs it as before. If the branch fails too
while the commit the run started from passes, the commits pushed since
broke the branch: the run waits on the new reason target_broken, uses
no repair round, and has its own verified change as its checkpoint
again. A run that started from a commit already failing the check may
be its fix, and is repaired as before.
Continuing merges the verified change onto the repaired branch and
checks the merge. An integration that continues reuses the change's own
verification under the same policy instead of repeating the checks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Since the Git config of an agent workspace is reduced to an allowlist
before each checkpoint, every checkpoint read `<workspace>/.git/config`.
A merge candidate is a worktree of the integration cache, whose `.git`
is a file, so the read failed with ENOTDIR: whenever the target branch
moved while a run was working, its integration stopped on an
infrastructure wait, and continuing failed the same way. No test merged
onto a moved target without a conflict.
A GitWorkspace now remembers the worktrees it added from a repository
WishForge owns and leaves their config alone; no agent can reach it. A
workspace whose `.git` someone else turned into a pointer file is still
refused rather than followed. Tests merge onto a target that moved
meanwhile, end to end and at the Git contract.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The Compose and Kubernetes adapters checked a candidate once. A
container that had started but did not listen yet made the request
throw, and the deployment was reported as of unknown state, to be
reconciled by hand; one stray error from the stable entry right after
the switch rolled a healthy release back.
The candidate checks and the checks after the switch are now repeated,
six attempts two to ten seconds apart, as the POC's already were, and
the Runner logs each repeat. A candidate that never answers is
reported as not switched, with the previous release still serving.
A missing address or missing checks are reported at once instead of
being asked again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A release's risk only counted what the target branch gained when the
run integrated. Commits people pushed to the branch directly, and
integrations that were never deployed, went out with the next release
without being classified: an environment preauthorized for automatic
release took a migration or a Dockerfile change pushed straight to the
branch without approval. The POC chose what to rebuild from the same
narrow diff, so worker and coordinator kept running old code; on the
local POC, WishForge had in fact only ever rebuilt the api.
The control plane now gives the verifier the commit of the release the
environment runs, and the classification covers everything between it
and the release, as well as what the integration brought. On the POC,
each deployment records the commit and the image a release put there.
The build plans from that snapshot, the one the release is checked
against: worker and coordinator keep their images only while what they
run differs from the source in web files alone. A component of unknown
source (never deployed by a release, restored by a rollback, or set by
hand, which leaves the annotations stale) is rebuilt, and the release
is marked partial: it needs approval and does not roll back on its own.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The POC build only accepted a source equal to the head of the Gitea
poc branch. Once someone pushed to poc after a run integrated, the
build failed, and so did every continue: a build stopped by a drop of
the link to the cluster could never finish if poc moved meanwhile, and
the run stayed waiting with an error that did not say why.
When poc has moved on, the build now fetches it and requires only that
its history contains the run's commit; it builds that commit and tells
the timeline that the newer commits deploy with a later run. A source
the branch lost to a rewrite is still never built: the run waits on
the repository with POC_SOURCE_REWRITTEN and says to cancel it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The agent's file tools are confined to its workspace, and the
workspace holds .git. It could plant .git/config and .gitattributes
there, and the executor then ran trusted git add, diff, bundle and
merge in that workspace to export the checkpoint and start a repair
round. Git honours repo-local configuration for every command and no
environment variable disables it, so a planted clean or smudge filter,
diff or merge driver, core.fsmonitor or sshCommand, an include, or a
url.insteadOf transport rewrite would run as the worker: in the
development host mode, as the operator, outside any sandbox. The
driver names are the agent's to choose, so -c overrides cannot reach
them.
Before the checkpoint and before mergeTarget, .git/config is now
reduced to core basics, remote, branch and extensions, which is what a
clone needs to fetch, merge and bundle; everything else, the planted
drivers and includes among it, is dropped. It is redone each time,
since a paused run's agent could plant again before it resumes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In the development host mode, protected checks and dependency
installations ran directly as the operator. They run the agent's code:
a test it wrote could read the home directory's secrets, reach the
network, or plant Git configuration that the trusted Git commands after
it would execute.
