resolveModelForDelegateTask returned input.userModel immediately without
availability checking when it was set, silently ignoring the user's
configured fallback_models. Effect: a team-mode category member
(e.g. hyperplan's 'artistry' category) configured with
{ model: "opencode/gemini-3.1-pro", fallback_models: [...] }
spawned with the unreachable primary even though a listed fallback was
reachable, leading to a dropped/broken team member instead of graceful
degradation.
Now, when the provider-models cache is warm AND userFallbackModels is
non-empty, the function verifies userModel is reachable via
fuzzyMatchModel. If not, it iterates userFallbackModels and promotes the
first reachable entry. Cold-cache (first-run) behavior is preserved -
the userModel is returned as-is when availability data is unavailable,
matching the existing 'trust the user' contract covered by the
pre-cache test fixtures.
Adds three regression tests covering: (1) unreachable primary + reachable
fallback -> fallback promoted, (2) reachable primary + reachable fallback
-> primary kept (fast path), (3) unreachable primary + unreachable
fallback -> legacy trust-user behavior preserved.
Sync the PR branch with the newest dev branch and resolve the new import-level conflicts in background-agent manager and runtime-fallback tests. Preserve both the delegated bootstrap coverage from this branch and the newer upstream test utilities and runtime wiring changes, then re-verify the affected delegated fallback suites and typecheck.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
The circuit breaker in manager.ts uses recordToolCall to detect when a subagent gets stuck repeating identical tool_use blocks. It passed partInfo.state?.input as the tool-input signature. When a model (Kimi K2.6 in the reporter's case) emits duplicate tool_use parts faster than the tool actually starts running, state.input is still null, so loop-detector falls back to the bare 'tool::__unknown-input__' signature. As soon as one part has state.input populated (next event), the signature flips to 'tool::{actual-args}' and the consecutive counter resets to 1, repeatedly. The breaker never reaches its 20-call threshold.
Add a top-level input?: Record<string, unknown> field to the local MessagePartInfo interface and prefer state.input when present, falling back to the part's own input when state is still pre-running. The OpenCode part payload carries the tool input as soon as the tool_use block is generated, so this fallback restores signature stability across the model's repeated emissions.
Verification: added 2 regression tests in manager-circuit-breaker.test.ts. Test 1 (reproduce) emits 20 part.updated events with only top-level input and asserts the task is cancelled by the breaker — fails before the fix, passes after. Test 2 confirms that when state.input IS present, it still wins over the top-level input (precedence preserved). All 10 manager-circuit-breaker tests pass, all 20 loop-detector tests pass, typecheck clean.
Cubic AI reviewer flagged the use of the untrusted Host header as the
URL base in startCallbackServer. The server only binds to 127.0.0.1,
so hardcoding "http://127.0.0.1" as the URL base is robust against
malformed or manipulated Host values and matches upstream behavior
prior to the node:http refactor.
The dist-bundle regression tests in
src/shared/dist-bundle-bun-globals.test.ts are guarded by
`test.skipIf(!existsSync("dist/index.js"))` and dist/ is
gitignored, so they silently skipped in CI which ran tests before
the build step. Adding the build step earlier ensures the
regression guard runs and a future raw `Bun.*` leak in the bundle
fails CI.
Existing test only checked `globalThis.Bun` top-level destructures
and `__require` calls. Add two new test cases:
1. Raw Bun runtime API scanner: scans dist/index.js for any
`Bun.<anyMethod>(` or `Bun.<anyMethod>.` call outside shim-safe
patterns (runtime.Bun, globalThis.Bun, typeof Bun, and the
"Bun is not defined" error-message string). Uses a negative
lookbehind so shim indirection (`runtime.Bun.foo`) passes.
2. Node smoke test: imports dist/index.js under
`node --input-type=module` and asserts stderr contains no
`ReferenceError` and no `Bun is not defined`. The existing
case 3 only checked exit code, which masked lazy-evaluation
crashes that fire after import. Reading exports forces lazy
module-level evaluation paths to run.
bun-install.ts streamToText() was reachable from the plugin bundle via
the cli/config-manager barrel re-export. Replace with the WHATWG
standard `new Response(stream).text()` pattern which works
identically in Bun and Node and avoids the last raw Bun.* runtime
call in dist/index.js.
The OAuth callback server was using Bun.serve, which would crash if
mcp-oauth code paths ever entered the plugin bundle. Switch to
node:http.createServer with the same WHATWG behavior:
- Binds to 127.0.0.1, preserves 200/400/404 status codes
- Translates fetch(Request)→Response to (req, res) callback style
- Clears OAuth timeout on success/error/missing-param paths
- Replaces server.stop(true) with server.close() for shutdown
Functional behavior and response bodies unchanged.
isPortAvailable() previously bound a one-shot Bun.serve and stopped it.
