@oneharness/sdk 0.4.1 → 0.4.3

package/dist/generated/contracts.d.ts

@@ -1,3 +1,4 @@
+export type ToolCallStatus = "completed" | "failed" | "timeout" | "interrupted";
 /**
  * The normalized, closed set of failure reasons oneharness can classify from a
  * harness's output. It is the single source for the `failure_kind` contract
@@ -332,6 +333,11 @@ export interface RunResult {
  * absent) so the shape is stable, mirroring the `usage` contract.
  */
 export interface ActionEvent {
+    /**
+     * Monotonic elapsed tool time. `None` means no terminal boundary was seen.
+     */
+    duration_ms: number | null;
+    finished_at: string | null;
     /**
      * Position of this event within the run, so "≤ N tool calls" and "did X
      * before Y" are expressible from a stable ordering (also array order).
@@ -358,6 +364,20 @@ export interface ActionEvent {
      * The result/observation text, when the trace exposes it; `null` otherwise.
      */
     output: string | null;
+    /**
+     * UTC interval bounds for tool execution, populated on history records.
+     */
+    started_at: string | null;
+    /**
+     * Terminal tool state, populated on history tool-call events.
+     */
+    status: ToolCallStatus | null;
+    /**
+     * Stable call identity within the session. Present on tool calls and their
+     * matching results when the provider exposes an identity; history fills a
+     * deterministic run-local identity for providers that do not.
+     */
+    tool_call_id: string | null;
     [k: string]: unknown;
 }
 /**

package/dist/generated/history-records.d.ts

@@ -1,37 +1,53 @@
-/**
- * The normalized, closed set of failure reasons oneharness can classify from a
- * harness's output. It is the single source for the `failure_kind` contract
- * value: serialized as the snake_case token a consumer reads in the report
- * (`auth`, `rate_limit`, `model_not_found`, `quota`, `tool_deferred`), so the
- * wire shape is unchanged — modeling it as an enum keeps a misspelled or
- * invalid kind unrepresentable and gives every producer/consumer (classifier,
- * `is_failure`, the fallback fall-through rule, the report, history) one
- * definition to share instead of scattered string literals.
- */
-export type FailureKind = "auth" | "rate_limit" | "model_not_found" | "quota" | "tool_deferred";
-/**
- * The outcome of attempting to run one harness.
- */
-export type Status = "ok" | "nonzero" | "timeout" | "spawn-error" | "skipped" | "planned";
-export type HistoryRecords = HistoryRecord[];
 /**
  * One harness run, normalized and frozen for the history log. Serialized as one
  * JSONL line per harness run, appended as the run finalizes. Carries only the
  * normalized cross-harness signals — no raw stdout/stderr.
  */
-export interface HistoryRecord {
-    duration_ms: number | null;
+export type HistoryRecord = {
+    duration_ms: number;
     /**
      * Best-effort normalized tool-call events; `null` when the harness exposes
      * no machine-readable trace.
      */
-    events: ActionEvent[] | null;
+    events: ((ActionEvent & {
+        duration_ms: number;
+        finished_at: string;
+        kind: "tool_call";
+        started_at: string;
+        status: "completed";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        duration_ms: number;
+        finished_at: string;
+        kind: "tool_call";
+        started_at: string;
+        status: "failed";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        kind: "tool_call";
+        started_at: string;
+        status: "timeout";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        kind: "tool_call";
+        started_at: string;
+        status: "interrupted";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        kind?: "tool_result" | undefined;
+        [k: string]: unknown;
+    }))[] | null;
     exit_code: number | null;
     /**
      * Best-effort classified failure reason (see [`FailureKind`]); `null` when
      * unclassified.
      */
     failure_kind: FailureKind | null;
+    finished_at: string | null;
     /**
      * Canonical harness id (e.g. `claude-code`).
      */
@@ -46,6 +62,7 @@ export interface HistoryRecord {
      * The effective top-level model for the run, if any.
      */
     model: string | null;
+    model_ms: number;
     /**
      * The human-meaningful session name (see [`session_name`]); repeated on
      * every record so a reader can resolve a session by name from any line.
@@ -65,7 +82,7 @@ export interface HistoryRecord {
      * run's single prompt).