With WF_HOST_CHECK_SANDBOX=true they run under Seatbelt instead. File
contents in the home directory are unreadable except the command's own
directory and the paths the operator lists; it may write only there,
in the caches the operator lists and in a temporary directory of its
own, never in a .git directory. Only installations reach the network;
checks may use loopback ports by opt-in, for test suites that start
local servers. The platform's own ports (control plane, Temporal and
its web UI, database, object storage, provisioner, Git service, IDE,
console) stay blocked in any case: the local start lists them from
their configured addresses. Checks get no answer from the keychain,
and a command whose home is the executor's (holding its credentials)
gets a private one. A sandbox that cannot start leaves the run waiting
on infrastructure; verification evidence records checkSandbox.
scripts/check-host-check-sandbox.ts checks all of this on the target
Mac, from outside the sandbox, then runs the POC's installation and
checks sandboxed on a recent droboticflow source. Enabled on the local
POC, a real wish passed through both, including a repair round for the
agent's own failing tests.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The public checks after a POC rollout (health, readiness, the entry
page, the API build commit and the protected smoke checks) were each
made once. Just after a rollout the public address can still reach a
Pod that is shutting down, which answers with the old build commit, and
the link can drop: either failed a healthy release and rolled it back.
They now take up to six attempts, waiting 2 to 10 seconds; a release
whose checks never pass is still rolled back.
Retries were also silent: a build slowed down by a flaky link looked
stuck. Every repeat now says what went unanswered and when the next
attempt comes, in the run's timeline during a build and in the Runner's
log during a release. Requests and checks share one retry helper.
The third live test found kubectl cp and exec reporting a failed dial
as "error: dial tcp ...: connect: operation timed out", without the
"Unable to connect to the server" of get. That upload was not retried
and the build stopped; dial failures and connection timeouts now count
as unanswered, checked against the messages seen on the POC link.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In the 2026-10-26 POC run the Mac's link to the cluster API dropped
about once a minute. One unanswered kubectl call ended the whole build
twice, though the Kaniko Pod kept building, and each manual resume
re-ran the protected verification. The release path had the same
weakness with worse consequences: a dropped rollout watch counted as a
failed rollout and rolled a healthy release back.
Only requests that are safe to repeat are repeated, and only when the
cluster API left them unanswered (no connection, a broken connection,
kubectl hung), never when it refused them:
- Reads take up to six attempts, waiting 2 to 30 seconds between them.
- The builder looks its Pod up by its attempt-unique name before each
create, adopting a Pod whose create answer was lost.
- A lost source upload is sent again. Unpacking runs once at a time,
refuses an upload whose SHA-256 differs from the archive, and marks
the context ready only when complete, so Kaniko never starts from a
partial context; a damaged upload is sent again.
- A dropped rollout watch resumes for the rest of the rollout timeout.
Patches are still never repeated. A link that stays down longer still
stops the run as an infrastructure fault.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude Code and CodeBuddy report a session's usage only in their final
result. A session stopped before it (paused, canceled or out of time)
reported nothing, so its tokens never reached the run's budget or the
monthly plan: the paused session of the 2026-10-26 POC run was recorded
as 0 tokens, and repeated pauses could have spent without limit.
The adapter now adds up the usage each model response carries in the
stream, once per response although the CLI repeats it on every content
block, and reports that as the session's final usage when no total
arrives. The executor meters it like any final usage; the timeline
marks it as estimated, since the last response's output may be
undercounted.
The final result usually repeats the agent's last message word for
word, which the timeline then showed twice; it is now shown once.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A check stopped at its time or output limit lost everything it had
printed: the repair prompt only said that WishForge stopped it, not
where it hung. The stop now carries the output so far, and the
verification evidence and failed installations keep it, with the
reason appended.
