`scripts/check-entry-graphs.mjs` built the list of files each export
reaches with `path.relative()`, which returns paths with `\` separators
on Windows. The allow and forbid patterns are written with `/`, which
caused two problems on Windows:
- The allow entry `packages/telemetry/src/index.ts` never matched, so
the bare `index.ts` forbid pattern flagged it and the check failed even
though nothing was wrong.
- Forbid patterns that contain a `/` (`providers/`, `runtime/host.ts`,
...) never matched, so real violations went unreported.
The fix converts the relative paths to `/` before any comparison. On
Linux and macOS nothing changes.
Testing:
- The scripts have no unit tests, so no test was added.
- `node scripts/check-entry-graphs.mjs` and `npm run check` pass on
Linux.
- I simulated Windows path handling with `path.win32`, without running
Windows itself:
- Before the fix: `relative(...)` gives
`packages\telemetry\src\index.ts`, and
`endsWith("packages/telemetry/src/index.ts")` is false.
- After the fix: the path becomes `packages/telemetry/src/index.ts`, and
the suffix check is true.
Fixes#11333
Requested by @badlogic
Co-authored-by: triagent <triagent@localhost>
`--model "<provider>/<id>"` returned "not found" when the provider id
itself contains a `/`. URL-derived ids such as
`llama-server=http://host:10800` are one example.
`splitProviderPrefix()` in `model-resolver.ts` split the reference at
the first `/`, which turned the prefix into `llama-server=http:`. No
provider has that id, so resolution fell through to not-found.
`splitProviderPrefix()` now compares the text against the provider ids
in the catalog. A provider matches when the text starts with its id
followed by `/`, and the longest matching id wins. Ordinary provider ids
resolve exactly as before.
Testing:
- I added two cases to the `resolveModelReference` table in
`test/model-resolver.test.ts`, using a provider
`llama=http://host:10800`: one plain, one with a `:high` thinking
suffix. Both fail without the change and pass with it. The test runs
every case against the catalog in both orders.
- `node ../../node_modules/vitest/dist/cli.js --run
test/model-resolver.test.ts`: 64 passed.
- `npm run check`: passes.
- Before the change, a standalone check of `resolveModelReference` with
the reporter's exact provider and model
(`llama-server=http://host:10800/unsloth/Qwen3.8-27B-GGUF:BF16`)
returned `not-found`. It now returns `resolved`.
- One test, `test/model-runtime-classifiers.test.ts` ("applies provider
compat from models.json to classifier models"), fails in my environment
both with and without this change. It is unrelated to this fix.
Fixes#11394
Requested by @badlogic
Co-authored-by: triagent <triagent@localhost>
When the agent directory is reached through a symlink (for example
`~/.pi` linked into a dotfiles repo), pi passed the symlinked path as
`--prefix` to `npm install` and `npm uninstall`. npm then writes lock
entries such as `../../../dotfiles/pi/agent/npm/node_modules/foo`
instead of `node_modules/foo`. Each later install adds one more nesting
level, so `package-lock.json` keeps growing.
This change resolves the install root with `realpathSync` before passing
it to the package manager:
- in `getNpmInstallArgs()`, which covers install and update for npm,
pnpm and bun;
- in `uninstallNpm()`.
The paths pi loads extensions from are unchanged.
**Testing**
- Added a regression test in `test/package-manager.test.ts`. It uses a
symlinked agent dir and checks that install and uninstall get the real
path as `--prefix`. The test fails without the fix and passes with it.
- Wrapped the existing `--prefix`/`--cwd` expectations in
`realpathSync(...)`. They now match on systems where the temp dir is
itself a symlink, such as macOS.
- Ran `npm run check` (clean) and `test/package-manager.test.ts` plus
`test/package-manager-ssh.test.ts` (all pass).
- Manual reproduction with `~/.pi` as a symlink, running `pi install
npm:ms` several times:
- before: lock keys grew to
`../../../dotfiles/pi/agent/npm/node_modules/ms`,
`../../../dotfiles/dotfiles/pi/...`, and so on;
- after: `[ '', 'node_modules/ms' ]`, and `pi remove npm:ms` leaves `[
'' ]`.
