Map pause_turn to "pauseTurn" instead of "stop" so the agent loop
continues when Anthropic's server pauses a long-running turn (e.g.
native web search hitting its iteration limit). Previously the
incomplete server_tool_use block was saved to history, causing a
400 invalid_request_error on the next API call.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The "Extra usage is required for long context requests" error from
Anthropic is a billing gate, not a transient rate limit. Classify it as
quota_exhausted so the handler enters the fallback path instead of an
infinite backoff loop. When no cross-provider fallback exists, attempt a
[1m] to base model downgrade before stopping cleanly.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When gsd is spawned as an RPC bridge child process, stdout is a pipe
(process.stdout.isTTY === undefined). The TUI render loop would run at
~4,600 renders/sec writing ANSI escape codes to the pipe, consuming
500%+ CPU per process while idle.
Add isTTY guard to Terminal interface, ProcessTerminal.start(), TUI.start(),
and requestRender() so the entire render pipeline is skipped on non-TTY stdout.
RemoteTerminal (browser-backed) correctly reports isTTY=true.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Saves in-progress daemon work from M005-m138xe that was sitting uncommitted.
Includes orchestrator expansion, event bridge/formatter enhancements,
message batcher tweaks, and discord bot additions.
Tests cover: provider registration, base URL + API type, reasoning +
context window specs, and non-collision with generated zai models.
Required by CI lint gate (require-tests.sh).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
GLM-5.1 is the latest Zhipu AI model with 204K context window and
131K max output tokens. It uses the Z.AI Coding Plan endpoint
(OpenAI-compatible) and supports reasoning via enable_thinking.
Not yet tracked by models.dev, so added to models.custom.ts alongside
existing alibaba-coding-plan entries. Merges additively with the
generated Z.AI provider (glm-5, glm-5-turbo, etc.).
Specs from https://docs.z.ai/devpack/using5.1
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: Migrated headless orchestrator to use execution_complete events,…
- "src/headless.ts"
- "src/headless-ui.ts"
- "src/tests/headless-v2-migration.test.ts"
GSD-Task: S06/T02
* test: Wired pi-coding-agent to re-export JSONL utils from @gsd/rpc-clie…
- "packages/pi-coding-agent/src/modes/rpc/jsonl.ts"
- "packages/pi-coding-agent/package.json"
- "packages/rpc-client/src/index.ts"
- "packages/rpc-client/src/jsonl.ts"
- "packages/rpc-client/src/rpc-client.ts"
- "packages/rpc-client/src/rpc-types.ts"
- "packages/rpc-client/src/rpc-client.test.ts"
- "packages/rpc-client/package.json"
GSD-Task: S06/T03
* feat: Wire --resume flag to resolve session IDs via prefix matching and…
- "src/headless.ts"
- "dist/headless.js"
GSD-Task: S01/T01
* test: Added 5 e2e integration tests proving headless JSON batch, SIGINT…
- "src/tests/integration/e2e-headless.test.ts"
GSD-Task: S01/T02
* test: Updated @gsd/rpc-client and @gsd/mcp-server to 2.52.0 with publis…
- "packages/rpc-client/package.json"
- "packages/mcp-server/package.json"
- "packages/rpc-client/.npmignore"
- "packages/mcp-server/.npmignore"
GSD-Task: S02/T01
* chore: auto-commit after complete-milestone
GSD-Unit: M002-gzq23a
* fix: revert jsonl.ts to inline implementation — @gsd-build/rpc-client not available at source-level test time in CI
The re-export from @gsd-build/rpc-client fails in CI because tests run against
TypeScript source (--experimental-strip-types) before any build step. The npm
dependency resolves to node_modules/ which requires dist/ to exist. Reverting
to the original inline implementation eliminates the cross-package dependency
for source-level imports.
The re-export from @gsd-build/rpc-client fails in CI because tests run against
TypeScript source (--experimental-strip-types) before any build step. The npm
dependency resolves to node_modules/ which requires dist/ to exist. Reverting
to the original inline implementation eliminates the cross-package dependency
for source-level imports.
