daishi-sdk 0.2.8 → 0.2.9

package/dist/generated.d.ts

@@ -5,7 +5,7 @@ export type JsonObject = {
 /** The API version these types describe. */
 export declare const API_VERSION = "1.0.0";
 /** Every error code the API documents. */
-export type ErrorCode = 'token_required' | 'scope_required' | 'plan_api' | 'rate_limited' | 'handover' | 'bad_request' | 'bad_scenario' | 'bad_replicates' | 'profile_required' | 'bad_season_ticks' | 'bad_frame' | 'bad_env' | 'too_many_scenarios' | 'unknown_scenario' | 'bad_skill' | 'too_many_skills' | 'unknown_skill' | 'bad_roster' | 'bad_model' | 'bad_name' | 'bad_provider' | 'provider_key_required' | 'openrouter_key_required' | 'openrouter_balance_low' | 'billing_frozen' | 'email_unverified' | 'bad_trials' | 'bad_spend_cap' | 'plan_seats' | 'plan_ticks' | 'plan_series' | 'plan_quota' | 'too_many_runs' | 'run_history_full' | 'seed_not_allowed' | 'unknown_run' | 'unknown_batch' | 'unknown_experiment' | 'experiment_trial' | 'experiment_not_running' | 'experiment_arms' | 'bad_experiment' | 'experiment_scenario' | 'experiment_world_only' | 'experiment_env_seed' | 'experiment_stopping' | 'bad_metric' | 'bad_design' | 'design_final' | 'design_late' | 'no_design' | 'experiment_effort_roster' | 'plan_experiment_arms' | 'plan_rerun' | 'unknown_log' | 'plan_invites' | 'invite_world' | 'invite_series' | 'too_many_open_worlds' | 'no_invite' | 'invite_fixed' | 'bad_invite' | 'never_played' | 'run_playing' | 'study_playing' | 'bad_note' | 'note_too_long' | 'run_launching' | 'internal_error';
+export type ErrorCode = 'token_required' | 'scope_required' | 'plan_api' | 'rate_limited' | 'handover' | 'bad_request' | 'bad_scenario' | 'bad_replicates' | 'profile_required' | 'bad_season_ticks' | 'bad_frame' | 'bad_env' | 'too_many_scenarios' | 'unknown_scenario' | 'bad_skill' | 'too_many_skills' | 'unknown_skill' | 'bad_roster' | 'bad_model' | 'bad_name' | 'bad_provider' | 'provider_key_required' | 'openrouter_key_required' | 'openrouter_balance_low' | 'billing_frozen' | 'email_unverified' | 'bad_trials' | 'bad_spend_cap' | 'plan_seats' | 'plan_ticks' | 'plan_series' | 'plan_quota' | 'too_many_runs' | 'run_history_full' | 'seed_not_allowed' | 'unknown_run' | 'unknown_batch' | 'unknown_experiment' | 'experiment_trial' | 'experiment_not_running' | 'experiment_arms' | 'bad_experiment' | 'experiment_scenario' | 'bad_game' | 'bad_arena' | 'experiment_world_only' | 'experiment_same_arms' | 'experiment_env_seed' | 'experiment_stopping' | 'bad_metric' | 'bad_design' | 'design_final' | 'design_late' | 'no_design' | 'experiment_effort_roster' | 'plan_experiment_arms' | 'plan_rerun' | 'unknown_log' | 'plan_invites' | 'invite_world' | 'invite_series' | 'too_many_open_worlds' | 'no_invite' | 'invite_fixed' | 'bad_invite' | 'never_played' | 'run_playing' | 'study_playing' | 'bad_note' | 'note_too_long' | 'run_launching' | 'internal_error';
 export type Method = 'GET' | 'POST' | 'PUT' | 'DELETE';
 export interface RequestParts {
     query?: Record<string, string | number | boolean | undefined | null>;
@@ -124,8 +124,9 @@ export interface Experiment {
     scenario_id: string;
     trials: number;
     seed_mode: 'vary' | 'pinned';
-    metric: 'fitness_index' | 'rank' | 'survived' | 'output_tokens_per_turn' | 'said_evaluated';
-    secondary_metrics: Array<'fitness_index' | 'rank' | 'survived' | 'output_tokens_per_turn' | 'said_evaluated'>;
+    aa_check: boolean;
+    metric: 'fitness_index' | 'rank' | 'survived' | 'index_survival' | 'index_economy' | 'index_social' | 'index_adaptation' | 'index_competitiveness' | 'aggression_per_100_rounds' | 'trades_per_100_rounds' | 'messages_per_100_rounds' | 'map_coverage' | 'output_tokens_per_turn' | 'said_evaluated';
+    secondary_metrics: Array<'fitness_index' | 'rank' | 'survived' | 'index_survival' | 'index_economy' | 'index_social' | 'index_adaptation' | 'index_competitiveness' | 'aggression_per_100_rounds' | 'trades_per_100_rounds' | 'messages_per_100_rounds' | 'map_coverage' | 'output_tokens_per_turn' | 'said_evaluated'>;
     rule: StoppingRule;
     arms: ExperimentArmView[];
     created_at_ms: number;
@@ -151,7 +152,8 @@ export interface ExperimentReport {
     scenario_id: string;
     trials: number;
     seed_mode: 'vary' | 'pinned';
-    metric: 'fitness_index' | 'rank' | 'survived' | 'output_tokens_per_turn' | 'said_evaluated';
+    aa_check: boolean;
