switchroom 0.19.19 → 0.19.23

package/dist/agent-scheduler/index.js

@@ -11329,7 +11329,8 @@ var HindsightConfigSchema = exports_external.object({
     retain: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `retain` LLM op (memory ingestion). Emits " + "`HINDSIGHT_API_RETAIN_LLM_*`. Absent → uses the global model/provider."),
     reflect: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `reflect` LLM op (synthesis / mental-model " + "refresh). Emits `HINDSIGHT_API_REFLECT_LLM_*`. Absent → uses global."),
     consolidation: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `consolidation` LLM op (background memory " + "merge). Emits `HINDSIGHT_API_CONSOLIDATION_LLM_*`. Absent → global.")
-  }).optional().describe("LLM knob for the hindsight container. The flat `provider`/`model` set " + "the global default (backward-compatible); optional `retain`/`reflect`/" + "`consolidation` blocks override individual ops. All fields optional; " + "unset fields fall back to the hard-coded defaults.")
+  }).optional().describe("LLM knob for the hindsight container. The flat `provider`/`model` set " + "the global default (backward-compatible); optional `retain`/`reflect`/" + "`consolidation` blocks override individual ops. All fields optional; " + "unset fields fall back to the hard-coded defaults."),
+  env: exports_external.record(exports_external.union([exports_external.string(), exports_external.number(), exports_external.boolean()])).optional().describe("Operator overrides for switchroom's capability-gated Hindsight " + "performance defaults. Only the keys switchroom actually manages are " + "honoured (`HINDSIGHT_PERF_ENV_KEYS` in " + "src/setup/hindsight-perf-defaults.ts: RERANKER_LOCAL_FP16, " + "LLM_MAX_CONCURRENT, RETAIN/CONSOLIDATION_LLM_MAX_CONCURRENT, " + "RECALL_MAX_CANDIDATES_PER_SOURCE, LINK_EXPANSION_PER_ENTITY_LIMIT, " + "LINK_EXPANSION_TIMEOUT, LLM_REASONING_EFFORT), plus the " + "embedded-PostgreSQL (pg0) sizing keys switchroom manages in " + "src/setup/hindsight-pg-defaults.ts (`HINDSIGHT_PG_ENV_KEYS`: " + "SWITCHROOM_HINDSIGHT_PG_EFFECTIVE_CACHE_SIZE, " + "SWITCHROOM_HINDSIGHT_PG_SHARED_BUFFERS — a postgres size string such " + "as `4GB`, or the sentinel `off` to leave pg0's own default for that " + "one knob). A value set here " + "REPLACES switchroom's default and is emitted even when the gating " + "capability is absent, so an operator can always force a knob. Other " + "`HINDSIGHT_API_*` keys are deliberately IGNORED — a blanket " + "passthrough would collide with the vars startHindsight() derives " + "itself (HINDSIGHT_API_PORT, the retain token/deadline budget).")
 });
 var MicrosoftWorkspaceConfigSchema = exports_external.object({
   microsoft_client_id: exports_external.string().min(1).optional().describe("Microsoft OAuth application (client) ID from Entra portal " + "(literal string or vault reference e.g. " + "'vault:microsoft-oauth-client-id'). OPTIONAL — omit it to use " + "switchroom's shipped default Microsoft app (zero-config). " + "Set it only to bring your own Entra app (BYO)."),

package/dist/auth-broker/index.js

@@ -16971,7 +16971,8 @@ var HindsightConfigSchema = exports_external.object({
     retain: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `retain` LLM op (memory ingestion). Emits " + "`HINDSIGHT_API_RETAIN_LLM_*`. Absent → uses the global model/provider."),
     reflect: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `reflect` LLM op (synthesis / mental-model " + "refresh). Emits `HINDSIGHT_API_REFLECT_LLM_*`. Absent → uses global."),
     consolidation: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `consolidation` LLM op (background memory " + "merge). Emits `HINDSIGHT_API_CONSOLIDATION_LLM_*`. Absent → global.")
