Commit graph

637 commits

Author SHA1 Message Date
triagent
66c2fa3d7a fix(coding-agent): update undici to 8.12.3 for security advisories 2026-10-26 13:50:55 +01:00
Armin Ronacher
936e5f40ae fix(evals): drop autoevals dependency
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.
2026-10-22 23:32:38 +02:00
Armin Ronacher
2685de7a17 fix: update deps for security advisories
Bump vitest to 4.1.12 (vite 8.3.4) and the gondolin example extension to 0.14.0, which drops node-forge. Gondolin's undici moves to 6.29.1.
2026-10-22 11:24:50 +02:00
Armin Ronacher
4a080252f0 Release v1.4.0 2026-10-22 00:29:13 +02:00
Mario Zechner
16f5f0af4d feat(durable): IndexedDbStorage, a browser storage backed by IndexedDB (@earendil-works/pi-durable/storage/indexeddb) 2026-10-21 03:02:55 +02:00
Bucky
b2d0da6fe3
fix(tui): render CJK emphasis next to punctuation (#10730)
- fixes #10154
2026-10-20 11:04:48 +02:00
Mario Zechner
48909d987a feat: telemetry propagation, span links and metrics; telemetry member in chord/context
- pi-telemetry: TelemetryPropagation (inject/extract, opaque carriers), span links (SpanOptions.links, addLink),
  TelemetryMetrics (counter, up-down counter, histogram), typed metric schemas (createTypedMetrics), in-memory
  measurement log, conformance tests for propagation and metrics
- chord/context: fixed Context.telemetry member (NOOP default), withTelemetry, traceIn
- durable: HarnessOptions.telemetry option type (no instrumentation yet)
2026-10-18 20:36:08 +00:00
Mario Zechner
ea7c648430 feat(durable): workerd tests for Durable Object hosting
Runs the storage conformance suite, the schema migration, an alarm-woken sleep across an eviction, and a
turn recovered through the recovery alarm in workerd via @cloudflare/vitest-plugin (npm run test:workers).

fix(durable): decline background timers in Cloudflare Workers. With nodejs_compat, timers have an unref(),
so the idle-memory timers were armed and a pending one kept a Durable Object from hibernating or being evicted.
2026-10-17 23:02:48 +00:00
Armin Ronacher
71023aec15 Release v1.3.0 2026-10-15 20:57:27 +02:00
Armin Ronacher
f13c00fb3a fix: pin internal dependencies to exact versions
Update release synchronization and dependency checks to enforce exact versions. Refresh both lockfiles and add regression coverage.

closes #10865
2026-10-13 14:28:15 +02:00
Armin Ronacher
06a4669355 Release v1.2.0 2026-10-13 00:46:55 +02:00
David Brailovsky
19cb534c3b fix(chord): add ws and @types/ws dev dependencies for websocket test types 2026-10-12 16:17:25 +02:00
Mario Zechner
0104fef1e9 feat(chord): replace the facet and service runtime with the chord2 host runtime
Moves chord2 (contracts, objects, cells, roots, plugins, hot reload, memory/IPC/WebSocket links)
from p2 into packages/chord, with its tests (now on vitest) and docs. The root export is the new
runtime plus the shared base (Context, JsonValue, JsonRepresentation, Draft, copyJson, isJsonValue,
replicatedState and its types). ./node now holds the host manager, child control, process locks,
and nodeLoader. ./context and ./delta are unchanged; ./bundler is removed.

