This adds cache-friendly dynamic tool loading anchored to tool results. Purely additive active-tool changes are recorded with `addedToolNames`, allowing supported Anthropic and OpenAI Responses models to load tool definitions at the point they become available instead of placing them in the cached prompt prefix.
It retains safe fallback behavior for unsupported models and non-additive changes but it will wipe caches.
* feat(coding-agent): add before_provider_headers extension hook
Extensions can already rewrite the request payload through before_provider_request, but there is no way to adjust the outgoing HTTP
headers of a provider call. This hook fills that gap for cases like request tracing, session correlation, or tenant routing.
Handlers mutate the headers map in place - a null value deletes a header - and the return value is ignored, so a handler cannot accidentally drop auth or attribution headers by
forgetting to spread.
* docs(coding-agent): document before_provider_headers extension hook
Add the before_provider_headers section and lifecycle-diagram entry to
extensions.md; drop the now-superseded proposal file.
session_before_compact and session_compact now carry
reason ("manual" | "threshold" | "overflow") and willRetry, matching
what the RPC protocol already exposes via auto_compaction_start/end.
Extensions can now distinguish manual /compact from threshold
auto-compaction and overflow recovery through the public API instead
of monkeypatching AgentSession internals.
When an extension queues a follow-up during `agent_end` it
gets stuck on the follow-up queue until after the next user
message.
Add a hasQueuedMessages() check to _handlePostAgentRun
so the existing while/continue loop drains them.
- One-line fix in _handlePostAgentRun
- Integration test in agent-session-queue
- git-merge-and-resolve example extension with tests
Add streamingBehavior to InputEvent so extensions can distinguish
idle prompts from mid-stream steers and queued follow-ups.
- Add streamingBehavior field to InputEvent type
- Thread it through ExtensionRunner.emitInput() and AgentSession.prompt()
- Add streaming-aware input gate example with tests
- Document in extensions.md
The notify() API only accepts "info" | "warning" | "error" — "success"
was a copy-paste error in the example.
Co-Authored-By: julien-agent <Agents+cyolo@huggingface.co>
promptGuidelines bullets are appended flat to the Guidelines section
with no tool name prefix. Using 'Use this tool when...' is ambiguous
because the LLM cannot tell which tool 'this' refers to. Updated docs
and examples to use explicit tool names instead.
Mario Zechner