Forwarded persisted provider stream timeout settings into model requests so slow local LLM streams can widen or disable first-event and idle watchdogs without environment variables.
Fixes#3878
- Added a fallback from `hashline` to `replace` mode for Kimi-family models to resolve compatibility issues.
- Introduced `PI_STRICT_EDIT_MODE` environment variable to bypass automatic model-specific edit-mode fallbacks.
- Updated `getEditVariantForModel` to perform case-insensitive matching for model variant configurations.
- Added comprehensive unit tests for edit mode resolution and settings configuration.
The non-multiplexer resize fast path borrows the alternate screen for
throwaway drag frames. Warp reports a terminal height one row different
for the alt buffer, so each alt enter/leave emits a fresh SIGWINCH that
re-enters the fast path — a self-sustaining loop that floods ED3 full
repaints with completely stable geometry (observed ~130
fullPaint(clearScrollback) frames over 15s, continuing after the drag
stopped). PI_FORCE_SYNC_OUTPUT cannot help (it is a loop, not tearing);
tmux works because the multiplexer path never toggles the alt buffer.
Route resize through the in-place repaint path (no alt-screen borrow, no
ED3 rewrap) for multiplexers and for terminals that re-report size on
alt-screen toggles, via resizeRepaintsInPlace(). Default-on for Warp,
overridable with PI_TUI_RESIZE_IN_PLACE=1|0. Tradeoff matches a
multiplexer: scrollback above the window keeps its old wrap.
Tests assert no alt-screen borrow / no ED3 across a Warp resize burst and
that the override toggles both ways; existing direct-terminal resize
tests now pin TERM_PROGRAM so they stay deterministic under Warp.
Individual conflict resolution now bypasses the LSP writethrough to prevent formatting from corrupting other unresolved marker blocks and to avoid noisy diagnostics in partially resolved files.
- Fixed help rendering so `--help` no longer triggers unrelated command loaders.
- Fixed startup span logging to emit markers only with PI_DEBUG_STARTUP set.
- Fixed logger startup trace behavior for `:start`, `:done`, and `:fail` phases.
- Fixed prompt template processing with cached raw-template compilation and safer formatting.
- Optimized symbol and tag parsing in prompt templates via manual parsers.
- Handled frame shrink by re-anchoring windowTop and chunkTo at commit boundaries.
- Reset committedRows when the frame shrank into committed content to keep history immutable.
- Treated geometryChanged like overlay when advancing chunkTo to stabilize repaint commit timing.
- Updated regressions to assert stable scrollback prefixes and no clear-home/dclear repaint bytes.
- Changed the `github-copilot` service provider to resolve credentials only from `COPILOT_GITHUB_TOKEN`.
- Updated CLI extra help text to document `COPILOT_GITHUB_TOKEN` as the GitHub Copilot environment variable.
- Reworded environment variable docs to reflect the revised Copilot/GitHub token usage and order.
- Added `PI_NO_SYNC_OUTPUT=1` env var to disable DEC 2026 wrappers while keeping autowrap guards active around paints.
- Removed Termux-specific height-change no-op; all non-multiplexer resizes now repaint to prevent phantom blank rows.
- Added `linux-normal-vteNoSync-small` stress scenario and issue-1765 regression tests.
Follow-up to CMUX_SURFACE_ID env var support — document it alongside
KITTY_WINDOW_ID, TMUX_PANE, etc. in environment-variables.md and
session-switching-and-recent-listing.md.
- Passed ANTHROPIC_SEARCH_BASE_URL through to Anthropic web search calls that use authStorage fallback credentials instead of only applying it with ANTHROPIC_SEARCH_API_KEY.
- Added regression coverage asserting fallback Anthropic credentials use the search-specific base URL.
- Updated the environment and web_search docs to reflect the actual credential and base URL resolution order.
Fixes#1694
The Anthropic web search path built request headers via buildAnthropicSearchHeaders, which never threaded model headers through buildAnthropicHeaders, so ANTHROPIC_CUSTOM_HEADERS was dropped from every web-search request regardless of mode. The streaming path's resolveAnthropicCustomHeaders also gated on isFoundryEnabled(), so users with a corporate ANTHROPIC_BASE_URL + ANTHROPIC_CUSTOM_HEADERS (e.g. X-Gateway-Key) got 401s on web_search unless they set CLAUDE_CODE_USE_FOUNDRY=true.