replicatedState stays a standalone module with the same exports. It no longer exposes the exact-op
subscription the removed service provider used, so listener failures of mutable states are always
reported asynchronously. The package depends on typebox instead of esbuild. The wire format stays JSON.
2026-10-12 10:41:59 +00:00
Mario Zechner
7472cda0d6 feat(coding-agent): remove the experimental server stack and the client, protocol, and server packages
Deletes packages/client, packages/protocol (CBOR codec), packages/server, coding-agent's
src/experimental (except source-resolver.ts, which source runs still preload), src/cli/experimental,
src/client, the example plugin, and their tests. coding-agent no longer depends on @earendil-works/chord.
The installer lock drops esbuild, so its platform-package sanity check goes too.
2026-10-12 10:41:59 +00:00
Mario Zechner
7b597d1481 feat(durable): durable code mode (@earendil-works/pi-durable/codemode)
A codemode tool whose scripts call the conversation's tools as nested calls and
survive a restart. The script runs deterministically (pi-codemode start()); each
result is journaled before it is delivered. A rerun starts the script again from
the stored start data, delivers the journaled results in order (nested calls
reattach by key c<id>), checks every recorded call count, holds calls the
journal lacks until replay ends and checks them against earlier attempts' keys,
then continues live. A call launches only once the count of the drain that made
it is committed, so a rerun can prove which calls are new. Divergence, a changed
module version or sandbox fingerprint, and a passed deadline end the call with a
stored error; a decided outcome is returned without a VM. store()/load() keep
values per conversation, rewindable and forked as of the fork's entry.

pi-codemode: CodemodeRun.finished, set when the outcome is decided.
2026-10-11 21:31:48 +00:00
Mario Zechner
97195ec3c4 build: share root config with pi-private
Everything outside apps/ is the same in pi and pi-private; apps/ exists only
in pi-private, and these files now tolerate its absence:
- workspaces include apps/*
- biome.json leaves apps/ to its own config
- the pre-commit hook runs the apps/mobile check only when it exists
- the Android APK workflow runs only in earendil-works/pi-private
- scripts/biome-check.mjs runs native Biome, or Biome WASM on Android
  (@biomejs/wasm-nodejs 2.3.5), for npm run check
From pi-private bac58de97, c2a8629da, 106714ebc.
2026-10-11 16:36:26 +00:00
Mario Zechner
42a3497d03 feat(durable): read returns images, optional Photon image processor
read returns an image file as one image block (programs get an ImageContent) plus an info diagnostic,
instead of an unsupported_image error. Limits are the conversation model's inputLimits.images.resize,
by default 2000x2000 pixels and 4.5 MB of base64.

- Without a processor: PNG, JPEG, GIF, and WebP within the limits pass through undecoded; the byte limit
  is checked before reading the file, dimensions from the header. Larger images and BMP are error results.
- With createCodingTools({ images }): the processor orients by EXIF, converts BMP to PNG, and shrinks to
  fit. ImageProcessor.prepare is async.
- @earendil-works/pi-durable/images: createPhotonImages(wasm) on @silvia-odwyer/photon 0.3.3 (web build);
  /images/node and /images/cloudflare load the wasm. The root and ./tools entries never reach it (enforced
  in check-entry-graphs).
- An image must be read whole: one that changes while read is read again, unlike a growing text file.
- A model without image input gets a diagnostic that it sees a placeholder.
2026-10-09 19:38:02 +00:00
Armin Ronacher
abe508e1b8 Release v1.1.0 2026-10-07 23:33:33 +02:00
Mario Zechner
70759f48be fix: address actionable npm audit findings 2026-10-07 23:00:59 +02:00
Christian Klotz
23cf2b948d
feat: unify package artifact validation (#10197)
* feat: unify package artifact validation

