The tool is named codemode again and scripts configure it with a first-line // @options: {...} instead of the // @exec: pragma. yield_time_ms is gone; max_output_tokens and timeout_ms remain. Comments, docs, and tests no longer describe the tool in terms of another agent.
The agent loop is back to main's tool execution: it only exports runToolCall(), honors isError results, and passes structuredContent through afterToolCall. Nested calls (ctx.executeTool, ids, events with parentToolCallId, the nestedCalls record) live in coding-agent and start on the first call.
AgentSession no longer knows exec or tool_search. Tools adjust the declared loadout through a generic prepareLoadout hook, and codemode and tool_search use it like any other tool.
exec and tool_search move to built-in extensions under src/extensions/ and register inactive (defaultActive: false). The CLI loads them with MCP; SDK sessions add createCodemodeExtension(), createToolSearchExtension(), and createMcpExtension(). Extensions gain pi.getSettings() and model catalog and classifier access on ModelRegistry.
While exec is active, codemode.mode on (default) appends the exec declaration to declared tools that scripts can call and lists only non-direct tools in the exec description. codemode.mode only lists every callable tool in the exec description and hides active direct tools from requests. The hiding is a request projection, so the transcript still declares the active set and /tree and resume keep it.
The exec listing depends on exposure, not on the active set, so tool_search loads do not redeclare exec.
- The exec description spends at most codemode.inlineBudget (default 3000) estimated tokens on tool declarations, filled round-robin across namespaces, cheapest first. Every namespace is listed with its tool count, and the listing says COMPLETE or PARTIAL.
- Scripts find omitted and deferred tools with searchTools(query, { limit, namespace }) and describeTool(name).
- tool_search, an optional built-in modeled on Codex, searches codemode and deferred tools and declares the matches for the next model call through the active tool set, so loads are recorded on the branch.
- Both use a BM25 ranker over Codex's search text (name, description, schema properties, namespace) behind a ToolRanker interface.
The codemode tool is now exec and follows the exec tool of OpenAI Codex, so scripts written for Codex run unchanged:
- // @exec: pragma with yield_time_ms, max_output_tokens (default 10000 tokens) and the pi addition timeout_ms; Codex's grammar and error messages
- text(), image() (data URLs, { image_url }, MCP ImageContent), exit(), ALL_TOOLS, tools under normalized identifiers; console and return values append text
- Results start with Script completed/failed and the wall time; failed scripts return an error result that keeps partial output and appends Script error
- Output over the token budget keeps its start and end like Codex; the full text is spilled to a temp file
- MCP tools resolve to their CallToolResult (isError resolves) and are declared as CallToolResult<T>; bash resolves to { output, exit_code, wall_time_seconds }, also for non-zero exits
- The description uses Codex's layout: helper list, deferred-tool guidance, shared MCP types, one section per tool grouped by namespace (MCP servers, with their instructions)
* feat(coding-agent,tui): add system theme derived from terminal colors
The new default system theme builds pi's colors from the terminal's reported foreground, background, and ANSI palette. Tokens take their hue and relative saturation from a palette slot; lightness is placed by OKLab lightness difference and WCAG 2 contrast minimums. Terminals that report only a background get built-in hues, and terminals that report nothing get ANSI indices with faint secondary text.
The TUI queries OSC 10, 11, and 4 in one burst ended by DA1, so replies complete in one round trip, and reports replies that arrive after the timeout. Startup never waits: the system theme starts in grayscale and updates when colors arrive. Light/dark detection now uses the reported colors instead of the ?996 query; mode 2031 notifications trigger a new query.
* fix(coding-agent): wait for terminal colors before building the startup header
The header and startup notices bake theme colors into their text. When the color replies arrived after they were built, as in Windows Terminal, they stayed grayscale. Startup now waits for the first color query, which ends at the DA1 reply or after 100 ms.
* fix(coding-agent): rebuild header and notices on theme changes
The startup header, loaded resources, and chat notices baked theme colors into their text, so they kept the old colors after a theme switch or when the system theme received the terminal's colors. They now use ThemedText, which rebuilds its text from a function whenever the UI is invalidated.
* fix(tui): keep focus on components that forward mouse events to children
A component that forwards a mouse event to a child it hosts, such as SettingsList with an open submenu, left keyboard focus on the child. When the host removed the child, focus stayed on a detached component and all keys were lost. The forwarding component now keeps focus, like delegating containers do.
* feat(coding-agent): describe the system theme in the theme selector
* feat(coding-agent): list the system theme above automatic in the theme selector
* refactor(coding-agent,tui): remove leftovers of the light/dark startup detection
Theme detection only reports dark or light now; the source and confidence fields only served saving the detected theme. The first-time setup no longer shows the detected appearance. Removes the TUI's unused queryTerminalColorScheme(), queryTerminalBackgroundColor(), queryTerminalForegroundColor(), and parseOsc11BackgroundColor(); queryTerminalColors() covers them.