Loosen the resolver to also apply when ANTHROPIC_BASE_URL points to a non-Anthropic host, export the baseUrl-keyed variant, and have buildAnthropicSearchHeaders pass the resolved custom headers as modelHeaders so search and streaming paths behave identically. Stock api.anthropic.com (no Foundry) still omits the headers.
Fixes#1693
- Expanded the existing entries in docs/environment-variables.md so the override-semantics ('search-only, isolates from main ANTHROPIC_API_KEY / ANTHROPIC_BASE_URL / FOUNDRY_BASE_URL') are spelled out, and added a usage note for enterprise-gateway split routing.
- Surfaced the search-only env vars (ANTHROPIC_SEARCH_API_KEY / ANTHROPIC_SEARCH_BASE_URL / ANTHROPIC_SEARCH_MODEL) in the Anthropic provider section of docs/tools/web_search.md, where users were already looking.
- Added ANTHROPIC_SEARCH_BASE_URL alongside ANTHROPIC_SEARCH_API_KEY in 'omp --help' so the pair shows up together in the CLI env-var summary.
Fixes#1694
OpenAI-compatible local servers can spend longer than the generic first-event budget processing large prompts before they emit response headers or SSE frames. The OpenAI-specific idle timeout now also acts as the OpenAI-family first-event floor unless an explicit OpenAI first-event timeout is configured.
Added regression coverage for OpenAI Responses request setup so a lower generic first-event watchdog no longer undercuts PI_OPENAI_STREAM_IDLE_TIMEOUT_MS.
Fixes#1603
- Changed tiny-device preference resolution to always default to CPU instead of platform-specific DirectML/CUDA heuristics.
- Updated settings schema, documentation, and changelog text to describe the CPU default while keeping accelerated providers behind explicit `providers.tinyModelDevice`/`PI_TINY_DEVICE` choices.
- Added persistent settings in the Providers tab for ONNX execution provider and quantization/precision, replacing env-var-only configuration.
- PI_TINY_DEVICE and PI_TINY_DTYPE env vars still override the matching setting at spawn time.
- Added tinyWorkerEnvOverlay to map settings onto worker env without clobbering explicit env vars.
- Updated docs and tests to reflect the new setting-first resolution order.
- Added `PI_TINY_DEVICE` env var to control ONNX execution provider (`gpu` default, `cpu`, `metal`, `cuda`, `dml`, `coreml`).
- Local tiny-model inference now tries accelerated GPU provider first and retries on CPU if initialization fails.
- Added `device.ts` module with normalization, preference resolution, and load-order helpers.
- Updated docs and model descriptions to drop CPU-specific language.
Wafer (https://wafer.ai) exposes a single OpenAI-compatible endpoint
(`https://pass.wafer.ai/v1`) for two SKUs whose entitlement differs
server-side, so we model them as two parallel providers — mirroring the
firepass/fireworks split so a user with both subscriptions can switch
without re-pasting:
- `wafer-pass` — flat-rate. `/v1/models` is filtered to entries whose
`wafer.tier === "pass_included"`.
- `wafer-serverless` — pay-as-you-go superset of Pass.
Both issue `wfr_…` keys. `/login wafer-pass` and `/login wafer-serverless`
paste-and-validate via `/v1/models`. `WAFER_PASS_API_KEY` and
`WAFER_SERVERLESS_API_KEY` are wired through `getEnvApiKey`.
Bundled catalog:
- `wafer-pass`: GLM-5.1, Qwen3.5-397B-A17B.
- `wafer-serverless`: GLM-5.1, Qwen3.5-397B-A17B, Kimi-K2.6, Qwen3.6-35B-A3B.
Dynamic discovery via `/v1/models` overlays additional models at runtime
and folds the `wafer` envelope (tier, capabilities, cents/M pricing) into
the canonical `Model<"openai-completions">` shape. GLM-family entries
carry the zai-style thinking compat (`thinkingFormat: "zai"`,
`reasoningContentField: "reasoning_content"`) so reasoning tokens land in
the right field. Cents-per-million → dollars-per-million via /100.
Tests (`packages/ai/test/wafer.test.ts`, 5 cases): bundled catalog
contract for both providers and wire-id pass-through (case-sensitive,
no rewrite — `GLM-5.1` must round-trip verbatim or upstream 404s).
Optional `packages/ai/test/wafer.live.ts` exercises a real round-trip
against `pass.wafer.ai` when `WAFER_PASS_API_KEY` is set.