* fix: restrict local artifact output paths

* fix: clarify package artifact module names

* feat: support pnpm package artifact consumers

* fix: preserve local release package installs

Keep npm and Bun consumer installs as runnable release artifacts while retaining isolated validation for other packages. Simplify smoke fixtures and avoid redundant release work.
2026-10-06 13:30:02 +02:00
Armin Ronacher
7c10bd4337 Release v1.0.4 2026-10-05 21:22:49 +02:00
Mario Zechner
ba03e03f2d feat(env): add @earendil-works/pi-env, remote execution environments over SSH
- RemoteExecutionEnv: a Durable ExecutionEnv on another machine whose
  results match NodeExecutionEnv there; Connection to the pi-env daemon
- packages/env/daemon: the Rust daemon for Linux, macOS, Android and
  Windows, following Node and libuv semantics
- env.yml runs Durable's env tests, the daemon's checks and pi-env's
  conformance and differential tests on Linux, macOS and Windows
2026-10-05 12:50:48 +02:00
Armin Ronacher
d78dc83d63 Release v1.0.3 2026-10-05 10:21:10 +02:00
Armin Ronacher
cd32f7725f Release v1.0.2 2026-10-04 02:41:16 +02:00
Armin Ronacher
a7229ddc21 Release v1.0.1 2026-10-03 14:20:57 +02:00
Armin Ronacher
b271b0a524 feat(ai): define Anthropic mid-conversation tools inline
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().
2026-10-02 12:30:48 +02:00
Armin Ronacher
0495646a83 fix(coding-agent): pin brace-expansion 5.0.12
minimatch 10.2.6 (latest) still allows brace-expansion ^5.0.8, so pin the
patched version directly to keep the shrinkwrap off vulnerable releases.

closes #10288
2026-10-02 10:40:58 +02:00
Armin Ronacher
a13d35a742 Release v1.0.0 2026-10-01 20:52:21 +02:00
Mario Zechner
7fd478a2e8 feat(agent): remove the experimental harness from pi-agent-core
pi-agent-core now contains only Agent, the agent loop, the proxy stream, and
their types. Removed the harness, sessions and session storage, pico3, harness
tools, compaction, skills, prompt templates, telemetry schemas, search types,
and the uuidv7 and pi-telemetry re-exports, plus the ./node, ./harness/* and
./experimental/pico3 subpath exports. Durable sessions live in
@earendil-works/pi-durable.

Also removed packages/session-backends and the experimental mini and micro
coding-agent frontends, with their scripts and build configuration.
2026-10-01 14:45:01 +02:00
Armin Ronacher
005af57d88 Release v0.99.2 2026-09-30 21:12:28 +02:00
Mario Zechner
445770e032 feat(durable): first coding-agent tool turn (Package 16)
Generation offers active registered tools through positional system entries and
hands a tool-calling answer to parallel or sequential pi.tool tasks and a
pi.post-tools task that applies addTools/terminate and continues the run. Tool
tasks validate, run beforeTool/afterTool, record intent with the replay policy,
publish bounded, sanitized, adaptively throttled progress in pi.live.tools, and
write results with a rendered diagnostics block. Hook dispatch with conversation
and subtree scopes, prepareArguments, HarnessOptions.env, and read/bash/edit/write
tools in pi-durable/tools. The env shell now streams raw output and spills past
thresholds; its bounded capture and publisher are removed.
2026-09-29 21:24:32 +02:00
Armin Ronacher
d86654abb8 Release v0.99.1 2026-09-29 20:06:55 +02:00
Armin Ronacher
4b060d3a98 Release v0.99.0 2026-09-29 19:04:28 +02:00
Armin Ronacher
8eb2bccf26 fix: bump vitest to 4.1.11 and gondolin's undici to 6.29.0
Addresses GHSA-82fw-gwwq-j7x9 (vitest mocker path traversal) and
GHSA-3wwx-pv8p-q78v (undici 6.x permessage-deflate DoS). Both are
dev/example-only; the shipped coding-agent shrinkwrap is unchanged.
2026-09-29 18:38:07 +02:00
Armin Ronacher
8562bcf66a feat(coding-agent): codemode and MCP
This adds codemode and MCP support to pi. Codemode (packages/codemode) runs
model-written JavaScript in a QuickJS wasm VM inside a worker. From there the
script calls pi's tools as async functions, uses a per-session store, and can
read the model catalog and run classifiers. The codemode tool in coding-agent
is compatible with Codex's exec tool, and codemode.mode works like Codex's
tool modes (on or only). Large results are written to a JSON temp file. MCP
(packages/mcp) is a standalone client for stdio and streamable HTTP servers,
with OAuth.