- A command that left a process running (a test's server, say) held
its pipes open until the time limit and counted as hanging, and in
host mode such processes stayed on the machine. A command now ends
when its own process exits: the rest of its process group gets two
seconds to drain the pipes and is then stopped, as is anything else
it left running.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
With WF_CLAUDE_COMMAND_SANDBOX=true, Claude Code also gets Bash, run in
its built-in sandbox through --settings:
- The sandbox must start (failIfUnavailable), and no command may run
outside it (allowUnsandboxedCommands: false).
- No network: an empty allowedDomains with strictAllowlist, since an
absent allowlist leaves the network open. Local binding stays off,
because it would also open every local port, Temporal's included.
- Commands cannot read the home directories, the CLI's home or the
worker's own directory, except the workspace, a per-run scratch
directory and WF_CLAUDE_COMMAND_READ_PATHS; they write only to the
workspace and the scratch directory; credential variables are unset.
- WF_CLAUDE_COMMAND_ENV gives commands toolchain variables, such as the
POC's read-only Go module cache.
The executor probes the sandbox first (Seatbelt on macOS; bubblewrap
and socat on Linux) and keeps file tools only where it cannot start,
saying so on the timeline. The adapter now writes the execution
contract into the prompt, for the tools the agent actually has.
scripts/check-claude-command-sandbox.ts checks a machine with one short
real session and judges each probe by its effect, not the agent's
account. On the local Mac every probe was blocked; the login keychain
remains reachable, because Claude Code's Seatbelt profile always allows
the security server. That limit is documented.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude Code with a tenant key started with bypassPermissions and every
tool, Bash included, and loaded the repository's settings, hooks and MCP
servers. It now runs like the native development login already did:
restricted mode with dontAsk, only Read/Edit/Write/Glob/Grep, confined to
the workspace, and no repository or user settings. Every Claude Code run
is told the verifier runs installs and tests.
CodeBuddy's agent runs commands with no sandbox of its own. Like Codex
without its sandbox, it now starts only in a development (host) sandbox,
says so on the timeline, and stops with PROVIDER_SANDBOX_UNAVAILABLE on
Kata.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Add authenticated LAN access, native Claude execution, checkpoint and budget recovery, and signed POC build/deploy/rollback contracts. Include local service management, regression coverage, and evidence from the completed POC delivery.
The first runs on k3s found these problems; a wish now goes from submission
through the Codex executor, independent verification and integration in
per-run pods.
- Development deployments refused to start because the images set
NODE_ENV=production. The local manifest and the sandbox Jobs now set
NODE_ENV to the deployment mode.
- The model proxy treated x-client-request-id as a per-request idempotency
key. Codex sends its conversation id there, so every second request of a
session failed with 409. Only Idempotency-Key names a single request now.
- Codex's command sandbox (bubblewrap) cannot start in a runc pod. Every
command failed and the agent retried until the budget ran out. The
executor now probes the sandbox before starting Codex. A Kata sandbox that
cannot run it waits as PROVIDER_SANDBOX_UNAVAILABLE. A development (host)
sandbox runs Codex without it, and the timeline records that.
- The prompt asked agents to commit, but Codex keeps .git read-only and the
platform commits the checkpoint itself. Agents now leave their changes
uncommitted, and get the platform's Git identity if they commit anyway. A
resolved merge is recorded even when its tree equals HEAD.
- scripts/k3s-local.mjs:
- excludes the VM and cluster ranges from a host proxy (NO_PROXY);
- uses its own Docker client configuration, so a stale credential
helper does not break builds;
- recovers from an interrupted k3s install;
- reports when Colima switches the current kubectl or Docker context.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Sandbox Jobs never received WF_DEPLOYMENT_MODE, which every worker requires
before anything else, so each Kubernetes sandbox exited at start. The
provisioner now passes its own mode.