Fixes#11358
Requested by @badlogic
Co-authored-by: triagent <triagent@localhost>
`./pi-test.sh --no-env` is supposed to run pi without any API keys, but
its hard-coded `unset` list had fallen behind
`packages/ai/src/env-api-keys.ts`. Credentials such as
`DEEPSEEK_API_KEY`, `MOONSHOT_API_KEY` and `ANTHROPIC_AUTH_TOKEN` were
still picked up from the environment.
This change adds the 26 missing variables to the list:
- the Anthropic auth token and federation variables
- the API keys for Ant Ling, Baseten, Cloudflare, DeepSeek, Fireworks,
Google Cloud, Kimi, Meta, Moonshot, Nvidia, Qwen token plan, Radius,
Together, Typesafe, Xiaomi (all plans) and ZAI coding CN
The list now covers every variable name in `env-api-keys.ts`.
Testing:
- No automated test covers this shell script, so none was added.
- A loop over every variable name in `env-api-keys.ts` confirmed each
now has an `unset` in `pi-test.sh`.
- Before the change, `PI_CODING_AGENT_DIR=$(mktemp -d)
DEEPSEEK_API_KEY=x ./pi-test.sh --no-env --offline -ne --list-models
deepseek` listed DeepSeek models.
- After the change, the same command with both `DEEPSEEK_API_KEY` and
`MOONSHOT_API_KEY` set prints "No models available."
- `bash -n pi-test.sh` and `npm run check` pass.
Fixes#11359
Requested by @badlogic
Co-authored-by: triagent <triagent@localhost>
A commit may be marked deferrable ({ persistence: { kind: "deferred", withinMs? } }) on Session, Conversation,
TaskRuntime and a tool's api.commit. When every write changes an existing conversation document with history
"latest" and fork "initial", it is adopted in memory and shown to watches at once, and stored with the next commit
that reads or writes the document, before the document leaves memory, at close, or within withinMs (default
settings.progress.persistWithinMs, 1000 ms). The generation partial throttle and the tool output throttle use it.
subscribeCommits() gets these commits only once stored, with exactly what was stored; internal observers get
memory-only publications. Spec §1/§13 changed, new §4.1. 32 streams over SQLite: storage transactions 562/s -> 99/s,
disk 14.3 -> 4.9 MB/s, CPU 29% -> 22% of one core. A crash loses up to about 1 s of streamed content.
Tracker revisions, applyImmutable() and applyImmutableBatches() copy each container on a changed path with
spread (Object.assign() onto a null-prototype object) instead of one Object.defineProperty() per key: same own
data properties, prototype and own __proto__ member, about 25 times faster per container. The copy-count test
counts key listings through a proxy instead of spying on Object.keys.
Adds a tracker GC regression test: 10,000 adopted changes retain only the document, not a context registration
per change. Follow-up to #9265.
Kimi Coding, Moonshot, and OpenCode Go generated K3.1 Pro and K3.1 Pro Highspeed with Kimi K2 settings because K3 detection matched exact IDs. Detect the K3 family by ID pattern, and Kimi Coding K3-style models by their effort options. Add implied subscription costs and clamp gateway output limits like K3.
- chord/delta: PendingOps (push, size, take -> PendingTake): raw pending ops, r drops everything
before it, a leaf index merges appends and primitive sets per path (cleared by any other op),
past 10,000 ops only "replace with the current value"; one batch is kept by reference and
received ops are never mutated
- chord: Watch queues frames in PendingOps while its listener is busy or not started and delivers
one call with the newest value, the folded ops (or [["r", newest]] after an overflow) and the
newest frame's context; replaces the 100-frame collapse. NativeWatch is unchanged and takes an
optional replace()
- durable: watchEvents keeps every event batch in order (NativeWatch with a snapshot replace);
document, view and task-graph watches fold; spec, README, example 04 and tests updated
- tests: fold fuzzers (tracker, appendText, splices/reorders, root arrays, diffRevisions) with
codec round trips, adversarial cases, cap, ownership, cost and GC guards
The suite's evicting run (PI_DURABLE_DOCUMENT_RETENTION_MS=0) evicts the unwatched pi.live after every
commit, so each partial commit replayed the document's delta chain and the per-commit cost grew with the
stream. Pin the document retention in that test so it measures appends, as the default retention does.
Follow-up to #9265.