- Rejected negative values in addition to non-numeric ones, falling back to per-server config or default 30s.
- Emitted a logger warning when an invalid env value is ignored.
- Added tests covering negative and non-numeric rejection cases.
- Removed vim edit mode and automatically map existing vim configurations to hashline mode.
- Deleted VimTool class, VimEngine implementation, and all vim-specific editing logic (2409 lines).
- Removed vim mode from EditMode union type, edit tool strategies, and configuration schemas.
- Deleted vim parser, command handler, buffer manager, and renderer modules.
- Updated documentation and tests to remove vim mode references and add deprecation mapping.
Bedrock now sends AWS_BEARER_TOKEN_BEDROCK as Authorization: Bearer before resolving SigV4 credentials, so failing profile credential_process hooks cannot block bearer-token requests.
Added regression coverage for a default profile credential_process failure with AWS_BEARER_TOKEN_BEDROCK set.
Fixes#1399
- Replaced Python execution with a local `python -u runner.py` subprocess and NDJSON stdin/stdout framing.
- Removed shared-gateway architecture, including coordinator lifecycle APIs, `useSharedGateway` wiring, and `jupyter` CLI/actions.
- Simplified setup checks to a plain Python 3 availability probe and removed automatic dependency-install fallbacks.
- Updated kernel cancellation and display processing to use status frames, SIGINT/SIGTERM escalation, and normalized output coercion.
- Added `python-runner` integration and display tests while deleting legacy websocket and kernel lifecycle test suites.
- Removed PI_STRICT_EDIT_MODE gating from edit-mode resolution so model fallbacks now always apply.
- Stopped injecting PI_STRICT_EDIT_MODE in edit-benchmark.py and rate-edit-tool.py execution environments.
- Removed PI_STRICT_EDIT_MODE from environment-variable documentation and strict-mode test coverage.
- Added a unified eval framework with parser grammar, backend interfaces, and JS/Python execution result types.
- Added eval tool docs and updated prompts for fenced cells, `eval.py`/`eval.js`, and fallback behavior.
- Replaced the built-in `python` tool with `eval` across registry, rendering, interactive modes, and tool settings.
- Migrated Python execution runtime from `src/ipy` to `src/eval/py`, renamed state fields, and removed legacy introspection.
- Refactored browser tooling from in-process VM helpers to worker-managed tab supervisors and protocol transport.
- Added eval parser fallback and JS tool-bridge tests, updated imports, and removed obsolete python-mode suites.
- Removed `process.env.PI_DEV` checks from `packages/natives/native/index.js`, dropping per-candidate debug load logging and load-error reporting from the native addon loader.
- Pruned `PI_DEV` and `--dev` usage from native build/run and runtime docs, including setup, variant, and troubleshooting guidance.
- Updated `packages/natives/CHANGELOG.md` to note removal of the `PI_DEV` loader diagnostic environment variable and associated console logging.
- Enabled Bedrock runtime and AWS credential calls to use a proxy-aware HTTP/1 handler when HTTPS_PROXY, HTTP_PROXY, or ALL_PROXY (including lowercase variants) is configured.
- Added a retry path that recreates the Bedrock client with HTTP/1 transport when an initial HTTP/2-related error occurs before streaming starts.
- Updated package and lock dependencies to include Bedrock credential-provider and proxy-agent support, and documented the new Bedrock proxy environment variables.
* add llama.cpp as local provider
* use responses api instead of messages
* use api-keys correctly for llama.cpp provider
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
- Added Tavily web search provider with API key authentication and credential discovery from environment or database.
- Integrated Tavily as highest-priority search provider in fallback chain with structured response mapping and error handling.
- Added Tavily OAuth login flow in CLI and auth-storage with manual API key input and validation.
- Added comprehensive test suite for Tavily provider covering registration, response mapping, error handling, and credential validation.
Fixes#313
* feat: Add LM Studio as a supported model provider with OpenAI-compatible API fetching and discovery.
Add LM Studio as a supported AI provider with optional API key, environment variables, and discovery.
* feat: Add rustup as a dev dependency.
* fix: Refine LM Studio API key handling to conditionally send authorization headers during model discovery based on whether the key is a default local token or a custom key, and add new tests.
* feat: Enhance OAuth token and account ID resolution for model providers in the model registry.
* rebase for packages/ai/CHANGELOG.md
* feat: improve implicit model discovery to independently auto-detect Ollama and LM Studio, and refine LM Studio base URL handling.
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
roboomp