* feat(ai): support Azure Foundry Chat Completions deployments
The Azure provider only implemented the Responses API, so Foundry
deployments that speak Chat Completions could not be used. On Chat
Completions the deepseek/deepseek-v4-pro model sends `thinking` and
`prompt_cache_key`, both of which Azure rejects with 400.
The provider now dispatches openai-completions alongside
azure-openai-responses. A stream wrapper resolves the Azure endpoint
onto the model first, since the shared openai-completions
implementation reads it off the model.
The request-shape differences are catalog compat rather than api code:
reasoning_effort instead of DeepSeek's thinking field, no prompt cache
parameters, reasoning_content kept on assistant turns so the prefix
Foundry cached stays byte-identical, and effort clamped to the
low/medium/high the deployment accepts.
The provider is renamed from azure-openai-responses to azure, since it
now serves more than the Responses API. The azure-openai-responses api
id is unchanged. Breaking: auth.json and models.json entries keyed on
azure-openai-responses must move to azure, and existing sessions see a
different provider on their next turn.
closes#9645
* feat(ai): apply the Azure deployment name map to Chat Completions
The Responses path already sent the deployment name from
AZURE_OPENAI_DEPLOYMENT_NAME_MAP. The Chat Completions path sent the
catalog model id, so any deployment not named after the model 404'd.
The Azure provider now swaps the deployment name into the request via
onPayload before dispatch, then runs the caller's own onPayload on it.
model.id stays the catalog id. The map helpers move to
azure-openai-config.ts so the provider can share them without
importing the SDK.
* docs(ai,coding-agent): add changelog entries for the Azure provider rename
Breaking: the azure-openai-responses provider is now azure. Users rename
the key in auth.json, models.json, and settings.json; SDK users switch to
getModel("azure", ...) and providers/azure.
Also note Azure Foundry Chat Completions support (DeepSeek V4 Pro).
---------
Co-authored-by: David Brailovsky <davidbrai@gmail.com>
When the terminal goes away, stdin reads and setRawMode fail with EIO (pi left in an orphaned background process group) or ENOTTY (revoked tty on macOS). These were uncaught, recorded in crashes.json, and prompted users to run /bug. Handle them on stdin like stdout/stderr and skip crash recording for dead terminal errors.
The bug report hint test stubbed InteractiveMode without the new
maybeShowInstallChangeWarning method.
On macOS fs.watch returns before libuv's FSEvents stream is live, so
changes made right after starting a watch could be lost. Rescan once
after installing native watchers there.
image() output is also written to a temp file and the result names the
path before each image, so later turns can reference generated images.
Output files are now created through one helper (still tmpdir()) and
are readable only by the user.
closes#10310
- required watch(targets, onChange): missing targets, recursive targets
with excludes, paths/overflow/error changes, native or polling mode
- NodeExecutionEnv: fs.watch events trigger rescans; changes are snapshot
differences plus event paths; watchers for new directories before rescans;
polling on network and FUSE file systems; directory budget
- conformance cases in native and polling mode
- BinaryReader.scanLines(): one pass inside the environment locates and
measures a span of lines, decoded exactly like the whole file
- read detects images from the header and PNG chunk headers, scans once,
and decodes only the head it shows; differential test against the
whole-file algorithm
- StreamDecoder: Node's streaming TextDecoder dropped a U+FEFF after a chunk
boundary in shell output and line readers
- fix the harness test to pick its tool result by call id
- ShellExecOptions.window and ShellOutputInfo.skipped: environments may omit
output outside the retained tail and report exact counts
- ToolExecutionApi.outputWindow (tail limits and progress pace) and
output(chunk, skipped); the bash tool passes both through
- OutputBuffer counts skips; property tests against the unskipped stream
- fix: progress snapshots no longer change which tail is kept
settings.progress.partialIntervalMs and outputIntervalMs replace the hardcoded
100 ms throttles for generation partials and running tool output.
refs #10357
Resolve the QuickJS wasm path once and spawn the bundled codemode worker
from an in-memory data: URL. Show a restart hint when errors occur after
the install changed on disk.
closes#10439
- FileSystem.openBinaryReader(): positional reads of one opened regular file, noFollow
- FileSystem.openDirReader(): paged listings, vanished entries skipped
- Shell.exec() accepts an argv array (no shell); onOutput reports the stream
- Env conformance suite in /testing, run for NodeExecutionEnv
- Work-branch workflow running env tests on Linux, macOS and Windows
- flushFile() on a directory returns is_directory on Windows too
- cwd tests check a marker file; Git Bash reports $PWD as an MSYS path
- retry temp dir removal while taskkill finishes killing descendants
- workflow running the env tests on Linux, macOS and Windows for durable-env-* branches
Cancelling a request or model refresh while an OAuth token refresh was in
flight discarded the rotated credential. Providers that rotate refresh tokens
(e.g. Sign in with ChatGPT) had already invalidated the old token, so the next
request failed with refresh_token_invalidated.