A local development cluster (k3s) has no Kata, no bubblewrap inside runc and no
TLS between services. For it, and only with WF_DEPLOYMENT_MODE=development:
- WF_ALLOW_INSECURE_HTTP=true lets services reach each other over plain HTTP
(Git, the model proxy, the provisioner and IDE gateway targets, the worker's
control-plane client); production refuses the setting outright.
- The provisioner accepts WF_RUN_SANDBOX_MODE=host and WF_KATA_RUNTIME_CLASS=none
and passes the HTTP settings to its sandboxes.
- The development seed is built into the image (dist/api/seed.mjs).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adding an executor touched the contracts, the API's availability check, the
worker and the console separately. Now it is an adapter plus one entry in
@wishforge/contracts' providerCatalog (name, executable variable, whether the
model proxy isolates its credentials) and one in the worker's
providerRegistry; the API, the console's options and MCP's submit_wish read
the catalog, and a test checks every entry is registered with the worker.
The CodeBuddy adapter already parsed Claude-Code-style stream-json, so it is
now a StreamJsonCliAdapter with a dialect per CLI. Claude Code runs headless
with --verbose and --permission-mode bypassPermissions inside the per-run
sandbox and receives only ANTHROPIC_* credentials (WF_CLAUDE_BIN). Like
CodeBuddy it is development-only until the model proxy supports it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In Kubernetes mode the per-run network policy allowed only DNS, the API,
Temporal and Git, so dependency installs could not reach a registry and image
builds had no builder.
- WF_RUN_INSTALL_PROXY_URL points both sandboxes at an operator's egress proxy
(pods labelled egress-proxy); the per-run policy admits it and installation
commands get HTTP(S)_PROXY, also inside bubblewrap, while checks still have
no network.
- WF_VERIFIER_DOCKER_HOST with a TLS client certificate points the verifier at
a remote builder daemon (pods labelled image-builder); a separate policy
lets only the verifier pod reach it, and release deletes that policy too.
Builds pass DOCKER_HOST, DOCKER_TLS_VERIFY and DOCKER_CERT_PATH, and refuse
a Docker context and a remote builder together.
- The control namespace's baseline admits sandbox traffic to both components.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
People's changes now reach the target branch the same way the agent's do. The
IDE credential carries a ref prefix and the Git service runs a pre-receive hook
on every push that refuses updates outside it, so the IDE can push only
`ide/` branches; the platform's own integration is unaffected.
- A wish may name a source branch. The run starts from that branch's head, the
agent builds on it, and verification, repair rounds, merging onto a moved
target and conflict repair work as before. A missing branch makes the run
wait (git_storage) until it is pushed.
- Release risk is now computed from the target branch before integration, not
from where the run started: a migration committed on the source branch would
otherwise have been missed and could have skipped approval.
- Clones work on `ide/work`; a plain `git push` publishes it.
- The console lists a project's IDE branches with a button to submit a wish
that merges one, and the new-wish form has a starting-point field; MCP
`submit_wish` accepts `sourceBranch`. The Git service lists branches under
a prefix for this (`POST /refs`).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Verification ran git inside the tree under test, kept no command output and
treated every infrastructure fault as a test failure; repairs went through an
executor lease the coordinator should not hold; and a project without delivery
could never succeed. This reworks the worker execution path and the control-plane
contracts it depends on.
- Verification exports the exact commit to a directory without .git, installs
dependencies (network allowed) and runs the protected commands under
bubblewrap in kata mode or directly in host mode; evidence records exit code,
duration, digest, a redacted output tail and the isolation used. Production
rejects host evidence. A failed installation waits as infrastructure.
- Waiting reasons are an enum with a redacted detail; dispatcher, GitHub and
model-proxy states map onto it, and the console explains each one with a way out.
- Repairs are requested by the coordinator through /internal/runs/:id/repair;
the control plane derives the failure summary from the verifier's evidence and
enforces the repair budget. Continuing after the budget is spent grants one more
round; a new requirement revision starts a fresh budget.
