@sammorrowdrums/mcpi 0.70.8 → 0.85.0-bootstrap.0

package/CHANGELOG.md

@@ -2,6 +2,1627 @@
 
 ## [Unreleased]
 
+### Breaking Changes
+
+- Renamed the public npm package from `@earendil-works/pi-coding-agent` to `@sammorrowdrums/mcpi`, the executable from `pi` to `mcpi`, and the package metadata field from `piConfig` to `mcpiConfig` with `name: "mcpi"`. The new package explicitly publishes to the public npm registry and requires Node.js 22.19 or newer.
+- mcpi no longer reads the legacy single-root layout or old names as a silent fallback. Move settings, auth, models, trust data, and user extensions/skills/prompts/themes to the platform config directory (`$XDG_CONFIG_HOME/mcpi`, fallback `~/.config/mcpi`; `%APPDATA%\mcpi` on Windows); move sessions to the platform state directory's `sessions/` subdirectory (`$XDG_STATE_HOME/mcpi`, fallback `~/.local/state/mcpi`; `%LOCALAPPDATA%\mcpi` on Windows); and recreate disposable package installs, binaries, and catalog caches under the platform cache directory (`$XDG_CACHE_HOME/mcpi`, fallback `~/.cache/mcpi`; `%LOCALAPPDATA%\mcpi` on Windows). Rename project `.pi` directories to `.mcpi` and every public `PI_*` variable or secret to `MCPI_*`. `MCPI_CODING_AGENT_DIR` remains an explicit single-root override. The extension API identifier and parameter `pi`, `pi.setEnv()`/`pi.unsetEnv()`, the extension package manifest `pi` field, internal upstream API/protocol symbols, Radius, `@mariozechner/clipboard`, and upstream attribution/licensing deliberately retain their existing names.
+
+### Added
+
+- Added `pi.setEnv(key, value)` and `pi.unsetEnv(key)` for setting environment variables on every subprocess mcpi spawns for the session, covering both the bash tool and `pi.exec()`. `pi.unsetEnv()` also masks variables mcpi inherited, and neither method mutates mcpi's own `process.env`. See [Session Environment](docs/extensions.md#session-environment).
+- Added an `env` option to `pi.exec()` for setting variables on a single call, taking precedence over the session environment.
+
+### Changed
+
+- Claude Opus 5 is now the default model for the `anthropic` (`claude-opus-5`), `amazon-bedrock` (`us.anthropic.claude-opus-5`), and `github-copilot` (`claude-opus-5`) providers, replacing Opus 4.8, Opus 4.6, and GPT-5.4 respectively. Opus 5 carries a 1M-token context window, prompt-cache pricing, and native `xhigh` and `max` thinking levels. On `github-copilot` the switch also trades capability: maximum output drops from GPT-5.4's 128k tokens to 64k, OpenAI grammar-tool support is lost, and the per-token rates are higher ($5/$25 per Mtok against GPT-5.4's $2.5/$15 base rates, plus a non-zero cache-write rate), so cost estimates rise; select a model explicitly to keep the previous behavior. GPT-5.4 is itself tiered and charges $5/$22.5 above 272k input tokens, so on long contexts its input and cache-read rates match Opus 5's and only output and cache writes remain higher. The `anthropic` and `amazon-bedrock` switches change neither pricing nor output limits. Note that the Bedrock inference profile has no `-v1` suffix, unlike the Opus 4.6 profile it replaces. Multi-vendor gateway providers keep their existing defaults, since pointing them at Opus 5 would switch vendor and per-token cost rather than move up a vendor's own lineup.
+- Changelog and release-note links now resolve relative paths against `SamMorrowDrums/mcpi`. Because mcpi is a fork rather than a rename, inherited `pi-mono` issue and pull request links continue to resolve against `earendil-works/pi` so upstream numbering stays correct.
+- The self-update instruction for binary installs now points at mcpi's releases instead of upstream's.
+- Release archives, the source archive, and the standalone executable inside each archive are now named `mcpi` rather than `pi` (for example `mcpi-linux-x64.tar.gz` and `mcpi-<version>-source.tar.gz`). The from-source launcher is now `mcpi-test.sh`.
+- The startup update check now reads mcpi's GitHub releases (`api.github.com/repos/SamMorrowDrums/mcpi/releases/latest`) instead of upstream's `pi.dev` endpoint, so it reports the same releases the self-update instructions point at. `MCPI_OFFLINE` and `MCPI_SKIP_VERSION_CHECK` disable it.
+- `/changelog` now opens mcpi's releases page.
+- Provider attribution headers now identify mcpi (`HTTP-Referer`, OpenRouter title, Cloudflare user agent, and the OpenCode client header), and the HTTP user agent product token is now `mcpi/<version>`. Providers that use attribution for identification still receive it.
+- The remote model catalog overlay is now opt-in. mcpi serves the catalog bundled with the release and makes no catalog network request unless `MCPI_CATALOG_URL` is set.
+- `/share` now requires `MCPI_SHARE_VIEWER_URL`, with no compatibility alias for the legacy prefix. mcpi hosts no transcript viewer, so when it is unset `/share` still creates and reports the gist but reports that no viewer is configured rather than printing a URL that would not load.
+- `enableInstallTelemetry` and `MCPI_TELEMETRY` now only control provider attribution headers.
+
+### Removed
+
+- Removed the legacy `@mariozechner/pi-*` module aliases. Extensions must import the current package names.
+- Removed the upstream Earendil announcement card, its `/dementedelves` slash command, and its bundled image. The interactive assets directory and its build and packaging steps are removed with it, since that card was its only consumer.
+- Removed the release workflow's pi.dev announcement job and its publishing script. The job required upstream's artifact bucket credentials, and publishing the GitHub release depended on it succeeding.
+- Removed install and update telemetry. mcpi no longer sends the upstream `report-install` ping, and it is not replaced.
+- Removed the update note rendered under the update banner. It was supplied by the retired upstream endpoint; GitHub's release payload has no equivalent field, and rendering release bodies there would flood the banner.
+- Removed the model catalog publishing workflow, which uploaded to upstream's artifact bucket using upstream's credentials. `npm run check:model-catalog` still validates a generated catalog locally.
+- Removed the `earendil-works/staff` membership gate from issue analysis. No mcpi maintainer can satisfy it, so it rejected every actor. Authorization now uses the repository write/admin permission check that already followed it.
+
+## [0.84.2] - 2026-08-14
+
+### New Features
+
+- **Fullscreen transcript search** — Search and navigate matches in fullscreen mode. See [TUI Fullscreen Viewport](docs/keybindings.md#tui-fullscreen-viewport).
+- **Configurable default tools** — Choose startup built-in tools globally or per project. See [Tools](docs/settings.md#tools).
+- **Configurable fullscreen exit output** — Print the transcript or only a resume hint on exit. See [Interactive Mode](docs/usage.md#interactive-mode).
+
+### Added
+
+- Added fullscreen transcript search with `Ctrl+Shift+F`, incremental match highlighting, configurable search match theme colors, and next/previous navigation with `Enter`/`Ctrl+G` and `Shift+Enter`/`Ctrl+Shift+G`.
+- Added experimental strict JSON-schema constrained sampling for the default `read`, `bash`, `edit`, and `write` tools under `PI_EXPERIMENTAL=1`.
+- Added a fullscreen exit output setting to choose between printing the final transcript and only a session resume hint.
+- Added the `defaultTools` setting for configuring the initial built-in tool selection globally or per project.
+- Added `--use-theme <name[/name]>` to choose an initial per-run interactive theme without changing saved settings ([#7722](https://github.com/earendil-works/pi/pull/7722) by [@rwachtler](https://github.com/rwachtler)).
+- Added `expandPromptTemplates` to extension `pi.sendUserMessage()` options for explicitly dispatching commands and expanding skills and prompt templates. See [`pi.sendUserMessage()`](docs/extensions.md#pisendusermessagecontent-options) ([#7857](https://github.com/earendil-works/pi/pull/7857) by [@mrexodia](https://github.com/mrexodia)).
+- Added inherited `createGatewayBindingFetch()` for routing Cloudflare AI Gateway requests through a Workers AI binding without an API token ([#7901](https://github.com/earendil-works/pi/pull/7901) by [@Maximo-Guk](https://github.com/Maximo-Guk)).
+- Added inherited `AssistantMessage.endTurn` to preserve OpenAI Codex's terminal `end_turn` signal for diagnostics ([#7766](https://github.com/earendil-works/pi/pull/7766)).
+- Added inherited unbound single-line transcript scrolling actions for fullscreen mode. See [TUI Fullscreen Viewport](docs/keybindings.md#tui-fullscreen-viewport) ([#7903](https://github.com/earendil-works/pi/pull/7903) by [@midastruth](https://github.com/midastruth)).
+
+### Changed
+
+- Changed inherited Kimi Coding requests to use pi's runtime `User-Agent` header.
+- Replaced the inherited Mistral SDK transport with a native Chat Completions HTTP stream, eliminating its generated client and schema runtime overhead.
+- Documented the generic `AI_AGENT=pi` process marker and how it differs from `PI_CODING_AGENT=true` ([#7747](https://github.com/earendil-works/pi/issues/7747)).
+- Changed inherited OpenAI Responses deferred tool loading to prefer message-anchored `additional_tools` where supported while retaining tool-search and top-level fallbacks ([#7709](https://github.com/earendil-works/pi/issues/7709)).
+- Reduced inherited fullscreen rendering allocation churn by painting full-width layout rows directly instead of recompositing them on every frame.
+
+### Fixed
+
+- Fixed managed-tool downloads delaying TUI startup and hiding diagnostics in fullscreen mode by mounting the TUI first and showing download progress and warnings inside it.
+- Fixed opening a model selector immediately after startup cancelling and restarting the in-progress model catalog refresh.
+- Fixed inherited GitHub Copilot login triggering API rate limits while enabling model policies by limiting concurrent policy updates ([#6187](https://github.com/earendil-works/pi/issues/6187)).
+- Fixed fullscreen transcript search snapping back to the current match during manual scrolling and fragmented mouse input leaking into the search query.
+- Fixed inherited required LaTeX arguments starting on a new line being parsed as empty ([#7760](https://github.com/earendil-works/pi/issues/7760)).
+- Updated the transitive `nanoid` development dependency to address a denial-of-service vulnerability.
+- Fixed fallback rendering for extension tool results to collapse long output and honor tool expansion ([#7979](https://github.com/earendil-works/pi/issues/7979)).
+- Fixed JSON and RPC `message_update` events dropping cumulative usage during streaming. See [JSON Event Mode](docs/json.md) and [RPC `message_update`](docs/rpc.md#message_update-streaming) ([#7982](https://github.com/earendil-works/pi/pull/7982) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed `pi.sendMessage(..., { triggerTurn: false })` steering an active run instead of only recording the custom message ([#8022](https://github.com/earendil-works/pi/pull/8022) by [@cristinaponcela](https://github.com/cristinaponcela)).
+- Fixed the `defaultTools` setting dropping extension and SDK custom tools when selecting built-in defaults.
+- Fixed the subagent example rejecting YAML array syntax for the `tools` frontmatter field ([#7598](https://github.com/earendil-works/pi/pull/7598) by [@alexsavio](https://github.com/alexsavio)).
+- Fixed the subagent example dropping parent session model, thinking, and tool configuration ([#7897](https://github.com/earendil-works/pi/pull/7897) by [@virtuald](https://github.com/virtuald)).
+- Fixed custom system prompts concatenating the current working directory with later appended prompt content ([#7887](https://github.com/earendil-works/pi/pull/7887) by [@distributedlock](https://github.com/distributedlock)).
+- Fixed inherited OpenAI Responses function and custom tool calls losing namespaces during streaming, proxying, and replay ([#7709](https://github.com/earendil-works/pi/issues/7709)).
+- Fixed inherited upstream request buffer failures not triggering automatic assistant retries.
+- Fixed inherited built-in and custom DeepSeek API models sending output limits through an unsupported field.
+- Fixed inherited Amazon Bedrock replay rejecting tool arguments that contain empty object keys while preserving all valid nested values ([#7882](https://github.com/earendil-works/pi/pull/7882) by [@muyiyr](https://github.com/muyiyr)).
+- Fixed inherited DeepSeek compatibility detection for base URLs whose hostname contains uppercase letters ([#7933](https://github.com/earendil-works/pi/pull/7933) by [@yearth](https://github.com/yearth)).
+- Fixed inherited Google Generative AI and Vertex AI responses with tool calls incorrectly treating output-limit or provider-error stops as normal tool use ([#8059](https://github.com/earendil-works/pi/issues/8059)).
+- Fixed inherited fullscreen mouse drag selection and OSC 8 link activation in terminals that report generic SGR mouse release button codes ([#7963](https://github.com/earendil-works/pi/issues/7963)).
+- Fixed inherited focused fullscreen overlays not receiving mouse wheel or viewport scroll keys such as PageUp and PageDown ([#7894](https://github.com/earendil-works/pi/issues/7894)).
+- Fixed inherited LaTeX control spaces split across line endings causing complete expressions to fall back to raw source.
+- Fixed split `Alt+Enter` input over SSH being misread as Escape, added `PI_TUI_ESC_TIMEOUT` for high-latency terminals, and limited that timeout to lone Escape input ([#7899](https://github.com/earendil-works/pi/pull/7899) by [@powerfooI](https://github.com/powerfooI)).
+- Fixed inherited idle fullscreen sessions repainting and clearing text selection when the terminal loses focus ([#7892](https://github.com/earendil-works/pi/pull/7892) by [@terrorobe](https://github.com/terrorobe)).
+- Fixed fullscreen selection copy to use the host clipboard and report failure instead of claiming success when OSC 52 is unsupported ([#8110](https://github.com/earendil-works/pi/pull/8110) by [@Panoplos](https://github.com/Panoplos)).
+
+## [0.84.1] - 2026-08-07
+
+### New Features
+
+- **Qwen Token Plan Individual** — Use the built-in provider for models documented for Individual subscriptions. See [API Keys](docs/providers.md#api-keys).
+- **Authentication readiness checks** — Use `pi auth check` to verify provider or model credentials, optionally emitting the resolved credential.
+- **Improved fullscreen interaction** — Select words and paragraphs with multiple clicks and configure half-page transcript scrolling. See [TUI Fullscreen Viewport](docs/keybindings.md#tui-fullscreen-viewport).
+- **Terminating blocked tool calls** — Extension `tool_call` handlers can stop all-terminating batches without another model call. See [Tool Events](docs/extensions.md#tool-events).
+
+### Added
+
+- Added Qwen Token Plan Individual as a built-in provider with its documented subscription model catalog and the shared international `QWEN_TOKEN_PLAN_API_KEY`. See [API Keys](docs/providers.md#api-keys) ([#7659](https://github.com/earendil-works/pi/pull/7659) by [@arasovic](https://github.com/arasovic)).
+- Added `pi auth check` provider/model auth preflight with optional credential output ([#7152](https://github.com/earendil-works/pi/issues/7152)).
+- Added `terminate` support to blocked extension `tool_call` events so all-terminating batches can skip the automatic follow-up model call. See [Tool Events](docs/extensions.md#tool-events) ([#7715](https://github.com/earendil-works/pi/pull/7715) by [@muyiyr](https://github.com/muyiyr)).
+- Added inherited double-click word and whitespace selection, granularity-aware drag selection, and triple-click paragraph selection in fullscreen mode ([#7725](https://github.com/earendil-works/pi/issues/7725), [#7733](https://github.com/earendil-works/pi/pull/7733) by [@volsa](https://github.com/volsa)).
+- Added inherited unbound half-page transcript scrolling actions for fullscreen mode. See [TUI Fullscreen Viewport](docs/keybindings.md#tui-fullscreen-viewport) ([#7735](https://github.com/earendil-works/pi/issues/7735)).
+
+### Changed
+
+- Softened the bash tool's `PI_*` environment guideline in an attempt to reduce unnecessary inspection commands ([#7128](https://github.com/earendil-works/pi/issues/7128)).
+- Reduced worst-case automatic terminal theme detection delay from 200 ms to 100 ms by probing color-scheme and background support concurrently.
+
+### Fixed
+
+- Fixed Bun standalone binaries crashing on startup when the cwd contains a `bunfig.toml` with `preload` by compiling with `--no-compile-autoload-bunfig` ([#7685](https://github.com/earendil-works/pi/pull/7685) by [@geril07](https://github.com/geril07)).
+- Fixed extension TUI method wrappers recursing indefinitely when delegating to the original method ([#7731](https://github.com/earendil-works/pi/issues/7731)).
+- Fixed right-click not pasting clipboard text in fullscreen mode on Windows.
+- Fixed inherited `Agent.reset()` clearing transcript and runtime state during active runs; it now rejects until the agent is idle ([#7717](https://github.com/earendil-works/pi/pull/7717) by [@wesleyzhangwq](https://github.com/wesleyzhangwq)).
+- Fixed inherited LaTeX relation, multiplication, and named-operator spacing, and matrix composition with stacked fractions, operator limits, and adjacent matrices.
+- Reduced inherited fullscreen mouse event volume under tmux, Zellij, and GNU Screen by using button-motion tracking instead of all-motion tracking.
+
+## [0.84.0] - 2026-08-06
+
+### New Features
+
+- **Fullscreen TUI mode** — Switch between regular and fullscreen modes at runtime, with a sticky editor and footer, independently scrollable transcript, and draggable scrollbars. See [UI & Display](docs/settings.md#ui-display).
+- **Mermaid and LaTeX rendering** — Render Mermaid diagrams and terminal-friendly Unicode math in interactive transcripts. See [Markdown settings](docs/settings.md#markdown) and [TUI Markdown](../tui/README.md#markdown).
+- **Per-directory context overrides** — Use `AGENTS.override.md` to replace context files for a specific directory. See [Context Files](docs/usage.md#context-files).
+- **Advanced custom model sampling** — Configure arbitrary OpenAI-compatible `samplingParams` and opt-in vLLM `thinking_token_budget` values. See [Sampling Parameters](docs/models.md#sampling-parameters).
+- **Baseten provider** — Use built-in Baseten authentication and model support. See [API Keys](docs/providers.md#api-keys).
+
+### Breaking Changes
+
+- Renamed the inherited pi-ai `ModelsStreamTransforms` interface to `ModelsRequestTransforms` because its header transformation now applies to all authenticated provider requests.
+- Changed JSON and RPC `message_update` events to emit only `assistantMessageEvent` deltas, removing the cumulative `message` and `assistantMessageEvent.partial` fields that caused quadratic output growth. Clients that need partial messages must assemble deltas between `message_start` and `message_end`; the latter remains authoritative ([#7290](https://github.com/earendil-works/pi/issues/7290)).
+- `ModelRegistry.getApiKeyAndHeaders()` now returns `ProviderHeaders` with `string | null` values and preserves `null` header-deletion markers. Extensions that inspect returned headers must handle `null`; extensions forwarding them to pi-ai streams should pass them through unchanged. This prevents placeholder OpenAI credentials from being sent through Cloudflare AI Gateway ([#7030](https://github.com/earendil-works/pi/issues/7030)).
+- Changed `ModelRegistry.refresh()` to accept `ModelsRefreshOptions` and return `ModelsRefreshResult` instead of discarding cancellation and provider errors.
+- Changed `ModelRuntime.setRuntimeApiKey()` to accept auth cancellation options rather than catalog refresh options. Call `refresh({ providers: [providerId], signal })` separately when remote freshness is required.
+- Required config-form extension OAuth `refreshToken(credentials, signal)` callbacks to accept and honor a concrete abort signal.
+- Replaced dynamic provider refresh context store access with the read-only `context.stored` snapshot and generation-checked `context.publish()` transaction.
+
+  **Providers built with `createProvider({ fetchModels })`:** no catalog-publication migration is required. Before and after, return the fetched models and register the resulting provider; `createProvider()` owns restoration, persistence, and in-memory publication.
+
+  ```ts
+  // Before
+  const beforeProvider = createProvider({
+    // ...
+    fetchModels: async ({ signal }) => {
+      const response = await fetch(catalogUrl, { signal });
+      return parseModels(await response.json());
+    },
+  });
+  pi.registerProvider(beforeProvider);
+
+  // After: unchanged
+  const afterProvider = createProvider({
+    // ...
+    fetchModels: async ({ signal }) => {
+      const response = await fetch(catalogUrl, { signal });
+      return parseModels(await response.json());
+    },
+  });
+  pi.registerProvider(afterProvider);
+  ```
+
+  **Handwritten native `Provider.refreshModels()`:** replace direct store access and pre-publication mutation with generation-guarded publications.
+
+  ```ts
+  // Before
+  refreshModels: async (context) => {
+    const stored = await context.store.read();
+    if (stored) currentModels = stored.models;
+    if (!context.allowNetwork) return;
+
+    const refreshed = await fetchModels(context.signal);
+    currentModels = refreshed;
+    await context.store.write({ models: refreshed, checkedAt: Date.now() });
+  },
+
+  // After
+  refreshModels: async (context) => {
+    if (context.stored) {
+      const restored = context.stored.models;
+      if (!(await context.publish({
+        update: () => { currentModels = restored; },
+      }))) return;
+    }
+    if (!context.allowNetwork) return;
+
+    const refreshed = await fetchModels(context.signal);
+    if (context.signal.aborted) return;
+    await context.publish({
+      persist: { models: refreshed, checkedAt: Date.now() },
+      update: () => { currentModels = refreshed; },
+    });
+  },
+  ```
+
+  For the config-form `pi.registerProvider(name, { refreshModels })`, callbacks that only return models remain unchanged; pi publishes the returned list. If such a callback previously used `context.store` for custom persistence, read `context.stored` and call `context.publish({ persist: entry })`. In `publish()`, omit `persist` to leave storage unchanged, pass a `ModelsStoreEntry` to write it, or pass `persist: null` to delete it.
+
+- Replaced the inherited pi-agent-core harness session model with the v4 lane-based `Session`, `SessionStorage`, and `SessionRepo` APIs, including durable operation records, global facts, shared sequence numbers, and tree-scoped lane views.
+- Promoted the inherited v2 session and `AgentHarness` API from pi-agent-core's experimental entrypoint to its default export and removed the experimental subpaths.
+- Removed the inherited legacy JSONL and in-memory repository APIs. Use pi-agent-core's v4 `JsonlSessionRepo` or `InMemorySessionRepo`, both implementing the new `SessionRepo` contract.
+- Added the inherited required pi-agent-core `FileSystem.renameFile()` operation for atomic JSONL publication; custom harness file-system implementations must provide same-filesystem replacement semantics ([#7707](https://github.com/earendil-works/pi/pull/7707) by [@davidbrai](https://github.com/davidbrai)).
+- Replaced experimental remote-session list summaries with durable `SessionMetadata`; `RemoteSession.sessions` no longer exposes runtime phase, model, thinking, attachment, or lock state, which remains available from acquired `SessionSnapshot` values ([#7708](https://github.com/earendil-works/pi/pull/7708)).
+
+### Added
+
+- Added built-in Baseten provider support with `BASETEN_API_KEY` authentication and `zai-org/GLM-5.2` as the default model.
+- Added experimental remote-session client APIs: the transport-neutral `PiClient`, CBOR protocol, Unix-socket transport, and `@sammorrowdrums/mcpi/client` `RemoteSession` controller with transcript reducers. See [Pi Client](../client/README.md) and [Remote Protocol](../protocol/README.md) ([#7344](https://github.com/earendil-works/pi/pull/7344), [#7348](https://github.com/earendil-works/pi/pull/7348), [#7371](https://github.com/earendil-works/pi/pull/7371), [#7409](https://github.com/earendil-works/pi/pull/7409)).
+- Added `CredentialSynchronizationError` for credential changes that commit successfully but fail to synchronize local model state.
+- Added chainable `pi.registerMarkdownTransformer()` hooks for display-only transformation of user and assistant Markdown. See [`pi.registerMarkdownTransformer()`](docs/extensions.md#piregistermarkdowntransformertransformer) ([#7231](https://github.com/earendil-works/pi/pull/7231) by [@xl0](https://github.com/xl0)).
+- Added an experimental fullscreen TUI mode, selectable through `--tui-mode fullscreen` or `/settings` ([#7304](https://github.com/earendil-works/pi/issues/7304)).