      */
     prompt: string;
-    schema_version: string;
+    schema_version: "0.3";
     /**
      * The oneharness session id this run belongs to (the history file's stem).
      */
@@ -74,6 +91,7 @@ export interface HistoryRecord {
      * The harness's own continuation id, when it exposed one; `null` otherwise.
      */
     session_id: string | null;
+    started_at: string;
     status: Status;
     /**
      * Best-effort final assistant text; `null` when extraction was impossible.
@@ -83,19 +101,127 @@ export interface HistoryRecord {
      * How `text` was extracted; `null` when absent.
      */
     text_source: string | null;
+    time_to_first_token_ms?: number | null | undefined;
     /**
      * RFC3339 UTC instant the record was written (append time).
      */
     timestamp: string;
+    tool_ms: number;
     usage: Usage;
     [k: string]: unknown;
-}
+} | {
+    duration_ms: number | null;
+    events: {
+        index: number;
+        input: unknown;
+        kind: string;
+        name: string | null;
+        output: string | null;
+        [k: string]: unknown;
+    }[] | null;
+    exit_code: number | null;
+    /**
+     * Best-effort classified failure reason (see [`FailureKind`]); `null` when
+     * unclassified.
+     */
+    failure_kind: FailureKind | null;
+    finished_at?: string | null | undefined;
+    /**
+     * Canonical harness id (e.g. `claude-code`).
+     */
+    harness: string;
+    /**
+     * Globally unique, time-ordered record id. This is also the cursor accepted
+     * by `history watch --after` and the exact id accepted by history lookup.
+     */
+    history_id: string;
+    labels?: HistoryLabels1 | undefined;
+    /**
+     * The effective top-level model for the run, if any.
+     */
+    model: string | null;
+    model_ms?: number | null | undefined;
+    /**
+     * The human-meaningful session name (see [`session_name`]); repeated on
+     * every record so a reader can resolve a session by name from any line.
+     */
+    name: string;
+    /**
+     * The normalized approval mode requested for the run.
+     */
+    permission_mode: "read-only" | "plan" | "default" | "edit" | "auto" | "bypass";
+    /**
+     * The project directory the run operated in (the real path, not the
+     * on-disk slug), so the list view can show where a session ran.
+     */
+    project: string;
+    /**
+     * The prompt this harness run received (its own, on a batch run; else the
+     * run's single prompt).
+     */
+    prompt: string;
+    schema_version: "0.1" | "0.2";
+    /**
+     * The oneharness session id this run belongs to (the history file's stem).
+     */
+    session: string;
+    /**
+     * The harness's own continuation id, when it exposed one; `null` otherwise.
+     */
+    session_id: string | null;
+    /**
+     * UTC invocation bounds and monotonic time attribution. The provider/tool
+     * split is conservative when a transcript has tool calls but lacks native
+     * boundaries: the observed invocation interval is attributed to the union
+     * of those calls, never double-counted.
+     */
+    started_at?: string | null | undefined;
+    status: Status;
+    /**
+     * Best-effort final assistant text; `null` when extraction was impossible.
+     */
+    text: string | null;
+    /**
+     * How `text` was extracted; `null` when absent.
+     */
+    text_source: string | null;
+    time_to_first_token_ms?: number | null | undefined;
+    /**
+     * RFC3339 UTC instant the record was written (append time).
+     */
+    timestamp: string;
+    tool_ms?: number | null | undefined;
+    usage: Usage1;
+    [k: string]: unknown;
+};
+export type ToolCallStatus = "completed" | "failed" | "timeout" | "interrupted";
+/**
+ * The normalized, closed set of failure reasons oneharness can classify from a
+ * harness's output. It is the single source for the `failure_kind` contract
+ * value: serialized as the snake_case token a consumer reads in the report
+ * (`auth`, `rate_limit`, `model_not_found`, `quota`, `tool_deferred`), so the
+ * wire shape is unchanged — modeling it as an enum keeps a misspelled or
+ * invalid kind unrepresentable and gives every producer/consumer (classifier,
+ * `is_failure`, the fallback fall-through rule, the report, history) one
+ * definition to share instead of scattered string literals.
+ */
+export type FailureKind = "auth" | "rate_limit" | "model_not_found" | "quota" | "tool_deferred";
+/**
+ * The outcome of attempting to run one harness.