-  }).optional().describe("LLM knob for the hindsight container. The flat `provider`/`model` set " + "the global default (backward-compatible); optional `retain`/`reflect`/" + "`consolidation` blocks override individual ops. All fields optional; " + "unset fields fall back to the hard-coded defaults.")
+  }).optional().describe("LLM knob for the hindsight container. The flat `provider`/`model` set " + "the global default (backward-compatible); optional `retain`/`reflect`/" + "`consolidation` blocks override individual ops. All fields optional; " + "unset fields fall back to the hard-coded defaults."),
+  env: exports_external.record(exports_external.union([exports_external.string(), exports_external.number(), exports_external.boolean()])).optional().describe("Operator overrides for switchroom's capability-gated Hindsight " + "performance defaults. Only the keys switchroom actually manages are " + "honoured (`HINDSIGHT_PERF_ENV_KEYS` in " + "src/setup/hindsight-perf-defaults.ts: RERANKER_LOCAL_FP16, " + "LLM_MAX_CONCURRENT, RETAIN/CONSOLIDATION_LLM_MAX_CONCURRENT, " + "RECALL_MAX_CANDIDATES_PER_SOURCE, LINK_EXPANSION_PER_ENTITY_LIMIT, " + "LINK_EXPANSION_TIMEOUT, LLM_REASONING_EFFORT), plus the " + "embedded-PostgreSQL (pg0) sizing keys switchroom manages in " + "src/setup/hindsight-pg-defaults.ts (`HINDSIGHT_PG_ENV_KEYS`: " + "SWITCHROOM_HINDSIGHT_PG_EFFECTIVE_CACHE_SIZE, " + "SWITCHROOM_HINDSIGHT_PG_SHARED_BUFFERS — a postgres size string such " + "as `4GB`, or the sentinel `off` to leave pg0's own default for that " + "one knob). A value set here " + "REPLACES switchroom's default and is emitted even when the gating " + "capability is absent, so an operator can always force a knob. Other " + "`HINDSIGHT_API_*` keys are deliberately IGNORED — a blanket " + "passthrough would collide with the vars startHindsight() derives " + "itself (HINDSIGHT_API_PORT, the retain token/deadline budget).")
 });
 var MicrosoftWorkspaceConfigSchema = exports_external.object({
   microsoft_client_id: exports_external.string().min(1).optional().describe("Microsoft OAuth application (client) ID from Entra portal " + "(literal string or vault reference e.g. " + "'vault:microsoft-oauth-client-id'). OPTIONAL — omit it to use " + "switchroom's shipped default Microsoft app (zero-config). " + "Set it only to bring your own Entra app (BYO)."),
@@ -18352,6 +18353,113 @@ for (const name of SHARED_FRAGMENTS) {
   }
 }
 
+// src/litellm/timeout-budget.ts
+var LITELLM_ROUTER_MARGIN_S = 10;
+var LITELLM_TIMEOUT_TIERS = {
+  interactive: {
+    group: "gpt-oss-20b",
+    localTimeoutS: 90,
+    fallbackGroup: "gpt-oss-20b-openrouter",
+    fallbackTimeoutS: 60
+  },
+  retain: {