+- Added runtime switching between regular and fullscreen TUI modes through `/settings`.
+- Added a sticky editor, status, widget, and footer dock to fullscreen mode while keeping the transcript independently scrollable.
+- Added a draggable transcript scrollbar to fullscreen mode with configurable `auto`, `always`, and `hidden` modes through `/settings`; `always` reserves the rightmost column.
+- Added page scrolling and marked-message navigation shortcuts to fullscreen mode.
+- Added an optional `scrollbarThumb` theme color for fullscreen scrollbar thumbs, falling back to `selectedBg`.
+- Added configurable themed Unicode rendering for supported Mermaid diagrams in interactive messages, including optional rendering while streaming. See [Markdown settings](docs/settings.md#markdown) ([#7624](https://github.com/earendil-works/pi/pull/7624) by [@xl0](https://github.com/xl0)).
+- Added opt-in `Ctrl+P`/`Ctrl+N` prompt history navigation, with explicit history bindings taking precedence over application shortcuts while the editor is focused.
+- Added per-directory `AGENTS.override.md` context files, which replace `AGENTS.md` or `CLAUDE.md` in the same directory while preserving context from other directories. See [Context Files](docs/usage.md#context-files) ([#7681](https://github.com/earendil-works/pi/pull/7681) by [@Marvae](https://github.com/Marvae)).
+- Added `AI_AGENT=pi` to CLI and RPC child-process environments for generic agent attribution. See [Environment Variables](README.md#environment-variables) ([#7493](https://github.com/earendil-works/pi/pull/7493) by [@renaudhartert-db](https://github.com/renaudhartert-db)).
+- Added inherited terminal-friendly Unicode rendering for LaTeX expressions in Markdown. See [TUI Markdown](../tui/README.md#markdown).
+- Added stacked transient notifications in fullscreen mode.
+- Added arbitrary OpenAI-compatible model sampling parameters through `samplingParams` in `models.json`, model overrides, extension providers, and stream options. See [Sampling Parameters](docs/models.md#sampling-parameters) ([#7568](https://github.com/earendil-works/pi/pull/7568) by [@mrexodia](https://github.com/mrexodia)).
+- Added inherited opt-in vLLM `thinking_token_budget` support for OpenAI-compatible models, reserving output tokens for the final answer ([#7638](https://github.com/earendil-works/pi/pull/7638) by [@bnsd55](https://github.com/bnsd55)).
+- Added inherited support for OpenAI-compatible streams that omit `finish_reason`, using `compat.supportsFinishReason` to infer normal and tool-use stops when the stream ends. See [OpenAI Compatibility](docs/models.md#openai-compatibility).
+- Added inherited deferred provider request contracts, durable response handles, authenticated fetch/cancel dispatch, and faux-provider support for pending, ready, failed, and cancelled responses ([#7339](https://github.com/earendil-works/pi/pull/7339) by [@davidbrai](https://github.com/davidbrai)).
+- Added inherited vendor-neutral telemetry contracts plus agent-owned typed AI-request and harness schemas, composed span starters, and callback helpers. See the [agent telemetry schema reference](../agent/docs/telemetry-schema.md).
+- Added inherited structured Amazon Bedrock failure diagnostics with HTTP status, modeled error code, and AWS request id when available ([#7286](https://github.com/earendil-works/pi/pull/7286) by [@brianstanley](https://github.com/brianstanley)).
+- Added inherited `AgentOptions.shouldStopAfterTurn` for gracefully stopping after a completed turn before queued messages or another model call are processed. See [Agent Options](../agent/README.md#agent-options) ([#7367](https://github.com/earendil-works/pi/pull/7367) by [@acmerfight](https://github.com/acmerfight)).
+- Added inherited v4 `JsonlSessionRepo` support for append-only JSONL harness sessions ([#7611](https://github.com/earendil-works/pi/pull/7611) by [@davidbrai](https://github.com/davidbrai)).
+- Added inherited bounded branch-entry and indexed open-operation recovery queries to the v4 session API ([#7448](https://github.com/earendil-works/pi/pull/7448), [#7646](https://github.com/earendil-works/pi/pull/7646)).
+- Added the inherited compile-complete `AgentHarness` v2 scaffold; unfinished operation paths reject with `HarnessNotImplemented` while durable execution is implemented.
+
+### Changed
+
+- Added inherited optional cancellation to pi-ai `ModelsStore` reads, writes, and deletions; catalog orchestration binds these waits to the provider refresh signal.
+- Reduced the inherited default fullscreen mouse wheel step from three lines to one for finer scrolling.
+
+### Fixed
+
+- Fixed the footer showing `(sub)` for generic OAuth/OpenID sign-ins without a known subscription; extension OAuth providers can opt in with `isSubscription`.
+- Fixed inherited OAuth token refreshes so stalled requests release the credential-store lock ([#7508](https://github.com/earendil-works/pi/issues/7508)).
+- Fixed inherited tool argument validation to preserve values that already match an `anyOf`/`oneOf` union arm before coercion, avoiding nullable unions converting `null` to another primitive value ([#7328](https://github.com/earendil-works/pi/issues/7328)).
+- Fixed inherited Fireworks GLM 5.2 requests sending the unsupported `prompt_cache_retention` field when long cache retention is enabled, and enabled session affinity for automatic prompt caching ([#7676](https://github.com/earendil-works/pi/issues/7676)).
+- Fixed inherited `JsonlSessionRepo` enforcing session IDs globally across working directories; IDs are now unique within each working directory.
+- Fixed inherited JSONL session forks and torn-tail repairs to publish atomically, avoiding partially written or corrupted sessions after interrupted writes ([#7707](https://github.com/earendil-works/pi/pull/7707) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed path-containing `find` globs returning no results on Windows ([#6817](https://github.com/earendil-works/pi/issues/6817)).
+- Fixed messages queued during manual `/compact` failing instead of being sent after compaction completes.
+- Fixed Git Bash, MSYS, Cygwin, and WSL drive paths passed to built-in file tools resolving against the current Windows drive instead of their native drive ([#7064](https://github.com/earendil-works/pi/issues/7064), [#7547](https://github.com/earendil-works/pi/issues/7547)).
+- Fixed project-level nested provider retry settings replacing unmodified global provider retry settings ([#7572](https://github.com/earendil-works/pi/issues/7572)).
+- Fixed inherited GitHub Copilot Grok 4.5 requests to use the supported Responses API ([#7560](https://github.com/earendil-works/pi/issues/7560)).
+- Fixed fullscreen shutdown leaking terminal capability-query replies into the parent shell prompt.
+- Fixed bare exact `--model` IDs shared by multiple providers choosing the first catalog entry instead of the sole authenticated provider or a clear ambiguity error ([#7327](https://github.com/earendil-works/pi/issues/7327)).
+- Fixed standalone x64 binaries requiring Haswell-era AVX2/BMI2 instructions by compiling release executables against Bun's baseline runtime ([#7390](https://github.com/earendil-works/pi/pull/7390) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed `Ctrl+X` copy confirmations in fullscreen mode adding a transcript status line instead of showing the transient `Copied!` marker.
+- Fixed Kitty image previews in fullscreen mode overlapping the sticky editor and footer dock while scrolling.
+- Fixed image-heavy fullscreen sessions lagging when layout changes retransmitted visible Kitty image payloads and rendered the transcript twice per frame.
+- Fixed spaces in `/settings` searches toggling the highlighted setting while typing multi-word queries such as **TUI mode** or **Quiet startup**.
+- Fixed custom editors not inheriting the default editor's autocomplete dropdown item limit ([#7333](https://github.com/earendil-works/pi/issues/7333)).
+- Fixed malformed resource arrays in package manifests crashing session startup ([#7187](https://github.com/earendil-works/pi/issues/7187)).
+- Fixed the DOOM overlay example downloading its shareware WAD from a dead URL.
+- Fixed `setToolsExpanded(false)` to be a no-op when tool output is already collapsed, avoiding redundant `Tool output: collapsed` startup notices from extensions ([#7292](https://github.com/earendil-works/pi/issues/7292)).
+- Fixed extension-driven model calls in custom compaction, handoff, and Q&A examples to dispatch through the coding-agent model runtime so custom providers and resolved auth options are preserved ([#7325](https://github.com/earendil-works/pi/pull/7325)).
+- Fixed long-running sessions using stale credentials after another process updates `auth.json` without serializing concurrent credential reads and delaying startup ([#7319](https://github.com/earendil-works/pi/issues/7319)).
+- Fixed concurrent `models-store.json` reads forming a file-lock convoy and delaying startup.
+- Updated the packaged `brace-expansion` dependency to 5.0.8 to address GHSA-mh99-v99m-4gvg ([#7316](https://github.com/earendil-works/pi/issues/7316)).
+- Fixed forced model availability refreshes remaining blocked behind a stalled earlier refresh ([#7301](https://github.com/earendil-works/pi/issues/7301), [#7421](https://github.com/earendil-works/pi/pull/7421) by [@a-yeyang](https://github.com/a-yeyang)).
+- Fixed `/model` catalog refresh failures to identify every catalog that failed.
+- Fixed provider login remaining stuck after saving credentials when a model catalog refresh stalls by separating local credential consistency from bounded background freshness ([#7027](https://github.com/earendil-works/pi/issues/7027), [#7113](https://github.com/earendil-works/pi/issues/7113), [#7418](https://github.com/earendil-works/pi/issues/7418)).
+- Fixed `/scoped-models` waiting for remote catalogs before rendering instead of showing cached models and cancelling refresh on close ([#7153](https://github.com/earendil-works/pi/issues/7153)).
+- Fixed `/model <name>` waiting for catalog refresh before checking cached model matches ([#7443](https://github.com/earendil-works/pi/issues/7443)).
+- Fixed stale availability snapshots and errors publishing after a newer availability pass.
+- Fixed stale pi.dev, Radius, llama.cpp, and extension catalog refreshes publishing after a newer provider refresh.
+- Fixed cancellation while waiting for file-backed credential or model-catalog locks, preventing cancelled mutations from running or committing later.
+- Fixed concurrent in-memory credential mutations losing unrelated provider updates by serializing their read-modify-write sections.
+- Updated `undici` to 8.9.0 and the packaged `brace-expansion` to 5.0.9 to address GHSA-8xcm-r25x-g524, GHSA-4cwx-7wf7-3272, GHSA-m8rv-5g2x-5cg5, GHSA-jr45-8vmc-qm54, GHSA-v3r7-h72x-cjcm, and GHSA-rgw5-rvv9-x895.
+- Fixed GitHub Copilot compaction and branch summaries using the Individual endpoint instead of the credential-resolved Business or Enterprise endpoint ([#6768](https://github.com/earendil-works/pi/issues/6768)).
+- Fixed extension model calls dropping credential-resolved endpoints when forwarding request authentication, including custom compaction with GitHub Copilot Business and Enterprise accounts ([#7579](https://github.com/earendil-works/pi/issues/7579)).
+- Fixed fullscreen transcript navigation leaving no editor-accessible `Home`, `End`, `PageUp`, or `PageDown` variants by adding Ctrl-modified editor bindings ([#7574](https://github.com/earendil-works/pi/issues/7574)).
+- Fixed extension event-bus listeners surviving session reloads and disposal ([#7656](https://github.com/earendil-works/pi/pull/7656) by [@tudoroancea](https://github.com/tudoroancea)).
+- Fixed `/copy` failing to read clipboard text on Wayland when no X11 clipboard is available ([#7387](https://github.com/earendil-works/pi/pull/7387)).
+- Fixed slow connections failing during the initial connection attempt by increasing the connect timeout ([#7435](https://github.com/earendil-works/pi/pull/7435) by [@muyiyr](https://github.com/muyiyr)).
+- Fixed oversized images returned by extension and built-in tools bypassing automatic image resizing. See [Image settings](docs/settings.md#terminal--images) ([#7330](https://github.com/earendil-works/pi/pull/7330) by [@tizmagik](https://github.com/tizmagik)).
+- Fixed session discovery missing sessions stored through symlinked directories ([#7552](https://github.com/earendil-works/pi/pull/7552) by [@muyiyr](https://github.com/muyiyr)).
+- Fixed manual compaction racing with threshold auto-compaction ([#7370](https://github.com/earendil-works/pi/pull/7370) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed responses truncated below their intended output limit ending the run instead of compacting and retrying once ([#7540](https://github.com/earendil-works/pi/pull/7540) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed Git package updates leaving dependencies missing when `git clean` cannot remove an ignored dependency directory ([#7570](https://github.com/earendil-works/pi/pull/7570) by [@mrexodia](https://github.com/mrexodia)).
+- Fixed `find` results from POSIX and Windows filesystem roots losing the first path segment or gaining duplicate trailing separators ([#7569](https://github.com/earendil-works/pi/pull/7569) by [@petrroll](https://github.com/petrroll)).
+- Fixed transient version-check, catalog, managed-tool, and package-management HTTP failures not being retried ([#7632](https://github.com/earendil-works/pi/pull/7632) by [@petrroll](https://github.com/petrroll)).
+- Fixed interactive errors ignoring the configured output padding.
+- Fixed the inherited OpenCode Go provider display name.
+- Fixed inherited provider error normalization treating arrays and class instances as structured response bodies instead of preserving their original errors ([#7205](https://github.com/earendil-works/pi/pull/7205) by [@erikogenvik](https://github.com/erikogenvik)).
+- Fixed inherited Anthropic streams dropping text or thinking included in the initial content-block event ([#7358](https://github.com/earendil-works/pi/pull/7358) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited Google history conversion dropping signed empty text and thinking blocks required for replay ([#7362](https://github.com/earendil-works/pi/pull/7362) by [@jingtao-wisdomgraph](https://github.com/jingtao-wisdomgraph)).
+- Fixed inherited OpenAI Codex cached WebSocket sessions being shared across different account credentials ([#7364](https://github.com/earendil-works/pi/pull/7364)).
+- Fixed inherited transient Google Generative AI and Vertex AI provider errors bypassing automatic retries ([#7471](https://github.com/earendil-works/pi/pull/7471) by [@vish-pr](https://github.com/vish-pr)).
+- Fixed inherited Gemini 3 tool call ids being discarded during history conversion, breaking signed multi-turn replay ([#7494](https://github.com/earendil-works/pi/pull/7494) by [@muyiyr](https://github.com/muyiyr)).
+- Restored inherited GitHub Copilot models returned through account-specific policy responses ([#7672](https://github.com/earendil-works/pi/pull/7672) by [@muyiyr](https://github.com/muyiyr)).
+- Replaced the inherited retired Qwen Token Plan `qwen3.8-max-preview` model with `qwen3.8-max` ([#7670](https://github.com/earendil-works/pi/pull/7670) by [@QuintinShaw](https://github.com/QuintinShaw)).
+- Fixed inherited terminal width accounting for Indic conjunct grapheme clusters ([#6987](https://github.com/earendil-works/pi/pull/6987) by [@petrroll](https://github.com/petrroll)).
+- Fixed inherited nested fullscreen stack layouts ignoring child minimum sizes.
+- Fixed inherited batched terminal color-scheme reports being parsed as one malformed response ([#7550](https://github.com/earendil-works/pi/pull/7550)).
+- Fixed inherited terminal progress clearing to emit the complete OSC 9;4 sequence ([#7581](https://github.com/earendil-works/pi/pull/7581)).
+- Fixed inherited iTerm2 image payloads omitting the size metadata required by the xterm.js image addon ([#7612](https://github.com/earendil-works/pi/pull/7612)).
+- Fixed inherited width truncation leaving OSC 8 hyperlinks unterminated ([#7657](https://github.com/earendil-works/pi/pull/7657) by [@xXJSONDeruloXx](https://github.com/xXJSONDeruloXx)).
+- Updated inherited GPT-5.6 Terra and Luna pricing across OpenAI and passthrough model catalogs.
+- Fixed inherited Fireworks Kimi K3 models to use the OpenAI-compatible API with native reasoning-effort levels and deferred tools ([#7199](https://github.com/earendil-works/pi/issues/7199), [#7230](https://github.com/earendil-works/pi/pull/7230) by [@XBeg9](https://github.com/XBeg9)).
+- Updated the inherited Groq Qwen reasoning override for the replacement `qwen/qwen3.6-27b` model.
+- Fixed inherited Windows Shift+Enter detection by reading modifier state from the native Win32 helper.
+- Fixed the inherited pi-tui npm package omitting the source and build scripts needed to rebuild its Windows and Darwin native addons.
+- Fixed inherited Windows console truecolor detection when Windows Terminal does not provide `WT_SESSION` to child shells.
+- Fixed inherited phantom fullscreen text selection from unmatched mouse events when changing terminal pane focus.
+- Fixed inherited keyboard input rendering latency on Windows by letting input preempt the throttled render timer.
+- Fixed inherited agent harness path handling on Windows for file basenames, recursive skill loading, and prompt template names.
+
+## [0.83.0] - 2026-07-29
+
+### New Features
+
+- **Credential export for external clients** — `pi auth print-api-key` and `pi auth print-bearer-token` export configured credentials with automatic OAuth refresh and minimum-validity enforcement.
+- **Headless OpenRouter sign-in** — Complete `/login` over SSH by pasting the redirect URL or authorization code when the loopback callback is unavailable. See [OpenRouter](docs/providers.md#openrouter).
+- **Claude Opus 5 on GitHub Copilot** — Use Claude Opus 5 through GitHub Copilot with adaptive thinking and a 1M context window. See [GitHub Copilot](docs/providers.md#github-copilot).
+
+### Breaking Changes
+
+- Upgraded bundled TypeBox aliases to 1.3.7, removing deprecated APIs including `Type.Base`, `Type.Awaited`, `Type.Promise`, `Type.AsyncIterator`, `Type.Iterator`, `Type.Options`, and `Value.Mutate`, while fixing compiled validation of nullable array tool arguments. Extensions using removed APIs must migrate to supported TypeBox APIs. See [Package Dependencies](docs/packages.md#dependencies) ([#7243](https://github.com/earendil-works/pi/pull/7243) by [@petrroll](https://github.com/petrroll)).
+
+### Added
+
+- Added `pi auth print-api-key` and `pi auth print-bearer-token` commands for exporting configured credentials to external clients, including automatic OAuth refresh and configurable minimum token validity ([#7168](https://github.com/earendil-works/pi/pull/7168)).
+- Exposed the session's resolved model scope as `ctx.scopedModels` to extensions. See [Extension Context](docs/extensions.md#ctxmodelregistry--ctxmodel--ctxthinkinglevel--ctxscopedmodels) ([#7191](https://github.com/earendil-works/pi/pull/7191) by [@pungggi](https://github.com/pungggi), [#7215](https://github.com/earendil-works/pi/pull/7215)).
+- Added inherited per-request `fetch` injection for supported text and image provider transports.
+- Added the inherited `"pending"` stop reason for partial streaming messages. See [Custom Provider Stream Pattern](docs/custom-provider.md#stream-pattern) ([#7151](https://github.com/earendil-works/pi/pull/7151) by [@lucasmeijer](https://github.com/lucasmeijer)).
+- Added inherited raw provider stop reasons across Google, Anthropic, Amazon Bedrock, Mistral, and OpenAI streams; unmapped terminal reasons now surface as provider errors instead of successful stops ([#7272](https://github.com/earendil-works/pi/pull/7272)).
+- Added manual redirect URL and authorization-code entry to OpenRouter login for remote and headless environments. See [OpenRouter](docs/providers.md#openrouter) ([#7114](https://github.com/earendil-works/pi/pull/7114) by [@rgarcia](https://github.com/rgarcia)).
+- Added inherited Claude Opus 5 support for GitHub Copilot with adaptive thinking and a 1M context window. See [GitHub Copilot](docs/providers.md#github-copilot) ([#7158](https://github.com/earendil-works/pi/pull/7158) by [@jay-aye-see-kay](https://github.com/jay-aye-see-kay)).
+
+### Changed
+
+- Changed inherited OAuth credential resolution to refresh tokens with less than five minutes of validity remaining instead of waiting until expiration ([#7168](https://github.com/earendil-works/pi/pull/7168)).
+
+### Fixed
+
+- Added a status line when the tool output expansion is toggled ([#7180](https://github.com/earendil-works/pi/issues/7180)).
+- Fixed file-backed `SYSTEM.md` and `APPEND_SYSTEM.md` prompts being omitted from the interactive startup context listing. See [System Prompt Files](docs/usage.md#system-prompt-files) ([#7096](https://github.com/earendil-works/pi/issues/7096)).
+- Fixed context files loading twice when a linked Git worktree is nested under its main repository. See [Context Files](docs/usage.md#context-files) ([#7221](https://github.com/earendil-works/pi/pull/7221) by [@arajkumar](https://github.com/arajkumar)).
+- Fixed llama.cpp streamed responses reporting zero token usage and leaving session context accounting empty. See [llama.cpp](docs/llama-cpp.md) ([#7258](https://github.com/earendil-works/pi/pull/7258) by [@SteveImmanuel](https://github.com/SteveImmanuel)).
+- Fixed session replacement and committed tree navigation during an active response to abort and persist the outgoing turn instead of leaving dangling tool calls. See [Sessions](docs/usage.md#sessions) ([#7022](https://github.com/earendil-works/pi/pull/7022) by [@tmustier](https://github.com/tmustier)).
+- Fixed failed Git package installs leaving partial directories that blocked clean retries. See [Install and Manage](docs/packages.md#install-and-manage) ([#7210](https://github.com/earendil-works/pi/pull/7210) by [@haoqixu](https://github.com/haoqixu)).
+- Fixed the `/model` selector retaining a stale selection while filtering instead of highlighting the top match ([#7211](https://github.com/earendil-works/pi/pull/7211) by [@christianbasch](https://github.com/christianbasch)).
+- Fixed direct RPC bash commands bypassing extension `user_bash` handlers. See [User Bash Events](docs/extensions.md#user-bash-events) ([#7214](https://github.com/earendil-works/pi/pull/7214)).
+- Fixed skills, prompts, and themes losing package source metadata after extensions reload resources. See [Resource Events](docs/extensions.md#resource-events) ([#6968](https://github.com/earendil-works/pi/issues/6968)).
+- Fixed cancellation of concurrently running user bash commands so every active command is aborted ([#7103](https://github.com/earendil-works/pi/pull/7103) by [@yzhg1983](https://github.com/yzhg1983)).
+- Fixed duplicate messages appearing when extensions switch sessions during interactive startup ([#7110](https://github.com/earendil-works/pi/pull/7110) by [@yzhg1983](https://github.com/yzhg1983)).
+- Fixed inherited Qwen Token Plan reasoning models to send their service-specific thinking controls and supported reasoning-effort levels ([#6951](https://github.com/earendil-works/pi/issues/6951), [#6998](https://github.com/earendil-works/pi/issues/6998)).
+- Fixed inherited Z.AI output limits being sent through an unsupported parameter. See [Providers](docs/providers.md) ([#7174](https://github.com/earendil-works/pi/pull/7174) by [@HyeokjaeLee](https://github.com/HyeokjaeLee)).
+- Fixed explicitly configured Amazon Bedrock profiles being overridden by ambient AWS access keys. See [Amazon Bedrock](docs/providers.md#amazon-bedrock) ([#7176](https://github.com/earendil-works/pi/pull/7176) by [@christianbasch](https://github.com/christianbasch)).
+- Fixed inherited image fallback paths overflowing narrow terminals, shortened home-directory paths, and made absolute paths clickable when terminal hyperlinks are available ([#7262](https://github.com/earendil-works/pi/pull/7262)).
+- Fixed inherited OpenAI-compatible tool calls losing their function arguments when malformed deltas also contain an empty `custom` object ([#7288](https://github.com/earendil-works/pi/pull/7288) by [@sunnyyoung](https://github.com/sunnyyoung)).
+
+## [0.82.1] - 2026-07-25
+
+### New Features
+
+- **Claude Opus 5** — Available on Anthropic and Amazon Bedrock with adaptive thinking (including `xhigh`), inference profiles, and prompt caching. See [Providers](docs/providers.md#api-keys).
+- **Anthropic gateway bearer auth** — `ANTHROPIC_AUTH_TOKEN` authenticates against Anthropic-compatible gateways that require `Authorization: Bearer`, including compaction and branch summaries. See [Environment Variables or Auth File](docs/providers.md#environment-variables-or-auth-file).