+ */
+export type Status = "ok" | "nonzero" | "timeout" | "spawn-error" | "skipped" | "planned";
+export type HistoryRecords = HistoryRecord[];
 /**
  * One normalized action a harness took, harness-agnostic so a single consumer
  * assertion works across harnesses. Every field is always serialized (null when
  * absent) so the shape is stable, mirroring the `usage` contract.
  */
 export interface ActionEvent {
+    /**
+     * Monotonic elapsed tool time. `None` means no terminal boundary was seen.
+     */
+    duration_ms: number | null;
+    finished_at: string | null;
     /**
      * Position of this event within the run, so "≤ N tool calls" and "did X
      * before Y" are expressible from a stable ordering (also array order).
@@ -122,6 +248,20 @@ export interface ActionEvent {
      * The result/observation text, when the trace exposes it; `null` otherwise.
      */
     output: string | null;
+    /**
+     * UTC interval bounds for tool execution, populated on history records.
+     */
+    started_at: string | null;
+    /**
+     * Terminal tool state, populated on history tool-call events.
+     */
+    status: ToolCallStatus | null;
+    /**
+     * Stable call identity within the session. Present on tool calls and their
+     * matching results when the provider exposes an identity; history fills a
+     * deterministic run-local identity for providers that do not.
+     */
+    tool_call_id: string | null;
     [k: string]: unknown;
 }
 /**
@@ -161,3 +301,40 @@ export interface Usage {
     output_tokens: number | null;
     [k: string]: unknown;
 }
+/**
+ * Caller-supplied metadata used to select related task-graph records.
+ * Omitted on the wire when empty for additive compatibility.
+ */
+export interface HistoryLabels1 {
+    [k: string]: string;
+}
+/**
+ * Best-effort token/cost accounting (every field `null` when unreported).
+ */
+export interface Usage1 {
+    /**
+     * Prompt tokens served from the provider's prompt cache (a cheap read of a
+     * previously-written prefix), when the harness reports them. `None` when the
+     * harness does not surface cache counts — never `0` as a guess.
+     */
+    cache_read_tokens: number | null;
+    /**
+     * Prompt tokens written to the provider's prompt cache (a.k.a. cache
+     * creation), when the harness reports them. `None` when not surfaced.
+     */
+    cache_write_tokens: number | null;
+    /**
+     * Total cost in USD, when the harness reports it (often absent on
+     * subscription auth, where there is no per-call dollar figure).
+     */
+    cost_usd: number | null;
+    /**
+     * Prompt/input tokens billed, when the harness reports them.
+     */
+    input_tokens: number | null;
+    /**
+     * Completion/output tokens billed, when the harness reports them.
+     */
+    output_tokens: number | null;
+    [k: string]: unknown;
+}

package/dist/generated/history-stream-envelope.d.ts

@@ -8,39 +8,56 @@ export type HistoryStreamEnvelope = {
     type: "record";
     [k: string]: unknown;
 };
-/**
- * The normalized, closed set of failure reasons oneharness can classify from a
- * harness's output. It is the single source for the `failure_kind` contract
- * value: serialized as the snake_case token a consumer reads in the report
- * (`auth`, `rate_limit`, `model_not_found`, `quota`, `tool_deferred`), so the
- * wire shape is unchanged — modeling it as an enum keeps a misspelled or
- * invalid kind unrepresentable and gives every producer/consumer (classifier,
- * `is_failure`, the fallback fall-through rule, the report, history) one
- * definition to share instead of scattered string literals.
- */
-export type FailureKind = "auth" | "rate_limit" | "model_not_found" | "quota" | "tool_deferred";
-/**
- * The outcome of attempting to run one harness.
- */
-export type Status = "ok" | "nonzero" | "timeout" | "spawn-error" | "skipped" | "planned";
 /**
  * One harness run, normalized and frozen for the history log. Serialized as one
  * JSONL line per harness run, appended as the run finalizes. Carries only the
  * normalized cross-harness signals — no raw stdout/stderr.
  */
-export interface HistoryRecord {
-    duration_ms: number | null;
+export type HistoryRecord = {
+    duration_ms: number;
     /**
      * Best-effort normalized tool-call events; `null` when the harness exposes
      * no machine-readable trace.