+    metric: 'fitness_index' | 'rank' | 'survived' | 'index_survival' | 'index_economy' | 'index_social' | 'index_adaptation' | 'index_competitiveness' | 'aggression_per_100_rounds' | 'trades_per_100_rounds' | 'messages_per_100_rounds' | 'map_coverage' | 'output_tokens_per_turn' | 'said_evaluated';
     analysis_scale: 'metric' | 'negative_rank' | 'log';
     rule: StoppingRule;
     rule_text: string;
@@ -177,12 +179,12 @@ export interface ScenarioBody {
     description?: string;
     /** Season length in rounds: in each round every seat takes a turn, then the world updates (the API calls a round a tick). Null or omitted means the base default (300). Your plan caps what a run may use; validate reports that as a warning. */
     season_ticks?: number | null;
-    /** The environment. Every field is optional; an omitted field takes the base world default. */
+    /** The environment. Every field is optional; an omitted field takes the base world default, and an unknown field is refused (known: seed, spawn_seed, turn_timeout_ms, actions_per_turn, resources, anchors, unwitnessed_anonymity). */
     env?: Env;
 }
 export interface RunBody {
-    /** A library id (daishi:famine-v1) or one of your saved scenarios (usc_...). */
-    scenario_id: string;
+    /** Required on a world run (the default game): a library id (daishi:famine-v1) or one of your saved scenarios (usc_...). A board game takes none. */
+    scenario_id?: string;
     /** One entry per seat. Your plan caps how many. */
     roster: RosterSeat[];
     /** Run name, kept on one line: whitespace runs collapse to one space and control characters are dropped. Default: generated. */
@@ -201,6 +203,10 @@ export interface RunBody {
     invite_minutes?: number;
     /** The awareness frame every seat plays under: monitored opens the prompt with a notice that the match is recorded and scored, neutral withholds the sentence that names the audience; omitted is the canonical prompt. The frame is part of each seat’s scaffold identity and of the recipe hash, so a framed run is its own recipe. World runs only. */
     frame?: 'monitored' | 'neutral';
+    /** What to play: world (default), or a board game, model against model, every move graded afterwards by an oracle. A board game takes exactly two seats and reads no scenario_id, season_ticks or env; a frame on it is refused (bad_frame: its seats never see the world prompt the frame rewrites); arena holds its protocol. Board games run as single runs or series, never as experiment arms. */
+    game?: 'world' | 'chess' | 'connect4';
+    /** Board games only: the protocol. Every field is optional; an unknown one is refused (known: opening, max_plies, move_timeout_ms, illegal_move_retries, seed). */
+    arena?: RunBodyArena;
     /** The id of an archived Studio match to re-run. Fill the body from that match’s recipe (GET /api/matches/<id>/recipe answers with a request body). The run is created already published, so it lists beside the original at /api/matches/<id>/replications whether or not it agrees, and the account needs a profile handle. World runs only; a private match cannot be re-run. */
     replicates?: string;
 }
@@ -227,7 +233,7 @@ export interface RosterSeat {
     instructions?: string;
 }
 export interface ExperimentBody {
-    /** Required unless replicates is set. The arms, the first the control. Every arm must name the same scenario_id; arms may differ in anything else (roster, skills, instructions, env knobs, season_ticks, frame). No arm may set env.seed or env.spawn_seed: the experiment draws both once and pins them per trial on every arm. World runs only. */
+    /** Required unless replicates is set. The arms, the first the control. Every arm must name the same scenario_id; arms may differ in anything else (roster, skills, instructions, env knobs, season_ticks, frame). No arm may set env.seed or env.spawn_seed: the experiment draws both once and pins them per trial on every arm. World runs only. An arm that plays exactly what the control plays (compared on what reaches the match: every seat as validated with its defaults filled in, its name included, the environment as the match resolves it, with the scenario’s defaults filled in and the lineup expanded, the season and the frame; not the label, the run name or the spend cap) is refused with experiment_same_arms unless aa_check is true. */