+- **Faster, more resilient model catalogs** — pi.dev catalogs revalidate with `If-None-Match` so unchanged providers answer with an empty `304`, and llama.cpp models stay listed across restarts. See [llama.cpp](docs/llama-cpp.md).
+
+### Added
+
+- Exposed the `outputPad` setting to custom message renderers. See [Extensions](docs/extensions.md) ([#7045](https://github.com/earendil-works/pi/pull/7045) by [@xl0](https://github.com/xl0)).
+- Added inherited `ANTHROPIC_AUTH_TOKEN` bearer authentication for Anthropic-compatible gateways. See [Providers](docs/providers.md#environment-variables-or-auth-file) ([#5871](https://github.com/earendil-works/pi/issues/5871)).
+- Added inherited Claude Opus 5 support for Anthropic and Amazon Bedrock with adaptive thinking, inference profiles, prompt caching, and preserved AWS validation messages ([#7081](https://github.com/earendil-works/pi/pull/7081) by [@unexge](https://github.com/unexge), [#7083](https://github.com/earendil-works/pi/pull/7083) by [@davidbrai](https://github.com/davidbrai)).
+
+### Changed
+
+- Changed pi.dev model catalog refreshes to revalidate with `If-None-Match`, so unchanged provider catalogs answer with an empty `304` instead of a full download.
+- Changed inherited Radius OAuth device authorization, token exchange, and refresh requests to use the configured gateway directly.
+- Changed inherited model loading errors to append the underlying cause, so auth failures such as `OAuth refresh failed for openai-codex` report the provider response instead of a bare wrapper message.
+
+### Fixed
+
+- Fixed compaction and branch summaries for providers whose authentication resolves entirely to request headers ([#5871](https://github.com/earendil-works/pi/issues/5871))
+- Fixed unavailable scoped models being hidden from `/models`, allowing them to be removed without editing settings manually ([#6949](https://github.com/earendil-works/pi/issues/6949), [#7032](https://github.com/earendil-works/pi/pull/7032) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed startup context file discovery to skip directories that match context file names such as `AGENTS.md`, which produced `EISDIR` warnings ([#7106](https://github.com/earendil-works/pi/pull/7106) by [@mrexodia](https://github.com/mrexodia)).
+- Fixed the llama.cpp extension to persist its model catalog, so llama.cpp models stay listed before the first successful refresh. See [llama.cpp](docs/llama-cpp.md) ([#7072](https://github.com/earendil-works/pi/pull/7072) by [@davidbrai](https://github.com/davidbrai)).
+
+## [0.82.0] - 2026-07-24
+
+### New Features
+
+- **Constrained tool sampling** — Tools can prefer or require strict JSON Schema sampling or use OpenAI Lark/regex grammars, with model capability metadata preventing unsupported requests. See [Constrained Sampling for Tools](../ai/README.md#constrained-sampling-for-tools).
+- **OpenRouter and Kimi Code sign-in** — Use `/login` to authorize OpenRouter or a Kimi Code subscription without manually configuring API keys. See [OpenRouter](docs/providers.md#openrouter).
+- **Session-aware, streaming bash integrations** — Bash tools receive current session/model metadata, while direct RPC bash commands stream correlated output. See [Bash Tool Session Environment](docs/environment-variables.md#bash-tool-session-environment) and [RPC bash events](docs/rpc.md#bash_execution_update).
+
+### Added
+
+- Added inherited `Tool.constrainedSampling` with strict JSON Schema (`prefer`/`require`) and OpenAI Lark/regex grammar variants across OpenAI, Anthropic, Amazon Bedrock, Google Gemini, and Mistral. See [Constrained Sampling for Tools](../ai/README.md#constrained-sampling-for-tools).
+- Added inherited `supportsGrammarTools` and `supportsStrictTools` compatibility flags, expanded `supportsStrictMode` coverage, and generated model capability metadata to gate constrained sampling.
+- Added inherited Kimi Code subscription OAuth login for the Kimi For Coding provider, including device authorization and automatic token refresh ([#6935](https://github.com/earendil-works/pi/pull/6935) by [@zaycruz](https://github.com/zaycruz)).
+- Added inherited OpenRouter OAuth PKCE login through `/login`, minting a user-controlled API key. See [OpenRouter](docs/providers.md#openrouter) ([#6927](https://github.com/earendil-works/pi/pull/6927) by [@rsaryev](https://github.com/rsaryev)).
+- Exposed `PI_SESSION_ID`, `PI_SESSION_FILE`, `PI_PROVIDER`, `PI_MODEL`, and `PI_REASONING_LEVEL` to commands run by built-in and factory-created bash tools. See [Bash Tool Session Environment](docs/environment-variables.md#bash-tool-session-environment).
+- Added streaming `bash_execution_update` events for direct RPC bash commands, correlated with request IDs. See [RPC bash events](docs/rpc.md#bash_execution_update) ([#6971](https://github.com/earendil-works/pi/pull/6971) by [@ananthakumaran](https://github.com/ananthakumaran)).
+
+### Changed
+
+- Changed inherited generated model catalogs to expose only provider-verified reasoning effort levels from models.dev ([#6928](https://github.com/earendil-works/pi/pull/6928) by [@davidbrai](https://github.com/davidbrai)).
+
+### Fixed
+
+- Fixed inherited DNS lookup failures such as `getaddrinfo`, `ENOTFOUND`, and `EAI_AGAIN` to trigger automatic assistant retries ([#6946](https://github.com/earendil-works/pi/pull/6946) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed inherited OpenRouter Anthropic cache breakpoints to advance through tool results and enabled cache control for `~anthropic/*-latest` aliases ([#6941](https://github.com/earendil-works/pi/pull/6941) by [@mteam88](https://github.com/mteam88)).
+- Fixed inherited OpenAI Codex WebSocket sessions to retry once without a missing previous-response continuation after `previous_response_not_found` errors ([#6955](https://github.com/earendil-works/pi/pull/6955) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed TUI debug and crash logs to respect custom agent directories instead of always writing under `~/.pi/agent` ([#6958](https://github.com/earendil-works/pi/pull/6958) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed slow Ctrl+G external-editor startup when the system temporary directory contains many entries ([#6903](https://github.com/earendil-works/pi/pull/6903) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed startup resource display to preserve relative paths for sibling npm extensions loaded by a package ([#6964](https://github.com/earendil-works/pi/pull/6964) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed compaction and branch-summary requests to use fresh routing session IDs with prompt caching disabled where supported ([#6618](https://github.com/earendil-works/pi/pull/6618) by [@tmustier](https://github.com/tmustier)).
+- Fixed explicit self-updates when `PI_SKIP_VERSION_CHECK` is set ([#6977](https://github.com/earendil-works/pi/issues/6977)).
+- Fixed scoped model IDs containing brackets to resolve as literal exact matches before glob matching ([#6210](https://github.com/earendil-works/pi/issues/6210)).
+- Fixed inherited OpenAI and Anthropic provider retry waits to honor abort signals and configured delay limits ([#6980](https://github.com/earendil-works/pi/pull/6980) by [@petrroll](https://github.com/petrroll)).
+- Fixed fresh installs from preferring bundled model catalogs over newer remote catalogs because package file mtimes were newer ([#7016](https://github.com/earendil-works/pi/pull/7016) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited editor scroll indicators overflowing narrow terminals ([#7015](https://github.com/earendil-works/pi/pull/7015) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed llama.cpp models to use the loaded context window as their output token limit instead of capping it at 16K ([#7034](https://github.com/earendil-works/pi/pull/7034) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed release source archives to include the generated provider model data used to build standalone binaries.
+- Updated the packaged `protobufjs` dependency to 7.6.5 to address GHSA-j3f2-48v5-ccww ([#7005](https://github.com/earendil-works/pi/issues/7005)).
+- Fixed `/copy` on Wayland to fall back to X11 or OSC 52 when `wl-copy` fails ([#7009](https://github.com/earendil-works/pi/pull/7009) by [@rkfshakti](https://github.com/rkfshakti)).
+- Fixed `/model` to reload updated `models.json` configuration when opening the model picker ([#6999](https://github.com/earendil-works/pi/issues/6999)).
+
+## [0.81.1] - 2026-07-21
+
+### New Features
+
+- **Verifiable release source archives** — GitHub releases now include deterministic, checksummed source archives with instructions for rebuilding standalone binaries. See [Building standalone binaries from release source](../../README.md#building-standalone-binaries-from-release-source).
+- **Resilient compaction and branch summaries** — Transient provider failures now follow the configured retry policy, with retry lifecycle events available to interactive, JSON, RPC, and SDK consumers. See [Compaction & Branch Summarization](docs/compaction.md) and [RPC retry events](docs/rpc.md#summarization_retry_scheduled--summarization_retry_attempt_start--summarization_retry_finished).
+
+### Added
+
+- Added deterministic, checksummed source archives to GitHub releases with documented standalone binary rebuild instructions ([#6913](https://github.com/earendil-works/pi/pull/6913) by [@christianklotz](https://github.com/christianklotz)).
+
+### Fixed
+
+- Fixed compaction and branch summarization to retry transient provider failures using the configured retry policy, with retry lifecycle events exposed to interactive, JSON, RPC, and SDK consumers ([#6901](https://github.com/earendil-works/pi/pull/6901) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed interactive startup waiting for background model catalog refresh while computing the footer provider count.
+- Restored the default stream fallback for extensions using the pre-0.81 agent-core API ([#6915](https://github.com/earendil-works/pi/issues/6915)).
+- Fixed inherited Kimi K3 models from Moonshot AI and Moonshot AI China to use the OpenAI thinking format and expose reasoning effort support.
+
+## [0.81.0] - 2026-07-21
+
+### New Features
+
+- **Local llama.cpp model management** — Connect to a llama.cpp router, search and download Hugging Face models, and explicitly load or unload models with live progress. See [llama.cpp](docs/llama-cpp.md).
+- **Full provider extensions** — Extensions can register complete pi-ai providers with authentication, model refresh, filtering, and custom streaming. See [Register New Provider](docs/custom-provider.md#register-new-provider).
+- **Qwen Token Plan providers** — Use the built-in international and China subscription providers with regional endpoints and API-key authentication. See [API Keys](docs/providers.md#api-keys).
+- **Expanded usage accounting** — Tool, compaction, and branch-summary usage is persisted and included in session totals. See [Compaction & Branch Summarization](docs/compaction.md).
+
+### Added
+
+- Added Qwen Token Plan and Qwen Token Plan China to built-in provider setup, default model resolution, and provider documentation ([#6858](https://github.com/earendil-works/pi/pull/6858) by [@QuintinShaw](https://github.com/QuintinShaw)).
+- Added the `get_available_thinking_levels` RPC command and `RpcClient.getAvailableThinkingLevels()` method ([#6865](https://github.com/earendil-works/pi/pull/6865) by [@cristinaponcela](https://github.com/cristinaponcela)).
+- Exported message and tool execution lifecycle event types from the package root ([#6772](https://github.com/earendil-works/pi/pull/6772) by [@davidbrai](https://github.com/davidbrai)).
+- Added built-in llama.cpp router support with `/login` connection setup and `/llama` Hugging Face model search and downloads, explicit loading, unloading, and live progress. See [llama.cpp](docs/llama-cpp.md).
+- Added extension registration for complete pi-ai providers, including native authentication, model refresh, filtering, and streaming behavior.
+- Added usage accounting for tools, compaction, and branch summaries in persisted sessions, footer totals, and session statistics ([#6671](https://github.com/earendil-works/pi/pull/6671) by [@davidbrai](https://github.com/davidbrai)).
+
+### Fixed
+
+- Updated the packaged `brace-expansion` dependency to 5.0.7 ([#6896](https://github.com/earendil-works/pi/pull/6896) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed persisted remote model catalogs from overriding newer bundled catalogs after an upgrade.
+- Fixed inherited stored API-key credentials to apply their provider-scoped `env` values, including Amazon Bedrock profiles ([#6864](https://github.com/earendil-works/pi/pull/6864) by [@cristinaponcela](https://github.com/cristinaponcela)).
+- Fixed inherited OpenAI-compatible cross-provider replay to keep tool call IDs unique when multiple calls share a provider call ID ([#6854](https://github.com/earendil-works/pi/pull/6854) by [@cristinaponcela](https://github.com/cristinaponcela)).
+- Fixed inherited Kimi K3 thinking levels to expose low, high, and max, and normalized the `k2p7` alias to `kimi-for-coding`.
+- Fixed inherited OpenCode Go models routed through the OpenAI Responses API.
+- Fixed inherited `pi-ai` package metadata to avoid repeated consumer lockfile changes ([#6812](https://github.com/earendil-works/pi/pull/6812) by [@jmfederico](https://github.com/jmfederico)).
+- Fixed inherited terminal shutdown to clear the editor's inverted software cursor before restoring the hardware cursor ([#6790](https://github.com/earendil-works/pi/pull/6790) by [@dam9000](https://github.com/dam9000)).
+- Fixed inherited ANSI-aware text wrapping to recognize CRLF and CR line endings while preserving styles ([#6764](https://github.com/earendil-works/pi/pull/6764) by [@xz-dev](https://github.com/xz-dev)).
+- Fixed inherited editor paste registry corruption after deleting and undoing paste markers, preventing literal or mismatched paste markers in submitted prompts ([#6844](https://github.com/earendil-works/pi/issues/6844)).
+- Fixed sessionless OpenAI Codex WebSocket requests to use UUIDv7 request IDs ([#6834](https://github.com/earendil-works/pi/pull/6834) by [@xl0](https://github.com/xl0)).
+- Fixed inherited GPT-5.6 Codex models to default to the 272K context window, avoiding automatic long-context pricing ([#6853](https://github.com/earendil-works/pi/pull/6853) by [@aadishv](https://github.com/aadishv)).
+- Fixed messages queued during compaction to preserve steering and follow-up delivery behavior ([#6730](https://github.com/earendil-works/pi/pull/6730) by [@dannote](https://github.com/dannote)).
+- Fixed read tool errors being syntax-highlighted as if they were file contents ([#6731](https://github.com/earendil-works/pi/pull/6731) by [@dannote](https://github.com/dannote)).
+- Fixed llama.cpp router download progress updates and removed redundant wording from model action confirmations.
+- Moved automatic model catalog network refresh out of startup initialization and into the running interactive and RPC modes.
+- Fixed persisted sessions being read and parsed twice when opened, reducing startup latency for large sessions ([#6793](https://github.com/earendil-works/pi/issues/6793)).
+- Fixed prompt-template defaults for all arguments (`${@:-default}` and `${ARGUMENTS:-default}`) ([#6695](https://github.com/earendil-works/pi/issues/6695)).
+- Fixed obsolete custom UI, custom tool, and custom editor examples in the extension documentation ([#6735](https://github.com/earendil-works/pi/issues/6735)).
+- Fixed Kimi Coding sessions to show API-equivalent implied costs with the subscription indicator.
+- Fixed OpenAI Responses early stream endings to trigger automatic retry instead of ending the agent run ([#6727](https://github.com/earendil-works/pi/issues/6727)).
+
+## [0.80.10] - 2026-07-16
+
+### New Features
+
+- **Kimi Coding thinking compatibility** — Kimi Coding models now use adaptive thinking correctly; K3 exposes its supported `max` level and supports replaying empty-signature thinking blocks. See [Kimi For Coding setup](docs/providers.md#api-keys) and [Model Options](docs/usage.md#model-options).
+
+### Fixed
+
+- Fixed inherited Kimi Coding requests to use Anthropic adaptive thinking effort without token budgets, and enabled empty thinking signatures for K3 and `kimi-for-coding`.
+- Fixed inherited Kimi K3 pricing metadata for Moonshot AI and Moonshot AI China.
+- Fixed inherited Kimi Coding K3 thinking-level metadata to expose only the supported `max` level ([#6737](https://github.com/earendil-works/pi/issues/6737)).
+- Fixed inherited catalog generation restoring xAI models removed in 0.80.9 ([#6736](https://github.com/earendil-works/pi/issues/6736)).
+
+## [0.80.9] - 2026-07-16
+
+### New Features
+
+- **Kimi K3 and deferred tool loading** — Use Kimi K3 across built-in providers, including progressive extension tool activation through Kimi’s native protocol. See [Dynamic Tool Loading](docs/extensions.md#dynamic-tool-loading), [OpenAI Compatibility](docs/models.md#openai-compatibility), and the [`kimi-deferred-tools.ts`](examples/extensions/kimi-deferred-tools.ts) example.
+
+### Added
+
+- Added inherited Kimi K3 support for Kimi Coding, Moonshot AI, Moonshot AI China, OpenRouter, and Vercel AI Gateway.
+- Added Kimi deferred tool loading for extension-driven tool activation. See [Dynamic Tool Loading](docs/extensions.md#dynamic-tool-loading), [OpenAI Compatibility](docs/models.md#openai-compatibility), and the [`kimi-deferred-tools.ts`](examples/extensions/kimi-deferred-tools.ts) example.
+
+### Changed
+
+- Changed xAI login to use a prefilled device-authorization link labeled “Sign in with SuperGrok or X Premium,” and changed the default xAI model to Grok 4.5 ([#6734](https://github.com/earendil-works/pi-mono/pull/6734) by [@Jaaneek](https://github.com/Jaaneek)).
+
+### Fixed
+
+- Fixed inherited Kimi K3 output limits for Vercel AI Gateway and OpenRouter models.
+- Fixed cloning or forking a session before its first assistant response to explain that the session must be saved first.
+
+### Removed
+
+- Removed Grok 3, Grok 3 Fast, Grok 4.20 variants, and Grok Code Fast 1 from the built-in xAI model catalog ([#6734](https://github.com/earendil-works/pi-mono/pull/6734) by [@Jaaneek](https://github.com/Jaaneek)).
+
+## [0.80.8] - 2026-07-16
+
+### New Features
+
+- **Unified model runtime and provider authentication** — `ModelRuntime` centralizes model configuration, provider-owned `/login`, and dynamic provider catalogs. See [Providers](docs/providers.md).
+- **Live model catalog refresh** — `/model` refreshes configured providers in the background, and `pi update --models` forces an immediate refresh. See [Install and Manage](docs/packages.md#install-and-manage).
+- **xAI device-code OAuth and Grok 4.5 Responses support** — Sign in to xAI with a device code and use Grok 4.5 with low, medium, or high thinking. See [xAI](docs/providers.md#xai-grokx-subscription).
+
+### Breaking Changes
+
+- Replaced the SDK's `CreateAgentSessionOptions.authStorage` and `modelRegistry` options with the async `modelRuntime` option. `AuthStorage` and its storage backends are no longer exported; use `ModelRuntime` (or a custom pi-ai `CredentialStore`), or `readStoredCredential()` for one-off reads of auth.json.
+- Removed redundant `ModelRuntime.getAll()`, `find()`, `getSnapshot()`, and `getAuthOptions()` projections. Use the pi-ai `Models` methods `getModels()`, `getModel()`, `getProviders()`, and `checkAuth()` directly.
+- Replaced SDK request-auth assembly through `ModelRegistry.getApiKeyAndHeaders()` with `ModelRuntime.getAuth()`. Passing a provider ID returns provider-scoped auth; passing a model also resolves built-in, `models.json`, and extension model headers.
+- Changed extension-facing `ModelRegistry.refresh()` from synchronous `void` to `Promise<void>` because `models.json` loading is asynchronous. Extensions must await it before making synchronous registry reads.
+- Moved canonical dynamic catalog refresh to async `ModelRuntime.refresh()`/pi-ai `Models.refresh()`. Legacy extension OAuth `modifyModels` remains supported as a synchronous compatibility projection after credential initialization.
+
+### Added
+
+- Added `ModelRuntime` as the canonical async SDK and internal model/auth facade while preserving the synchronous extension-facing `ModelRegistry` API. `ModelRuntime.create()` accepts any pi-ai `CredentialStore` through its `credentials` option.
+- Added provider-owned `/login` discovery directly from registered pi-ai providers, including ambient auth status and informational links.
+- Added file-backed dynamic catalogs in `models-store.json`, per-provider pi.dev catalog overlays, and Radius gateway support including offline migration from legacy credential-cached catalogs.
+- Added extension provider `refreshModels(context)` support for dynamic model discovery with optional provider-controlled persistence.
+- Added `pi update --models` to force an immediate model catalog refresh without updating pi or extensions.
+- Added inherited xAI device-code OAuth login and Grok 4.5 OpenAI Responses support, with low, medium, and high thinking levels ([#6651](https://github.com/earendil-works/pi-mono/pull/6651) by [@Jaaneek](https://github.com/Jaaneek)).
+
+### Changed
+
+- Changed `ModelRuntime` to compose built-in providers, immutable `models.json` configuration, and extension overlays through ad-hoc pi-ai provider methods.
+- Changed `ModelRuntime` to own final request assembly: `getAuth(model)` includes configured model headers, stream methods resolve auth once, and `before_provider_headers` runs as the Models-only header transform before provider dispatch.
+- Changed `/model` to render the current model snapshot immediately, refresh configured providers in the background, and update the open selector with partial results or timeout errors.
+
+### Fixed
+
+- Fixed configured-provider catalog refresh to parse pi.dev's model-ID keyed responses, throttle checks to once per four hours, send the versioned pi user agent, treat unimplemented routes as unavailable overlays, and show concise refresh status in `/model`.
+- Fixed adjacent assistant thinking blocks to render as one thinking section.
+- Fixed inherited OpenAI Codex session IDs longer than 64 characters to meet the API limit ([#6630](https://github.com/earendil-works/pi-mono/issues/6630)).
+- Fixed inherited terminal output to normalize tab characters consistently ([#6697](https://github.com/earendil-works/pi-mono/pull/6697) by [@xz-dev](https://github.com/xz-dev)).
+- Fixed the Windows terminal title after checking npm packages ([#6629](https://github.com/earendil-works/pi-mono/issues/6629)).
+- Fixed Bun standalone binaries to bundle OAuth adapters for interactive logins.
+
+## [0.80.7] - 2026-07-14
+
+### Breaking Changes
+
+- Removed the `openai-responses` `compat.sendSessionIdHeader` flag from `models.json`. Session-affinity behavior is now controlled by `compat.sessionAffinityFormat` (`"openai"`, `"openai-nosession"`, or `"openrouter"`). Replace `sendSessionIdHeader: false` with `sessionAffinityFormat: "openai-nosession"` ([#6496](https://github.com/earendil-works/pi-mono/pull/6496) by [@petrroll](https://github.com/petrroll)).
+
+### New Features
+
+- **Cache-friendly dynamic tool loading** - Extensions can add tools during execution while supported Anthropic and OpenAI Responses models preserve prompt-cache prefixes. See [Dynamic Tool Loading](docs/extensions.md#dynamic-tool-loading).
+- **Message copy shortcut** - `Ctrl+X` copies the last assistant message in the transcript or the selected message in `/tree`, making older and branched messages directly copyable. See [Display and Message Queue](docs/keybindings.md#display-and-message-queue).
+- **Fable 5 `xhigh` and `max` thinking** - Native `xhigh` and `max` thinking levels are available across generated provider catalogs. See [Model Options](docs/usage.md#model-options).
+
+### Added
+
+- Added cache-friendly dynamic tool loading for extension tools activated by tool results. Supported Anthropic and OpenAI Responses models load definitions where they become available, preserving the cached prompt prefix. See [Dynamic Tool Loading](docs/extensions.md#dynamic-tool-loading) ([#6474](https://github.com/earendil-works/pi-mono/pull/6474)).
+- Added inherited native `xhigh` and `max` thinking levels for Claude Fable 5 across all generated provider catalogs ([#6490](https://github.com/earendil-works/pi-mono/pull/6490) by [@davidbrai](https://github.com/davidbrai)).
+- Added `Ctrl+X` to copy the last assistant message, or the selected message in `/tree`.
+- Added inherited `toolChoice` support for OpenAI and Codex Responses, including required and named tool selection ([#6588](https://github.com/earendil-works/pi-mono/pull/6588) by [@xl0](https://github.com/xl0)).