- chord: Delta appendText(draft, key, text) / StringKeys<T> record an append op without the
O(length) prefix compare that a plain `draft[key] += text` costs in prepare()
- durable: partial commits append text and thinking deltas with appendText (assignJson plan,
checked by length), and apply tool-call argument changes from their own StreamingJsonParser
of the raw toolcall_delta text instead of reassigning the arguments snapshot
- durable "." entry-graph budget 73 -> 76 for the parser it now imports
- ai: StreamingJsonParser / ToolCallArgumentsStream read each argument delta once (tolerant,
immutable snapshots, linear cost); every provider, pi-messages and the faux provider use it
and keep stream state (partialJson, partialArgs, index, customInput, streamIndex, Bedrock
reasoning bytes) off the content blocks; grammar tool input appends per delta
- agent: streamProxy uses the same parser
- chord: Delta append ops own their text (ownedSlice), so ops and replicas no longer keep the
whole growing string alive
- durable, ai, mcp: bounded error excerpts and summaries own their characters
- coding-agent: tool calls render streamed arguments once per frame, not once per delta
Placeholder rows below a Kitty image line can contain box padding,
borders, or side-by-side text. Stopping the backward search at the
first non-blank row dropped those images once their first row scrolled
above the viewport. Search back at most the tallest registered image
height instead; the existing hiddenRows check keeps results correct.
Image placeholder rows inside padded or colored boxes contain spaces and
SGR codes, which stopped the backward search for the image line, so the
whole image disappeared once its first row scrolled out of view.
With a sessionId, the faux provider reported newly cached prompt tokens
both as input and as cacheWrite, so input + cacheRead + cacheWrite
exceeded the estimated prompt. Every prompt token now goes either to
cacheRead or to cacheWrite, and input is 0 while caching is simulated.
/model and /scoped-models listed only `id [provider]`, so renamed
overrides from models.json were invisible in the list. Rows now show
the name in parentheses when it has words the id lacks, e.g.
`minimax/minimax-m3 (MiniMax M3 [parasail]) [openrouter]`. Names that
only restate the id with different casing, separators, or a dropped
namespace/version suffix stay hidden.
closes#5916
When a todo call fails schema validation, createErrorToolResult produces
details: {} (a truthy empty object), so renderResult skips both the
!details and details.error branches, then switch (details.action) has no
default and returns undefined. ToolExecutionComponent.updateDisplay()
then calls addChild(undefined), and the next Box.render pass crashes the
whole interactive TUI.
Add a default case that renders the validation error text.
Only x64 and arm64 map to prebuilt release archives. ARM32 and ia32 previously
fell back to x86-64 binaries; now pi warns and recommends the system package manager.
fixes#11209
Fix docs and `--help` drift: update the provider checklist to the
`src/api` layout, fix broken MCP anchors, and document `/mcp`, `pi mcp
add|remove`, `PI_CLEAR_ON_SHRINK`, and `"disabled"` timeouts.
closes#11243
`execCommand()` (the function behind `pi.exec()`) decoded each stdout
and stderr chunk on its own with `data.toString()`. When a multi-byte
UTF-8 character was split across two pipe chunks, each half was turned
into U+FFFD, so the result was corrupted. For example, `"你好"` came back
as `"���好"` while the command still exited with code 0.
This change gives stdout and stderr each their own
`StringDecoder("utf8")`. A decoder holds back incomplete bytes until the
rest of the character arrives. Both decoders are flushed with `end()`
before the promise resolves, on both the success path and the error
path. `waitForChildProcess()` can resolve without a stream `end` event,
so the decoders are flushed there and not in an `end` handler. The
return shape, exit codes, and kill behavior are unchanged.
**Testing**
- Added a regression test to `packages/coding-agent/test/exec.test.ts`.
The child process splits `"你好"` across two writes on both stdout and
stderr. The test fails without the fix and passes with it: `node
../../node_modules/vitest/dist/cli.js --run test/exec.test.ts` reports 3
passed.
- `npm run check` passes.
- Reproduction from the issue: a child that writes the first byte of
`"你好"` and then the rest 100 ms later. Before the fix the result was
`{"stdout":"���好",...}`. After the fix it is
`{"stdout":"你好","stderr":"","code":0,"killed":false}`.