The core only gets general mechanisms; codemode, tool_search and MCP are
built-in extensions that use them. Other extensions can replace these
built-ins. Tools declare an exposure: direct, model-only, codemode, deferred
or hidden. prepareLoadout() lets an orchestrating tool change which tool
declarations the model sees. ctx.executeTool() runs nested calls through
validation and the tool_call/tool_result hooks. Those calls emit events with
parentToolCallId and are recorded as bounded nestedCalls on the parent
result, which compaction and HTML export use. Tools can also return
structuredContent with an outputSchema, and can report errors with isError
instead of throwing. MCP servers come from mcp.json (global, or per project
after the project is trusted) or from pi.registerMcpServer(). They are
managed with /mcp and pi mcp list|login|logout, and their runtimes load on
first use.

Closes #10040
2026-09-29 09:12:50 +02:00
David Brailovsky
ab30693d64
fix(ai): upgrade openai SDK to 7.19.0 (#10044)
* fix(ai): upgrade openai SDK to 7.19.0

Adds the "fast" service tier to the SDK types, needed to price
GPT-6 Fast mode requests correctly. Drops the local
prompt_cache_options type, which the SDK now defines.

* fix(coding-agent): check Cloudflare compat request via fetch instead of SDK mock

pi-ai now resolves its own nested openai 7.x while evals keeps 6.x at the
root, so vi.mock("openai") in coding-agent no longer reached pi-ai's client.
Capture the outgoing request with a fake fetch and assert the URL and headers.

* fix(ai): drop any casts for stream_options and max_tokens in openai-completions

stream_options is typed by the SDK, so assign it directly. max_tokens is
deprecated by OpenAI but still needed for OpenAI-compatible providers
that reject max_completion_tokens; use a narrow cast instead of any to
avoid the deprecation warning.
2026-09-25 17:27:12 +02:00
Armin Ronacher
ca7460d16b feat: build with TypeScript 7 and run sources with plain node
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
2026-09-25 13:14:33 +02:00
Armin Ronacher
f07218c4d4 Release v0.87.1 2026-09-22 21:28:02 +02:00
Armin Ronacher
16787ad5b2 Release v0.87.0 2026-09-21 18:31:52 +02:00
Armin Ronacher
13cbf77df2 Release v0.86.1 2026-09-20 13:04:11 +02:00
Armin Ronacher
ecac0a9c4e Release v0.86.0 2026-09-20 01:00:41 +02:00
Mario Zechner
0801601621 feat(durable): move Pico into dedicated package 2026-09-18 13:39:09 +02:00
Christian Klotz
42cd371ba4
feat(coding-agent): add TUI context footer eval (#9705) 2026-09-17 13:21:31 +01:00
Christian Klotz
d7296c063b
feat(coding-agent): isolate documentation lift evals (#9635) 2026-09-15 17:54:18 +01:00
Christian Klotz
f3564a1d41
docs: validate documentation navigation and reachability (#9380)
* feat: use docs manifest for documentation evals

* feat: support nested documentation navigation

* docs(coding-agent): validate documentation reachability

* docs(coding-agent): remove catalog schema version
2026-09-09 17:34:42 +02:00
Armin Ronacher
4a6ed01945
fix(coding-agent): update runtime dependencies (#9341) 2026-09-08 16:04:35 +02:00
Armin Ronacher
caf6dfe731
feat(tui): Simplify clipboard handling (#9163)
Replace the external clipboard dependency with small macOS, Windows,
and X11 helpers and integrate them into coding-agent.

Run native clipboard operations on worker threads and make command
fallbacks asynchronous. Preserve incremental X11 transfers, legacy text
encodings, native image formats, and existing Wayland and platform tools.

Include native prebuilds with ARM64 page alignment, packaging updates,
and regression coverage.
2026-09-05 23:52:32 +02:00
Armin Ronacher
d981de1229 Release v0.85.1 2026-09-05 13:54:46 +02:00
Armin Ronacher
1382777ed8 fix(coding-agent): keep remote harness dependencies development-only
Separate stable and development entrypoints, exclude remote harness code from distributions, and verify isolated consumer installs before release. Fixes #9132.
2026-09-05 12:45:04 +02:00
Armin Ronacher
107d79f110 Release v0.85.0 2026-09-04 11:57:38 +02:00