+
+### Fixed
+
+- Fixed inherited OpenRouter model context windows to use the top provider's actual context length ([#6481](https://github.com/earendil-works/pi-mono/pull/6481) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited OpenRouter OpenAI-compatible session IDs to use the `x-session-id` header instead of OpenAI-specific session-affinity fields ([#6496](https://github.com/earendil-works/pi-mono/pull/6496) by [@petrroll](https://github.com/petrroll)).
+- Fixed `Ctrl+V` to paste clipboard text when the pasteboard does not contain an image.
+- Fixed `/login amazon-bedrock` to prompt for and save a Bedrock API key instead of only displaying ambient AWS credential setup instructions.
+- Fixed inherited Amazon Bedrock ambient AWS credentials to keep using SigV4 authentication, including for custom model IDs ([#6532](https://github.com/earendil-works/pi-mono/pull/6532) by [@ribelo](https://github.com/ribelo)).
+- Fixed inherited Cloudflare Workers AI and AI Gateway authentication to use ambient account and gateway IDs when stored credentials contain only an API key ([#6292](https://github.com/earendil-works/pi-mono/pull/6292) by [@markphelps](https://github.com/markphelps)).
+- Fixed inherited legacy terminal decoding for Alt+symbol key combinations such as `Alt+,` and `Alt+.` ([#6523](https://github.com/earendil-works/pi-mono/pull/6523) by [@ribelo](https://github.com/ribelo)).
+- Fixed the GitHub Copilot `mai-code-1-flash-picker` model to route through the `/responses` endpoint ([#6544](https://github.com/earendil-works/pi-mono/pull/6544) by [@petrroll](https://github.com/petrroll)).
+- Fixed branch summaries to work with providers that use ambient authentication instead of API keys ([#6595](https://github.com/earendil-works/pi-mono/pull/6595) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited Amazon Bedrock errors to report unhandled provider stop reasons instead of only `An unknown error occurred` ([#6598](https://github.com/earendil-works/pi-mono/pull/6598) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed npm package removal when installed packages have conflicting peer dependencies ([#6604](https://github.com/earendil-works/pi-mono/pull/6604) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited Azure OpenAI Responses reasoning replay when `encrypted_content` appears only in the terminal response event ([#6608](https://github.com/earendil-works/pi-mono/pull/6608) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited Anthropic-compatible proxies that omit `usage` from `message_delta` events ([#6611](https://github.com/earendil-works/pi-mono/pull/6611) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited OpenCode OpenAI Responses models to omit the unsupported `session-id` header while preserving other cache-affinity data ([#6645](https://github.com/earendil-works/pi-mono/pull/6645) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed system prompt cache invalidation across dates by removing the current date from the default prompt ([#6621](https://github.com/earendil-works/pi/issues/6621)).
+
+## [0.80.6] - 2026-07-09
+
+### New Features
+
+- **`max` thinking level** - New opt-in thinking level above `xhigh`, natively supported on GPT-5.6 and adaptive Claude models, available across CLI (`--thinking max`), SDK, RPC, and model selection. Custom themes can define `thinkingMax`. See [CLI Reference](docs/usage.md#cli-reference).
+- **Input-based pricing tiers** - Request-wide input-token pricing tiers for accurate long-context cost accounting (e.g. GPT-5.4/5.5/5.6 long-context rates), also configurable for custom models in `models.json` and `modelOverrides`. See [Model Configuration](docs/models.md#model-configuration).
+
+### Added
+
+- Added the opt-in `max` thinking level across CLI, SDK, RPC, model selection, and themes. Custom themes can define `thinkingMax`; existing themes fall back to `thinkingXhigh`.
+- Added request-wide input-token pricing tiers to custom model costs in `models.json`, `modelOverrides`, and extension-registered providers.
+- Added `~` (home directory) expansion for the `shellPath` setting ([#6470](https://github.com/earendil-works/pi/pull/6470) by [@aaronkyriesenbach](https://github.com/aaronkyriesenbach)).
+
+### Fixed
+
+- Fixed inherited post-compaction output-token budgeting to ignore stale assistant usage from before the compaction boundary ([#6464](https://github.com/earendil-works/pi/issues/6464)).
+- Fixed inherited GPT-5.4 and GPT-5.5 long-context cost accounting while retaining the intentional 272K default context limit for models that require an explicit override.
+- Fixed inherited GPT-5.6 metadata to keep direct OpenAI requests in the 272K short-context tier while exposing the Codex backend's 372K context window with long-context pricing, and removed the nonexistent bare `gpt-5.6` alias.
+- Fixed inherited Anthropic message conversion to preserve thinking blocks with empty thinking text but a valid signature instead of dropping them, avoiding thinking-block errors on newer Claude models ([#6457](https://github.com/earendil-works/pi/pull/6457) by [@davidbrai](https://github.com/davidbrai)).
+
+## [0.80.5] - 2026-07-09
+
+## [0.80.4] - 2026-07-09
+
+### New Features
+
+- **Prompt cache miss visibility** - Significant cache misses can be shown in transcripts via `showCacheMissNotices`. See [Model & Thinking](docs/settings.md#model--thinking).
+- **Project-local resource configuration** - `pi config -l` and Tab switching manage global vs project-local package resources. See [Enable and Disable Resources](docs/packages.md#enable-and-disable-resources).
+- **Extension lifecycle and provider hooks** - Extensions get `agent_settled`, `before_provider_headers`, entry renderers, and `InlineExtension`. See [agent_start / agent_end / agent_settled](docs/extensions.md#agent_start--agent_end--agent_settled), [before_provider_headers](docs/extensions.md#before_provider_headers), and [InlineExtension](docs/sdk.md#inlineextension).
+- **New inherited model and transport support** - GPT-5.6 metadata, Copilot Claude Sonnet 5, and zstd Codex SSE transport are available through inherited provider support. See [Providers](docs/providers.md) and [Model Options](docs/usage.md#model-options).
+
+### Added
+
+- Added inherited OpenAI GPT-5.6 model metadata for `gpt-5.6`, `gpt-5.6-sol`, `gpt-5.6-terra`, and `gpt-5.6-luna`, plus verified `openai-codex` support for `gpt-5.6-sol`, `gpt-5.6-terra`, and `gpt-5.6-luna`.
+- Added inherited Claude Sonnet 5 to the GitHub Copilot model catalog ([#6200](https://github.com/earendil-works/pi/issues/6200)).
+- Added inherited zstd request-body compression for the OpenAI Codex Responses SSE transport.
+- Added `/login <provider>` support with provider autocomplete.
+- Added public SDK exports for CLI-equivalent model and scoped-model resolution ([#6201](https://github.com/earendil-works/pi/issues/6201)).
+- Added extension and RPC `agent_settled` events plus session-level idle waiting for fully settled agent runs ([#6363](https://github.com/earendil-works/pi/issues/6363)).
+- Added `before_provider_headers` extension hook support for injecting provider request headers ([#6350](https://github.com/earendil-works/pi/pull/6350) by [@pmateusz](https://github.com/pmateusz)).
+- Added an `InlineExtension` type for named inline extension factories ([#6267](https://github.com/earendil-works/pi/pull/6267) by [@any-victor](https://github.com/any-victor)).
+- Added extension entry renderers for persisted display-only session entries that are rendered in interactive mode without being sent to the model context.
+- Added project-local resource override management to `pi config`, including project mode startup with `pi config -l` and Tab switching between global and project scopes ([#6309](https://github.com/earendil-works/pi/pull/6309)).
+- Added inherited `InMemorySessionStorage` and `JsonlSessionStorage` exports from the agent harness ([#6435](https://github.com/earendil-works/pi/issues/6435)).
+- Added inherited custom metadata support in JSONL session headers ([#6417](https://github.com/earendil-works/pi/pull/6417) by [@ArcadiaLin](https://github.com/ArcadiaLin)).
+- Added a `showCacheMissNotices` setting and `/settings` toggle for significant prompt-cache miss transcript notices.
+
+### Fixed
+
+- Fixed inherited retry classification for gRPC `ResourceExhausted` provider errors such as NVIDIA NIM transient exhaustion responses ([#6449](https://github.com/earendil-works/pi/pull/6449) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited retry classification for Cloudflare 524 timeout responses ([#6239](https://github.com/earendil-works/pi/issues/6239)).
+- Fixed inherited GitHub Copilot device-code login polling to wait before the first token poll and to honor server-provided `slow_down` intervals, avoiding incorrect failures or apparent hangs after browser authorization ([#6187](https://github.com/earendil-works/pi/issues/6187)).
+- Fixed inherited OpenAI Codex WebSocket sessions to rotate cached connections before the backend's 60-minute limit, avoiding connection-limit failures on long sessions ([#6268](https://github.com/earendil-works/pi/issues/6268)).
+- Fixed inherited DS4 server context overflow detection for `Prompt has ... tokens, but the configured context size is ... tokens` errors ([#6262](https://github.com/earendil-works/pi/issues/6262)).
+- Fixed inherited Fireworks GLM 5.2 Fast to use the OpenAI-compatible endpoint and `thinkingLevelMap`, aligning it with GLM 5.2 ([#6195](https://github.com/earendil-works/pi/issues/6195)).
+- Fixed the fork menu to ignore duplicate selection of the same entry ([#6430](https://github.com/earendil-works/pi/pull/6430) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed native clipboard support in Bun standalone releases ([#6418](https://github.com/earendil-works/pi/pull/6418) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed inherited GitHub Copilot extended context window models to use `contextWindow: 1000000`, preventing premature compaction and under-budgeting ([#6439](https://github.com/earendil-works/pi/issues/6439)).
+- Fixed inherited editor paste marker accounting when paste markers are deleted or terminal state is cleared ([#6397](https://github.com/earendil-works/pi/pull/6397) by [@affanali2k3](https://github.com/affanali2k3)).
+- Fixed `null` message content from imported transcripts or custom clients to normalize at ingestion boundaries instead of failing during context construction ([#6343](https://github.com/earendil-works/pi/pull/6343)).
+- Fixed inherited tool calls from length-truncated assistant messages to fail instead of waiting for missing tool results ([#6285](https://github.com/earendil-works/pi/pull/6285)).
+- Fixed inherited OpenAI Completions and Responses providers to send `(no tool output)` instead of `(see attached image)` when a tool result has empty text and no image content.
+- Fixed inherited OpenAI Responses and Azure OpenAI Responses requests to avoid sending `max_output_tokens` values below the provider minimum ([#6265](https://github.com/earendil-works/pi/issues/6265)).
+- Fixed inherited Amazon Bedrock prompt-cache points for Claude Fable 5 and Claude Sonnet 5 ([#6235](https://github.com/earendil-works/pi/issues/6235)).
+- Fixed inherited Amazon Bedrock Claude 5 prompt-cache pricing metadata by removing stale fallback overrides.
+- Fixed inherited OpenAI Codex user-agent construction to synchronously load Node OS metadata, avoiding a startup race that could report `pi (browser)` in Node/Bun.
+- Fixed `pi update` for pnpm installations to suggest pruning pnpm's self-update cache when the executable points at a removed cached version ([#6279](https://github.com/earendil-works/pi/pull/6279) by [@rajp152k](https://github.com/rajp152k)).
+- Fixed Xiaomi Token Plan model metadata to follow the upstream models.dev token-plan catalogs, removing unsupported `mimo-v2-omni` variants ([#6204](https://github.com/earendil-works/pi/issues/6204)).
+- Fixed startup model selection to skip unauthenticated saved defaults so configured local custom models can be selected instead ([#6231](https://github.com/earendil-works/pi/issues/6231)).
+- Fixed the question extension example to run question tool calls sequentially so multiple questions in one assistant turn remain answerable ([#6189](https://github.com/earendil-works/pi/issues/6189)).
+- Fixed `/login` to report auth storage persistence failures instead of claiming credentials were saved when `auth.json` is locked ([#6223](https://github.com/earendil-works/pi/issues/6223)).
+- Fixed split-turn compaction to serialize summary requests so single-concurrency local providers do not fail with 429 errors ([#5536](https://github.com/earendil-works/pi/issues/5536)).
+- Fixed compaction retained-token budgeting to count context-visible custom messages ([#6326](https://github.com/earendil-works/pi/issues/6326)).
+- Fixed custom session entries appended during assistant streaming to render before the live assistant message, matching persisted session order.
+- Fixed non-positive or oversized bash tool timeouts to fail with a clear validation error instead of being clamped to an immediate timeout ([#6181](https://github.com/earendil-works/pi/issues/6181)).
+- Fixed the edit tool schema to allow model-invented extra replacement fields instead of rejecting otherwise valid edits ([#6278](https://github.com/earendil-works/pi/issues/6278)).
+- Fixed new session resets to clear cached label timestamps ([#6354](https://github.com/earendil-works/pi/issues/6354)).
+- Fixed auto-retry for Bun fetch socket-drop errors reported as `socket connection was closed`, so transient provider disconnects do not end headless runs without retrying ([#6431](https://github.com/earendil-works/pi/issues/6431)).
+- Fixed `models.json` `modelOverrides` to apply to extension-registered provider models ([#6367](https://github.com/earendil-works/pi/issues/6367)).
+- Fixed project context file discovery to use stable parent traversal on Windows so startup no longer hangs while loading AGENTS.md or CLAUDE.md ([#6369](https://github.com/earendil-works/pi/issues/6369)).
+- Fixed `--session-id` startup to warn when no existing project session has that id and pi creates a new session ([#6407](https://github.com/earendil-works/pi/issues/6407)).
+- Fixed `/reload` help text and docs to consistently mention themes and context files ([#6395](https://github.com/earendil-works/pi/issues/6395)).
+
+### Removed
+
+- Removed default attribution headers from Vercel AI Gateway requests.
+
+## [0.80.3] - 2026-06-30
+
+### New Features
+
+- **Anthropic Claude Sonnet 5 support** - Claude Sonnet 5 is available through inherited Anthropic-compatible and Bedrock provider catalogs with adaptive thinking enabled. See [Providers](docs/providers.md) and [Model Options](docs/usage.md#model-options).
+- **Configurable output spacing** - `outputPad` controls horizontal padding for user messages, assistant messages, and thinking blocks. See [Settings](docs/settings.md#ui--display).
+- **External editor configuration** - `externalEditor` lets Ctrl+G use a configured editor before `$VISUAL`/`$EDITOR` fallbacks. See [Settings](docs/settings.md#ui--display) and [Keybindings](docs/keybindings.md).
+- **Richer RPC session tree access** - RPC clients can inspect session entries and tree snapshots with `get_entries` and `get_tree`. See [get_entries](docs/rpc.md#get_entries) and [get_tree](docs/rpc.md#get_tree).
+- **Extension session metadata updates** - Extensions can observe session name changes through `session_info_changed`. See [session_info_changed](docs/extensions.md#session_info_changed).
+- **Modern Azure Foundry endpoint support** - Azure OpenAI Responses provider setup supports current Microsoft Foundry endpoint URLs. See [Azure OpenAI](docs/providers.md#azure-openai).
+
+### Added
+
+- Added inherited Anthropic Claude Sonnet 5 model support.
+- Added `get_entries` and `get_tree` RPC commands for reading session entries and tree snapshots over RPC ([#6078](https://github.com/earendil-works/pi/pull/6078) by [@geraschenko](https://github.com/geraschenko)).
+- Added a package `./rpc-entry` export for launching Pi directly in RPC mode.
+- Added session-name change events for extensions ([#6175](https://github.com/earendil-works/pi/pull/6175) by [@xl0](https://github.com/xl0)).
+- Added inherited Azure OpenAI Responses support for modern Microsoft Foundry endpoint URLs ([#6004](https://github.com/earendil-works/pi/pull/6004) by [@gukoff](https://github.com/gukoff)).
+- Added inherited `Usage.reasoning` token counts for providers that report reasoning/thinking token usage ([#6057](https://github.com/earendil-works/pi/issues/6057)).
+- Added an `externalEditor` settings.json override for Ctrl+G external editor commands, with default fallbacks to Notepad on Windows and `nano` elsewhere ([#6122](https://github.com/earendil-works/pi/issues/6122)).
+- Added an `outputPad` setting for user message, assistant message, and thinking horizontal padding ([#6168](https://github.com/earendil-works/pi/issues/6168)).
+
+### Changed
+
+- Changed the default OpenAI model to `gpt-5.5`.
+- Changed inherited OpenAI Codex Responses SSE response-header waits to use the configured HTTP timeout instead of the previous fixed 20 second timeout, reducing false timeouts on slow connections ([#4945](https://github.com/earendil-works/pi/issues/4945)).
+
+### Fixed
+
+- Fixed inherited Claude Sonnet 5 metadata to use adaptive thinking payloads for Anthropic-compatible and Bedrock requests.
+- Fixed inherited generated Xiaomi MiMo model pricing to match current pay-as-you-go pricing from models.dev ([#6138](https://github.com/earendil-works/pi/issues/6138)).
+- Fixed inherited provider HTTP errors to include response bodies instead of opaque SDK messages ([#5832](https://github.com/earendil-works/pi/pull/5832) by [@stephanmck](https://github.com/stephanmck)).
+- Fixed inherited `streamSimple()` max-token caps so providers that count input and output against one context window do not reject long requests ([#5595](https://github.com/earendil-works/pi/issues/5595)).
+- Fixed inherited OpenAI Responses streams to preserve reasoning replay state when output items finish out of order ([#6009](https://github.com/earendil-works/pi/issues/6009)).
+- Fixed inherited Z.AI preserved thinking requests to send `thinking.clear_thinking: false` when thinking is enabled, allowing replayed `reasoning_content` to participate in provider caching ([#6083](https://github.com/earendil-works/pi/issues/6083)).
+- Fixed pre-prompt compaction to stop after compaction instead of continuing immediately ([#6074](https://github.com/earendil-works/pi/pull/6074) by [@yzhg1983](https://github.com/yzhg1983)).
+- Fixed resource notifications to stay before messages when resuming sessions ([#6048](https://github.com/earendil-works/pi/pull/6048) by [@haoqixu](https://github.com/haoqixu)).
+- Fixed startup benchmark timing output to print after TUI shutdown, preserve extension timings, and drain terminal-query replies before stopping benchmark mode ([#6030](https://github.com/earendil-works/pi/pull/6030) by [@xl0](https://github.com/xl0), [#6063](https://github.com/earendil-works/pi/pull/6063) by [@xl0](https://github.com/xl0)).
+- Fixed extension tool changes to apply before the next provider request in the same agent run without dropping `before_agent_start` system-prompt overrides ([#6162](https://github.com/earendil-works/pi/issues/6162)).
+- Fixed a crash when undici emits an internal client error while terminating a mid-stream HTTP response ([#6133](https://github.com/earendil-works/pi/issues/6133)).
+- Fixed the compaction event regression test to cover status indicator cleanup and keep CI passing.
+- Fixed interactive status indicators so ending work, retry, compaction, or branch-summary indicators no longer shrink the TUI when clear-on-shrink is enabled ([#6026](https://github.com/earendil-works/pi/pull/6026)).
+- Fixed `--session` and `SessionManager.open()` to reject non-empty invalid session files without overwriting them ([#6002](https://github.com/earendil-works/pi/issues/6002)).
+- Fixed user-message transcript rendering to keep visible backslashes in Markdown escape sequences such as `\"` ([#6105](https://github.com/earendil-works/pi/issues/6105)).
+- Fixed assistant messages stopped by output length to show a visible incomplete-response error ([#4290](https://github.com/earendil-works/pi/issues/4290)).
+- Fixed `--no-session --session-id` so ephemeral CLI runs can use deterministic session IDs for provider cache affinity ([#6070](https://github.com/earendil-works/pi/issues/6070)).
+- Fixed disk BMP image files to be detected, converted to PNG, and attached through `read` and CLI `@file` inputs ([#6047](https://github.com/earendil-works/pi/issues/6047)).
+- Fixed auto-retry for provider stream errors that explicitly tell callers to retry the request ([#6019](https://github.com/earendil-works/pi/issues/6019)).
+
+## [0.80.2] - 2026-06-23
+
+### Changed
+
+- Changed inherited pi-ai `ApiKeyCredential` to use the `auth.json`-compatible discriminator `type: "api_key"` and provider-scoped `env` values instead of `type: "api-key"` and metadata.
+- Renamed the inherited agent-core public harness shell execution options type from `ExecutionEnvExecOptions` to `ShellExecOptions`.
+
+### Fixed
+
+- Fixed inherited Anthropic-compatible custom models to use explicit compatibility metadata instead of provider-name heuristics for session-affinity headers and unsupported tool-field omissions.
+- Fixed inherited request-scoped `apiKey` and `env` values to participate in provider auth resolution, so providers such as Cloudflare can derive request-specific base URLs from explicit call options ([#6021](https://github.com/earendil-works/pi/issues/6021)).
+- Restored inherited temporary legacy per-API stream aliases such as `streamSimpleOpenAICompletions` on the pi-ai compat entrypoint ([#6016](https://github.com/earendil-works/pi/issues/6016), [#6017](https://github.com/earendil-works/pi/issues/6017)).
+- Restored inherited runtime `detectCompat` fallback in `openai-completions` for models without explicit compat metadata ([#6020](https://github.com/earendil-works/pi/issues/6020)).
+
+## [0.80.1] - 2026-06-23
+
+### Fixed
+
+- Fixed inherited Amazon Bedrock scoped `AWS_PROFILE` endpoint resolution for built-in inference profile endpoints.
+- Fixed inherited Fireworks Anthropic-compatible requests to apply session-affinity and unsupported tool-field defaults for custom Fireworks models.
+- Fixed inherited Together MiniMax M2.7 metadata to avoid unsupported Together reasoning toggles.
+
+## [0.80.0] - 2026-06-23
+
+### Changed
+
+- Added `Ctrl+J` as a default newline keybinding alongside `Shift+Enter`.
+- Renamed the displayed `zai` provider label to ZAI Coding Plan (Global) for clarity ([#5965](https://github.com/earendil-works/pi/issues/5965)).
+- pi-ai's old global API (`stream`/`complete`/`completeSimple`, `getModel`/`getModels`/`getProviders`, `registerApiProvider`, `getEnvApiKey`, ...) moved off the `@sammorrowdrums/mcpi-ai` root entrypoint to `@sammorrowdrums/mcpi-ai/compat`. Extensions are not affected at runtime: the extension loader resolves the pi-ai root to the compat entrypoint (a strict superset), so existing extensions keep working unchanged. Extension sources that typecheck against pi-ai's published types should switch those imports to `@sammorrowdrums/mcpi-ai/compat` (or migrate to the new `createModels()`/provider-factory API). The compat entrypoint and the loader alias will be removed in a future release with a migration guide.
+
+### Fixed
+
+- Fixed session names to normalize newline characters before storing or displaying labels ([#5999](https://github.com/earendil-works/pi/pull/5999) by [@haoqixu](https://github.com/haoqixu)).
+- Fixed the session selector to order threaded session trees by the latest activity anywhere in each subtree ([#5784](https://github.com/earendil-works/pi/pull/5784) by [@Perlence](https://github.com/Perlence)).
+- Fixed extension-related crash and startup-failure reporting to suggest restarting with `pi -ne`.
+- Fixed inherited OpenAI Responses streams to fail before missing terminal events and fixed context usage and compaction estimates to ignore malformed all-zero assistant usage after truncated responses ([#5526](https://github.com/earendil-works/pi/pull/5526) by [@dmmulroy](https://github.com/dmmulroy)).
+- Fixed inherited OpenAI Codex Responses WebSocket sessions to reconnect once when OpenAI's connection limit is reached before output starts ([#5973](https://github.com/earendil-works/pi/issues/5973)).
+- Fixed inherited Amazon Bedrock endpoint resolution to honor scoped `AWS_PROFILE` values.
+- Fixed inherited Cloudflare providers to require account/gateway configuration and route built-in compat calls through provider auth.
+- Fixed provider-scoped auth environment values to reach inherited `Models`/`ImagesModels` API calls and compat API-key injection.
+- Fixed inherited OpenCode Go GLM-5.2 metadata to expose `xhigh` reasoning and send the provider's max reasoning effort ([#5967](https://github.com/earendil-works/pi/issues/5967)).
+- Fixed `pi --resume` to load user package themes and resolve automatic light/dark theme settings.