That call was reachable from the plugin bundle through
src/shared/index.ts barrel re-export and crashed on Electron.
Switch to node:net.createServer().listen(port, host), which Bun fully
implements as well. Adds a 2s safety timeout and removes both
"error" and "listening" handlers on resolution to prevent listener
leaks. Behavior is bit-equivalent: returns true iff a server can bind
to (host, port) right now.
Test file is fully rewritten away from stale Bun.serve mocking. New
tests exercise: free-port detection via port 0, EADDRINUSE handling
via a real net.createServer blocker, findAvailablePort range
exhaustion, getAvailableServerPort auto-selection, 127.0.0.1 default
hostname binding, and probe-server resource cleanup.
Eliminates 19 unguarded `Bun.*` runtime call sites in the plugin bundle
that crashed with `ReferenceError: Bun is not defined` under Electron.
Per-tool-call hot paths (executed on every Read/Edit):
- src/tools/hashline-edit/hash-computation.ts: Bun.hash.xxHash32 → bunHashXxh32
- src/tools/hashline-edit/hashline-edit-executor.ts: 8 sites via bunFile/bunWrite
- src/hooks/hashline-read-enhancer/hook.ts: Bun.file → bunFile
- src/hooks/hashline-edit-diff-enhancer/hook.ts: 2 sites via bunFile
Plugin-load paths:
- src/hooks/claude-code-hooks/config.ts and config-loader.ts: Bun.file → bunFile
- src/features/claude-code-mcp-loader/loader.ts: Bun.file → bunFile
- src/features/claude-code-plugin-loader/mcp-server-loader.ts: Bun.file → bunFile
- src/features/team-mode/deps.ts: Bun.spawn → spawn shim
- src/hooks/session-notification-utils.ts: Bun.which → bunWhich, also drops
the bare `declare const Bun` ambient declaration
- src/shared/binary-downloader.ts: Bun.write → bunWrite
Pure mechanical API swaps. No control-flow or signature changes.
The plugin builds with `bun build --target bun` and runs under OpenCode
CLI (Bun SEA) but also under OpenCode Desktop (Electron / Node V8) where
`globalThis.Bun` does not exist. Mirror the existing `bun-spawn-shim.ts`
pattern for three more Bun runtime APIs:
- bun-file-shim: bunFile()/bunWrite() backed by node:fs/promises with
ArrayBuffer slicing to avoid Node Buffer pool exposure
- bun-hash-shim: pure-JS XXH32, bit-exact with Bun.hash.xxHash32 verified
by 1200-pair fuzz comparison so existing hashline LINE#ID tags remain
stable across runtimes
- bun-which-shim: synchronous PATH walker with Windows .exe/.cmd/.bat/.com
extensions plus isUnsafeCommandName guard that rejects path separators,
parent traversal, drive letters and null bytes before any probe
Each shim uses the canonical `runtime.Bun !== undefined` detection and
delegates to native Bun under IS_BUN, otherwise uses Node primitives.
Each ships with a co-located test that exercises both branches via the
`node:vm.runInNewContext` pattern from bun-hash-shim.test.ts.
Handle OpenCode session events that carry the session ID under properties.info.id or properties.info.sessionID so background tasks and continuation hooks do not miss idle/error/delete events.
Add regression coverage for nested session.idle events completing background tasks and waking continuation hooks.
Sync the PR branch with the latest dev branch and resolve the remaining conflict in sync-task.test.ts while preserving both the new upstream poll-recovery coverage and this branch's delegated bootstrap cleanup and isolation coverage. Re-verified the affected delegated fallback suites and typecheck after the merge resolution.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
When a subagent session (e.g. Momus on GPT) hits a quota/usage-limit
error and the agent's category has no `fallback_models` configured, the
runtime-fallback hook previously returned silently. The OpenCode session
stayed in `retry` status indefinitely while the SDK kept hitting the
limit, the sync-task poller treated `retry` as active work, and the
parent's pending `task` tool call never resolved — leaving a stuck
"waiting for subagent" indicator in the parent conversation.
Narrow fix: at the `fallbackModels.length === 0` exit point, if the
session is a known subagent AND the error classifies as
`quota_exceeded`, abort the subagent session. The existing
`getTerminalSessionError` path in `sync-session-poller.ts` then surfaces
the error via the parent's tool result, which is the persistent surface
the user is already watching.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
YeonGyu-Kim