Fixes#11312
Requested by @davidbrai
---------
Co-authored-by: triagent <triagent@localhost>
Co-authored-by: David Brailovsky <davidbrai@gmail.com>
**Problem.** A line of many `>` characters makes `marked` produce one
nested blockquote token per `>`. The blockquote branch of
`Markdown.renderToken` renders its children at `Math.max(1, width - 2)`
columns, then wraps each child line again at that width and adds a `│ `
prefix.
Once the nesting uses up the width (about 39 levels at 80 columns), the
width stays clamped at 1. From then on, each child line (`│ x`, 3
columns wide) is wrapped into about 3 lines at every further level, so
the output roughly triples per level. At 80 columns:
- 50 levels: 4096 lines, about 30 s to render;
- 55 levels: `push(...lines)` exceeds the JavaScript argument limit and
throws `RangeError: Maximum call stack size exceeded`, which crashes pi.
Reopening the session crashes it again.
**Fix.**
- When there is no room left for another border (`width < 3`), the
blockquote branch now renders its child tokens at the same width without
adding a border and without wrapping them again.
- Child lines are appended with a loop instead of a spread `push`.
Quotes that fit in the width render exactly as before.
**Testing.**
- Added a regression test in `packages/tui/test/markdown.test.ts`: 60
nested `>` rendered at width 80 give one line that keeps the content.
Without the fix the test fails with the RangeError; with it, all 92
tests in that file pass (`node --test test/markdown.test.ts`).
- `npm run check` passes.
- Reproduction script rendering `">".repeat(n) + "x"` at width 80:
- before: 50 levels gave 4096 lines in 29.5 s, and 55 or 60 levels threw
a RangeError;
- after: 40, 50, 60 and 200 levels each give 1 line in about 10 ms.
**Not covered.** A run of about 2000 `>` still overflows the stack
inside `marked`'s own lexer, before pi's renderer runs. That is a
separate limit and is not changed here.
Fixes#11272
Requested by @davidbrai
Co-authored-by: triagent <triagent@localhost>
fix(coding-agent): start when a configured package fails to install
A package in settings.json that could not be installed (registry
unreachable, package missing, failing git prepare step) crashed startup
with an uncaught rejection and a raw Node stack.
Resolving packages now catches the install failure, skips that package
the same way offline mode does, and reports it as an extension warning:
Warning: Extension package "npm:foo": failed to install (...).
Run "pi remove npm:foo" to remove it from settings.json.
Project packages point at `pi remove <source> --local`. `-e` sources
say to check the source instead. Pi tries the install again on the next
start or /reload.
--help and --list-models now print runtime diagnostics, so the warning
shows there too. pi config prints it as well. pi install and
pi update --extensions still fail with a non-zero exit.
closes#11088
This commit makes it so we store the responseModel (i.e. the "phyiscal"
model used) on each PiMessage. This allows e.g. Radius to know which
physical model was used by virtual models (like `cheap`). It's
especially important after we merged
https://github.com/earendil-works/pi/pull/11000
(9113094291), where Pi will drop thinking
traces when the model name doesn't match - with this change we can check
the physical model instead.
Tested locally on darwin-arm64, darwin-x64, linux-arm64, linux-x64,
windows-arm64 and windows-x64: the CI smoke checks plus HTTPS responses,
file tools, image resizing and session resume. Aborting a streamed reply
still stops immediately (#10031, #8823).
autoevals@0.3.0 declares engines npm: please-use-pnpm, so every npm install printed an EBADENGINE warning. 0.4.1 removes that but adds a pnpm-enforcing preinstall script. The eval only used the Levenshtein scorer, so inline an equivalent normalized similarity helper instead.
fuzzyMatch scored only the greedy leftmost alignment, so a query could be
scattered over an earlier unrelated part of the text (opus via "openrouter",
astra via "radius radius/gpt") and the real match ranked last. It now also
scores every contiguous occurrence and keeps the best alignment.
/resume matched one concatenated id/name/messages/cwd string. Scattered
matches in megabytes of message text or in UUIDs were noise, and the
position penalty buried real hits deep in a transcript. Fields are now
matched separately: name and cwd fuzzy, id and messages exact only, with no
position penalty. Ranking is name text, then id/message/cwd text, then
scattered name/cwd matches. Lowercased message text is cached per session.
closes#11220