+- Fixed `models.json` custom providers so stored credentials can satisfy auth without a redundant provider-level `apiKey` ([#5953](https://github.com/earendil-works/pi/issues/5953)).
+
+### Removed
+
+- Removed inherited selective-provider `@sammorrowdrums/mcpi-ai/base` and `@sammorrowdrums/mcpi-agent-core/base` entrypoints; use the root packages with explicit `Models` provider factories instead.
+
+## [0.79.10] - 2026-06-22
+
+### New Features
+
+- **Extension compaction event context** - Extension `session_before_compact` and `session_compact` events now include `reason` and `willRetry`, so extensions can distinguish manual `/compact`, threshold auto-compaction, and overflow retry flows. See [session_before_compact / session_compact](docs/extensions.md#session_before_compact--session_compact) and [Custom Summarization via Extensions](docs/compaction.md#custom-summarization-via-extensions).
+- **Safer update flow** - `pi update` installs the exact checked Pi version, and update notices show the changelog URL, making upgrades more predictable. See [Install and Manage](docs/packages.md#install-and-manage).
+
+### Added
+
+- Added `reason` and `willRetry` metadata to extension `session_before_compact` and `session_compact` events so extensions can distinguish manual, threshold, and overflow compaction flows ([#5962](https://github.com/earendil-works/pi/pull/5962) by [@PizzaMarinara](https://github.com/PizzaMarinara)).
+
+### Fixed
+
+- Fixed the `find` tool to respect nested git repository boundaries when parent `.gitignore` rules ignore the nested repo ([#5960](https://github.com/earendil-works/pi/issues/5960)).
+- Fixed the usage docs slash command table to include `/trust` and `/import` ([#5959](https://github.com/earendil-works/pi/issues/5959)).
+- Fixed inherited OpenAI-compatible streaming to preserve encrypted `reasoning_details` that arrive before matching tool call deltas ([#5114](https://github.com/earendil-works/pi/issues/5114)).
+- Fixed broken TUI documentation links to the plan-mode extension example ([#5957](https://github.com/earendil-works/pi/issues/5957)).
+- Fixed transient extension UI and session-start messages emitted during session replacement or reload so they remain visible, and kept reload input blocked until reload completes ([#5943](https://github.com/earendil-works/pi/issues/5943)).
+- Fixed the plan-mode example to preserve active custom tools, skip the action prompt when no plan is found, and queue refinement/execution follow-ups correctly from `agent_end` ([#5940](https://github.com/earendil-works/pi/issues/5940)).
+- Fixed `pi update` to install the exact version returned by the Pi update check, make `--force` reinstall that checked version, fail instead of falling back to an unversioned reinstall when no version is available, and report both the old and updated versions.
+- Fixed update notifications to display the actual changelog URL as the hyperlink text.
+
+## [0.79.9] - 2026-06-20
+
+### New Features
+
+- **Chat-template thinking compatibility** - OpenAI-compatible custom providers can map Pi thinking levels into `chat_template_kwargs`, enabling vLLM/Hugging Face chat-template models such as DeepSeek to use provider-native thinking controls. See [Custom Provider API Types](docs/custom-provider.md#api-types) and [OpenAI Compatibility](docs/models.md#openai-compatibility).
+- **GLM-5.2 provider improvements** - GLM-5.2 now has corrected Fireworks OpenAI-compatible routing and OpenRouter `xhigh` thinking support, improving `/model` behavior and high-effort reasoning for GLM-5.2 users. See [Model Options](docs/usage.md#model-options).
+
+### Added
+
+- Added inherited configurable `chat-template` thinking support for OpenAI-compatible providers that use `chat_template_kwargs`, such as DeepSeek models behind vLLM ([#5673](https://github.com/earendil-works/pi/issues/5673)).
+
+### Fixed
+
+- Fixed inherited Fireworks GLM-5.2 metadata to use the OpenAI-compatible Chat Completions endpoint with `reasoning_effort` support ([#5923](https://github.com/earendil-works/pi/issues/5923)).
+- Fixed same-directory session switches to reuse imported extension modules while preserving fresh extension instances and lifecycle events ([#5905](https://github.com/earendil-works/pi/issues/5905)).
+- Fixed deep session branches taking quadratic time to build context or branch paths ([#5909](https://github.com/earendil-works/pi/issues/5909)).
+- Fixed inherited OpenRouter GLM-5.2 metadata to expose `xhigh` reasoning and send OpenRouter's native `xhigh` effort ([#5770](https://github.com/earendil-works/pi/issues/5770)).
+- Fixed inherited Markdown streaming code fence rendering so partial closing fences no longer make code blocks shrink or flicker while content streams ([#5846](https://github.com/earendil-works/pi/pull/5846) by [@xl0](https://github.com/xl0)).
+- Fixed fuzzy `edit` matches to preserve untouched line blocks instead of rewriting the whole file through normalized content ([#5899](https://github.com/earendil-works/pi/issues/5899)).
+- Fixed bash commands through legacy WSL `bash.exe` to pass scripts over stdin so shell variables expand in the target bash ([#5893](https://github.com/earendil-works/pi/issues/5893)).
+- Fixed `/model` to hide GitHub Copilot models that are unavailable to the authenticated account ([#5897](https://github.com/earendil-works/pi/issues/5897)).
+- Fixed `/model` selector search to rank exact provider-prefixed matches before proxy-provider model ID matches ([#5892](https://github.com/earendil-works/pi/issues/5892)).
+
+## [0.79.8] - 2026-06-19
+
+### New Features
+
+- **Selective provider base entry points** - SDK users can pair `@sammorrowdrums/mcpi-ai/base` and `@sammorrowdrums/mcpi-agent-core/base` with explicit provider registration to keep bundled applications from including unused provider transports. See [`pi-ai` Base Entry Point](../ai/README.md#base-entry-point) and [`pi-agent-core` Base Entry Point](../agent/README.md#base-entry-point).
+- **Mistral prompt caching** - Mistral sessions now use provider-side prompt caching with session affinity and cached-token usage/cost accounting. See [API Keys](docs/providers.md#api-keys) and [Environment Variables](docs/usage.md#environment-variables).
+- **Post-compaction token estimates** - Compact results and compaction events now include estimated post-compaction token counts so clients can show the approximate context reduction. See [RPC compact](docs/rpc.md#compact) and [compaction events](docs/rpc.md#compaction_start--compaction_end).
+- **OpenRouter Fusion alias** - `openrouter/fusion` is available as a built-in OpenRouter model alias. See [API Keys](docs/providers.md#api-keys).
+
+### Added
+
+- Added inherited `@sammorrowdrums/mcpi-ai/base` and `@sammorrowdrums/mcpi-agent-core/base` entry points for selective provider registration in bundled applications ([#5348](https://github.com/earendil-works/pi/pull/5348) by [@FredKSchott](https://github.com/FredKSchott)).
+- Added inherited Mistral prompt caching using the pi session ID as `prompt_cache_key`, including cached-token usage and cost accounting ([#5854](https://github.com/earendil-works/pi/issues/5854)).
+- Added estimated post-compaction token counts to compact results and compaction events ([#5877](https://github.com/earendil-works/pi/issues/5877)).
+- Added the inherited OpenRouter Fusion alias as `openrouter/fusion` ([#5866](https://github.com/earendil-works/pi/pull/5866) by [@dannote](https://github.com/dannote)).
+
+### Fixed
+
+- Updated vulnerable runtime dependencies, including `undici` and the packaged `protobufjs` transitive dependency.
+- Fixed compaction to refuse sessions with no eligible messages instead of producing empty summaries ([#4811](https://github.com/earendil-works/pi/issues/4811)).
+- Fixed successful overflow-triggered auto-compaction to avoid retrying completed assistant responses ([#5720](https://github.com/earendil-works/pi/issues/5720)).
+
+## [0.79.7] - 2026-06-18
+
+### New Features
+
+- **Automatic theme mode** - `/settings` can choose separate light and dark themes and follow terminal color-scheme changes. See [Selecting a Theme](docs/themes.md#selecting-a-theme).
+- **Self-only updates by default** - `pi update` now updates pi only, with `pi update --all` for updating pi and packages together. See [Install and Manage](docs/packages.md#install-and-manage).
+- **Extension API helpers** - extensions can use `CONFIG_DIR_NAME` for project config paths and import edit diff helpers for edit-style diffs. See [`ctx.cwd`](docs/extensions.md#ctxcwd) and [SDK Exports](docs/sdk.md#exports).
+- **Warp inline images** - Warp terminals now get inline image rendering through Kitty graphics detection. See [Image](docs/tui.md#image).
+
+### Added
+
+- Added automatic theme mode so `/settings` can use separate light and dark themes and follow terminal color-scheme changes ([#5874](https://github.com/earendil-works/pi/pull/5874)).
+- Added inherited Warp terminal image capability detection so inline images render through Warp's Kitty graphics support ([#5841](https://github.com/earendil-works/pi/pull/5841) by [@dodiego](https://github.com/dodiego)).
+- Exported `CONFIG_DIR_NAME` from the coding-agent public API so extensions can resolve project config paths without hardcoding `.pi` ([#5869](https://github.com/earendil-works/pi/pull/5869) by [@xl0](https://github.com/xl0)).
+- Exported edit diff helpers (`generateDiffString`, `generateUnifiedPatch`, and `EditDiffResult`) from the public API for extensions that need edit-style diffs ([#5756](https://github.com/earendil-works/pi/pull/5756) by [@xl0](https://github.com/xl0)).
+
+### Changed
+
+- Changed bare `pi update` to update only pi, added `pi update --all` for updating pi and extensions together, and clarified extension update prompts.
+- Reserved `/` in theme names for automatic light/dark theme settings.
+- Updated extension docs, examples, runtime help, trust prompts, and config labels to use the configured project config directory instead of hardcoded `.pi` paths.
+
+### Fixed
+
+- Fixed RPC unknown-command errors to include the request id so clients do not hang waiting for a response ([#5868](https://github.com/earendil-works/pi/issues/5868)).
+- Fixed `/model` autocomplete and model selection searches to match provider/model queries regardless of whether the provider or model token is typed first.
+- Fixed the tree navigator to horizontally pan deep entries so the selected item remains readable ([#5830](https://github.com/earendil-works/pi/issues/5830)).
+
+## [0.79.6] - 2026-06-16
+
+### Fixed
+
+- Fixed HTTP dispatcher configuration to preserve a caller's deliberate `fetch` override instead of reinstalling the undici global fetch over it.
+- Fixed inherited OpenCode Go DeepSeek V4 thinking-off requests to send the provider's `thinking: { type: "disabled" }` compatibility parameter.
+
+## [0.79.5] - 2026-06-16
+
+### New Features
+
+- **Provider-scoped API key environments** - `auth.json` API key entries can now include `env` overrides for provider-specific Cloudflare, Azure OpenAI, Google Vertex, Amazon Bedrock, cache retention, and proxy settings without changing the project shell. See [Auth File](docs/providers.md#auth-file).
+- **Global HTTP proxy setting** - Configure `httpProxy` once in global settings to apply `HTTP_PROXY` and `HTTPS_PROXY` to Pi-managed HTTP clients. See [Network](docs/settings.md#network).
+- **Vercel AI Gateway attribution** - Vercel AI Gateway requests now include Pi attribution headers by default. See [API Keys](docs/providers.md#api-keys).
+
+### Added
+
+- Added Vercel AI Gateway request attribution headers (`http-referer` and `x-title`) for Vercel AI Gateway models ([#5798](https://github.com/earendil-works/pi/pull/5798) by [@rwachtler](https://github.com/rwachtler)).
+- Added an `xp` footer marker when experimental features are enabled.
+- Added a global `httpProxy` setting that applies as `HTTP_PROXY` and `HTTPS_PROXY` for Pi-managed HTTP clients ([#5790](https://github.com/earendil-works/pi/issues/5790)).
+- Added `auth.json` API key `env` values so provider-specific environment overrides can be scoped to Pi and propagated to inherited provider configuration ([#5728](https://github.com/earendil-works/pi/issues/5728)).
+
+### Changed
+
+- Updated the vendored Markdown parser used by HTML session exports to `marked` 18.0.5.
+
+### Fixed
+
+- Fixed inherited OpenAI Responses streaming to tolerate null message content from OpenAI-compatible servers before tool calls ([#5819](https://github.com/earendil-works/pi/issues/5819)).
+- Fixed inherited OpenCode DeepSeek V4 thinking requests to avoid sending both `thinking` and `reasoning_effort` ([#5818](https://github.com/earendil-works/pi/issues/5818)).
+- Fixed device-code login to stop opening the browser automatically.
+- Fixed inherited editor Cursor Up handling so non-empty drafts jump to the start of the line before browsing input history ([#5789](https://github.com/earendil-works/pi/pull/5789) by [@4h9fbZ](https://github.com/4h9fbZ)).
+- Fixed inherited Z.AI GLM-5.2 thinking requests to send `reasoning_effort` with the provider's `high`/`max` effort mapping ([#5770](https://github.com/earendil-works/pi/issues/5770)).
+- Fixed successful `pi update` on Windows to exit naturally instead of calling `process.exit(0)`, avoiding a Node.js/libuv assertion after version-check network requests ([#5805](https://github.com/earendil-works/pi/issues/5805)).
+- Fixed inherited Google and `google-vertex` Gemini model metadata to map `latest` aliases to the current models, add Gemini 3.5 Flash for Vertex, correct Gemini 2.5 Flash Vertex cache pricing, and remove shut-down Vertex preview models ([#5761](https://github.com/earendil-works/pi/issues/5761)).
+- Fixed the session selector to stay open and show the all-sessions empty state when both current-folder and all-scope session lists are empty ([#5747](https://github.com/earendil-works/pi/issues/5747)).
+- Fixed inherited Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).
+
+## [0.79.4] - 2026-06-15
+
+### New Features
+
+- **Automatic first-run theme selection** - pi detects the terminal background on first run and defaults to the `dark` or `light` theme. See [Selecting a Theme](docs/themes.md#selecting-a-theme).
+- **Standalone binary integrity checksums** - GitHub release assets now include `SHA256SUMS` files for verifying standalone binary downloads. See [Quickstart Install](docs/quickstart.md#install).
+
+### Added
+
+- Added `SHA256SUMS` integrity files to standalone binary GitHub release assets ([#5739](https://github.com/earendil-works/pi/issues/5739)).
+- Added first-run interactive theme detection from the terminal background ([#5385](https://github.com/earendil-works/pi/pull/5385) by [@vegarsti](https://github.com/vegarsti)).
+
+### Fixed
+
+- Fixed bash tool output collection to keep draining stdout/stderr after the child exits while descendants still write, avoiding truncated late output ([#5753](https://github.com/earendil-works/pi/pull/5753) by [@Mearman](https://github.com/Mearman)).
+- Fixed `/tree` help rendering to show compact wrapped controls instead of truncating them on narrow terminals ([#5055](https://github.com/earendil-works/pi/issues/5055)).
+- Fixed SIGTERM/SIGHUP interactive shutdown to keep signal handlers installed until terminal cleanup completes, preventing `signal-exit` from re-sending the signal and leaving the terminal in raw/Kitty keyboard mode ([#5724](https://github.com/earendil-works/pi/issues/5724)).
+- Fixed extensions documentation to clarify that `pi.getActiveTools()` returns active tool names while `pi.getAllTools()` returns tool metadata ([#5729](https://github.com/earendil-works/pi/issues/5729)).
+- Fixed question and questionnaire extension examples to wrap long prompt, option, and help text instead of truncating it ([#5708](https://github.com/earendil-works/pi/pull/5708) by [@xl0](https://github.com/xl0)).
+- Fixed package commands such as `pi list`, `pi install`, and `pi update` to terminate after completing even if an extension leaves background handles open ([#5687](https://github.com/earendil-works/pi/issues/5687)).
+- Fixed `pi update` for pnpm global installs whose configured `global-bin-dir` no longer matches the active pnpm home ([#5689](https://github.com/earendil-works/pi/issues/5689)).
+- Fixed npm package specs that use ranges or tags (for example `@^1.2.7`) so installed package resources still load instead of being treated as mismatched exact pins ([#5695](https://github.com/earendil-works/pi/issues/5695)).
+- Fixed inherited Anthropic 1-hour prompt-cache write cost accounting to price 1-hour cache writes at 2x input instead of the 5-minute cache-write rate ([#5738](https://github.com/earendil-works/pi/pull/5738) by [@theBucky](https://github.com/theBucky)).
+- Fixed inherited GitHub Copilot Claude adaptive-thinking effort metadata to match manually checked Copilot model capabilities ([#4637](https://github.com/earendil-works/pi/issues/4637)).
+- Fixed inherited OpenCode/OpenCode Go completion model metadata to omit long-retention cache fields for routes that reject `prompt_cache_retention` ([#5702](https://github.com/earendil-works/pi/issues/5702)).
+- Fixed inherited overlay compositing over CJK wide characters so borders stay aligned when an overlay starts inside a full-width cell ([#5297](https://github.com/earendil-works/pi/issues/5297)).
+- Fixed inherited WezTerm inline Kitty image rendering during full redraw fallbacks so image padding rows are reserved before the placement is drawn without regressing tall-image placement ([#5618](https://github.com/earendil-works/pi/issues/5618), [#4415](https://github.com/earendil-works/pi/issues/4415)).
+- Fixed custom provider config so plain uppercase API key and header values remain literals instead of being treated as legacy environment references; use explicit `$ENV_VAR` syntax for environment variables ([#5661](https://github.com/earendil-works/pi/issues/5661)).
+
+## [0.79.3] - 2026-06-13
+
+### Fixed
+
+- Fixed inherited OpenAI GPT-5.4/GPT-5.5 and OpenAI Codex GPT-5.4/GPT-5.4 mini/GPT-5.5 context window metadata to use the observed 272k-token Codex backend limit, avoiding a billing hazard from prompts above Codex's accepted limit (reported by [@trethore](https://github.com/trethore)).
+
+## [0.79.2] - 2026-06-12
+
+### New Features
+
+- **Clearer Bedrock validation guidance** - Amazon Bedrock data retention validation errors now link to AWS data retention documentation. See [Amazon Bedrock](docs/providers.md#amazon-bedrock).
+
+### Added
+
+- Added an experimental first-time setup flow behind `PI_EXPERIMENTAL=1` that asks for a dark/light theme choice (preselecting the detected appearance) and opt-in analytics data sharing on first launch with the default agent directory; opting in stores a `trackingId` in `settings.json` ([#5587](https://github.com/earendil-works/pi/pull/5587) by [@vegarsti](https://github.com/vegarsti)).
+- Added AWS data retention documentation links to inherited Amazon Bedrock unsupported data retention mode validation errors ([#5561](https://github.com/earendil-works/pi/pull/5561) by [@unexge](https://github.com/unexge)).
+
+### Fixed
+
+- Fixed project trust detection to ignore global `~/.pi/agent` state when running from `$HOME`, and made `pi update` use only saved or explicit project trust without prompting ([#5619](https://github.com/earendil-works/pi/issues/5619)).
+- Fixed experimental first-time setup to skip forked sessions instead of rerunning the setup prompts ([#5627](https://github.com/earendil-works/pi/pull/5627) by [@vegarsti](https://github.com/vegarsti)).
+- Fixed inherited OpenAI-compatible context overflow detection for parenthesized `maximum context length (N)` errors ([#5677](https://github.com/earendil-works/pi/issues/5677)).
+- Fixed inherited OpenAI GPT-5.4/GPT-5.5 and OpenAI Codex GPT-5.4/GPT-5.4 mini/GPT-5.5 context window metadata to match current OpenAI limits ([#5644](https://github.com/earendil-works/pi/issues/5644)).
+- Fixed inherited Anthropic refusal stops to preserve provider `stop_details` explanations in error messages ([#5666](https://github.com/earendil-works/pi/pull/5666) by [@rwachtler](https://github.com/rwachtler)).
+- Increased the inherited OpenAI Codex Responses SSE response-header timeout to 20 seconds to reduce false-positive stalls while retaining the bounded wait introduced for zero-event hangs ([#4945](https://github.com/earendil-works/pi/issues/4945)).
+- Fixed inherited Claude Fable 5 thinking-off requests to omit Anthropic's unsupported `thinking.type: "disabled"` payload ([#5567](https://github.com/earendil-works/pi/pull/5567) by [@tmustier](https://github.com/tmustier)).
+- Fixed inherited late tool progress callbacks after tool settlement to be ignored instead of emitting stale `tool_execution_update` events ([#5573](https://github.com/earendil-works/pi/issues/5573)).
+- Fixed inherited user-message transcript rendering so standalone `+` messages no longer render as `-` ([#5657](https://github.com/earendil-works/pi/issues/5657)).
+- Fixed inherited slash-separated fuzzy queries so provider/model completions remain matchable after insertion.
+- Fixed inherited WezTerm inline Kitty image rendering so reserved row clears do not erase all but the top strip of tool image previews ([#5618](https://github.com/earendil-works/pi/issues/5618)).
+- Fixed inherited editor wrapping for CJK text to break at character boundaries instead of leaving large trailing gaps ([#5585](https://github.com/earendil-works/pi/pull/5585) by [@haoqixu](https://github.com/haoqixu)).
+- Fixed inherited loose Markdown list rendering to preserve blank-line separation between list items ([#5562](https://github.com/earendil-works/pi/pull/5562) by [@Perlence](https://github.com/Perlence)).
+- Fixed `--model` resolution for authenticated custom model IDs whose slash prefix matches an unauthenticated built-in provider ([#5643](https://github.com/earendil-works/pi/issues/5643)).
+- Fixed `/fork` to keep session parent chains connected when the forked path contains labels ([#5669](https://github.com/earendil-works/pi/issues/5669)).
+- Fixed `/share` and `/export` HTML exports to use the active fallback theme when the configured custom theme no longer exists ([#5596](https://github.com/earendil-works/pi/issues/5596)).
+- Fixed custom fallback model IDs with `:<thinking>` suffixes to preserve the requested thinking level when the provider template model does not advertise reasoning ([#5560](https://github.com/earendil-works/pi/pull/5560) by [@haoqixu](https://github.com/haoqixu)).
+
+## [0.79.1] - 2026-06-09
+
+### New Features
+
+- **Claude Fable 5** - Claude Fable 5 is now available on the Anthropic and Amazon Bedrock providers, with adaptive thinking and `xhigh` effort support.
+- **Prompt template defaults** - Prompt templates can use default positional arguments such as `${1:-7}` for optional values. See [Prompt Template Arguments](docs/prompt-templates.md#arguments).
+- **Configurable project trust defaults** - `defaultProjectTrust` lets users choose whether unresolved project trust asks, always trusts, or never trusts by default, and extensions can inspect effective trust decisions. See [Project Trust](docs/security.md#project-trust) and [`ctx.isProjectTrusted()`](docs/extensions.md#ctxisprojecttrusted).
+- **Natural extension autocomplete triggers** - Extension autocomplete providers can declare trigger characters such as `#` or `$` so suggestions open without slash-command prefixes. See [Autocomplete Providers](docs/extensions.md#autocomplete-providers).
+
+### Added
+
+- Added default-value expansion for prompt template positional arguments, e.g. `${1:-7}` ([#5553](https://github.com/earendil-works/pi/pull/5553) by [@dannote](https://github.com/dannote)).
+- Added `areExperimentalFeaturesEnabled` feature guard to allow users to opt in to early features ([#5547](https://github.com/earendil-works/pi/pull/5547) by [@vegarsti](https://github.com/vegarsti)).
+- Added `ctx.isProjectTrusted()` for extensions to observe the effective project trust decision, including temporary trust decisions ([#5523](https://github.com/earendil-works/pi/issues/5523)).
+- Added a global `defaultProjectTrust` setting to choose whether unresolved project trust asks, always trusts, or never trusts by default.
+- Added extension autocomplete trigger character support for `ctx.ui.addAutocompleteProvider()` wrappers ([#4703](https://github.com/earendil-works/pi/issues/4703)).
+- Added Claude Fable 5 model support inherited from `@sammorrowdrums/mcpi-ai` for the Anthropic and Amazon Bedrock providers, with adaptive thinking and `xhigh` effort support.