      */
-    events: ActionEvent[] | null;
+    events: ((ActionEvent & {
+        duration_ms: number;
+        finished_at: string;
+        kind: "tool_call";
+        started_at: string;
+        status: "completed";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        duration_ms: number;
+        finished_at: string;
+        kind: "tool_call";
+        started_at: string;
+        status: "failed";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        kind: "tool_call";
+        started_at: string;
+        status: "timeout";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        kind: "tool_call";
+        started_at: string;
+        status: "interrupted";
+        tool_call_id: string;
+        [k: string]: unknown;
+    }) | (ActionEvent & {
+        kind?: "tool_result" | undefined;
+        [k: string]: unknown;
+    }))[] | null;
     exit_code: number | null;
     /**
      * Best-effort classified failure reason (see [`FailureKind`]); `null` when
      * unclassified.
      */
     failure_kind: FailureKind | null;
+    finished_at: string | null;
     /**
      * Canonical harness id (e.g. `claude-code`).
      */
@@ -55,6 +72,7 @@ export interface HistoryRecord {
      * The effective top-level model for the run, if any.
      */
     model: string | null;
+    model_ms: number;
     /**
      * The human-meaningful session name (see [`session_name`]); repeated on
      * every record so a reader can resolve a session by name from any line.
@@ -74,7 +92,7 @@ export interface HistoryRecord {
      * run's single prompt).
      */
     prompt: string;
-    schema_version: string;
+    schema_version: "0.3";
     /**
      * The oneharness session id this run belongs to (the history file's stem).
      */
@@ -83,6 +101,7 @@ export interface HistoryRecord {
      * The harness's own continuation id, when it exposed one; `null` otherwise.
      */
     session_id: string | null;
+    started_at: string;
     status: Status;
     /**
      * Best-effort final assistant text; `null` when extraction was impossible.
@@ -92,19 +111,126 @@ export interface HistoryRecord {
      * How `text` was extracted; `null` when absent.
      */
     text_source: string | null;
+    time_to_first_token_ms?: number | null | undefined;
     /**
      * RFC3339 UTC instant the record was written (append time).
      */
     timestamp: string;
+    tool_ms: number;
     usage: Usage;
     [k: string]: unknown;
-}
+} | {
+    duration_ms: number | null;
+    events: {
+        index: number;
+        input: unknown;
+        kind: string;
+        name: string | null;
+        output: string | null;
+        [k: string]: unknown;
+    }[] | null;
+    exit_code: number | null;
+    /**
+     * Best-effort classified failure reason (see [`FailureKind`]); `null` when
+     * unclassified.
+     */
+    failure_kind: FailureKind | null;
+    finished_at?: string | null | undefined;
+    /**
+     * Canonical harness id (e.g. `claude-code`).
+     */
+    harness: string;
+    /**
+     * Globally unique, time-ordered record id. This is also the cursor accepted
+     * by `history watch --after` and the exact id accepted by history lookup.
+     */
+    history_id: string;
+    labels?: HistoryLabels1 | undefined;
+    /**
+     * The effective top-level model for the run, if any.
+     */
+    model: string | null;
+    model_ms?: number | null | undefined;
+    /**
+     * The human-meaningful session name (see [`session_name`]); repeated on
+     * every record so a reader can resolve a session by name from any line.
+     */
+    name: string;
+    /**
+     * The normalized approval mode requested for the run.
+     */
+    permission_mode: "read-only" | "plan" | "default" | "edit" | "auto" | "bypass";
+    /**
+     * The project directory the run operated in (the real path, not the
+     * on-disk slug), so the list view can show where a session ran.
+     */
+    project: string;
+    /**
+     * The prompt this harness run received (its own, on a batch run; else the
+     * run's single prompt).
+     */
+    prompt: string;
+    schema_version: "0.1" | "0.2";
+    /**
+     * The oneharness session id this run belongs to (the history file's stem).
+     */
+    session: string;
+    /**
+     * The harness's own continuation id, when it exposed one; `null` otherwise.
+     */
+    session_id: string | null;
+    /**
+     * UTC invocation bounds and monotonic time attribution. The provider/tool
+     * split is conservative when a transcript has tool calls but lacks native
+     * boundaries: the observed invocation interval is attributed to the union
+     * of those calls, never double-counted.