* refactor(pi-ai): replace model-ID pattern matching with capability metadata
Add ModelCapabilities to Model<TApi> and a CAPABILITY_PATCHES mechanism
so call sites read model.capabilities fields instead of parsing model IDs
or hardcoding provider names.
- types.ts: add ModelCapabilities interface (supportsXhigh, requiresToolCallId,
supportsServiceTier, charsPerToken) and capabilities?: ModelCapabilities to
Model<TApi>
- models.ts: add CAPABILITY_PATCHES table applied at registry init; patches
declare GPT-5.x and Opus 4.6 capabilities once instead of repeating ID
checks at every call site; supportsXhigh() now reads capabilities only
- service-tier.ts: extract SERVICE_TIER_MODEL_PREFIXES constant so the gating
list has a single named home; add path comment pointing to issue #2546 for
the full capability-driven follow-up
No behaviour change. New models and providers can declare capabilities in
their model definitions without touching function logic.
Closes#2546
* fix(pi-ai): apply capability patches to custom/discovered/extension models
Models constructed outside the static pi-ai registry (custom models
from models.json, extension-registered models, discovered models)
bypassed CAPABILITY_PATCHES — causing supportsXhigh() to silently
return false for GPT-5.x or Opus 4.6 variants registered through
those paths.
Export applyCapabilityPatches() from pi-ai and call it in ModelRegistry
after model assembly in all three construction paths: loadModels(),
applyProviderConfig(), and discoverModels().
Add regression tests covering patching, precedence, idempotency,
and synthetic models that mimic the custom/extension path.
Closes#2546
On Windows, `spawn()` with `detached: true` sets the
CREATE_NEW_PROCESS_GROUP flag in CreateProcess. In certain terminal
contexts — notably VSCode's integrated terminal (ConPTY), Windows
Terminal, and some MSYS2/Git Bash configurations — this flag conflicts
with the parent process group hierarchy and causes a synchronous EINVAL
from libuv, making *every* bash/async_bash/bg_shell command fail
immediately with `spawn EINVAL`.
The bg-shell extension already guards against this with
`detached: process.platform !== "win32"` (process-manager.ts:109),
but three other spawn sites were missed:
- `packages/pi-coding-agent/src/core/tools/bash.ts` (bash tool)
- `packages/pi-coding-agent/src/core/bash-executor.ts` (RPC executor)
- `src/resources/extensions/async-jobs/async-bash-tool.ts` (async_bash)
This commit aligns all spawn sites with the bg-shell pattern.
Additionally fixes two related issues:
1. `killProcessTree()` in shell.ts used `detached: true` on its own
`taskkill` spawn call — unnecessary and potentially problematic
in the same terminal contexts. Removed.
2. `killTree()` in async-bash-tool.ts used Unix-only
`process.kill(-pid)` with no Windows fallback. On Windows, negative
PIDs (process group kill) are not supported, so orphaned child
processes could survive timeout kills. Now uses `taskkill /F /T`
on Windows, matching the bg-shell and shell.ts implementations.
Includes a regression test that statically verifies no spawn site
uses unconditional `detached: true`, plus a smoke test confirming
the platform-guarded pattern works on all platforms.
Reproduction: Run GSD v2.42-v2.51 inside VSCode on Windows 11 with
Git Bash as the shell. Any bash tool call fails with `spawn EINVAL`.
The error is 100% reproducible and affects all shell operations
(bash, async_bash, bg_shell start).
Co-authored-by: Matt Haynes <matt@auroraventures.io>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The webSearchResult branch deleted entries from pendingTools after rendering,
which removed the duplicate-prevention guard. Subsequent streaming tokens
re-iterated content blocks, re-created the serverToolUse component, and
re-rendered the search result — producing 18+ duplicate blocks.
The message_end handler already calls pendingTools.clear(), so the explicit
deletes were unnecessary and harmful.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