+
+### Fixed
+
+- Fixed inherited Amazon Bedrock inference profile ARN region resolution to prefer the ARN's embedded region over `AWS_REGION` ([#5527](https://github.com/earendil-works/pi/pull/5527) by [@AJM10565](https://github.com/AJM10565)).
+- Fixed inherited IME hardware cursor positioning while slash-command autocomplete is visible ([#5283](https://github.com/earendil-works/pi/pull/5283) by [@smoosex](https://github.com/smoosex)).
+- Fixed inherited z.ai thinking-off requests to send the provider's `thinking: { type: "disabled" }` compatibility parameter ([#5330](https://github.com/earendil-works/pi/issues/5330)).
+- Fixed inherited OpenCode completions model metadata to send explicit `maxTokens` as `max_tokens` ([#5331](https://github.com/earendil-works/pi/issues/5331)).
+- Fixed inherited Moonshot Kimi thinking-off requests to send the provider's `thinking: { type: "disabled" }` compatibility parameter ([#5531](https://github.com/earendil-works/pi/issues/5531)).
+- Fixed inherited Azure OpenAI Responses requests to disable server-side response storage ([#5530](https://github.com/earendil-works/pi/issues/5530)).
+- Fixed inherited Azure GPT-5.4 and GPT-5.5 context window metadata to 1,050,000 tokens, matching Azure Foundry deployments instead of OpenAI's 272k limit ([#5559](https://github.com/earendil-works/pi/issues/5559)).
+- Fixed inherited OpenAI and Azure GPT-5 Pro `maxTokens` metadata to 128,000, correcting an upstream value that duplicated the input sub-limit as the output limit ([#5559](https://github.com/earendil-works/pi/issues/5559)).
+- Fixed inherited prompt history navigation to restore the current draft when returning from history browsing ([#5494](https://github.com/earendil-works/pi/issues/5494)).
+- Fixed inherited wrapping for mixed Latin and CJK text so unspaced CJK runs can break at grapheme boundaries without leaving large trailing gaps ([#5495](https://github.com/earendil-works/pi/issues/5495)).
+- Fixed extension OAuth login prompts to keep previous submitted prompt rows stable instead of mirroring the active input value ([#5433](https://github.com/earendil-works/pi/issues/5433)).
+- Fixed `/reload` to apply updated `steeringMode` and `followUpMode` settings to the current session ([#5377](https://github.com/earendil-works/pi/issues/5377)).
+- Fixed invalid `models.json` syntax to skip startup config migrations and report the normal file-path-aware models error instead of a raw JSON parse stack trace ([#5418](https://github.com/earendil-works/pi/issues/5418)).
+- Fixed GitHub release notes and interactive changelog links to resolve package-relative documentation URLs correctly ([#5516](https://github.com/earendil-works/pi/issues/5516)).
+- Fixed CLI help and version output, including plain redirected `--help`/`--version` output and simplified `list`/`config` help text.
+- Fixed `/new` from ephemeral sessions to keep the new session ephemeral instead of persisting it by default ([#5045](https://github.com/earendil-works/pi/issues/5045)).
+- Clarified custom model docs that `name` and `modelOverrides.name` do not replace model IDs in the footer or primary model lists ([#4841](https://github.com/earendil-works/pi/issues/4841)).
+
+## [0.79.0] - 2026-06-08
+
+### New Features
+
+- **Project trust for local inputs** - Pi now asks before loading project-local settings, resources, instructions, and packages, with saved decisions and `--approve` / `--no-approve` controls for non-interactive modes. See [Project Trust](README.md#project-trust).
+- **Extension-controlled trust decisions** - Global and CLI extensions can handle `project_trust`, decide, remember, or defer project trust before project-local resources load. See [`project_trust`](docs/extensions.md#project_trust).
+- **Cache-hit visibility in the footer** - The interactive footer now shows the latest prompt cache hit rate (`CH`). See [Interactive Mode](README.md#interactive-mode).
+- **Richer SDK and RPC extension surfaces** - Public exports now include RPC extension UI request/response types and package asset path helpers. See [Extension UI Protocol](docs/rpc.md#extension-ui-protocol) and [SDK Exports](docs/sdk.md#exports).
+
+### Added
+
+- Added a `project_trust` extension event so global and CLI extensions can decide or defer project trust during startup and runtime cwd switches.
+- Added project trust gating for project-local settings, resources, instructions, and packages ([#5332](https://github.com/earendil-works/pi/pull/5332)).
+- Added the latest prompt cache hit rate to the interactive footer.
+- Exported RPC extension UI request and response types from the public API ([#5455](https://github.com/earendil-works/pi/issues/5455)).
+- Exported coding-agent package asset path helpers from the public API ([#5415](https://github.com/earendil-works/pi/issues/5415)).
+
+### Fixed
+
+- Fixed package exports by removing the stale `./hooks` subpath that pointed at non-existent build output.
+- Fixed inherited TUI rendering to clear stale lines when content shrinks to zero.
+- Fixed inherited autocomplete suggestions to refresh after editor cursor movement ([#5499](https://github.com/earendil-works/pi/pull/5499) by [@Roman-Galeev](https://github.com/Roman-Galeev)).
+- Fixed `/reload` to persist project trust when an implicitly trusted session creates a project `.pi` directory.
+- Fixed project trust input discovery to traverse parent directories portably.
+- Fixed inherited intermittent Shift+Enter handling by making Kitty keyboard protocol fallback response-driven instead of timeout-driven ([#5188](https://github.com/earendil-works/pi/issues/5188)).
+- Fixed the compaction summarization system prompt to use neutral AI assistant wording for non-coding agents ([#5401](https://github.com/earendil-works/pi/issues/5401)).
+- Fixed `models.json` schema support and inherited OpenAI Responses custom-provider handling for `compat.supportsDeveloperRole: false` ([#5456](https://github.com/earendil-works/pi/issues/5456)).
+- Fixed inherited prompt history navigation to place the cursor at the start when browsing upward and at the end when browsing downward ([#5454](https://github.com/earendil-works/pi/issues/5454)).
+- Fixed tmux setup documentation to require tmux 3.5 for `extended-keys-format csi-u` and document the tmux 3.2-3.4 fallback ([#5432](https://github.com/earendil-works/pi/issues/5432)).
+- Fixed inherited OpenRouter routing preferences on OpenAI-compatible custom providers to work when the custom provider base URL does not point directly at OpenRouter ([#5347](https://github.com/earendil-works/pi/issues/5347)).
+- Fixed built-in tool expand hints to style closing parentheses consistently ([#5359](https://github.com/earendil-works/pi/issues/5359)).
+- Fixed skill-wrapped prompts to insert spacing between skill instructions and the user message ([#5371](https://github.com/earendil-works/pi/pull/5371) by [@Perlence](https://github.com/Perlence)).
+
+## [0.78.1] - 2026-06-04
+
+### New Features
+
+- **More built-in provider coverage** - Added Ant Ling and NVIDIA NIM provider setup, plus MiniMax-M3 support for the direct MiniMax providers. See [Providers](docs/providers.md).
+- **Richer extension context** - Extensions can use `ctx.mode` and `ctx.getSystemPromptOptions()` to adapt behavior across TUI, RPC, JSON, and print modes and inspect base system prompt inputs. See [Extensions](docs/extensions.md).
+
+### Added
+
+- Added containerization documentation and a Gondolin extension example for routing built-in tools into a local micro-VM.
+- Added Ant Ling provider selection and setup documentation.
+- Added MiniMax-M3 model support inherited from `@sammorrowdrums/mcpi-ai` for the `minimax` and `minimax-cn` direct providers ([#5313](https://github.com/earendil-works/pi/issues/5313)).
+- Added NVIDIA NIM provider selection, setup documentation, and direct NIM request attribution headers.
+- Added `ctx.mode` to extension contexts so extensions can distinguish TUI, RPC, JSON, and print mode.
+- Added `ctx.getSystemPromptOptions()` for extension commands to inspect the current base system prompt inputs ([#5306](https://github.com/earendil-works/pi/pull/5306) by [@xl0](https://github.com/xl0)).
+
+### Fixed
+
+- Fixed temporary extension package installs to use a private `~/.pi/agent/tmp/extensions` directory with `0700` permissions instead of `os.tmpdir()/pi-extensions`.
+- Fixed git package source handling to reject unsafe host/path components and keep managed clone paths inside install roots.
+- Fixed stored XSS in HTML session exports by sanitizing Markdown link and image URLs with a scheme allow-list after stripping control characters.
+- Fixed SDK embedding in bundled Node apps failing with `ENOENT` when `package.json` is not present next to the bundle entrypoint. The package metadata reader now gracefully handles missing `package.json` by using defaults, enabling `createAgentSession()` without requiring package-adjacent files at runtime ([#5226](https://github.com/earendil-works/pi/issues/5226)).
+- Fixed HTTP timeout setting not being respected for non-Codex providers (e.g., llama.cpp via OpenAI-compatible API). The `httpIdleTimeoutMs` setting (set via `/settings` HTTP timeout) now applies as the default SDK request timeout for all providers that support it, not just OpenAI Codex Responses. Disabling the timeout (HTTP timeout = false) now correctly disables SDK timeouts for all supported providers by sending a maximum int32 value (effectively infinite) instead of 0, since SDKs treat timeout=0 as an immediate timeout ([#5294](https://github.com/earendil-works/pi/issues/5294)).
+- Fixed inherited Amazon Bedrock requests to replace blank required user/tool-result text with a placeholder and skip blank replay text blocks ([#4975](https://github.com/earendil-works/pi/issues/4975)).
+- Fixed inherited Anthropic Claude Opus 4.7+ requests to suppress deprecated temperature parameters ([#5251](https://github.com/earendil-works/pi/pull/5251) by [@yzhg1983](https://github.com/yzhg1983)).
+- Fixed inherited OpenAI GPT-5.5 generated metadata to omit unsupported minimal thinking ([#5243](https://github.com/earendil-works/pi/issues/5243)).
+- Fixed inherited OpenRouter Kimi K2.6 thinking replay and developer-role instruction handling ([#5309](https://github.com/earendil-works/pi/issues/5309)).
+- Fixed inherited OpenRouter reasoning instruction requests to preserve the system role when required ([#5221](https://github.com/earendil-works/pi/pull/5221) by [@PriNova](https://github.com/PriNova)).
+- Fixed inherited overlay focus restoration so non-capturing overlays remain interactive after UI rerenders and explicit focus release ([#5235](https://github.com/earendil-works/pi/pull/5235) by [@nicobailon](https://github.com/nicobailon)).
+- Fixed inherited tab width accounting in column slicing and overlay compositing so tab-containing output cannot exceed the terminal width ([#5218](https://github.com/earendil-works/pi/issues/5218)).
+- Fixed opening and listing very large JSONL session files by reading session entries line-by-line instead of materializing the full file as one string ([#5231](https://github.com/earendil-works/pi/issues/5231)).
+- Fixed the footer branch display in WSL `/mnt/...` repositories to refresh after branch changes ([#5264](https://github.com/earendil-works/pi/pull/5264) by [@psoukie](https://github.com/psoukie)).
+- Fixed `renderShell: "self"` tool renderers that emit no component lines leaving a blank chat row ([#5299](https://github.com/earendil-works/pi/issues/5299)).
+- Restored inherited NVIDIA Qwen 3.5 122B NIM model support.
+
+## [0.78.0] - 2026-05-29
+
+### New Features
+
+- **Named startup sessions** - `--name` / `-n` sets the session display name before startup across interactive, print, JSON, and RPC modes. See [Naming Sessions](docs/sessions.md#naming-sessions) and [Session Options](docs/usage.md#session-options).
+- **Clickable file tool paths** - built-in file tool titles render OSC 8 `file://` hyperlinks when the terminal supports them, including supported tmux clients.
+
+### Added
+
+- Exported `convertToPng` for extension authors ([#5167](https://github.com/earendil-works/pi-mono/pull/5167) by [@xl0](https://github.com/xl0)).
+- Exported `parseArgs` and type `Args` for extension authors ([#5202](https://github.com/earendil-works/pi-mono/pull/5202) by [@xl0](https://github.com/xl0)).
+- Added `--name` / `-n` to set the session display name at startup ([#5153](https://github.com/earendil-works/pi-mono/issues/5153)).
+- Added a resume command hint when exiting interactive sessions ([#5176](https://github.com/earendil-works/pi-mono/pull/5176) by [@yzhg1983](https://github.com/yzhg1983)).
+- Added OSC 8 `file://` hyperlinks to file paths shown in built-in file tool titles ([#5189](https://github.com/earendil-works/pi-mono/pull/5189) by [@mpazik](https://github.com/mpazik)).
+- Added custom Amazon Bedrock request header support inherited from `@sammorrowdrums/mcpi-ai` ([#5178](https://github.com/earendil-works/pi-mono/pull/5178) by [@stephanmck](https://github.com/stephanmck)).
+
+### Fixed
+
+- Clarified the WezTerm/WSL IME hardware cursor docs to state that cursor visibility remains opt-in ([#5200](https://github.com/earendil-works/pi-mono/issues/5200)).
+- Fixed the GitLab Duo custom provider example to use adaptive thinking for Claude models, expose xhigh thinking, and include newer verified model IDs ([#5201](https://github.com/earendil-works/pi-mono/issues/5201)).
+- Fixed Bun release archive creation to install and copy the matching `@mariozechner/clipboard` base package and native sidecars ([#5184](https://github.com/earendil-works/pi-mono/issues/5184)).
+- Fixed early interactive input typed before the prompt loop starts so it is buffered instead of dropped ([#5195](https://github.com/earendil-works/pi-mono/pull/5195) by [@yzhg1983](https://github.com/yzhg1983)).
+- Fixed OpenRouter Moonshot Kimi K2.6 requests to use `system` instead of unsupported `developer` messages ([#5159](https://github.com/earendil-works/pi-mono/issues/5159)).
+- Fixed OpenCode Go Kimi K2.6 thinking requests to send `thinking` objects instead of invalid string values, and fixed OpenCode Zen Grok Build thinking requests to omit unsupported `reasoning_effort` ([#5169](https://github.com/earendil-works/pi-mono/issues/5169)).
+- Fixed OpenAI Codex Responses SSE streams to abort response body reads after terminal events.
+- Fixed OpenCode Kimi K2.6 generated metadata to use Anthropic-style thinking metadata instead of invalid reasoning-effort parameters.
+- Fixed OSC 8 hyperlinks to pass through tmux when the client supports them ([#5189](https://github.com/earendil-works/pi-mono/pull/5189) by [@mpazik](https://github.com/mpazik)).
+- Fixed ANSI text wrapping to avoid stack overflows on very long wrapped lines ([#5185](https://github.com/earendil-works/pi-mono/issues/5185)).
+
+## [0.77.0] - 2026-05-28
+
+### New Features
+
+- **Claude Opus 4.8 support** - Adds Anthropic Claude Opus 4.8 metadata and updates Opus adaptive-thinking coverage.
+- **Selective tool disablement** - `--exclude-tools` / `-xt` disables specific built-in, extension, or custom tools while leaving the rest available. See [Tool Options](docs/usage.md#tool-options).
+- **Headless Codex subscription login** - `/login` can use device-code auth for ChatGPT Plus/Pro Codex subscriptions. See [Subscriptions](docs/providers.md#subscriptions) and [OpenAI Codex](docs/providers.md#openai-codex).
+- **Streaming-aware extension input** - extensions can distinguish idle prompts, mid-stream steers, and queued follow-ups with `InputEvent.streamingBehavior`. See [Input Events](docs/extensions.md#input-events).
+
+### Added
+
+- Added `--exclude-tools` / `-xt` to disable specific built-in, extension, or custom tools while leaving the rest available ([#5109](https://github.com/earendil-works/pi/issues/5109)).
+- Added OpenAI Codex subscription device-code login as a selectable headless alternative while keeping browser login as the default ([#4911](https://github.com/earendil-works/pi/pull/4911) by [@vegarsti](https://github.com/vegarsti)).
+- Added `streamingBehavior` to extension input events so extensions can distinguish idle prompts from mid-stream steers and queued follow-ups ([#5107](https://github.com/earendil-works/pi/pull/5107) by [@DanielThomas](https://github.com/DanielThomas)).
+- Added Claude Opus 4.8 model metadata for Anthropic and updated Opus adaptive-thinking coverage to use it.
+
+### Fixed
+
+- Fixed startup timing output so `readPipedStdin` no longer includes `createAgentSessionRuntime` work ([#4829](https://github.com/earendil-works/pi/issues/4829)).
+- Fixed OpenRouter DeepSeek V4 `xhigh` reasoning metadata to preserve OpenRouter's native effort instead of sending DeepSeek's `max` effort ([#4801](https://github.com/earendil-works/pi/issues/4801)).
+- Fixed custom session directories so current-folder resume/continue lookups stay scoped to the active cwd while all-session listings cover the custom directory.
+- Fixed SIGTERM/SIGHUP exits to run extension `session_shutdown` cleanup and restore the terminal: signal-triggered shutdown now emits `session_shutdown` before any terminal writes, and SIGHUP no longer hard-exits, so extension resources (e.g. sockets) are released even when the terminal is gone ([#5080](https://github.com/earendil-works/pi/issues/5080)).
+- Fixed keyboard protocol negotiation to ignore mismatched or delayed terminal responses, avoiding false Kitty keyboard protocol detection ([#5091](https://github.com/earendil-works/pi/pull/5091) by [@mitsuhiko](https://github.com/mitsuhiko)).
+- Fixed Windows startup crashes under MSYS2 ucrt64 Node.js by updating the native clipboard addon to napi-rs 3.x ([#5028](https://github.com/earendil-works/pi/issues/5028)).
+- Fixed API key and header config resolution to treat plain strings as literals, support `$ENV_VAR` / `${ENV_VAR}` interpolation and `$!` bang escaping, and require explicit env syntax for config files, avoiding Windows case-insensitive env matches corrupting literal keys ([#5095](https://github.com/earendil-works/pi/issues/5095)).
+- Fixed session disposal to abort in-flight agent, compaction, branch summary, retry, and bash work ([#5029](https://github.com/earendil-works/pi/pull/5029) by [@TerminallyChilI](https://github.com/TerminallyChilI)).
+- Fixed `pi.getAllTools()` to expose each tool's `promptGuidelines` for extensions that need per-tool guideline attribution ([#4879](https://github.com/earendil-works/pi/issues/4879)).
+- Fixed OpenAI Codex Responses replay after switching from Anthropic extended-thinking sessions by generating unique fallback message item IDs for converted thinking/text blocks ([#5148](https://github.com/earendil-works/pi/issues/5148)).
+- Fixed Anthropic-compatible replay for providers that return empty thinking signatures by adding an opt-in `allowEmptySignature` compatibility flag ([#4464](https://github.com/earendil-works/pi/issues/4464)).
+- Fixed OpenAI and OpenRouter GPT-5.5 Pro thinking level metadata to expose only supported medium, high, and xhigh efforts.
+- Fixed OpenCode Go Kimi K2.6 thinking-off requests to send `thinking: "none"` ([#5078](https://github.com/earendil-works/pi/issues/5078)).
+- Fixed Xiaomi Token Plan model metadata to omit unsupported `mimo-v2-flash` variants ([#5075](https://github.com/earendil-works/pi/issues/5075)).
+- Fixed follow-up messages queued by `agent_end` extension handlers to drain before the agent becomes idle ([#5115](https://github.com/earendil-works/pi/pull/5115) by [@DanielThomas](https://github.com/DanielThomas)).
+- Fixed extension input events to report `streamingBehavior` only for prompts actually queued during streaming ([#5107](https://github.com/earendil-works/pi/pull/5107) by [@DanielThomas](https://github.com/DanielThomas)).
+- Fixed system prompt tool-selection guidance to avoid preferring unavailable file exploration tools ([#5132](https://github.com/earendil-works/pi/issues/5132)).
+- Fixed fenced `diff` code blocks and other highlight.js scopes to keep theme-aware syntax colors after the `cli-highlight` replacement ([#5092](https://github.com/earendil-works/pi/issues/5092)).
+
+## [0.76.0] - 2026-05-27
+
+### New Features
+
+- **Explicit session IDs for automation** - `--session-id <id>` lets scripts create or resume an exact project-local session. See [Sessions](docs/usage.md#sessions).
+- **RPC bash output can stay out of model context** - RPC clients can pass `excludeFromContext` to `bash` for commands whose output should not be sent with the next prompt. See [RPC mode](docs/rpc.md#bash).
+- **More predictable provider retries and timeouts** - Codex WebSocket/SSE waits are bounded, and `retry.provider.maxRetries` controls provider retries instead of hidden SDK defaults. See [Retry settings](docs/settings.md#retry).
+- **Better terminal editing across environments** - Apple Terminal Shift+Enter, Windows/JetBrains capability detection, and Unicode-aware word navigation improve interactive editing. See [Terminal setup](docs/terminal-setup.md) and [Keybindings](docs/keybindings.md).
+
+### Added
+
+- Added `--session-id` to let CLI callers use an exact project-local session ID, creating it if missing ([#4874](https://github.com/earendil-works/pi/issues/4874)).
+- Added `excludeFromContext` flag to the `bash` RPC command for parity with the internal `executeBash` API ([#5039](https://github.com/earendil-works/pi/issues/5039)).
+
+### Fixed
+
+- Fixed user message transcript rendering to preserve user-authored ordered-list markers ([#5013](https://github.com/earendil-works/pi/issues/5013)).
+- Fixed self-update commands to bypass npm, pnpm, and Bun minimum release age gates for explicit `pi update` runs ([#4929](https://github.com/earendil-works/pi/issues/4929)).
+- Fixed context token estimates to count user image attachments consistently with tool result images ([#4983](https://github.com/earendil-works/pi/issues/4983)).
+- Fixed `httpIdleTimeoutMs` to apply to OpenAI Codex Responses WebSocket idle waits, added `websocketConnectTimeoutMs` for bounded WebSocket connect waits, and added a 10s Codex SSE response-header timeout ([#4945](https://github.com/earendil-works/pi/issues/4945)).
+- Fixed `RpcClient` to reject pending requests and consume stdin pipe errors when the child process exits unexpectedly ([#4764](https://github.com/earendil-works/pi/issues/4764)).
+- Fixed managed npm extension updates to avoid package managers installing or resolving pi host packages as peer dependencies ([#4907](https://github.com/earendil-works/pi/issues/4907)).
+- Fixed RPC mode raw stdout writes to retry transient backpressure errors and flush queued protocol output during shutdown ([#4897](https://github.com/earendil-works/pi/issues/4897)).
+- Fixed OpenAI Codex Responses cache-affinity headers to send `session-id` instead of proxy-incompatible `session_id` ([#4967](https://github.com/earendil-works/pi/issues/4967)).
+- Fixed `openai-codex/gpt-5.3-codex-spark` model metadata to use its 128k context window ([#4969](https://github.com/earendil-works/pi/issues/4969)).
+- Fixed OpenRouter/Poolside context overflow detection for `maximum allowed input length` errors ([#4943](https://github.com/earendil-works/pi/issues/4943)).
+- Fixed provider retry controls so `retry.provider.maxRetries` is honored, SDK retries default to `0`, and quota/billing 429s are not retried behind Pi's retry handling ([#4991](https://github.com/earendil-works/pi-mono/pull/4991) by [@mitsuhiko](https://github.com/mitsuhiko)).
+- Fixed Apple Terminal `Shift+Enter` by detecting local macOS modifier state when Terminal.app sends plain Return.
+- Fixed Windows Terminal capability detection to enable OSC 8 hyperlinks, preserving clickable long URLs across wrapped lines ([#4923](https://github.com/earendil-works/pi/issues/4923)).
+- Fixed JetBrains terminal capability detection to enable truecolor while disabling unsupported OSC 8 hyperlinks ([#5037](https://github.com/earendil-works/pi-mono/pull/5037) by [@Perlence](https://github.com/Perlence)).
+- Fixed editor and input word navigation/deletion to use Unicode word boundaries while preserving ASCII punctuation boundaries ([#5022](https://github.com/earendil-works/pi-mono/pull/5022) by [@haoqixu](https://github.com/haoqixu), [#5067](https://github.com/earendil-works/pi-mono/pull/5067) by [@haoqixu](https://github.com/haoqixu), [#5068](https://github.com/earendil-works/pi-mono/pull/5068) by [@haoqixu](https://github.com/haoqixu)).