- Execution identities may only move a run within their own stages and only to
running or waiting; success comes from integration evidence (no delivery
configured) or deployment acceptance. The unused preview stage is gone.
- Integration fast-forwards when the target has not moved, merges and re-verifies
otherwise, retries when a push finds the target moved, and turns merge conflicts
into a repair round that merges the current target for the agent to resolve.
- Successful runs that needed a repair leave a project lesson; active lessons are
injected into later prompts, and admins can list, add, disable and delete them.
- Executor progress (messages, commands, file changes, plan updates) is stored as
normalized events; previously agent messages were recorded as the literal word
"output". Provider failures keep the work as a checkpoint and wait as
provider_error instead of failing the run.
- Workers declare WF_SANDBOX_MODE=host|kata (host refused in production),
heartbeat with retries until the lease could have expired, and retry safe
control-plane reads with backoff.
- tests/local-loop.test.ts runs the loop end to end with real Git, the in-process
control plane behind its internal routes and a scripted agent.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Integration caches are bare clones instead of mirrors. A mirror
remote refuses explicit refspecs, so every push to the target branch
or a GitHub review branch failed. Caches created by earlier versions
are corrected (remote.origin.mirror=false) and the target ref is
force-synchronised from the remote.
- Checkpoints bundle only the commits after their base (base..HEAD)
instead of the full history, so repositories with real history no
longer exceed the inline limit. Restoring clones the project
repository for the base, verifies and applies the bundle, then checks
the tree against the recorded patch. An unchanged workspace produces
no bundle; patches are capped at 4 MiB.
- Git commands get a 10 minute default timeout instead of the generic
120 s, which failed clones and pushes of larger repositories.
- Command output is decoded per stream with StringDecoder, so UTF-8
characters split across chunks are no longer corrupted (this made
executor/verifier patch digests disagree), and output accounting is
incremental instead of quadratic.
- The Git service forwards Content-Encoding to http-backend; gzipped
upload-pack negotiations previously failed with "bad line length".
- API JSON bodies: 16 MB for checkpoint uploads, 2 MB for the model
proxy, 1 MB elsewhere (was 8 MB everywhere, before authentication).
Regression tests push a verified candidate through a fresh and a legacy
mirror cache and restore an incremental checkpoint from its repository.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Security-relevant behaviour (development tokens, loopback HTTP, inline
checkpoints, raw provider keys, optional verification profiles) was
keyed off NODE_ENV === 'production', so any deployment that forgot
NODE_ENV silently ran with development rules.
- @wishforge/contracts exports deploymentMode/isProduction/
requireDeploymentMode. WF_DEPLOYMENT_MODE wins; misspelled values and
development combined with NODE_ENV=production are rejected; NODE_ENV
remains a fallback only for libraries and tests.
- All API, runtime, artifact, Git service and operator-script checks use
isProduction.
- The API, worker, Git service and Runner refuse to start without an
explicit WF_DEPLOYMENT_MODE; the IDE gateway treats anything other
than an explicit development mode as production.
- The development seed loads .env.local before checking the mode.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The API signed Runner tasks with keys sorted by localeCompare, while the
runner verified with code-unit order; environment keys such as
API_URL/API2 or DB_HOST/DBA sort differently, so valid deployment tasks
were rejected with INVALID_SIGNATURE. A third copy lived in the agent
package.
canonicalJson now lives in @wishforge/contracts (code-unit key order,
undefined properties omitted, non-JSON values rejected) and is used by
the API digest, Runner task signing/verification, the runner's state
digest and agent bundle digests. Binding digests computed by the old
locale-dependent order may differ, so releases requested before this
change must be requested again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Drop the WorkBuddy Cloud executor stub: it always reported
"unverified" and could never run. WorkBuddy remains an MCP client for
submitting wishes. Providers are now codex and codebuddy; an unknown
provider waits with an explicit reason instead of a fake adapter.