+    group: "gpt-oss-20b-retain",
+    localTimeoutS: 200,
+    fallbackGroup: "gpt-oss-20b-retain-openrouter",
+    fallbackTimeoutS: 90
+  },
+  consolidation: {
+    group: "gpt-oss-20b-consolidation",
+    localTimeoutS: 200,
+    fallbackGroup: "gpt-oss-20b-consolidation-openrouter",
+    fallbackTimeoutS: 90
+  }
+};
+function litellmChainSeconds(tier) {
+  assertPositive(tier.localTimeoutS, `${tier.group} localTimeoutS`);
+  if (tier.fallbackGroup === null)
+    return tier.localTimeoutS;
+  assertPositive(tier.fallbackTimeoutS, `${tier.fallbackGroup} fallbackTimeoutS`);
+  return tier.localTimeoutS + tier.fallbackTimeoutS;
+}
+function minimumClientBudgetSeconds(tier, marginS = LITELLM_ROUTER_MARGIN_S) {
+  return litellmChainSeconds(tier) + marginS;
+}
+function clientBudgetSeconds(tier, floorS = 0, marginS = LITELLM_ROUTER_MARGIN_S) {
+  return Math.max(Math.ceil(floorS), minimumClientBudgetSeconds(tier, marginS));
+}
+function assertPositive(value, label) {
+  if (!Number.isFinite(value) || value <= 0) {
+    throw new Error(`litellm timeout budget: ${label} must be a positive number, got ${value}`);
+  }
+}
+
+// src/setup/hindsight-perf-defaults.ts
+var HINDSIGHT_RERANKER_MAX_CANDIDATES_FOR_DERIVATION = 150;
+var HINDSIGHT_DEFAULT_RECALL_MAX_CANDIDATES_PER_SOURCE = Math.ceil(HINDSIGHT_RERANKER_MAX_CANDIDATES_FOR_DERIVATION * 0.4);
+var HINDSIGHT_DEFAULT_LINK_EXPANSION_PER_ENTITY_LIMIT = 50;
+var HINDSIGHT_DEFAULT_LINK_EXPANSION_TIMEOUT_S = 2;
+var HINDSIGHT_DEFAULT_LLM_REASONING_EFFORT = "low";
+var HINDSIGHT_DEFAULT_LLM_MAX_CONCURRENT = 4;
+var HINDSIGHT_DEFAULT_RETAIN_LLM_MAX_CONCURRENT = 1;
+var HINDSIGHT_DEFAULT_CONSOLIDATION_LLM_MAX_CONCURRENT = 1;
+var HINDSIGHT_DEFAULT_RERANKER_LOCAL_FP16 = "true";
+var HINDSIGHT_PERF_DEFAULTS_UNGATED = [
+  [
+    "HINDSIGHT_API_RECALL_MAX_CANDIDATES_PER_SOURCE",
+    String(HINDSIGHT_DEFAULT_RECALL_MAX_CANDIDATES_PER_SOURCE)
+  ],
+  [
+    "HINDSIGHT_API_LINK_EXPANSION_PER_ENTITY_LIMIT",
+    String(HINDSIGHT_DEFAULT_LINK_EXPANSION_PER_ENTITY_LIMIT)
+  ],
+  [
+    "HINDSIGHT_API_LINK_EXPANSION_TIMEOUT",
+    String(HINDSIGHT_DEFAULT_LINK_EXPANSION_TIMEOUT_S)
+  ],
+  ["HINDSIGHT_API_LLM_REASONING_EFFORT", HINDSIGHT_DEFAULT_LLM_REASONING_EFFORT]
+];
+var HINDSIGHT_PERF_DEFAULTS_GPU = [
+  ["HINDSIGHT_API_RERANKER_LOCAL_FP16", HINDSIGHT_DEFAULT_RERANKER_LOCAL_FP16]
+];
+var HINDSIGHT_PERF_DEFAULTS_LOCAL_LLM = [
+  ["HINDSIGHT_API_LLM_MAX_CONCURRENT", String(HINDSIGHT_DEFAULT_LLM_MAX_CONCURRENT)],
+  [
+    "HINDSIGHT_API_RETAIN_LLM_MAX_CONCURRENT",
+    String(HINDSIGHT_DEFAULT_RETAIN_LLM_MAX_CONCURRENT)
+  ],
+  [
+    "HINDSIGHT_API_CONSOLIDATION_LLM_MAX_CONCURRENT",
+    String(HINDSIGHT_DEFAULT_CONSOLIDATION_LLM_MAX_CONCURRENT)