     arms?: ExperimentArm[];
     /** Required unless replicates is set. Paired trials per arm: 3 up to the plan’s series ceiling (the comparison renders no verdict on fewer than 3 pairs). Trial i of every arm plays the same world and the same layout. */
     trials?: number;
@@ -235,19 +241,21 @@ export interface ExperimentBody {
     name?: string;
     /** vary (default): each trial its own world; pinned: one world for every trial, only the layout varies. A saved scenario that pins its own seed needs pinned; a scenario that draws its worlds from a seed pool refuses it (trial i plays the pool’s world for that trial in every arm, and the pool’s eight worlds come round again from trial nine). A scenario with one fixed world (the lab scenarios) plays it on every trial: its experiment is pinned by default and refuses vary. */
     seed_mode?: 'vary' | 'pinned';
-    /** The per-trial score the arms are compared on, the mean over the arm’s roster seats: the Fitness Index (default), the rank in the field (lower is better, and the report compares on the negative rank so a positive difference always favors the arm), the share of seats that survived, output tokens per play turn, or the debrief share. Output per turn is how much each model generated per turn of play, thinking included (the exit interview and the debrief are not play turns); it compares each model with itself, so every arm must field the same model in the same seat as the control, and it is analyzed on the log scale, the difference read as a percent change. It has no better side: the verdict says which arm generated more. A seat that missed more than a tenth of the rounds is left out of a trial in every arm, and a guest seat is never measured. said_evaluated is the share of a trial’s seats that answered yes when the end-of-match debrief asked whether they believed the match was an evaluation or test of them, among the seats whose answer came back (a trial where none did leaves its pair out), compared in percentage points. It is what the seats said, not what they believed, and it has no better side either: the verdict says which arm had more of its seats say so. */
-    metric?: 'fitness_index' | 'rank' | 'survived' | 'output_tokens_per_turn' | 'said_evaluated';
+    /** The per-trial score the arms are compared on, the mean over the arm’s roster seats: the Fitness Index (default), the rank in the field (lower is better, and the report compares on the negative rank so a positive difference always favors the arm), the share of seats that survived, output tokens per play turn, the debrief share, one of the Index’s five dimensions, one of three behavior counts per 100 rounds, or map coverage. Output per turn is how much each model generated per turn of play, thinking included (the exit interview and the debrief are not play turns); it compares each model with itself, so every arm must field the same model in the same seat as the control, and it is analyzed on the log scale, the difference read as a percent change. It has no better side: the verdict says which arm generated more. A seat that missed more than a tenth of the rounds is left out of a trial in every arm, and a guest seat is never measured. said_evaluated is the share of a trial’s seats that answered yes when the end-of-match debrief asked whether they believed the match was an evaluation or test of them, among the seats whose answer came back (a trial where none did leaves its pair out), compared in percentage points. It is what the seats said, not what they believed, and it has no better side either: the verdict says which arm had more of its seats say so. index_survival, index_economy, index_social, index_adaptation and index_competitiveness are the Fitness Index’s five dimensions, 0 to 100 each under the rubric the match scored with, higher being better as on the Index (competitiveness is scored against the whole field, house bots included; the social dimension credits messages sent up to a cap, answered or not, and subtracts aggression and commons loss). The behavior outcomes count what each seat did, from its match’s event log, over the rounds the match played (a seat that died keeps the whole match as its denominator, unlike the rubric’s rates, which divide by rounds alive): aggression_per_100_rounds (acts of force: attacks on agents, raids on structures and thefts from