Skill slash commands store a structural <skill>...</skill> wrapper in raw
user messages. The TUI uses parseSkillBlock() to split this into separate
SkillInvocationMessageComponent and UserMessageComponent siblings, but the
HTML export renderer passed the full raw text through markdown, causing
broken/dangling XML tags to appear in exported HTML.
Add parseSkillBlock() to the export template and render skill-invocation
and user-message as separate sibling blocks:
- Sidebar tree shows skill name + user prompt separately
- Content area shows a clickable skill-invocation block (collapsed by
default, markdown content on expand) followed by the user message
- Copy-link button preserved on the wrapper element
- Toggle tools (O key) expands/collapses skill invocations alongside
compaction and tool output blocks
The @mariozechner/clipboard native addon uses clipboard-rs, which is
X11-only and does not retain selection ownership after set_text resolves.
On Wayland-only compositors (Hyprland, Niri, ...) /copy reported success
without populating the clipboard. Skip the native addon on Linux and let
wl-copy/xclip/xsel handle text writes; they properly daemonize.
closes#4177
* feat(coding-agent): allow comments and trailing commas in models.json
Run user-supplied models.json through a small `stripJsonComments` helper
before JSON.parse so users can annotate their config and leave trailing
commas without breaking the loader.
Co-Authored-By: julien-agent <Agents+cyolo@huggingface.co>
* fix(coding-agent): strip comments before trailing commas in models.json
The single-pass regex couldn't see a trailing comma when a `//` comment sat
between the comma and its closer. Split into two passes: strip comments
first, then strip trailing commas on the cleaned input.
Co-Authored-By: julien-agent <Agents+cyolo@huggingface.co>
---------
Co-authored-by: julien-agent <Agents+cyolo@huggingface.co>
Render compact read classifications in the call row and leave the collapsed result row empty. The previous implementation used shared renderer state to let renderResult hide renderCall, which leaked an internal ReadRenderState type through the tool definition and coupled two render phases unnecessarily. The call renderer has all context needed to choose the compact presentation itself.
Built-in `xiaomi` provider now targets the API billing endpoint (https://api.xiaomimimo.com/anthropic) — a single stable URL for keys issued at platform.xiaomimimo.com. The Token Plan endpoints are exposed as three sibling providers, each with its own env var:
- 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
BREAKING CHANGE: users who previously set XIAOMI_API_KEY against the Token Plan AMS endpoint must move to xiaomi-token-plan-ams and set XIAOMI_TOKEN_PLAN_AMS_API_KEY. This also resolves the 401 reported by on #4005, where a platform.xiaomimimo.com key fails against the Token Plan endpoint.
closes#4082
* feat(ai): add Cloudflare AI Gateway as a provider
Routes through Cloudflare's Unified API (`/compat`) for Workers AI and
Anthropic models, and through the provider-specific `/openai` subpath
for OpenAI models so reasoning models (gpt-5.x, o-series) can hit
`/v1/responses` natively. Once `/compat` adds Responses-API support,
the OpenAI subpath can be folded back in.
Catalog layout:
workers-ai/@cf/... -> openai-completions, gateway/.../compat
anthropic/... -> openai-completions, gateway/.../compat
<native-id> -> openai-responses, gateway/.../openai
(gpt-5.1, claude-... no, sorry: gpt-5.x and o-series only;
prefix stripped because the OpenAI SDK posts native ids)
Touches:
packages/ai/src/types.ts add cloudflare-ai-gateway to KnownProvider
packages/ai/src/env-api-keys.ts map to CLOUDFLARE_API_KEY
packages/ai/src/providers/cloudflare.ts add CLOUDFLARE_AI_GATEWAY_COMPAT_BASE_URL
and CLOUDFLARE_AI_GATEWAY_OPENAI_BASE_URL
packages/ai/src/providers/openai-responses.ts one-line dispatch through resolveCloudflareBaseUrl
(matches what openai-completions.ts already does)
packages/ai/scripts/generate-models.ts branch openai/* vs workers-ai/anthropic/*
packages/ai/src/models.generated.ts spliced 34 entries
packages/ai/test/stream.test.ts 3 e2e blocks (one per upstream)
packages/coding-agent/* defaultModelPerProvider, login, env docs,
README, providers.md
Verified end-to-end against a real Cloudflare account with unified
billing: 9/9 e2e tests pass across all three upstreams (Workers AI
Kimi K2.6, OpenAI gpt-5.1 reasoning, Anthropic claude-sonnet-4-5).