+- Fixed the development docs `AGENTS.md` link to point at the pi-mono guidelines ([#5041](https://github.com/earendil-works/pi/issues/5041)).
+
+## [0.75.5] - 2026-05-23
+
+### New Features
+
+- **Cleaner read tool output** - Collapsed `read` tool cards now show only the read line by default, while `Ctrl+O` still expands the full file content.
+- **Faster file tools on Windows** - Built-in file tools now use async filesystem operations during streaming, and image resizes run off the main TUI thread in a worker.
+- **More reliable package updates** - `pi update` and git package installs now reconcile pinned git refs and keep package settings intact. See [Packages](docs/packages.md).
+- **Custom Anthropic-compatible adaptive thinking** - Custom provider model configs can opt into adaptive-thinking Claude behavior with `compat.forceAdaptiveThinking`. See [Custom providers](docs/custom-provider.md) and [Models](docs/models.md).
+
+### Added
+
+- Added `compat.forceAdaptiveThinking` support to custom Anthropic-compatible model configuration docs and validation ([#4797](https://github.com/earendil-works/pi-mono/pull/4797) by [@mbazso](https://github.com/mbazso)).
+- Added a standard unified patch to edit tool result details for SDK consumers ([#4821](https://github.com/earendil-works/pi/issues/4821)).
+- Added a Codex subscription login method selector with device-code auth for headless environments.
+
+### Changed
+
+- Changed collapsed read tool cards to show only the read line until expanded ([#4916](https://github.com/earendil-works/pi/issues/4916)).
+- Replaced the inherited optional `koffi` dependency for Windows VT input with a tiny vendored native helper, reducing install size while preserving Shift+Tab handling ([#4480](https://github.com/earendil-works/pi/issues/4480)).
+- Changed the root development install documentation to use `npm install --ignore-scripts` ([#4868](https://github.com/earendil-works/pi/issues/4868)).
+
+### Fixed
+
+- Fixed `pi update` to reconcile git-pinned packages to their configured ref ([#4869](https://github.com/earendil-works/pi/issues/4869)).
+- Fixed package/resource path handling for Windows and glob/pattern resolution ([#4873](https://github.com/earendil-works/pi-mono/pull/4873) by [@mitsuhiko](https://github.com/mitsuhiko)).
+- Fixed config pattern matching to resolve patterns from the correct base directory ([#4898](https://github.com/earendil-works/pi-mono/pull/4898) by [@haoqixu](https://github.com/haoqixu)).
+- Fixed theme pickers to list themes by their content name instead of file stem ([#4830](https://github.com/earendil-works/pi-mono/pull/4830) by [@Perlence](https://github.com/Perlence)).
+- Fixed OpenCode Zen/Go requests to send per-session OpenCode routing headers ([#4847](https://github.com/earendil-works/pi/issues/4847)).
+- Fixed Amazon Bedrock provider loading under strict package managers by inheriting the declared `@smithy/node-http-handler` dependency from `@sammorrowdrums/mcpi-ai` ([#4842](https://github.com/earendil-works/pi/issues/4842)).
+- Fixed inherited Amazon Bedrock Claude requests to send the model output token cap by default, avoiding Bedrock's 4096-token default truncation ([#4848](https://github.com/earendil-works/pi/issues/4848)).
+- Fixed exported session HTML to escape quote characters in attribute values ([#4832](https://github.com/earendil-works/pi/issues/4832)).
+- Fixed GitHub Copilot device-code login to keep opening the verification URL in browser-capable environments while ignoring browser launch failures for headless use ([#4788](https://github.com/earendil-works/pi-mono/pull/4788) by [@vegarsti](https://github.com/vegarsti)).
+- Fixed git package installs to reconcile existing checkouts to the requested ref and update package settings without losing filters ([#4870](https://github.com/earendil-works/pi/issues/4870)).
+- Published a 0.74.2 rescue release that tells Node 20 users to upgrade Node before updating to newer Pi versions ([#4876](https://github.com/earendil-works/pi/issues/4876)).
+- Fixed final bash tool cards to avoid rendering duplicate full-output truncation paths ([#4819](https://github.com/earendil-works/pi/issues/4819)).
+- Fixed bash tool truncation line counts to ignore the trailing newline as an extra output line ([#4818](https://github.com/earendil-works/pi/issues/4818)).
+- Fixed footer home-directory abbreviation to avoid shortening sibling paths that only share the same prefix ([#4878](https://github.com/earendil-works/pi/issues/4878)).
+- Fixed macOS Bun release binaries to resolve the native clipboard sidecar so Ctrl+V image paste can load `@mariozechner/clipboard` ([#4307](https://github.com/earendil-works/pi/issues/4307)).
+- Fixed coding-agent tools to avoid synchronous filesystem operations during streaming and moved image resizing off the main TUI thread ([#4756](https://github.com/earendil-works/pi-mono/pull/4756) by [@mitsuhiko](https://github.com/mitsuhiko)).
+
+## [0.75.4] - 2026-05-20
+
+### New Features
+
+- **Hardened npm install and release path** - Pi now ships the CLI with a generated shrinkwrap for transitive dependencies, blocks accidental lockfile changes, verifies dependency pinning and lifecycle-script allowlists in checks, disables lifecycle scripts for self-update and local release installs where supported, and smoke-tests isolated npm and Bun installs before release. See [Supply-chain hardening](../../README.md#supply-chain-hardening).
+
+### Added
+
+- Added interactive update notes after `pi update` runs, so users can see the installed version's changelog before continuing ([#4724](https://github.com/earendil-works/pi-mono/pull/4724) by [@mitsuhiko](https://github.com/mitsuhiko)).
+- Exported image resize utilities from the package root for SDK consumers ([#4775](https://github.com/earendil-works/pi-mono/pull/4775) by [@xl0](https://github.com/xl0)).
+
+### Changed
+
+- Changed source syntax to avoid TypeScript constructs that require JavaScript emit, keeping core sources compatible with Node.js strip-only TypeScript checks.
+- Removed web UI workspace references from the CLI package and dropped the package-level development watch script.
+- Published npm installs now include an `npm-shrinkwrap.json` to lock transitive dependencies for the CLI package.
+- Improved terminal theme detection for light/dark and truecolor handling.
+- Changed self-update package-manager commands to disable lifecycle scripts during reinstall.
+
+### Fixed
+
+- Fixed the system prompt to tell models to resolve pi docs and examples under the absolute package paths before reading topic-specific relative references ([#4752](https://github.com/earendil-works/pi/issues/4752)).
+- Fixed extension `ctx.abort()` during tool-call preflight to stop later confirmations and restore queued interactive input like Escape ([#4276](https://github.com/earendil-works/pi/issues/4276)).
+- Fixed AgentSession retry, compaction, and event settlement to use the awaited agent lifecycle instead of a separate event queue, and added `willRetry` to `agent_end` session events.
+- Fixed forked session runtime state to keep the active session id aligned with the fork target ([#4799](https://github.com/earendil-works/pi-mono/pull/4799) by [@Perlence](https://github.com/Perlence)).
+- Fixed the subagent extension's parallel mode to return useful per-task output and failed-task diagnostics to the parent model instead of 100-character previews ([#4710](https://github.com/earendil-works/pi/issues/4710)).
+- Fixed Windows local bash execution to hide helper console windows when launched from background SDK processes ([#4699](https://github.com/earendil-works/pi/issues/4699)).
+- Fixed managed npm extension folders to set cloud-sync ignore metadata where supported ([#4763](https://github.com/earendil-works/pi/issues/4763)).
+- Fixed HTTP idle timeout configuration so long-running provider streams can avoid premature idle disconnects ([#4759](https://github.com/earendil-works/pi-mono/pull/4759) by [@mitsuhiko](https://github.com/mitsuhiko)).
+- Fixed default system prompt boundaries to use explicit XML tags for clearer file separation ([#4709](https://github.com/earendil-works/pi-mono/pull/4709) by [@herrnel](https://github.com/herrnel)).
+- Fixed HTML share/export sidebar clicks for shared tool entries to scroll to the rendered tool call ([#4664](https://github.com/earendil-works/pi-mono/pull/4664) by [@yzhg1983](https://github.com/yzhg1983)).
+- Fixed theme palettes to set explicit text colors and avoid terminal-default color drift.
+- Fixed truecolor detection to align terminal image rendering and interactive theme decisions.
+- Fixed loader indicator startup inherited from `@sammorrowdrums/mcpi-tui` so initialization cannot run before frames are available.
+- Fixed OpenAI-compatible default output token requests inherited from `@sammorrowdrums/mcpi-ai` to avoid reserving impossible context windows on servers such as vLLM ([#4675](https://github.com/earendil-works/pi/issues/4675)).
+- Fixed OpenAI prompt cache keys inherited from `@sammorrowdrums/mcpi-ai` to stay within the 64-character provider limit ([#4720](https://github.com/earendil-works/pi/issues/4720)).
+- Fixed Windows npm-family package commands for fnm-managed Node.js installs that expose both extensionless Unix scripts and `.cmd` shims ([#4793](https://github.com/earendil-works/pi/issues/4793)).
+
+## [0.75.3] - 2026-05-18
+
+### Fixed
+
+- Fixed undici 8 HTTP/2 destroyed-session races crashing the Node CLI by preserving the previous HTTP/1.1-only fetch dispatcher behavior ([#4681](https://github.com/earendil-works/pi/issues/4681)).
+
+## [0.75.2] - 2026-05-18
+
+### Fixed
+
+- Fixed Bun-compiled release binaries failing to start when Bun's built-in undici shim lacks npm undici's `install` export ([#4661](https://github.com/earendil-works/pi-mono/pull/4661) by [@dmasiero](https://github.com/dmasiero)).
+- Fixed Xiaomi MiMo generated model metadata to replay assistant tool-call messages with `reasoning_content` for thinking-mode multi-turn requests, inherited from `@sammorrowdrums/mcpi-ai` ([#4678](https://github.com/earendil-works/pi/issues/4678)).
+- Fixed Windows external editor handoff so vim/nvim can receive input after opening from the TUI ([#4612](https://github.com/earendil-works/pi/issues/4612)).
+- Fixed Windows npm self-updates to move loaded native dependency packages out of the active install before reinstalling pi ([#4157](https://github.com/earendil-works/pi/issues/4157)).
+- Fixed `pi update --self` detection for pnpm v11 global installs whose package path resolves through the pnpm store ([#4647](https://github.com/earendil-works/pi/issues/4647)).
+- Fixed Windows pnpm self-updates to resolve pnpm command shims and run through pnpm instead of requiring manual updates ([#4157](https://github.com/earendil-works/pi/issues/4157)).
+- Fixed Windows npm-family command execution to use cross-spawn instead of parsing `.cmd` shim internals ([#4665](https://github.com/earendil-works/pi/issues/4665)).
+
+## [0.75.1] - 2026-05-18
+
+### Fixed
+
+- Fixed config selectors to scale their visible row count to terminal height ([#4243](https://github.com/earendil-works/pi-mono/pull/4243) by [@samjonester](https://github.com/samjonester)).
+- Fixed Anthropic-compatible API-key requests to ignore unrelated `ANTHROPIC_AUTH_TOKEN` environment values, avoiding invalid bearer credentials for providers such as Xiaomi MiMo inherited from `@sammorrowdrums/mcpi-ai` ([#4342](https://github.com/earendil-works/pi/issues/4342)).
+- Fixed Amazon Bedrock message conversion to skip unknown content blocks instead of failing the stream, inherited from `@sammorrowdrums/mcpi-ai` ([#4223](https://github.com/earendil-works/pi/issues/4223)).
+- Fixed Azure OpenAI Responses and OpenAI Responses error formatting to prefix HTTP status codes onto `errorMessage`, so transient 5xx and 429 errors are correctly matched by the agent-level auto-retry classifier inherited from `@sammorrowdrums/mcpi-ai` ([#4232](https://github.com/earendil-works/pi/issues/4232)).
+- Fixed OpenCode Go Kimi reasoning replay by normalizing streamed `reasoning` fields back to `reasoning_content` for OpenCode Go only, inherited from `@sammorrowdrums/mcpi-ai` ([#4251](https://github.com/earendil-works/pi/issues/4251)).
+- Fixed Xiaomi MiMo model metadata to use the OpenAI-compatible endpoints and `openai-completions` API, restoring multi-turn thinking/tool-call sessions inherited from `@sammorrowdrums/mcpi-ai` ([#4505](https://github.com/earendil-works/pi/issues/4505)).
+- Fixed JSON parse failures for compressed fetch responses under Node 26.0 by installing undici fetch globals alongside pi's global dispatcher ([#4650](https://github.com/earendil-works/pi/issues/4650), [#4652](https://github.com/earendil-works/pi/issues/4652), [#4653](https://github.com/earendil-works/pi/issues/4653)).
+- Fixed npm-family package commands on Windows to avoid shell argument splitting when install prefixes contain spaces ([#4623](https://github.com/earendil-works/pi/issues/4623)).
+
+### Removed
+
+- Removed non-working OpenAI Codex fast model variants inherited from `@sammorrowdrums/mcpi-ai`.
+
+## [0.75.0] - 2026-05-17
+
+### Breaking Changes
+
+- Raised the minimum supported Node.js version to 22.19.0.
+
+### Fixed
+
+- Fixed compaction summary calls to use custom agent stream functions, preserving proxy-backed LLM routing ([#4484](https://github.com/earendil-works/pi/issues/4484)).
+- Fixed system prompt and context file boundaries to use explicit XML tags instead of Markdown headings, reducing inconsistent boundary ingestion by models ([#4541](https://github.com/earendil-works/pi-mono/pull/4541) by [@herrnel](https://github.com/herrnel)).
+- Fixed OpenAI Codex generated model metadata to use the current upstream model list inherited from `@sammorrowdrums/mcpi-ai` ([#4603](https://github.com/earendil-works/pi-mono/pull/4603) by [@mattiacerutti](https://github.com/mattiacerutti)).
+- Fixed GitHub Copilot GPT model thinking metadata inherited from `@sammorrowdrums/mcpi-ai` to map unsupported minimal thinking to low ([#4622](https://github.com/earendil-works/pi-mono/pull/4622) by [@mattiacerutti](https://github.com/mattiacerutti)).
+- Fixed user-scoped npm pi packages to install under `~/.pi/agent/npm/` instead of npm's global package root, avoiding permission errors with system-managed Node installs ([#4587](https://github.com/earendil-works/pi/issues/4587)).
+- Fixed Mistral requests failing after the global fetch proxy/timeout workaround by removing the custom fetch override and using undici 8 dispatcher support instead ([#4619](https://github.com/earendil-works/pi/issues/4619)).
+- Fixed default output token requests for models whose advertised output limit is effectively their full context window, avoiding impossible provider requests inherited from `@sammorrowdrums/mcpi-ai` ([#4614](https://github.com/earendil-works/pi/issues/4614)).
+
+## [0.74.1] - 2026-05-16
+
+### New Features
+
+- **Image generation support** - Added image generation APIs, generated image model metadata, and built-in OpenRouter image generation support inherited from `@sammorrowdrums/mcpi-ai`.
+- **Together AI provider** - Added Together AI as a built-in provider with `/login` API-key auth, default model resolution, and setup docs. See [README.md#providers--models](README.md#providers--models) and [docs/providers.md](docs/providers.md).
+- **Windows ARM64 standalone binaries** - Added standalone release artifacts for Windows ARM64.
+- **Improved terminal and markdown rendering** - Added markdown list indentation, task-list checkbox rendering, large markdown robustness, and inline image placement fixes inherited from `@sammorrowdrums/mcpi-tui`.
+
+### Added
+
+- Added image generation support from `@sammorrowdrums/mcpi-ai`, including image generation APIs, image model metadata, and built-in OpenRouter image generation support ([#3887](https://github.com/earendil-works/pi-mono/pull/3887) by [@cristinaponcela](https://github.com/cristinaponcela)).
+- Added Together AI to built-in provider setup, `/login` API-key auth, and default model resolution ([#3624](https://github.com/earendil-works/pi-mono/pull/3624) by [@Nutlope](https://github.com/Nutlope)).
+- Added Windows ARM64 standalone binary release artifacts ([#4458](https://github.com/earendil-works/pi/pull/4458) by [@brianmichel](https://github.com/brianmichel)).
+
+### Fixed
+
+- Fixed Node 26 OpenAI-compatible streams timing out after five idle minutes by routing global fetch through pi's undici dispatcher ([#4519](https://github.com/earendil-works/pi/issues/4519)).
+- Fixed pnpm global package installs by resolving the global package root from pnpm's layout.
+- Fixed macOS clipboard access errors under sandboxed pasteboard denial so they do not abort the process ([#4492](https://github.com/earendil-works/pi/issues/4492)).
+- Fixed the scoped model startup hint to show the configured model-cycle keybinding ([#4508](https://github.com/earendil-works/pi/issues/4508)).
+- Fixed resource path display to disambiguate package/resource names that collide across package locations.
+- Fixed `fd` auto-download on macOS x86_64 by pinning the last release that ships an Intel macOS binary ([#4559](https://github.com/earendil-works/pi/issues/4559)).
+- Fixed skill diagnostics to stop warning when a skill name differs from its parent directory ([#4534](https://github.com/earendil-works/pi/issues/4534)).
+- Fixed prompt template argument parsing to split unquoted multiline input on newlines ([#4553](https://github.com/earendil-works/pi/issues/4553)).
+- Fixed `--resume` session listing to cap in-flight session metadata loads and avoid OOM on large session histories ([#4583](https://github.com/earendil-works/pi/issues/4583)).
+- Fixed interactive error messages to render with trailing spacing so reload errors do not run into resource listings ([#4510](https://github.com/earendil-works/pi/issues/4510)).
+- Fixed `.agents` package provenance metadata to survive package-manager scans.
+- Fixed nested code fences in the Termux setup documentation so the example AGENTS.md renders correctly ([#4503](https://github.com/earendil-works/pi/issues/4503)).
+- Fixed tool output expansion while extension confirmation dialogs are focused ([#4429](https://github.com/earendil-works/pi/issues/4429)).
+- Fixed auto-retry for Anthropic streams that end before `message_stop` ([#4433](https://github.com/earendil-works/pi/issues/4433)).
+- Fixed compaction summary calls to clamp requested output tokens to model limits.
+- Fixed uncaught interactive-mode exceptions to restore the terminal before exiting ([#4426](https://github.com/earendil-works/pi-mono/pull/4426) by [@ofa1](https://github.com/ofa1)).
+- Fixed ANSI stripping to match `strip-ansi` behavior after dependency removal.
+- Fixed UUIDv7 sequence generation shared by session IDs after dependency removal.
+- Fixed OpenRouter cached-token usage accounting, Fireworks caching compatibility, and OpenAI Codex WebSocket proxy handling inherited from `@sammorrowdrums/mcpi-ai`.
+- Fixed markdown list wrapping, task-list checkboxes, large markdown rendering, WezTerm Kitty keyboard escape handling, and short-viewport inline image placement inherited from `@sammorrowdrums/mcpi-tui`.
+- Fixed theme sharing across package scopes so extensions do not crash with `Theme not initialized` ([#4333](https://github.com/earendil-works/pi/issues/4333)).
+- Fixed keybinding hints to show Option instead of Alt on macOS ([#4289](https://github.com/earendil-works/pi/issues/4289)).
+- Fixed the interactive update notification to render the changelog as an OSC 8 hyperlink when the terminal supports hyperlinks ([#4280](https://github.com/earendil-works/pi/issues/4280)).
+
+## [0.74.0] - 2026-05-07
+
+### Changed
+
+- Updated repository links and package references for the move to `earendil-works/pi-mono` and `@earendil-works/*` package scopes.
+
+## [0.73.1] - 2026-05-07
+
+### New Features
+
+- **Self-update support for the npm scope migration**: `pi update --self` now supports the upcoming package rename from `@mariozechner/pi-coding-agent` to `@sammorrowdrums/mcpi`. After the new package is published, existing global installs can update through the normal self-update flow; pi will uninstall the old global package and install the package name returned by the version check endpoint.
+- **Interactive OAuth login selection**: OAuth providers can now present multiple login choices in `/login`, enabling provider-specific interactive authentication flows. See [Providers](docs/providers.md).
+- **JSONC-style `models.json` parsing**: `models.json` now allows comments and trailing commas, making custom provider and model configuration easier to maintain. See [Providers](docs/providers.md) and [Custom Providers](docs/custom-provider.md).
+
+### Added
+
+- Added interactive login selection support so OAuth providers can present multiple login choices ([#4190](https://github.com/earendil-works/pi-mono/pull/4190) by [@mitsuhiko](https://github.com/mitsuhiko)).
+
+### Changed
+
+- Changed `pi update --self` to honor the active package name returned by the Pi version check endpoint, defaulting to the current package when omitted and uninstalling the old global package before installing a renamed package.
+- Changed extension loading to use upstream `jiti` 2.7 instead of the `@mariozechner/jiti` fork ([#4244](https://github.com/earendil-works/pi-mono/pull/4244) by [@pi0](https://github.com/pi0)).
+- Changed `models.json` parsing to allow comments and trailing commas ([#4162](https://github.com/earendil-works/pi-mono/pull/4162) by [@julien-c](https://github.com/julien-c)).
+
+### Fixed
+
+- Fixed `pi -p` treating prompts that start with YAML frontmatter as extension flags instead of user messages ([#4163](https://github.com/badlogic/pi-mono/issues/4163)).
+- Fixed pending tool results not updating in the live TUI after toggling thinking block visibility while the tool is running ([#4167](https://github.com/badlogic/pi-mono/issues/4167)).
+- Fixed `/copy` reporting success on Linux without writing the clipboard on Wayland-only compositors (Hyprland, Niri, ...) by skipping the X11-only native addon on Linux and routing through `wl-copy`/`xclip`/`xsel` instead ([#4177](https://github.com/badlogic/pi-mono/issues/4177)).
+- Fixed HTML session exports to strip skill wrapper XML from rendered user messages ([#4234](https://github.com/earendil-works/pi-mono/pull/4234) by [@aliou](https://github.com/aliou)).
+- Fixed OpenAI-compatible chat completion streams that interleave content and tool-call deltas in the same choice.
+- Fixed OpenAI Codex OAuth refresh failures writing directly to stderr while the TUI is active ([#4141](https://github.com/badlogic/pi-mono/issues/4141)).
+- Fixed OpenAI Codex Responses requests to send a non-empty system prompt ([#4184](https://github.com/earendil-works/pi-mono/issues/4184)).
+- Fixed Kimi For Coding model resolution for the Kimi K2 P6 alias ([#4218](https://github.com/earendil-works/pi-mono/issues/4218)).
+- Fixed Kitty inline image redraws to stay within TUI-owned terminal regions and avoid writing below the active viewport.
+- Fixed Kitty inline image rendering by letting the terminal allocate image ids and bounding parsed image ids to valid values.
+- Fixed inline image capability detection to disable inline images in cmux terminals.
+
+## [0.73.0] - 2026-05-04
+
+### New Features
+
+- **Xiaomi MiMo API billing and regional Token Plan providers** - `xiaomi` now uses API billing, with separate `xiaomi-token-plan-{cn,ams,sgp}` providers. See [docs/providers.md#api-keys](docs/providers.md#api-keys) and [README.md#providers--models](README.md#providers--models). ([#4112](https://github.com/badlogic/pi-mono/pull/4112) by [@Phoen1xCode](https://github.com/Phoen1xCode))
+- **Incremental bash output streaming** - Bash tool output now appears while commands run instead of only after completion. ([#4145](https://github.com/badlogic/pi-mono/issues/4145))
+- **Compact read rendering** - Interactive `read` output for Pi docs, context files, and skills is collapsed by default and shows selected line ranges.
+
+### Breaking Changes
+
+- Switched the built-in `xiaomi` provider from Token Plan AMS to Xiaomi's API billing endpoint, and renamed its `/login` display from "Xiaomi MiMo Token Plan" to "Xiaomi MiMo". `XIAOMI_API_KEY` now refers to the API billing key from [platform.xiaomimimo.com](https://platform.xiaomimimo.com). Users on Token Plan should switch to the appropriate `xiaomi-token-plan-*` provider and set the corresponding env var ([#4112](https://github.com/badlogic/pi-mono/pull/4112) by [@Phoen1xCode](https://github.com/Phoen1xCode)).