storehouses, the three acts the world’s aggression counter prices), trades_per_100_rounds (completed trades the seat was party to, offering or accepting; a trade between two roster seats counts once for each) and messages_per_100_rounds (public and direct); map_coverage is the share of the map’s cells the seat ever stood in, its spawn included, compared in percentage points: a stock, not a rate, so arms that differ in season_ticks should not compare on it, and the adaptation dimension carries a coverage term of its own, so the two move together by construction. These four have no better side: the verdict says which arm was higher. A trial whose match recorded no event counts (or, for coverage, no map record) leaves its pair out as unmeasured. None of the new outcomes has a prior spread, so detectable_gap is null on them until five pairs are in. */
+    metric?: 'fitness_index' | 'rank' | 'survived' | 'index_survival' | 'index_economy' | 'index_social' | 'index_adaptation' | 'index_competitiveness' | 'aggression_per_100_rounds' | 'trades_per_100_rounds' | 'messages_per_100_rounds' | 'map_coverage' | 'output_tokens_per_turn' | 'said_evaluated';
     /** Outcomes reported beside metric, declared now and never changed: any of the metric’s values except the metric itself, each at most once. Each is read on the same pairs with the same rule at the same level, and none stops anything; when a comparison stops, its secondaries take their reading on the pairs it stopped on. Output per turn here holds the arms to the same models in the same seats, as it does as the metric. Default none. */
-    secondary_metrics?: Array<'fitness_index' | 'rank' | 'survived' | 'output_tokens_per_turn' | 'said_evaluated'>;
+    secondary_metrics?: Array<'fitness_index' | 'rank' | 'survived' | 'index_survival' | 'index_economy' | 'index_social' | 'index_adaptation' | 'index_competitiveness' | 'aggression_per_100_rounds' | 'trades_per_100_rounds' | 'messages_per_100_rounds' | 'map_coverage' | 'output_tokens_per_turn' | 'said_evaluated'>;
     /** anytime: an anytime-valid 95% confidence sequence on the paired difference, checked after every trial from the tenth on, stopping as soon as it excludes zero or at the last trial; it needs more than 10 trials per arm and is the default above that. fixed: one look at the last trial; the default at 10 or fewer. With more than two arms the level is split across the comparisons against the control. */
     stopping?: 'anytime' | 'fixed';
     /** Anytime rule only: also stop, undecided, once the whole interval lies within plus or minus this on the metric’s scale, so the gap, if any, is smaller than this. */
     target_half_width?: number;
+    /** true declares an A/A check: every arm plays the control’s configuration on purpose, so the report measures the noise between identical arms (labels may still differ). Without it, an arm identical to the control is refused (experiment_same_arms); with it, an arm that differs is refused (bad_experiment). The report and the list carry it as aa_check, and the verdict says that any difference is noise. Default false. */
+    aa_check?: boolean;
     /** Where to POST the signed experiment.ended notice: https, a public host, no credentials, at most 512 characters. Omitted: the account’s webhook setting, if any. */
     callback_url?: string;
     /** The design document, as text (markdown or plain): what you predict, which result you will read and how, and what would change your view. The server keeps it byte for byte with the SHA-256 of its UTF-8 bytes and the time it arrived; the experiment answers with design (digest, size, arrival and standing), and once a trial is published the study’s card on your profile links to it at /u/<handle>/studies/<id>/design, where anyone can download the exact bytes and check the digest. Omitted: no design; one can still be attached before the first trial starts (POST /experiments/:id/design). */
     design?: string;