* feat(coding-agent): match the reviewed system and light/dark theme design
The system theme now follows the reviewed design: color families with OKHSL saturation curves, palette slots per family, contrast rules per token and panel, relaxation for mid-gray backgrounds, and the terminal foreground for body text. Each contrast level is a target-lightness curve fitted to the reviewed output. The built-in dark and light themes use the reviewed Pi dark and light colors.
* feat(coding-agent): show the pi logo in the startup header
A two-line pixel logo replaces the app name. Its first line carries the version, its second line the first line of key hints.
* feat(tui,coding-agent): support OKHSL colors in themes
parseColor() accepts okhsl(H S L), and okhslColor() and colorToOkhsl() construct and read OKHSL colors. OKHSL saturation is relative to the sRGB gamut, so every value is in gamut. Theme files accept okhsl() values; HTML exports convert them to hex. The OKHSL code moves from coding-agent into pi-tui, where colors.ts now shares its Oklab conversion instead of keeping a second copy.
* refactor(coding-agent): write the built-in themes in OKHSL
The built-in dark and light themes use okhsl() values, with variables for colors that several roles share, so they read as color families and serve as editable templates. Near-identical values collapsed into one; no color changes visibly.
* refactor(coding-agent,tui): simplify terminal color and theme code
Share the terminal color query between startup and the theme controller, merge the query's resolve/late-reply state into one callback, keep a single global for terminal colors, use oklab.ts arrays directly in colors.ts, and drop leftover helpers and exports.
* fix(coding-agent): use one terminal light/dark decision everywhere
Theme pairs, the system theme, and Theme.appearance now share getTerminalTheme(): the reported background decides, then the terminal's light/dark report, then COLORFGBG, then dark.
COLORFGBG is classified by palette index like Vim (0-6 and 8 dark) and only reads the last field, so rxvt's "default" no longer picks up the foreground index.
Simplify the tests added on this branch.
* fix(ai): use an OpenRouter model that still exists in beta test
OpenRouter removed anthropic/claude-3-haiku, which broke type checking in CI after model regeneration.
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.
#7638 hardcoded vLLM's thinking_token_budget. Map thinkingBudgets through
thinkingTokenBudgetField, keep the boolean as a vLLM alias, clamp so the
answer keeps 1024 tokens, and document it.
fixes#8274
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
Images produced by tools (extensions, MCP bridges, screenshot tools) went into
session history at full resolution because processImage was only wired to the
read tool and @file CLI attachments. Providers validate every image in the
request, so one oversized image poisons the whole conversation: Anthropic drops
its per-image cap from 8000px to 2000px once a request carries many images, and
every later turn re-sends the same payload. Switching models does not help.
Normalize tool result images in AgentSession.afterToolCall, after the extension
tool_result hook so extension-injected images are covered too. Honors
images.autoResize, and keeps the original block when processing fails so an
unavailable image backend does not delete tool output.
Refs #5369
Assisted-By: devx/86bf3b09-9aba-4d03-8154-50fca3ffc9b5
Replace OpenAI and Anthropic SDK retries with local request retries that
preserve configured retry counts, enforce maxRetryDelayMs, and make retry
backoff interruptible through AbortSignal.
Alternatives considered: Racing SDK requests against AbortSignal would make
cancellation observable but would not let Pi enforce maxRetryDelayMs before
the SDK enters its retry sleep. Patching private SDK internals would be brittle,
while disabling provider retries entirely would ignore explicitly configured
maxRetries.
Also, align the custom OpenAI Codex retry loop with the documented
maxRetryDelayMs behavior. Oversized server-requested delays now fail immediately
instead of being clamped, allowing the visible, abortable agent-level retry
policy to handle the failure.
Fixes#6911
getShellPath() now runs the configured shellPath through the existing
normalizePath() helper, mirroring getSessionDir(). This lets shellPath
point at a home-directory-relative shell wrapper (e.g.
~/.local/bin/agent-shell-sandbox) and resolves consistently across
machines and OSes with different home directories.
refs #6458
Detect prompt cache misses per turn by comparing each assistant message's
cache reads against the previous request's prompt tokens (core/cache-stats.ts).
Significant misses emit a warning-colored transcript notice at the turn they
occur, noting idle gaps past the cache TTL and model switches when relevant.
/session gained cache statistics: a compact token/cache breakdown with hit
rate, a $-prefixed cost section with per-model cost breakdown, and the
cumulative cost re-billed due to cache misses.
Behind PI_EXPERIMENTAL=1, show a first-time setup dialog on interactive startup when the default agent directory is used and settings.json does not exist. The dialog preselects the detected terminal appearance with an explicit dark/light choice (live preview) and asks for opt-in analytics data sharing. Submitting writes settings.json, which serves as the completion marker; opting in stores a generated trackingId. Escape at any point skips out of setup.