+     */
+    started_at?: string | null | undefined;
+    status: Status;
+    /**
+     * Best-effort final assistant text; `null` when extraction was impossible.
+     */
+    text: string | null;
+    /**
+     * How `text` was extracted; `null` when absent.
+     */
+    text_source: string | null;
+    time_to_first_token_ms?: number | null | undefined;
+    /**
+     * RFC3339 UTC instant the record was written (append time).
+     */
+    timestamp: string;
+    tool_ms?: number | null | undefined;
+    usage: Usage1;
+    [k: string]: unknown;
+};
+export type ToolCallStatus = "completed" | "failed" | "timeout" | "interrupted";
+/**
+ * The normalized, closed set of failure reasons oneharness can classify from a
+ * harness's output. It is the single source for the `failure_kind` contract
+ * value: serialized as the snake_case token a consumer reads in the report
+ * (`auth`, `rate_limit`, `model_not_found`, `quota`, `tool_deferred`), so the
+ * wire shape is unchanged — modeling it as an enum keeps a misspelled or
+ * invalid kind unrepresentable and gives every producer/consumer (classifier,
+ * `is_failure`, the fallback fall-through rule, the report, history) one
+ * definition to share instead of scattered string literals.
+ */
+export type FailureKind = "auth" | "rate_limit" | "model_not_found" | "quota" | "tool_deferred";
+/**
+ * The outcome of attempting to run one harness.
+ */
+export type Status = "ok" | "nonzero" | "timeout" | "spawn-error" | "skipped" | "planned";
 /**
  * One normalized action a harness took, harness-agnostic so a single consumer
  * assertion works across harnesses. Every field is always serialized (null when
  * absent) so the shape is stable, mirroring the `usage` contract.
  */
 export interface ActionEvent {
+    /**
+     * Monotonic elapsed tool time. `None` means no terminal boundary was seen.
+     */
+    duration_ms: number | null;
+    finished_at: string | null;
     /**
      * Position of this event within the run, so "≤ N tool calls" and "did X
      * before Y" are expressible from a stable ordering (also array order).
@@ -131,6 +257,20 @@ export interface ActionEvent {
      * The result/observation text, when the trace exposes it; `null` otherwise.
      */
     output: string | null;
+    /**
+     * UTC interval bounds for tool execution, populated on history records.
+     */
+    started_at: string | null;
+    /**
+     * Terminal tool state, populated on history tool-call events.
+     */
+    status: ToolCallStatus | null;
+    /**
+     * Stable call identity within the session. Present on tool calls and their
+     * matching results when the provider exposes an identity; history fills a
+     * deterministic run-local identity for providers that do not.
+     */
+    tool_call_id: string | null;
     [k: string]: unknown;
 }
 /**
@@ -170,3 +310,40 @@ export interface Usage {
     output_tokens: number | null;
     [k: string]: unknown;
 }
+/**
+ * Caller-supplied metadata used to select related task-graph records.
+ * Omitted on the wire when empty for additive compatibility.
+ */
+export interface HistoryLabels1 {
+    [k: string]: string;
+}
+/**
+ * Best-effort token/cost accounting (every field `null` when unreported).
+ */
+export interface Usage1 {
+    /**
+     * Prompt tokens served from the provider's prompt cache (a cheap read of a
+     * previously-written prefix), when the harness reports them. `None` when the
+     * harness does not surface cache counts — never `0` as a guess.
+     */
+    cache_read_tokens: number | null;
+    /**
+     * Prompt tokens written to the provider's prompt cache (a.k.a. cache
+     * creation), when the harness reports them. `None` when not surfaced.
+     */
+    cache_write_tokens: number | null;
+    /**
+     * Total cost in USD, when the harness reports it (often absent on
+     * subscription auth, where there is no per-call dollar figure).
+     */
+    cost_usd: number | null;
+    /**
+     * Prompt/input tokens billed, when the harness reports them.
+     */
+    input_tokens: number | null;
+    /**
+     * Completion/output tokens billed, when the harness reports them.
+     */
+    output_tokens: number | null;
+    [k: string]: unknown;
+}