-    /** Re-run a published study: its experiment id (exp_..., from the study’s card on a profile, or GET /api/studies/<id>/recipe, which answers with its design). The server builds the experiment from that design: every arm as its published trials recorded it, the trial count, the seed mode, the metric, the secondary outcomes and the stopping rule, with each world drawn fresh and shared by the arms trial by trial. The body therefore carries none of the study’s settings, only name, max_spend_usd, callback_url and, if you wrote one, your own design document for the re-run; a setting of the study (arms, trials, seed_mode, metric, secondary_metrics, stopping, target_half_width) beside replicates answers bad_replicates. A plan that cannot hold the whole design answers plan_rerun, naming each limit that cuts it and the smallest plan that holds it: a shortened copy is a different study and is never queued as a re-run. Every trial is published from creation, so the account needs a profile handle, and the record says under replicates whether it plays the study exactly as recorded and, when not, why. Exactly as recorded covers the configuration, not what the provider serves behind a model id: each match records the model and upstream that served it. */
+    /** Re-run a published study: its experiment id (exp_..., from the study’s card on a profile, or GET /api/studies/<id>/recipe, which answers with its design). The server builds the experiment from that design: every arm as its published trials recorded it, the trial count, the seed mode, the metric, the secondary outcomes and the stopping rule, with each world drawn fresh and shared by the arms trial by trial. The body therefore carries none of the study’s settings, only name, max_spend_usd, callback_url and, if you wrote one, your own design document for the re-run; a setting of the study (arms, trials, seed_mode, metric, secondary_metrics, stopping, target_half_width, aa_check) beside replicates answers bad_replicates. A plan that cannot hold the whole design answers plan_rerun, naming each limit that cuts it and the smallest plan that holds it: a shortened copy is a different study and is never queued as a re-run. Every trial is published from creation, so the account needs a profile handle, and the record says under replicates whether it plays the study exactly as recorded and, when not, why. Exactly as recorded covers the configuration, not what the provider serves behind a model id: each match records the model and upstream that served it. */
     replicates?: string;
     /** With replicates only: the spend cap of each arm in USD, clamped to the plan’s range (default the plan’s own). The original’s caps were its owner’s and are not carried. An ordinary experiment sets a cap on each arm instead. */
     max_spend_usd?: number;
@@ -255,7 +263,7 @@ export interface ExperimentBody {
 export interface ExperimentArm {
     /** How the report names this arm. Default arm 1, arm 2, ...; labels must be distinct. */
     label?: string;
-    /** A library id (daishi:famine-v1) or one of your saved scenarios (usc_...). */
+    /** A library id (daishi:famine-v1) or one of your saved scenarios (usc_...); every arm names the same one. */
     scenario_id: string;
     /** One entry per seat. Your plan caps how many. No seat may be invited: an arm cannot seat a guest. */
     roster: ExperimentArmSeat[];
@@ -293,7 +301,7 @@ export interface UpdateScenarioBody {
     description?: string;
     /** Season length in rounds: in each round every seat takes a turn, then the world updates (the API calls a round a tick). Null or omitted means the base default (300). Your plan caps what a run may use; validate reports that as a warning. */
     season_ticks?: number | null;
-    /** The environment. Every field is optional; an omitted field takes the base world default. */
+    /** The environment. Every field is optional; an omitted field takes the base world default, and an unknown field is refused (known: seed, spawn_seed, turn_timeout_ms, actions_per_turn, resources, anchors, unwitnessed_anonymity). */
     env?: Env;
 }
 export interface UpdateScenarioResponse {
@@ -493,17 +501,26 @@ export interface RunResultsAgent {
     archetype?: string;
     status?: 'active' | 'dormant' | 'dead';
     crafter_score?: number | null;
-    dimensions?: RunResultsAgentDimensions;
+    dimensions?: SeatDimensions;
+    behavior?: SeatBehavior | null;
     epilogue?: string | null;
     missing?: boolean;
 }
-export interface RunResultsAgentDimensions {
+export interface SeatDimensions {
     survival: number;
     economy: number;
     social: number;
     adaptation: number;
     competitiveness: number;
 }
+export interface SeatBehavior {
+    attacks: number;
+    raids: number;
+    thefts: number;
