Struct ExecContext 

pub struct ExecContext {

    pub token: CancellationToken,
    pub background: CancellationToken,
    pub notify: Option<Sender<Msg>>,
    pub progress: Sender<ProgressEvent>,
    pub call_id: ToolCallId,
    pub turn: TurnId,
    pub workdir: PathBuf,
    pub config: Arc<Config>,
    pub model_id: String,
    pub task_id: Option<String>,
    pub session_id: Option<String>,
    pub message_index: Option<i64>,
    pub scratchpad: Option<PathBuf>,
    pub safety_mode: SafetyMode,
    pub plan_file: Option<PathBuf>,
    pub plan_permissions: PlanPermissions,
    pub context_percent: Option<u8>,
    pub intent: Option<String>,
    pub classifier: Option<Arc<dyn AutoClassifier>>,
    pub approval: Option<ApprovalBroker>,
    pub questions: Option<QuestionBroker>,
    pub tasks: Option<TaskBroker>,
}

What a ToolExecutor::execute() receives.

Fields

token: CancellationToken

background: CancellationToken

Ctrl+B “background this” signal, parallel to token. Tools that can detach a running child (execute_command, agent) select on it; the live path sets it from the turn scope, tests leave it never-fired.

notify: Option<Sender<Msg>>

Turn-independent channel back to the main reducer loop. Detached work (a backgrounded subagent) reports through this after the owning turn is gone — the per-turn progress channel dies with the turn. None in tests and contexts that never detach.

progress: Sender<ProgressEvent>

call_id: ToolCallId

turn: TurnId

workdir: PathBuf

config: Arc<Config>

Parent session’s app::Config. Needed by SubagentTool so the child reducer uses the same Ollama host, reasoning prefs, MCP servers, etc. Other tools don’t consult it — keeping it as a typed field (rather than a global) means the dependency is explicit in the signature.

model_id: String

Parent session’s active model id (e.g. "anthropic/claude-opus-4-7"). Subagents inherit this so they hit the same provider.

task_id: Option<String>

Durable daemon task that owns this tool call, when execution was launched through the runtime task queue.

session_id: Option<String>

Conversation id of the interactive session dispatching this call — stamped by the reducer onto Cmd::ExecuteTool so checkpoints can be anchored to a conversation position. None on headless/daemon paths.

message_index: Option<i64>

Conversation length (messages().len()) at dispatch; pairs with session_id for checkpoint anchoring (see CheckpointOrigin).

scratchpad: Option<PathBuf>

Per-session scratch directory, when the session has one materialized (Msg::ScratchpadReady). Stamped by the reducer onto Cmd::ExecuteTool; like background/notify it is field-set after construction on the live path — None in tests and before the directory is confirmed on disk.

safety_mode: SafetyMode

Effective live safety mode for this call (from the session, not the static config; floored to ReadOnly while a plan is being drafted). The policy gate builds its PolicyEngine from this.

plan_file: Option<PathBuf>

Some(path) while the session is in plan mode: the one path the policy gate exempts from the read-only floor, and the flag the plan carve-outs (memory writes, known-safe builds) and the task tools key on. Defaults to None in new — the live dispatch path sets it, like background/notify.

plan_permissions: PlanPermissions

LIVE per-category plan permission levels, threaded from the reducer (the frozen startup config would go stale under /plan config edits). Only consulted while plan_file is Some; defaults in new.

context_percent: Option<u8>

Context-window fill at dispatch, when known (exit_plan_mode shows it on the clear-context approval option). Defaults to None in new.

intent: Option<String>

The user’s stated intent for the turn (latest user message), passed to the Auto-mode classifier so it can judge whether an action is aligned.

classifier: Option<Arc<dyn AutoClassifier>>

LLM classifier for SafetyMode::Auto. Some only when the effective mode is Auto and a provider is bound; the gate awaits it to resolve a PolicyDecision::Classify. None ⇒ the gate fails safe (escalate).

approval: Option<ApprovalBroker>

Inline-approval back-channel (interactive runs only). Some lets the gate prompt the user and park until they answer; None (headless) falls back to the out-of-band DB-approval flow.

questions: Option<QuestionBroker>

Inline-question back-channel for ask_user_question (interactive runs only). Some lets the tool park until the user answers; None (headless) makes the tool proceed with best judgment instead of blocking.

tasks: Option<TaskBroker>

The checklist broker for the task tools (single writer for all task state). Present on every live path — interactive, headless, and subagent runners each own one; None only in bare test contexts, where the tools degrade to a graceful no-op.

Implementations

impl ExecContext

pub fn new( token: CancellationToken, progress: Sender<ProgressEvent>, call_id: ToolCallId, turn: TurnId, workdir: PathBuf, config: Arc<Config>, model_id: String, task_id: Option<String>, session_id: Option<String>, message_index: Option<i64>, safety_mode: SafetyMode, intent: Option<String>, classifier: Option<Arc<dyn AutoClassifier>>, approval: Option<ApprovalBroker>, questions: Option<QuestionBroker>, tasks: Option<TaskBroker>, ) -> Self

pub fn checkpoint_origin(&self) -> CheckpointOrigin

Checkpoint provenance for this call — every checkpoint-creating tool passes this so file snapshots anchor to the conversation position that produced them (rewind/fork surfaces them by anchor).

Trait Implementations

impl Debug for ExecContext

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.