feat: inject and steer new guidance into the running turn

[mulyawansentosa]

Summary

Closes #113, #117.

While a turn was running, Enter was rejected with "wait for the current response or press esc
to interrupt", so sending a follow-up instruction meant waiting for the whole turn or
interrupting the agent. This PR makes new instructions flow into the work that is already
running:

1. Mid-turn injection — a prompt sent while a turn runs becomes a user message that is read
   before the model's next step of that turn.
2. Steering a streaming answer — if the model is still writing an answer, that answer is cut
   short so the prompt is read immediately; what it already wrote stays in the conversation.

How it works

SessionManager keeps a per-session FIFO queue of supplemental prompts
(addSupplementaryPrompt, max 10). Before every LLM call of the running turn the queue is
drained and each entry becomes a user message with its images and selected skills:

user:      install nginx
assistant: <tool_calls>              ← working
tool:      <result>
user:      stop, use apache instead     ← guidance, read by the next LLM call
assistant: <revised plan>

When the model is streaming an answer, steerActiveSession() aborts that single request:

user:      explain how the deploy works
assistant: The deploy runs in three stag…      ← cut short here
user:      no, just tell me the rollback step   ← read straight away
assistant: <answer to the new instruction>

Details:

• The partial answer is kept as an assistant message with meta.interrupted, so the model (and
  the transcript) still know what it had said when the user changed direction.
• Steering only targets the model stream: tools are never interrupted, so a running
  npm install finishes and the guidance is injected at the next request boundary.
• A steered answer is not an interruption: the turn continues, the status stays completed, and
  the aborted request is not retried.
• If a turn would otherwise end with guidance still queued, the loop stays alive for one more
  iteration instead of deferring the guidance to a later, unrelated turn.
• Esc still interrupts the whole turn.
• Guidance is not injected while the session waits for the user (an ask_user_question answer or
  a permission decision), so it can never be consumed as that answer.
• The prompt is stored verbatim with role: "user" and meta.isSupplementary. user was chosen
  over a system reminder from the original sketch because it is the strongest signal for
  superseding earlier instructions and it carries images natively.

Configuration

steerMode controls what happens when a prompt arrives while the model is writing:

Value	Behaviour
interrupt (default)	Cut the streaming answer short, keep its text, read the prompt now
queue	Wait and inject the prompt at the next LLM call of the turn

Running tools are never interrupted in either mode.

UI

  guidance 1. just tell me the rollback step
> _
  esc to interrupt · ctrl+c to cancel input · 1 guidance queued · backspace to remove

Injected guidance is labelled in the transcript (✧ Guidance sent while the turn was running),
and so is a cut-short answer (— superseded by your guidance). Backspace on an empty prompt
removes the last entry that has not been injected yet.

Changes

File	Change
packages/core/src/session.ts	supplemental queue, drain before each request, per-request steer signal, keep the loop alive while guidance is pending, MessageMeta.isSupplementary / .interrupted
packages/core/src/common/llm-retry.ts	LlmSteeredError carrying the partial answer
packages/core/src/settings.ts, index.ts	steerMode setting and exports
packages/cli/src/ui/views/App.tsx	hands prompts typed while busy to the session, mirrors the pending queue, steers when configured, removes the last entry
packages/cli/src/ui/views/PromptInput.tsx	lists pending guidance, keeps Enter usable while busy, Backspace removes the last entry
packages/cli/src/ui/components/MessageView/*	labels injected guidance and cut-short answers
core tests	9 tests for queue semantics, mid-flight injection, steering and the no-op case; settings test for steerMode
cli tests	4 Ink integration tests + 3 formatting tests
docs	configuration.md/_en.md table and section, README key tables

Testing

• npm run check — type check, ESLint and Prettier all pass
• npm test — 333 CLI + 392 core + 59 VS Code tests pass
• Core tests assert the actual request payloads, i.e. that guidance added while a request is in
  flight shows up in the next request of the same turn, and that a steered answer appears in the
  follow-up request together with the guidance.

中文说明

AI 正在回复时，Enter 不再被拒绝：消息会作为补充指引，在本轮下一次 LLM 调用前作为 user 消息
（含图片与 skills）注入，模型因此能结合已完成的工作修改甚至推翻之前的指令。如果模型正在流式输出
回答，该回答会被截断，已生成内容保留在对话中（标记 meta.interrupted），新指令立即被读取；正在
执行的命令不会被中断，steering 只作用于模型输出流。可用 steerMode 选择 "interrupt"（默认，截断
并立即读取）或 "queue"（等到下次请求边界再注入）。等待 ask_user_question 或权限确认时不会注入，
Esc 仍会中断整个轮次。

[mulyawansentosa]

Opened from the wrong fork by mistake. The implementation is now opened from the org fork instead: #357