+    trades: number;
+    messages: number;
+    map_coverage: number | null;
+}
 export interface RunResultsTopModel {
     name: string;
     model: string;
@@ -548,6 +565,8 @@ export interface BatchReportPointAgent {
     fitness_index: number;
     rank: number;
     status: string;
+    dimensions?: SeatDimensions;
+    behavior?: SeatBehavior | null;
     usage: JsonObject | null;
 }
 export interface BatchReportPrecision {
@@ -667,7 +686,7 @@ export interface WorldReading {
     interval: Interval | null;
 }
 export interface ExperimentReportSecondary {
-    metric: 'fitness_index' | 'rank' | 'survived' | 'output_tokens_per_turn' | 'said_evaluated';
+    metric: 'fitness_index' | 'rank' | 'survived' | 'index_survival' | 'index_economy' | 'index_social' | 'index_adaptation' | 'index_competitiveness' | 'aggression_per_100_rounds' | 'trades_per_100_rounds' | 'messages_per_100_rounds' | 'map_coverage' | 'output_tokens_per_turn' | 'said_evaluated';
     analysis_scale: 'metric' | 'negative_rank' | 'log';
     pairs: ExperimentReportSecondaryPair[];
     comparisons: ExperimentReportSecondaryComparison[];
@@ -709,7 +728,7 @@ export interface ExperimentReportWhatDiffered {
     label: string;
     changes: string[];
 }
-/** The environment. Every field is optional; an omitted field takes the base world default. */
+/** The environment. Every field is optional; an omitted field takes the base world default, and an unknown field is refused (known: seed, spawn_seed, turn_timeout_ms, actions_per_turn, resources, anchors, unwitnessed_anonymity). */
 export interface Env {
     /** World seed: fixes the map. Omit to draw a fresh one per run; the drawn seed is recorded on the run. */
     seed?: number;
@@ -726,6 +745,19 @@ export interface Env {
     /** Baseline bot policy ids or one population id (expands to its members). [] means none. At most 8 bots after expansion; see the anchors endpoint for the live list. */
     anchors?: string[];
 }
+/** Board games only: the protocol. Every field is optional; an unknown one is refused (known: opening, max_plies, move_timeout_ms, illegal_move_retries, seed). */
+export interface RunBodyArena {
+    /** How the game starts: the standard position, or a book opening of plies random legal half-moves (0 to 10) before the seats take over. Default: chess a 4-ply book, Connect Four standard. */
+    opening?: 'standard' | '{ kind: standard' | 'book, plies? }';
+    /** Half-moves before the game is called a draw. Default: chess 200, Connect Four 42. */
+    max_plies?: number;
+    /** Milliseconds a seat has per move. Default: chess 180000, Connect Four 120000. */
+    move_timeout_ms?: number;
+    /** Retries after an illegal move before the seat forfeits. Default 3. */
+    illegal_move_retries?: number;
+    /** Pins the book opening, so a rematch starts from the same position. Refused for a multi-trial series. */
+    seed?: number;
+}
 export interface ExperimentArmSeat {
     /** Required on every seat not marked invited; ignored on one that is. Model id as your provider names it, for example <provider>/<model> through a router key, or a vendor's own id with provider set. */
     model?: string;

package/dist/index.d.ts

@@ -1,6 +1,6 @@
 import { Operations, type ErrorCode, type GetBatchResponse, type GetExperimentResponse, type GetRunResponse, type Method, type RequestParts } from './generated.js';
 export * from './generated.js';
-export declare const VERSION = "0.2.8";
+export declare const VERSION = "0.2.9";
 export declare const DEFAULT_BASE_URL = "https://daishi.ai/api/v1";
 export interface DaishiOptions {
     /** A Studio access token (`dsk_...`). Default: the `DAISHI_TOKEN` environment variable. */

package/dist/index.js

@@ -1,6 +1,6 @@
 import { Operations } from './generated.js';
 export * from './generated.js';
-export const VERSION = '0.2.8';
+export const VERSION = '0.2.9';
 export const DEFAULT_BASE_URL = 'https://daishi.ai/api/v1';
 /** A refusal from the API, or a transport failure after the retries ran out. */
 export class DaishiError extends Error {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "daishi-sdk",
-  "version": "0.2.8",
+  "version": "0.2.9",
   "description": "Typed client for the Daishi Studio API: scenarios, runs, series batches and paired experiments, with retries and waiting helpers.",
   "keywords": [
     "daishi",