+  ]
+];
+var HINDSIGHT_PERF_ENV_KEYS = new Set([
+  ...HINDSIGHT_PERF_DEFAULTS_UNGATED,
+  ...HINDSIGHT_PERF_DEFAULTS_GPU,
+  ...HINDSIGHT_PERF_DEFAULTS_LOCAL_LLM
+].map(([k]) => k));
+
+// src/setup/hindsight-pg-defaults.ts
+var HINDSIGHT_PG_MEM_LIMIT_MIB_FOR_DERIVATION = 8 * 1024;
+var HINDSIGHT_PG_APP_ANON_MIB = 2560;
+var HINDSIGHT_PG_PAGE_CACHE_FLOOR_MIB = 2048;
+var HINDSIGHT_PG_SHARED_BUFFERS_BUDGET_MIB = HINDSIGHT_PG_MEM_LIMIT_MIB_FOR_DERIVATION - HINDSIGHT_PG_APP_ANON_MIB - HINDSIGHT_PG_PAGE_CACHE_FLOOR_MIB;
+var HINDSIGHT_PG_DEFAULT_SHARED_BUFFERS_MIB = 1536;
+var HINDSIGHT_PG_DEFAULT_EFFECTIVE_CACHE_SIZE_MIB = 4096;
+function pgMib(mib) {
+  return `${mib}MB`;
+}
+var HINDSIGHT_PG_EFFECTIVE_CACHE_SIZE_ENV = "SWITCHROOM_HINDSIGHT_PG_EFFECTIVE_CACHE_SIZE";
+var HINDSIGHT_PG_SHARED_BUFFERS_ENV = "SWITCHROOM_HINDSIGHT_PG_SHARED_BUFFERS";
+var HINDSIGHT_PG_DEFAULTS = [
+  [
+    HINDSIGHT_PG_EFFECTIVE_CACHE_SIZE_ENV,
+    pgMib(HINDSIGHT_PG_DEFAULT_EFFECTIVE_CACHE_SIZE_MIB)
+  ],
+  [HINDSIGHT_PG_SHARED_BUFFERS_ENV, pgMib(HINDSIGHT_PG_DEFAULT_SHARED_BUFFERS_MIB)]
+];
+var HINDSIGHT_PG_ENV_KEYS = new Set(HINDSIGHT_PG_DEFAULTS.map(([k]) => k));
+
 // src/setup/hindsight.ts
 var HINDSIGHT_DEFAULT_API_PORT = 18888;
 var HINDSIGHT_DEFAULT_MCP_URL = `http://127.0.0.1:${HINDSIGHT_DEFAULT_API_PORT}/mcp/`;
@@ -18361,6 +18469,18 @@ var HINDSIGHT_IMAGE_REPO = "ghcr.io/switchroom/switchroom-hindsight";
 var HINDSIGHT_IMAGE = `${HINDSIGHT_IMAGE_REPO}:latest`;
 var HINDSIGHT_BROKER_SOCK_VOLUME = `auth-broker-${HINDSIGHT_CONSUMER_NAME}-sock`;
 var HINDSIGHT_CREDS_MIRROR_VOLUME = `consumer-creds-${HINDSIGHT_CONSUMER_NAME}`;
+var HINDSIGHT_DEFAULT_RETAIN_MAX_COMPLETION_TOKENS = 16384;
+var HINDSIGHT_RETAIN_MIN_TOKENS_PER_SECOND = 80.6;
+function hindsightRetainLlmTimeoutSeconds(maxCompletionTokens = HINDSIGHT_DEFAULT_RETAIN_MAX_COMPLETION_TOKENS, tokensPerSecond = HINDSIGHT_RETAIN_MIN_TOKENS_PER_SECOND) {
+  if (!(maxCompletionTokens > 0) || !(tokensPerSecond > 0)) {
+    throw new Error(`hindsight retain budget: maxCompletionTokens (${maxCompletionTokens}) and ` + `tokensPerSecond (${tokensPerSecond}) must both be positive`);
+  }
+  return Math.ceil(maxCompletionTokens / tokensPerSecond);
+}
+function hindsightRetainClientTimeoutSeconds() {
+  return clientBudgetSeconds(LITELLM_TIMEOUT_TIERS.retain, hindsightRetainLlmTimeoutSeconds());
+}
+var HINDSIGHT_RETAIN_CLIENT_DEADLINE_S = hindsightRetainClientTimeoutSeconds() + LITELLM_ROUTER_MARGIN_S;
 var HINDSIGHT_HEALTHCHECK_PY = 'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8888/health",timeout=4).getcode()==200 else 1)';
 var HINDSIGHT_HEALTHCHECK_CMD = `python3 -c '${HINDSIGHT_HEALTHCHECK_PY}'`;