+
+### Added
+
+- Added three Xiaomi MiMo Token Plan regional providers visible in `/login`: `xiaomi-token-plan-cn` (`XIAOMI_TOKEN_PLAN_CN_API_KEY`), `xiaomi-token-plan-ams` (`XIAOMI_TOKEN_PLAN_AMS_API_KEY`), `xiaomi-token-plan-sgp` (`XIAOMI_TOKEN_PLAN_SGP_API_KEY`). Each defaults to `mimo-v2.5-pro` ([#4112](https://github.com/badlogic/pi-mono/pull/4112) by [@Phoen1xCode](https://github.com/Phoen1xCode)).
+
+### Changed
+
+- Changed `read` tool rendering to collapse Pi documentation, AGENTS/CLAUDE context files, and `SKILL.md` contents by default in interactive output.
+
+### Fixed
+
+- Fixed generated OpenAI-compatible model metadata for Qwen 3.5/3.6 and MiniMax M2.7, so those models work through the built-in provider catalog ([#4110](https://github.com/badlogic/pi-mono/pull/4110) by [@jsynowiec](https://github.com/jsynowiec)).
+- Fixed Bedrock Claude Opus 4.7 `xhigh` thinking requests by preserving the provider's native effort value.
+- Fixed OpenAI Codex WebSocket transport to fall back to SSE when setup fails before streaming starts, and surface transport diagnostics in the assistant message ([#4133](https://github.com/badlogic/pi-mono/issues/4133)).
+- Fixed OpenAI Codex WebSocket transport keeping `--print` and JSON mode processes alive after the response by closing cached WebSocket sessions during session shutdown ([#4103](https://github.com/badlogic/pi-mono/issues/4103)).
+- Fixed compact `read` tool calls to render directly and include selected line ranges in interactive output.
+- Fixed interactive sessions to exit when terminal input is lost instead of continuing in a broken state.
+- Fixed bash tool output to stream incrementally while commands run instead of waiting for command completion ([#4145](https://github.com/badlogic/pi-mono/issues/4145)).
+- Fixed selector and autocomplete fuzzy ranking to prioritize exact matches.
+
+## [0.72.1] - 2026-05-02
+
+## [0.72.0] - 2026-05-01
+
+### New Features
+
+- **Xiaomi MiMo Token Plan provider** - New Anthropic-compatible provider with `XIAOMI_API_KEY` auth, default model (`mimo-v2.5-pro`), and `/login` display. See [docs/providers.md](docs/providers.md). ([#4005](https://github.com/badlogic/pi-mono/pull/4005) by [@Phoen1xCode](https://github.com/Phoen1xCode)).
+- **Model thinking level metadata** - Models can now declare which thinking levels they support via `thinkingLevelMap`, replacing the old `reasoningEffortMap`. See [docs/models.md#thinking-level-map](docs/models.md#thinking-level-map) and [docs/custom-provider.md](docs/custom-provider.md). ([#3208](https://github.com/badlogic/pi-mono/issues/3208)).
+- **Custom provider base URL overrides** - `pi.registerProvider()` now respects per-model `baseUrl` settings. See [docs/custom-provider.md](docs/custom-provider.md). ([#4063](https://github.com/badlogic/pi-mono/issues/4063)).
+- **Post-turn stop callback** - Agent loop can now exit gracefully after a completed turn via `shouldStopAfterTurn`. See [`packages/agent/README.md`](https://github.com/badlogic/pi-mono/blob/main/packages/agent/README.md).
+- **Self-update detection fix** - `pi` now correctly identifies and applies available updates. ([#3942](https://github.com/badlogic/pi-mono/issues/3942), [#3980](https://github.com/badlogic/pi-mono/issues/3980), [#3922](https://github.com/badlogic/pi-mono/issues/3922)).
+
+### Breaking Changes
+
+- Replaced `compat.reasoningEffortMap` in `models.json` and `pi.registerProvider()` model definitions with model-level `thinkingLevelMap` ([#3208](https://github.com/badlogic/pi-mono/issues/3208)). Migration: move old mappings from `compat.reasoningEffortMap` to `thinkingLevelMap`. Use string values for provider-specific thinking values and `null` for unsupported pi levels that should be hidden and skipped by cycling. See `docs/models.md#thinking-level-map` and `docs/custom-provider.md`.
+
+### Added
+
+- Added Xiaomi MiMo Token Plan provider support with `XIAOMI_API_KEY`, default model resolution, `/login` display support, and provider documentation ([#4005](https://github.com/badlogic/pi-mono/pull/4005) by [@Phoen1xCode](https://github.com/Phoen1xCode)).
+- Added model-level `thinkingLevelMap` support in `models.json` and `pi.registerProvider()`, allowing models to expose only the thinking levels they actually support ([#3208](https://github.com/badlogic/pi-mono/issues/3208)).
+- Added `shouldStopAfterTurn` agent loop callback for post-turn stop control, inherited from `@mariozechner/pi-agent-core`. See [`packages/agent/README.md`](https://github.com/badlogic/pi-mono/blob/main/packages/agent/README.md).
+
+### Fixed
+
+- Fixed the default transport setting to use `auto`, allowing OpenAI Codex to use cached WebSocket context when available ([#4083](https://github.com/badlogic/pi-mono/issues/4083)).
+- Fixed `pi.registerProvider()` to honor per-model `baseUrl` overrides ([#4063](https://github.com/badlogic/pi-mono/issues/4063)).
+- Fixed self-update detection so `pi` correctly identifies when a newer version is available and applies updates ([#3942](https://github.com/badlogic/pi-mono/issues/3942), [#3980](https://github.com/badlogic/pi-mono/issues/3980), [#3922](https://github.com/badlogic/pi-mono/issues/3922)).
+
+## [0.71.1] - 2026-05-01
+
+### Added
+
+- Added `websocket-cached` to the transport setting options for the OpenAI Codex provider used with ChatGPT subscription auth. This keeps the same WebSocket open for a session and, after the first request, sends only the new conversation items instead of resending the full chat history when possible.
+
+## [0.71.0] - 2026-04-30
+
+### Breaking Changes
+
+- Removed built-in Google Gemini CLI and Google Antigravity support. Existing configurations using those providers must switch to another supported provider.
+
+### New Features
+
+- Cloudflare AI Gateway provider support with `CLOUDFLARE_API_KEY`/`CLOUDFLARE_ACCOUNT_ID`/`CLOUDFLARE_GATEWAY_ID`, default model resolution, and `/login` display. See [docs/providers.md#cloudflare-ai-gateway](docs/providers.md#cloudflare-ai-gateway). ([#3856](https://github.com/badlogic/pi-mono/pull/3856) by [@mchenco](https://github.com/mchenco)).
+- Moonshot AI provider support with `MOONSHOT_API_KEY`, default model resolution, and `/login` display.
+- Mistral Medium 3.5 built-in model support. See [docs/providers.md#api-keys](docs/providers.md#api-keys). ([#4009](https://github.com/badlogic/pi-mono/pull/4009) by [@technocidal](https://github.com/technocidal)).
+- Extension APIs can replace finalized `message_end` messages, wrap custom editor factories via `ctx.ui.getEditorComponent()`, and observe thinking level changes. See [docs/extensions.md#message_start--message_update--message_end](docs/extensions.md#message_start--message_update--message_end), [docs/extensions.md#widgets-status-and-footer](docs/extensions.md#widgets-status-and-footer), and [docs/extensions.md#thinking_level_select](docs/extensions.md#thinking_level_select).
+- `PI_CODING_AGENT_SESSION_DIR` configures session storage from the environment. See [docs/usage.md#environment-variables](docs/usage.md#environment-variables).
+
+### Added
+
+- Added Cloudflare AI Gateway as a built-in provider with `CLOUDFLARE_API_KEY`/`CLOUDFLARE_ACCOUNT_ID`/`CLOUDFLARE_GATEWAY_ID` setup, default model resolution, `/login` display support, and provider documentation ([#3856](https://github.com/badlogic/pi-mono/pull/3856) by [@mchenco](https://github.com/mchenco)).
+- Added Moonshot AI as a built-in provider with `MOONSHOT_API_KEY` setup, default model resolution, and `/login` display support.
+- Added Mistral Medium 3.5 built-in model support via `@mariozechner/pi-ai` ([#4009](https://github.com/badlogic/pi-mono/pull/4009) by [@technocidal](https://github.com/technocidal)).
+- Added routed OpenAI-compatible response model metadata in assistant messages, so providers such as OpenRouter can expose the concrete model used ([#3968](https://github.com/badlogic/pi-mono/pull/3968) by [@purrgrammer](https://github.com/purrgrammer)).
+- Added `PI_CODING_AGENT_SESSION_DIR` as an environment equivalent to `--session-dir` ([#4027](https://github.com/badlogic/pi-mono/issues/4027)).
+- Added `message_end` extension result support for replacing finalized messages, enabling extensions to override assistant usage cost ([#3982](https://github.com/badlogic/pi-mono/issues/3982)).
+- Added top-level `name` support to `pi.registerProvider()` so extension-registered providers can show a friendly name in `/login` ([#3956](https://github.com/badlogic/pi-mono/issues/3956)).
+- Added `ctx.ui.getEditorComponent()` so extensions can wrap the currently configured custom editor factory ([#3935](https://github.com/badlogic/pi-mono/issues/3935)).
+- Added a `thinking_level_select` extension event for observing thinking level changes ([#3888](https://github.com/badlogic/pi-mono/issues/3888)).
+
+### Fixed
+
+- Fixed WSL clipboard image paste by passing the PowerShell save path directly instead of through a custom environment variable ([#2469](https://github.com/badlogic/pi-mono/issues/2469)).
+- Fixed Google Vertex Gemini 3 tool call replay for unsigned tool calls ([#4032](https://github.com/badlogic/pi-mono/issues/4032)).
+- Fixed blocked `edit` tool results rendering the rejection reason twice after interactive extension confirmation ([#3830](https://github.com/badlogic/pi-mono/issues/3830)).
+- Fixed extension-triggered thinking level changes refreshing the interactive editor border immediately ([#3888](https://github.com/badlogic/pi-mono/issues/3888)).
+- Fixed the coding-agent README See Also link to point at `@mariozechner/pi-agent-core` ([#4023](https://github.com/badlogic/pi-mono/issues/4023)).
+- Fixed `grep` and `find` tool argument injection for flag-like search patterns ([#4018](https://github.com/badlogic/pi-mono/issues/4018)).
+- Fixed PowerShell shell command output on Windows by only spawning detached processes on Unix ([#4013](https://github.com/badlogic/pi-mono/pull/4013) by [@picasso250](https://github.com/picasso250)).
+- Fixed Bun package manager `node_modules` discovery when `npmCommand` is configured to use Bun ([#3998](https://github.com/badlogic/pi-mono/pull/3998) by [@thirtythreeforty](https://github.com/thirtythreeforty)).
+- Fixed edit and edit-preview access failures to report filesystem errors correctly ([#3955](https://github.com/badlogic/pi-mono/pull/3955) by [@rwachtler](https://github.com/rwachtler)).
+- Fixed `ProcessTerminal` sizing to use `COLUMNS` and `LINES` before falling back to 80x24 ([#4004](https://github.com/badlogic/pi-mono/issues/4004)).
+- Updated `@anthropic-ai/sdk` to clear GHSA-p7fg-763f-g4gf audit findings ([#3992](https://github.com/badlogic/pi-mono/issues/3992)).
+- Updated `@mariozechner/clipboard` to an attested release so package managers with trust policies do not reject installs ([#3946](https://github.com/badlogic/pi-mono/issues/3946)).
+- Fixed project context discovery to load `AGENTS.MD` files in addition to `AGENTS.md` ([#3949](https://github.com/badlogic/pi-mono/issues/3949)).
+- Fixed `/handoff` to use compacted session context instead of pre-compaction raw messages ([#3945](https://github.com/badlogic/pi-mono/issues/3945)).
+- Fixed DeepSeek V4 Flash `xhigh` thinking support so requests map to DeepSeek's `max` reasoning effort ([#3944](https://github.com/badlogic/pi-mono/issues/3944)).
+- Fixed Anthropic streams that end before `message_stop` to be treated as errors instead of successful partial responses ([#3936](https://github.com/badlogic/pi-mono/issues/3936)).
+- Fixed generated OpenAI-compatible DeepSeek V4 reasoning compatibility outside the direct DeepSeek provider ([#3940](https://github.com/badlogic/pi-mono/issues/3940)).
+- Fixed idle follow-up submission to clear the editor like normal message submission ([#3926](https://github.com/badlogic/pi-mono/issues/3926)).
+- Fixed editor rendering artifacts for Thai Sara Am and Lao AM vowel characters ([#3904](https://github.com/badlogic/pi-mono/issues/3904)).
+- Fixed DeepSeek V4 Flash and V4 Pro pricing metadata to match current official rates ([#3910](https://github.com/badlogic/pi-mono/issues/3910)).
+- Updated the sandbox extension example lockfile to resolve the vulnerable `lodash-es` transitive dependency ([#3901](https://github.com/badlogic/pi-mono/issues/3901)).
+- Fixed DeepSeek prompt cache hits to be tracked from OpenAI-compatible usage responses ([#3880](https://github.com/badlogic/pi-mono/issues/3880)).
+
+### Removed
+
+- Removed the discontinued Qwen CLI OAuth custom provider extension example ([#3832](https://github.com/badlogic/pi-mono/pull/3832) by [@4h9fbZ](https://github.com/4h9fbZ)).
+- Removed Google Gemini CLI and Google Antigravity built-in login, default model, documentation, and example extension support.
+
+## [0.70.6] - 2026-04-28
+
+### New Features
+
+- Cloudflare Workers AI provider support with `CLOUDFLARE_API_KEY`/`CLOUDFLARE_ACCOUNT_ID` setup. See [docs/providers.md#api-keys](docs/providers.md#api-keys). ([#3851](https://github.com/badlogic/pi-mono/pull/3851) by [@mchenco](https://github.com/mchenco))
+- Pi update checks now use `pi.dev` and identify Pi with a `pi/<version>` user agent. See [docs/packages.md](docs/packages.md). ([#3877](https://github.com/badlogic/pi-mono/pull/3877) by [@mitsuhiko](https://github.com/mitsuhiko))
+
+### Added
+
+- Added Cloudflare Workers AI as a built-in provider with `CLOUDFLARE_API_KEY`/`CLOUDFLARE_ACCOUNT_ID` setup, default model resolution, `/login` support, and provider documentation ([#3851](https://github.com/badlogic/pi-mono/pull/3851) by [@mchenco](https://github.com/mchenco)).
+
+### Changed
+
+- Changed Pi version checks to identify Pi with a `pi/<version>` user agent ([#3877](https://github.com/badlogic/pi-mono/pull/3877) by [@mitsuhiko](https://github.com/mitsuhiko)).
+
+### Fixed
+
+- Fixed config selector scroll indicators to show item counts instead of line counts ([#3820](https://github.com/badlogic/pi-mono/pull/3820) by [@aliou](https://github.com/aliou)).
+- Fixed exported HTML to escape embedded image data and session metadata, preventing crafted session content from injecting markup ([#3819](https://github.com/badlogic/pi-mono/pull/3819) by [@justinpbarnett](https://github.com/justinpbarnett), [#3883](https://github.com/badlogic/pi-mono/pull/3883) by [@justinpbarnett](https://github.com/justinpbarnett)).
+- Fixed Bun-based package manager startup by locating global `node_modules` relative to Bun's install layout ([#3861](https://github.com/badlogic/pi-mono/pull/3861) by [@thirtythreeforty](https://github.com/thirtythreeforty)).
+- Fixed Bedrock inference profile capability checks by normalizing profile ARNs to the underlying model name.
+- Fixed file discovery to fall back to `fdfind` when `fd` is unavailable.
+- Fixed `pi update` to skip self-update reinstalls when the installed version is already current ([#3853](https://github.com/badlogic/pi-mono/issues/3853)).
+- Fixed Cloudflare Workers AI attribution headers to honor the install telemetry setting.
+- Fixed `pi update --self` detection and execution for Windows package-manager shim installs, including symlinked global package roots, and print the manual fallback command when self-update fails ([#3857](https://github.com/badlogic/pi-mono/issues/3857)).
+
+## [0.70.5] - 2026-04-27
+
+### Fixed
+
+- Fixed HTML export preserving ANSI-renderer trailing padding as extra blank wrapped lines.
+
+## [0.70.4] - 2026-04-27
+
+### Fixed
+
+- Fixed packaged `pi` startup failing because the session selector imported a source-only utility path.
+
+## [0.70.3] - 2026-04-27
+
+### New Features
+
+- `pi update` can now update pi itself in addition to installed pi packages. See [docs/packages.md](docs/packages.md). ([#3680](https://github.com/badlogic/pi-mono/pull/3680) by [@mitsuhiko](https://github.com/mitsuhiko))
+- Azure Cognitive Services endpoint support for Azure OpenAI Responses deployments. See [docs/providers.md#api-keys](docs/providers.md#api-keys). ([#3799](https://github.com/badlogic/pi-mono/pull/3799) by [@marcbloech](https://github.com/marcbloech))
+- Suppressible Anthropic extra-usage billing warning via `warnings.anthropicExtraUsage` in `/settings`. See [docs/settings.md](docs/settings.md). ([#3808](https://github.com/badlogic/pi-mono/issues/3808))
+- Extension-controlled working row visibility via `ctx.ui.setWorkingVisible()`, allowing extensions to hide the built-in loader row and render custom working state. See [docs/extensions.md](docs/extensions.md) and [examples/extensions/border-status-editor.ts](examples/extensions/border-status-editor.ts). ([#3674](https://github.com/badlogic/pi-mono/issues/3674))
+
+### Added
+
+- Added `pi update` support for updating pi itself in addition to installed pi packages ([#3680](https://github.com/badlogic/pi-mono/pull/3680) by [@mitsuhiko](https://github.com/mitsuhiko)).
+- Added Azure Cognitive Services endpoint support for Azure OpenAI Responses base URLs ([#3799](https://github.com/badlogic/pi-mono/pull/3799) by [@marcbloech](https://github.com/marcbloech)).
+- Added `warnings.anthropicExtraUsage` and a `/settings` warnings submenu to suppress the Anthropic extra usage billing warning ([#3808](https://github.com/badlogic/pi-mono/issues/3808))
+- Added `ctx.ui.setWorkingVisible()` so extensions can hide the built-in interactive working loader row without reserving layout space, plus a border-status editor example that moves working state into a custom editor border ([#3674](https://github.com/badlogic/pi-mono/issues/3674))
+
+### Fixed
+
+- Fixed duplicate printable characters from Kitty keyboard protocol CSI-u plus raw character input on layouts such as Italian ([#3780](https://github.com/badlogic/pi-mono/issues/3780)).
+- Fixed API-key environment discovery and Bun startup to fall back to `/proc/self/environ` when Bun's sandbox leaves `process.env` empty ([#3801](https://github.com/badlogic/pi-mono/pull/3801) by [@mdsjip](https://github.com/mdsjip)).
+- Fixed Bun sandboxed package-manager commands when `process.env` is empty ([#3807](https://github.com/badlogic/pi-mono/pull/3807) by [@mdsjip](https://github.com/mdsjip)).
+- Fixed symlinked packages, resources, skills, and sessions being duplicated in selectors and loaders ([#3818](https://github.com/badlogic/pi-mono/pull/3818) by [@aliou](https://github.com/aliou)).
+- Fixed Bedrock prompt-caching and adaptive-thinking capability checks for inference profile ARNs ([#3527](https://github.com/badlogic/pi-mono/pull/3527) by [@anirudhmarc](https://github.com/anirudhmarc)).
+- Fixed OpenAI Codex Responses default verbosity to `low` when no verbosity is specified.
+- Stopped sending empty `tools` arrays to providers that reject them when tools are disabled ([#3650](https://github.com/badlogic/pi-mono/pull/3650) by [@HQidea](https://github.com/HQidea)).
+- Fixed Anthropic SSE parsing to ignore unknown proxy events such as OpenAI-style `done` terminators ([#3708](https://github.com/badlogic/pi-mono/issues/3708)).
+- Fixed provider registration with override-only `models.json` entries to preserve built-in model lists ([#3651](https://github.com/badlogic/pi-mono/issues/3651)).
+- Fixed `/login` to show auth supplied by `models.json` provider definitions.
+- Fixed HTML export whitespace around extension-rendered tool output and expandable output hints.
+- Fixed bash executor temp output streams leaking file descriptors when output was truncated by line count ([#3786](https://github.com/badlogic/pi-mono/issues/3786))
+- Fixed extension `pi.setSessionName()` updates to refresh the interactive terminal title immediately ([#3686](https://github.com/badlogic/pi-mono/issues/3686))
+- Fixed `/tree` cancellation via `session_before_tree` leaving the session stuck in compaction state ([#3688](https://github.com/badlogic/pi-mono/issues/3688))
+- Fixed Escape interrupt handling when extensions hide the built-in working loader row ([#3674](https://github.com/badlogic/pi-mono/issues/3674))
+- Fixed coding-agent test expectations for current default models and missing-auth guidance.
+- Fixed long local-LLM SSE streams aborting at 5 minutes with `UND_ERR_BODY_TIMEOUT` by disabling undici `bodyTimeout`/`headersTimeout` on the global dispatcher; provider SDKs continue to enforce their own deadlines via `retry.provider.timeoutMs` ([#3715](https://github.com/badlogic/pi-mono/issues/3715))
+
+## [0.70.2] - 2026-04-24
+
+### Fixed
+
+- Fixed provider retry/timeout forwarding to omit undefined provider request controls, avoiding downstream SDK validation errors such as `timeout must be an integer` when `retry.provider.timeoutMs` is not configured ([#3627](https://github.com/badlogic/pi-mono/issues/3627))
+
+## [0.70.1] - 2026-04-24
+
+### New Features
+
+- DeepSeek provider support with V4 Flash/Pro models and `DEEPSEEK_API_KEY` authentication. See [README.md#providers--models](README.md#providers--models) and [docs/providers.md#api-keys](docs/providers.md#api-keys).
+- Provider request timeout/retry controls via `retry.provider.{timeoutMs,maxRetries,maxRetryDelayMs}`, useful for long-running local inference and provider SDK retry behavior. See [docs/settings.md#retry](docs/settings.md#retry). ([#3627](https://github.com/badlogic/pi-mono/issues/3627))
+
+### Added
+
+- Added DeepSeek to built-in provider setup, default model resolution, and provider documentation.
+
+### Fixed
+
+- Fixed `/copy` to avoid unbounded OSC 52 writes and clipboard races that could break terminal rendering or panic the native clipboard addon ([#3639](https://github.com/badlogic/pi-mono/issues/3639))
+- Fixed extension flag docs to show `pi.getFlag()` using registered flag names without the CLI `--` prefix ([#3614](https://github.com/badlogic/pi-mono/issues/3614))
+- Fixed provider retry/timeout settings wiring by adding `retry.provider.{timeoutMs,maxRetries,maxRetryDelayMs}`, migrating legacy `retry.maxDelayMs`, and forwarding provider controls into `streamSimple` request options ([#3627](https://github.com/badlogic/pi-mono/issues/3627))
+- Fixed Windows git package installs to bypass `cmd.exe` for native git commands, so install paths containing spaces no longer break `pi install git:...` with `fatal: Too many arguments` ([#3642](https://github.com/badlogic/pi-mono/issues/3642))
+- Fixed DeepSeek V4 session replay 400 errors by sending DeepSeek-compatible thinking controls and replayed assistant `reasoning_content` fields ([#3636](https://github.com/badlogic/pi-mono/issues/3636))
+- Fixed GPT-5.5 generated context window metadata to use the observed 272k limit.
+- Fixed CSI-u Ctrl+letter decoding inside bracketed paste, so pasted modified-key escape sequences no longer become literal editor text ([#3623](https://github.com/badlogic/pi-mono/pull/3623) by [@Exrun94](https://github.com/Exrun94))
+
 ## [0.70.0] - 2026-04-23
 
 ### New Features