The caller's signal now cancels only the wait for the credential lock. Once a
refresh starts, it completes and is persisted, bounded by the refresh timeout.
Request auth and model-list refresh share this path.
Assign each conversation its own UUIDv7 and forward it to model requests for prompt-cache affinity. Lazily backfill legacy conversations and cover real Codex cache reuse.
Closes#10424
Add missing entries for the Together DeepSeek V4 Pro fix and the Nix flake, duplicate user-facing ai and tui changes into coding-agent, and add the New Features section.
Add pi.registerToolRenderer((toolName, next) => renderers), which chooses the
renderers for calls to any tool, including tools that are not registered.
Resolvers run in extension load order; next() returns what the remaining
resolvers, then the registered tool, would use. Interactive mode and HTML
export both resolve through it.
The MCP extension uses it to render every mcp__<server>__<tool> call with the
MCP renderers, so calls in a resumed session no longer render fully expanded
before their server connects, or for good if it never does.
closes#10285
Kitty-protocol terminals only accept PNG. pi-tui now exposes
setImageTranscoder(); Image converts JPEG/GIF/WebP through it and shows
the text fallback without one. coding-agent registers a photon-based
transcoder, so images from extensions and all ToolExecutionComponent
hosts render.
closes#10292
Send thinking.block_binding with prefix_mismatch_behavior=drop_block and
the thinking-binding-controls-2026-08-01 beta for Bedrock Claude Opus 4.7+,
Sonnet 5+, and Fable 5, matching the Anthropic provider. Opus 4.6 and
Sonnet 4.6 reject the field, and GovCloud is skipped.
closes#10324
The scheduled npm audit failed on GHSA-86w9-cpqp-85rv, which has no fixed node-forge release. node-forge is only reachable through gondolin in the private gondolin example extension, and gondolin only verifies certificates from its own CA with exponent 65537, so the low-exponent forgery does not apply. The audit now runs through scripts/npm-audit.mjs, which fails on any other advisory at or above moderate.
A .pi/mcp.json entry without command, url, or type overrides only enabled,
exposure, and toolExposure of the global server with the same name. /mcp can
enable or disable a global server for the trusted project, and pi mcp list
shows the override.
closes#10277
Add a Nix flake that builds Pi from the checkout on aarch64/x86_64 Linux
and macOS. The build is offline: provider model data is hydrated from a
pi.dev model catalog revision pinned in nix/model-catalog.json, and the
runtime dependency tree comes from packages/coding-agent/install-lock with
internal packages built from source.
The Nix workflow keeps the catalog pin current on main, builds release
tags on all systems, and fast-forwards the stable branch to each release
that builds. The release script refreshes the pin before tagging.
text(), image(), and console.* fail the script with a RangeError past
MAX_OUTPUT_CHARS (16 Mi) characters or MAX_OUTPUT_ITEMS (100000) items.
closes#10283
When port 1455 was held by another pending login (another pi session
or the Codex CLI), login fell back to a paste prompt, but the browser
callback reached the other listener, which rejected it with "OAuth
state mismatch". Fail before opening the browser with a port-in-use
error instead.
fixes#10265
npm installs no longer pin transitive dependencies. Pinned installs come
from the pi.dev installer lockfile. pi update on global npm installs now
recommends migrating with the installer.
closes#5653
List @cf/cloudflare/clef and @cf/cloudflare/clef-flash under
cloudflare-workers-ai in the classifier models table and add changelog
entries crediting #10316 and #10322.
The gateway's /anthropic passthrough forwards the model ID to Anthropic
unchanged. models.dev lists the gateway's Claude models with dotted
versions (claude-opus-5.5), which Anthropic rejects with a 404. Convert
dots to dashes (claude-opus-5-5) when generating the catalog.
Adds oauth.clientRegistration: "cimd", which identifies pi with its Client ID Metadata Document on pi.dev instead of dynamic client registration, matching Codex: a shared document when the authorization server sends iss, otherwise a document and callback path specific to the MCP server. Authorization responses are only accepted on the exact redirect URI. Dynamic client registration stays the default.
closes#10302
A trailing comma in --models produced an empty pattern, which
matched every model by substring and added an extra model to
the model cycle.
fixes#10334
Switch native Anthropic tool changes to the inline-tools-2026-09-15 beta. Later tools are defined by value in tool_addition blocks, so the top-level tool list stays fixed and same-name redefinitions no longer fall back to resending the full tool list. The deferred placeholder is kept.
Upgrade @anthropic-ai/sdk to 0.129.0 and deprecate hasToolRedefinitions().
