HTTP servers without an Authorization header use OAuth. Connections send the stored token and refresh it after a 401; /mcp login runs the browser authorization code flow (PKCE, dynamic client registration) with a loopback callback or a pasted redirect URL, and /mcp logout removes the credentials. Tokens are stored per server URL in mcp-auth.json. Pre-registered clients are configured with the oauth block.
Adds a built-in mcp extension that reads mcp.json (agent dir, and .pi/mcp.json for trusted projects) in the common mcpServers format, connects stdio and streamable HTTP servers at session start, and registers their tools as mcp__<server>__<tool>. Calls go through the regular tool pipeline, so hooks and permission extensions apply. /mcp shows server status.
By default a server's tools are codemode-only: the new nestedOnly tool flag keeps them executable for other tools but out of the model's tool declarations, and pi activates the codemode tool for them. "exposure": "direct" declares them to the model as well. structuredContent from tools with an outputSchema reaches codemode scripts as data.
Adds a built-in, opt-in codemode tool that runs model-written JavaScript in the codemode sandbox. Scripts call the other active tools as tools.<name>(args), including concurrently with Promise.all; only the return value, console output, and images attached with image() reach the model.
Nested calls run through the agent loop via a new AgentToolContext (5th execute argument, ctx.executeTool for extension tools), so argument validation and the beforeToolCall/afterToolCall hooks apply. Hooks and tool_call/tool_result events carry the parent call id.
Tools can declare outputSchema and return structuredContent; codemode passes that to scripts and falls back to text content otherwise. The codemode package gains globals, declaration rendering from JSON Schema, and optional deadlines.
Successful RPC prompt, steer, and follow_up responses include
data.disposition ("handled", "queued", or "started" for prompt), so clients
know whether to wait for agent_settled.
fixes#9098
Replace the tsgo native preview with typescript@7.0.2 and port the check scripts to the TS 7 API. Target ES2024, drop useDefineForClassFields: false and unused decorator options, and enable verbatimModuleSyntax. Replace tsx with node plus the source resolver hook, passed to --import as a file URL.
closes#9965
Strict tool schemas make models send null for omitted optional fields.
The read renderer only treated undefined as missing, so full-file reads
rendered as "path:1".
fixes#9996
Temporary git extensions (-e git:...@ref) were cached in a folder keyed
only by host and repo path. After changing the pinned ref, pi reused the
old checkout without refreshing it and kept loading the first downloaded
commit. Include the ref in the temporary folder hash so each ref gets
its own checkout. Unpinned sources keep their existing folder.
closes#9982
Expose theme colors as values and add theme.style() for combined styling.
- @earendil-works/pi-tui gains a Color type (palette index, sRGB, OKLCH) with parseColor(), mixColors(), colorToHex(), colorToRgb(), styleText() and related helpers.
- Theme JSON accepts #rgb and oklch(...) values and an optional appearance ("dark" or "light"), detected from the theme colors when omitted.
- theme.style() combines tokens or concrete colors with text attributes; theme.colors exposes concrete colors, including the terminal's reported default colors (OSC 10/11) for tokens set to "".
- Terminals with TERM=*-direct are detected as truecolor.
Move catalog layout, index validation, version selection, and request
negotiation into scripts/model-catalog-protocol.ts. pi.dev keeps an
identical copy, so the publisher and a test running the current client
exercise the same selection pi.dev performs. Replaces the cross-repository
compatibility dispatch.
Related to #9099.
Separate conversation content from instructions and replace prefix/suffix wording with continuation-oriented summarization guidance.
Hopefully this avoids the refusals.
Fixes#9652
Since 0.86 the prompt and tool declarations live in transcript system
messages, so a context handler that filters or slices messages could drop
them. After extension-driven compaction this sent requests without built-in
tools and made Codex emit raw tool-call text.
context handlers now see the conversation only. An unchanged list keeps the
transcript as is; a changed list gets the replayed prompt sections and tool
declarations as one leading system message. Handler-added system messages
are kept after it.
Add context_with_system, which runs after every context handler on the full
transcript and sends its result verbatim, for extensions that need to edit
system messages per request. Dropping the leading system message is reported
as an extension error.
closes#9789, closes#9822
Make SessionManager projections authoritative for provider requests, add append-only context edits and actionable turn boundaries, and preserve existing queue scheduling during continuation and recovery.
3349e1db1 (#9618) limited OSC 52 to SSH/mosh so a desktop terminal that ignores
it no longer reports a false success. That also disabled the only clipboard
route for containers and WSL without WSLg, which have no display to gate on.
Emit OSC 52 again on display-less Linux. On WSL, write the Windows clipboard
through PowerShell (verified, no OSC 52 size cap), preferring OSC 52 in
Windows Terminal where it is known to work. Desktop sessions with a display
still report the failure.
closes#9688
Fall back to the latest safe assistant boundary when trailing tool results exceed the retained-token budget, allowing older history to compact before the next provider request.
Closes#9740
Remove SystemMessage.replace. A prompt forced from before_agent_start is a rendering
of the current prompt for the run, not conversation state: persisting it as a
replacing system message wrote the full prompt and tool list on every change,
lost the structured sections while forced, and disabled mid-conversation system
messages for the rest of the session once a replacement existed.
The transcript now always records section patches. AgentSession wraps
transformContext and, when a forced prompt is active, collapses the system
messages into one head carrying the forced text and the current tools. Providers
receive the same request as before; nothing is persisted and the projection ends
with the run.
The evals harness validated the without_docs variant from the transcript, which
relied on the persisted replacement. Its transform extension now records the
prompt it forced and validates that instead.
Map signal termination to conventional nonzero exit codes and reject null exit codes from custom shell operations while preserving partial output.
fixes#9577
Add SystemMessage.replace: replaying a system message with the flag discards the
accumulated prompt content, sections, and tools before applying it, and providers
collapse the transcript into one leading system message whenever a later message
replaces it.
A forced prompt from before_agent_start is opaque, so it is persisted as a replace
message holding the text in content with no sections (the agent loop fills in the
full tool set). Leaving force mode persists another replace message with the
structured sections. Previously the forced prompt became a preamble section patch,
so models with native mid-conversation system messages kept the original prompt
as their leading system prompt and received the forced one as a later update.
* fix(coding-agent): fail closed on user bash hook errors
Prevent failed execution-routing hooks from falling back to the local shell.
Fixes#9068
* fix(coding-agent): validate user bash hook results
* docs(coding-agent): clarify user bash result semantics
* docs(coding-agent): streamline user bash semantics
* fix(coding-agent): strengthen user bash regressions
* docs(coding-agent): clarify user bash breaking change
This change makes system prompt text and tool changes part of the transcript rather than silently rewriting its starting conditions. This lets Pi record when instructions changed or tools became available, restore that state after resuming or navigating branches, and preserve cached prompt prefixes where the upstream supports it.
