When a payload reports weighted counters but omits hard_cap, the soft/hard
split collapses to a single umans:requests row keyed off the authoritative
weighted effective-request counter, so a spent account can report exhausted
instead of being stuck at warning forever. Raw burst traffic above the limit
still never fabricates exhaustion; weighted headroom stays decisive (#7858).
xAI's /v1/responses rejects presence/frequency penalties for every Grok
model, not only reasoners. Gate supportsPenaltyAndStopParams on isXaiHost
so xai/grok-2 no longer serializes presence_penalty.
First-party xAI /v1/responses rejects reasoning.summary. Bake
supportsReasoningSummary=false for both xai and xai-oauth so paid
grok-4.5 effort requests send only reasoning.effort, matching SuperGrok.
Exa MCP servers were always filtered out because the native Exa integration covers web_search_exa. But configs that explicitly request web_fetch_exa or web_search_advanced_exa have no native equivalent, so filtering them made /mcp reconnect exa fail and hid those tools. Keep the MCP server mounted when its tools restriction includes anything beyond web_search_exa, while still extracting the API key for native search.
Move the per-request date/cwd line out of the system prompt into a
first-turn system-reminder so open-weight providers keep their tool-schema
prefix cache; the reminder refreshes itself at midnight. Closes#7404.
Generated with Codebuff 🤖
Co-Authored-By: Codebuff <noreply@codebuff.com>
Split the request limit into a weighted soft-cap row and a raw burst-ceiling
row so healthy accounts no longer read as exhausted; surface the rolling
window's resets_at as a countdown. Closes#7858.
Generated with Codebuff 🤖
Co-Authored-By: Codebuff <noreply@codebuff.com>
- Switched Docker images to build native addons via cargo/napi-rs (`OMP_NATIVE_BUILD_BACKEND=cargo`) instead of Bazel.
- Updated Cargo.toml workspace members explicitly to prevent loading errors from stale directories under crates/.
- Added depth-agnostic patterns to .dockerignore files to exclude nested build outputs from Docker build contexts.
- Added OMP_NATIVE_CARGO_PROFILE environment variable to support configuring cargo profiles for addon builds.
The win32 addon static-CRT switch enabled the static_link_msvcrt cc
feature, but audiopus_sys's bundled opus is built through the generated
CMake toolchain, which pinned CMAKE_MSVC_RUNTIME_LIBRARY=MultiThreadedDLL
(/MD) as authoritative under CMP0091 NEW. The opus objects could then
still emit /MD and pull VCRUNTIME140.dll / conflict with the static CRT
the rest of the addon links, leaving the outcome dependent on compile-
flag ordering.
Pin CMAKE_MSVC_RUNTIME_LIBRARY to MultiThreaded (static release /MT) in
the msvc toolchain.cmake so opus deterministically matches rustc's
+crt-static and the static_link_msvcrt feature.
Verified with a fully cold `bazel build //:natives-win32-x64-baseline`
(opus recompiled): the produced .node imports no VCRUNTIME140.dll and no
api-ms-win-crt-* — only core Windows system DLLs.
Fixes#8439
The shipped win32-x64 pi_natives addon linked the dynamic MSVC CRT (/MD)
and imported VCRUNTIME140.dll from the Visual C++ Redistributable, which
is absent on a clean Windows install. LoadLibrary of the extracted .node
then failed with error 126 ("The specified module could not be found"),
so omp could not start after a fresh `irm install.ps1 | iex`.
Static-link the CRT for the win32 addon: +crt-static for rustc (crate
BUILD select) plus the static_link_msvcrt cc feature enabled for win32 in
the native_addon transition, so its C deps (opus/cmake, tree-sitter,
blake3, ring) compile /MT in lock-step. The rebuilt .node imports only
core Windows system DLLs -- no VCRUNTIME140.dll, no api-ms-win-crt-*.