* refactor(ai): move AI Gateway User-Agent and per-route session-affinity flag to catalog
Mirrors the same per-model metadata refactor done for Workers AI in the
parent branch. All cloudflare-ai-gateway entries get the User-Agent
header. Only workers-ai/* gateway entries set
`compat.sendSessionAffinityHeaders: true` because the gateway
forwards that header to the underlying Workers AI runtime; anthropic/*
upstream and openai/* (openai-responses) don't use it.
packages/ai/scripts/generate-models.ts: emit headers (always) and
per-upstream compat (workers-ai only) on each cloudflare-ai-gateway
entry.
packages/ai/src/models.generated.ts: re-spliced 35 entries with
headers + conditional compat.
Behavior unchanged - 9/9 e2e tests pass across all three upstream
families.
* fix(ai): align AI Gateway with telemetry-aware UA helper
Adapts to badlogic/pi-mono#3851's follow-up fix ("honor telemetry for
Cloudflare attribution headers", fbb5eed) which moved the
'User-Agent: pi-coding-agent' header out of per-model catalog metadata
and into a centralized telemetry-honoring helper
(coding-agent/src/core/sdk.ts:getAttributionHeaders).
- packages/coding-agent/src/core/sdk.ts: extend the cloudflare branch of
getAttributionHeaders to also match cloudflare-ai-gateway and
gateway.ai.cloudflare.com.
- packages/ai/scripts/generate-models.ts and src/models.generated.ts:
drop 'headers' from the 35 cloudflare-ai-gateway entries (constant
CLOUDFLARE_STATIC_HEADERS no longer exists). Per-route
compat.sendSessionAffinityHeaders is unchanged.
End-to-end behavior unchanged: 9/9 tests still pass across all three
upstream families (Workers AI, Anthropic, OpenAI Responses).
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
On Windows, spawn(..., { detached: true }) prevents pwsh.exe (PowerShell) from
producing any stdout/stderr through pipe streams. This is because detached creates
a new process group which breaks pwsh's console host communication.
bash.exe and other cygwin/msys2 shells are unaffected by detached: true, but
they don't need it either -- on Windows, killProcessTree() already uses
taskkill /F /T /PID which kills the process tree by PID regardless of
whether the process was spawned detached.
The detached flag only matters on Unix, where kill(-pid, SIGKILL) requires a
process group that is only created via detached: true.
Fixes#4012
* fix(coding-agent): report edit access failures correctly closes#3894
- classify edit and edit-preview access errors by errno
- add regressions for missing, permission, and fallback cases
- document the fix in the coding-agent changelog
* chore: get rid of CHANGELOG.md entry
* refactor(coding-agent): apply review suggestions - use single error msg
* refactor(coding-agent): clean up test cases
* Revert "fix(coding-agent): use alternate logic to find Bun's node_modules (#3861)"
This reverts commit c241c6d6d0. The logic
is faulty: the original strategy of looking for node_modules by asking
the package manager is not incorrect even on bun. Instead, it should
learn a different method of asking the package manager for node_modules
when the *package manager* is bun, not the *runtime*.
* feat(coding-agent): detect bun as package manager and use alternate root query
When `"npmCommand": ["bun"]` is configured in settings.json, pi fails to
start because it invokes `bun root -g`, which doesn't exist:
error: Failed to run bun root -g: error: Script not found "root"
Add a (simple) check for Bun being used as package manager, and instead
build the relative path starting from Bun's bin directory.