- Remove internal routes nobody calls (/internal/releases/:id/begin,
/accept, /failure and /internal/workspaces/:id/provisioned) with
their domain methods, the never-consumed release.ready and
release.rollback outbox events, an unreachable idempotency branch,
dead helpers in runtime/deploy.ts and an unused RunnerBroker
dependency.
- Enable noUnusedLocals in the base and web TypeScript configs; the
runtime package now extends the base config.
- Add tests/tsconfig.json and include it in `npm run typecheck`. This
surfaced tests still calling the deleted begin/accept path (now
exercised through the Runner protocol) and five latent type errors.
- Web: provider capability labels match the API's keys and the wish
form disables unavailable providers.
- Delete the invalid example Runner Job manifest; stop tracking the
generated apps/web/next-env.d.ts.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The IDE carried a second, Theia-internal coordination system: multi-
client save barriers, a hash-chained snapshot store, IndexedDB draft
recovery, transferable debugger-control leases that intercepted
Theia's plugin RPC, Ed25519 actor assertions from the gateway, and an
API gate that blocked every agent integration while any IDE workspace
was open until a human imported a coordinated snapshot. It depended on
Theia internals, made F5 debugging require five environment variables
plus a gateway-signed header, and stalled agent runs. IDE and agents
now hand off through Git commits (docs/architecture.md ADR-7).
- Delete apps/ide/coordination, apps/ide/security, the policy
extension's coordination/draft/DAP-guard/lifecycle-safety modules and
the unused product.json; the policy extension keeps only the managed
extension allow-list and scoped collaboration.
- API: workspace snapshot import/match/check routes are gone. The
project integration lease (one integrating run per project, fenced)
moves to domain/integration-lease.ts and is still enforced on
integrate/build transitions and build evidence.
- Workspace lifecycle: pause/resume no longer requires a save barrier;
automatic sleep needs 30 idle minutes and zero gateway connections,
which the gateway now reports itself. The lifecycle/integration
authorize relays and the gateway's assertion signing are removed;
gateway edit roles match the contract roles.
- Worker: no snapshot matching, workspace-input gate or local lock
file during integration; runtime workspace-snapshot is removed.
- Web: the snapshot import panel is removed from run detail.
- Provisioner workspaces no longer mount coordination state or the
gateway public key; local setup no longer generates gateway keys.
The local Theia build under apps/ide/lib must be rebuilt to pick up the
slimmer policy extension.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Environments defaulted to "private" visibility, which required a
separate per-environment preview gateway, capability tokens, signed
anonymous/authorized probe proofs and API-side proof verification;
without that stack every deployment was blocked. Access control for a
deployed application is now the target environment's responsibility
(docs/requirements.md FR-G6).
- Delete apps/preview-gateway, the API preview controllers/domain
(previews, private-access-verifier) and runtime private-access.
- Environments keep an optional application URL; production releases
still require one plus a fresh access check reported by the Runner.
The URL may never share an origin with the console, API or IDE.
- Release bindings, runner task payloads, deployment evidence and
rollback compatibility no longer carry visibility or private-access
policy digests. PATCH /v1/environments/:id/access becomes
/v1/environments/:id/application-url.
- Web: the delivery launch route is gone; environments configure an
application URL only (the always-rejected "Runner ID" field is
removed); releases and run detail link the live application URL.
- Remove the preview-gateway image target and test:preview script.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds prettier 3.9.8 (exact) with a shared config (single quotes,
120 columns, trailing commas), .prettierignore, .editorconfig and the
`format` / `format:check` scripts, then formats all TypeScript,
JavaScript, CSS, JSON and YAML sources.
Purely mechanical: no behaviour change. Typecheck passes, the vitest
suite and the 74 IDE node tests produce the same results as before
(socket-binding tests still cannot run inside this sandbox).
Previously the longest source line was ~3000 characters; reviewing the
following semantic changes now produces readable diffs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Imports the previously untracked working tree as-is so that the review
changes that follow (requirements -> design -> implementation) can be
reviewed as diffs and reverted if needed. No content changes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>