Rules and the tool list follow the declared tools (active minus
hiddenDeclarations). The skills hint names no tool when the reader is
hidden. Codemode shows each tool's prompt guidelines with its
declaration, via the new ToolLoadout.getPromptGuidelines().
closes#10343
close() now aborts a per-connection signal that closes the in-flight
client, cancels the retry wait, and waits for the connect attempt to
settle before returning.
closes#10249
--tools no longer removes MCP tools unless an entry starts with mcp__, so
pi --tools codemode can reach MCP servers. Unnamed MCP tools are never
declared directly; only tool_search can load them. --no-tools still
removes everything.
--tools and --exclude-tools accept * patterns, for example
--tools read,codemode,'mcp__radius__*'. --no-mcp disables the built-in
MCP support for one run.
OpenID Connect authorization servers treat a registration without application_type as a web client and reject http loopback redirect URIs. Derive it from redirect_uris when unset (MCP SEP-837): native for loopback hosts and custom schemes, otherwise web.
closes#10493
* fix(coding-agent): keep syntax colors on multiline tokens
- format each line of a highlighted span separately
- add regression test for python docstrings
- fixes#10143
* fix(coding-agent): use text color for string interpolations
- map highlight.js `subst` scope to text color
* 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
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
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.
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
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
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
Login and MCP sign-in screens show a copy hint and copy the URL to the
clipboard (OSC 52 over SSH). /mcp login in the TUI now uses the MCP
sign-in screen instead of a notification.
Move the codemode script reference, including the models API, into
docs/codemode.md and keep only one line per global in the tool
description. Declared tools get a one-line note on how scripts call them,
and the codemode system prompt guidance and MCP server section are shorter.
With the default tools a GPT-5.6 request drops from about 5,300 to 3,300
tokens.
Errors now point the way back: unknown tools and models members name close
matches, models.classify() and models.generateImages() validate their
arguments, unknown or mistyped models point to getAvailableOfType(),
store() overflow explains the store, and unshown generated images get a note.
Scripts run image models with the session's credentials, like
models.classify(). Results are base64 image blocks that image() attaches
to the codemode result; usage counts toward the session cost.
The top-level /login menu offers Sign in with Radius with its status,
with an animated shimmer on the Radius row and a short Radius intro.
After a Radius sign-in it offers to configure the Radius MCP server in
the global mcp.json with auth.provider and reloads. Cancelling a login
returns to the menu it was started from. OAuth sign-ins without a
subscription are labeled as accounts.
Co-authored-by: niloc <5925270+colindaymond@users.noreply.github.com>
Session workers now host a durable Harness over a per-session sqlite storage.
The server keeps each session in <sessionDir>/<id>/ with meta.json and
session.sqlite and never opens the storage itself. Workers hold retirement
while the Harness task graph has live tasks and resume interrupted work on
open.
Transcript serves the root conversation's durable view directly, Models
follows the conversation's agent document, and AgentController maps prompt,
steer, follow-up, queue cancellation, abort, and compaction onto the root
conversation, plus waitForPrompt. navigate, nextRun, and resume are dropped
(see experimental/services/README.md TODO). The durable TUI and the worker
share harness-setup.ts.
pi-server exports its own SessionMetadata and no longer depends on
pi-agent-core. Chord accepts readonly JSON types in service contracts without
walking them, which recursive JSON types like pi-ai's made too deep.
Palette colors now keep the bell-curve falloff and are
also capped at the palette color's OKLCH chroma times that falloff.
Lightness and hue are unchanged, so contrast is unchanged.
closes#10255
The session restored its tool loadout before MCP servers reconnected, so deferred tools that tool_search had loaded were dropped. Restored tools that are not registered yet now stay pending and are activated when they register, until a setActiveTools() call deactivates a tool or the next prompt starts.
Runs the pinned @modelcontextprotocol/conformance client scenarios for 2025-03-26, 2025-06-18, and 2025-11-25 against pi's MCP connection and OAuth sign-in, and fails on regressions against a committed check-level baseline.
A step-up sign-in requested only the scopes of the insufficient_scope challenge, so the new token lost the scopes granted before and other requests asked for sign-in again. Tokens now record their granted scope and step-up requests the union (SEP-2350).
The configured metadata document replaces discovery and is trusted as
configured. Authorization codes are only exchanged when the response's
iss parameter names the flow's authorization server.
closes#10172
HTTP MCP servers can set "auth": { "provider": "<provider>" } to send the provider's current /login token as the bearer token instead of using MCP OAuth. The token is read on every request, so provider refreshes apply and nothing is copied to mcp-auth.json. Only allowed in the global mcp.json and from extensions, and requires https except on loopback hosts.
MCP tool and namespace names now replace - with _ like Codex, so the
pi tool name is also the codemode identifier. Tools of a server whose
names collide all get a hash suffix, and server names that differ only
in - and _ are rejected.
closes#10239
When the session's initial tools come from defaultTools, /reload activates
names added to the resolved selection. Removals do not deactivate tools, and
explicit --tools/--no-tools/--no-builtin-tools keep overriding the setting.
closes#10245
In codemode.mode "only", tools whose declarations codemode hides were still
listed in the <tools> section. Drop their snippets so the list matches the
declared tools.
closes#10192
The first prompt waits only for servers with direct tools. Other servers
connect in the background; codemode scripts, tool_search, and the
resource tools wait for the servers they need. codemode and tool_search
are activated from the config.
Tool declarations no longer depend on connected servers: the codemode
description leaves out deferred tools, and the tool_search description
no longer lists sources. Servers are listed in an mcp_servers system
prompt section instead, set in before_agent_start from the config and
connected state, so changes are appended to the conversation.
describeNamespace() and searchTools() accept mcp__dev-radius,
mcp__dev_radius, dev-radius, and dev_radius.
closes#10212
getBranchSelection looked up the model catalog once per assistant message,
which made prompt submission scale with session length. Walk the branch
backward instead: only the last model_change can hold against later
responses, so at most that model needs a lookup.
closes#10198
Adds oauth.clientName (and pi mcp add --oauth-client-name) to set the
client_name sent during dynamic client registration. Defaults to pi.
closes#10226
MCP codemode exposure no longer lists tools, tool counts, or server
instructions in the codemode description. Servers are listed by name and
an optional mcp.json description; scripts find tools with searchTools()
and read instructions with describeNamespace(). codemode-deferred is an
alias for codemode.
refs #10212
image() now rejects malformed base64 and data without a PNG, JPEG, GIF,
or WebP signature, and derives the MIME type from the signature. Invalid
image blocks were persisted and made every later provider request fail.
closes#10215
registerNativeProvider() did not update the auth snapshot, so the provider
stayed unconfigured until an async refresh saved a snapshot that included it.
At startup that refresh can resolve before its result is saved, so initial
model selection saw the provider as unconfigured and fell back to another
provider or warned that no models are available.
Share registerProvider's provisional entry through markProvisionallyConfigured()
so native providers with a stored credential or a models.json apiKey are
configured immediately.
fixes#9962
Add gpt-6.1-sol to the OpenAI, Azure OpenAI Responses, and OpenAI Codex
providers with official pricing ($2 input, $0.10 cached input, $2.50
cache writes, $10 output, long-context tier above 272k). The model
rejects reasoning.effort "none", so off is unsupported and clamps to
the lowest effort.
Structured bash results now hold the full output up to 1 MiB instead of the
model-facing 2000 lines or 50KB, keeping the first and last 512 KiB of longer
output, and add truncated and full_output_path.