Fixes#8439
Kept direct Herdr panes on the host-safe in-place resize path so streaming redraws no longer clear and replay pane scrollback.
Updated the resize regression, stress scenario, renderer docs, and changelog.
Fixes#8431
- Generalized thinking loop guard and helper functions to support Gemini, DeepSeek, and Grok model families.
- Replaced `withGeminiThinkingLoopGuard` and related Gemini-specific symbols with generalized counterparts.
- Removed deprecated `enableGeminiThinkingLoopGuard` options and associated tests.
- Updated test suites and agent session logic to use the generalized thinking loop guard and model family tokens.
- Replaced blanket subagent advisor global settings with fine-grained per-agent configuration and frontmatter support.
- Added dashboard keybindings and inline override editors for managing agent advisor patterns.
- Implemented settings migration logic to convert legacy global options into per-agent settings.
- Updated session persistence and execution layers to restore and enforce per-agent advisor behaviors.
- Updated user agent and openrouter titles in packages/ai from Oh-My-Pi to omp.
- Integrated getOpenRouterHeaders into image generation tool requests in packages/coding-agent.
- Updated provider documentation and test assertions to reflect the rebrand.
The per-command non-interactive env hardcoded an unguarded CI=1, which clap parses as a strict boolean and rejects (breaking e.g. tauri android build). It also overrode the session env, so the documented PI_BASH_NO_CI opt-out never reached bash-tool commands.
buildNonInteractiveEnv now injects CI=true and strips CI when PI_BASH_NO_CI/CLAUDE_BASH_NO_CI is set, matching buildSpawnEnv in procmgr.ts.
Fixes#8229
Documented that the hosted Go relay has no published source or standalone binaries, and linked the repository's WebSocket-only local protocol relay with its startup command and limitations.
Fixes#8165
projectLabel() basenames the primary checkout root to build the Hindsight
`project:` tag, and it preserved case. Hindsight matches tags literally,
so a checkout at ~/code/General retained and recalled under
`project:General` while every other client of the same bank used
`project:general`. One repository then owns two scopes that never meet:
recall filters on the session's own tag, so neither side sees the other's
facts, and consolidation treats them as unrelated projects. A live bank
measured 581 facts stranded under a case variant on 2026-08-09.
Fold the case at the source, after the primary-root resolution added for
issue #2232, so the worktree axis and the casing axis collapse together.
Per-project bank ids lowercase for the same reason.
- hindsight/bank.ts: lowercase the resolved basename, and document why.
- test/hindsight-bank.test.ts: cover the fold on plain paths, on a
mixed-case checkout root, and on a linked worktree of one. The non-repo
fallback assertion now folds its own mkdtemp suffix.
- docs/memory.md: state how the project label is derived.
- CHANGELOG: Fixed entry under Unreleased.
- Lifted legacy Type.Unsafe documents into callable omptype schemas so Optional and Object composition preserve validation and required fields.
- Ran installed extension factories against the normal throwaway loader surface before accepting a plugin install.
- Added regression coverage and documented the stronger rollback gate.
Fixes#8143
- Added comprehensive reference documentation for OpenAI compatibility flags, reasoning levels, and tool handling policies.
- Detailed provider-specific quirks covering stream handling, authentication, quotas, and catalog model behaviors.
- Updated provider endpoint constraints with cross-references to the new compatibility and quirks references.
Harness-initiated session aborts previously cancelled compaction before the handoff reason was recorded. The handoff catch then saw only an aborted signal and replaced the harness reason with "Handoff cancelled".
Abort the handoff first with the session reason, forward caller-signal reasons, and reserve "Handoff cancelled" for direct or unreasoned cancellation. Add a regression test for an in-flight handoff aborted through AgentSession.abort.
Fixes#7993
- Runtime error now just says to download vscode-js-debug from its GitHub repo;
tarball recipe, extract path, env var, and Mason detail stay in docs/tools/debug.md.
can1357