 var DOCKER_PROBE_TIMEOUT_MS = 60 * 1000;

package/dist/cli/notion-write-pretool.mjs

@@ -12088,7 +12088,8 @@ var HindsightConfigSchema = exports_external.object({
     retain: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `retain` LLM op (memory ingestion). Emits " + "`HINDSIGHT_API_RETAIN_LLM_*`. Absent \u2192 uses the global model/provider."),
     reflect: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `reflect` LLM op (synthesis / mental-model " + "refresh). Emits `HINDSIGHT_API_REFLECT_LLM_*`. Absent \u2192 uses global."),
     consolidation: HindsightPerOpLlmSchema.optional().describe("Per-op override for the `consolidation` LLM op (background memory " + "merge). Emits `HINDSIGHT_API_CONSOLIDATION_LLM_*`. Absent \u2192 global.")
-  }).optional().describe("LLM knob for the hindsight container. The flat `provider`/`model` set " + "the global default (backward-compatible); optional `retain`/`reflect`/" + "`consolidation` blocks override individual ops. All fields optional; " + "unset fields fall back to the hard-coded defaults.")
+  }).optional().describe("LLM knob for the hindsight container. The flat `provider`/`model` set " + "the global default (backward-compatible); optional `retain`/`reflect`/" + "`consolidation` blocks override individual ops. All fields optional; " + "unset fields fall back to the hard-coded defaults."),
+  env: exports_external.record(exports_external.union([exports_external.string(), exports_external.number(), exports_external.boolean()])).optional().describe("Operator overrides for switchroom's capability-gated Hindsight " + "performance defaults. Only the keys switchroom actually manages are " + "honoured (`HINDSIGHT_PERF_ENV_KEYS` in " + "src/setup/hindsight-perf-defaults.ts: RERANKER_LOCAL_FP16, " + "LLM_MAX_CONCURRENT, RETAIN/CONSOLIDATION_LLM_MAX_CONCURRENT, " + "RECALL_MAX_CANDIDATES_PER_SOURCE, LINK_EXPANSION_PER_ENTITY_LIMIT, " + "LINK_EXPANSION_TIMEOUT, LLM_REASONING_EFFORT), plus the " + "embedded-PostgreSQL (pg0) sizing keys switchroom manages in " + "src/setup/hindsight-pg-defaults.ts (`HINDSIGHT_PG_ENV_KEYS`: " + "SWITCHROOM_HINDSIGHT_PG_EFFECTIVE_CACHE_SIZE, " + "SWITCHROOM_HINDSIGHT_PG_SHARED_BUFFERS \u2014 a postgres size string such " + "as `4GB`, or the sentinel `off` to leave pg0's own default for that " + "one knob). A value set here " + "REPLACES switchroom's default and is emitted even when the gating " + "capability is absent, so an operator can always force a knob. Other " + "`HINDSIGHT_API_*` keys are deliberately IGNORED \u2014 a blanket " + "passthrough would collide with the vars startHindsight() derives " + "itself (HINDSIGHT_API_PORT, the retain token/deadline budget).")
 });
 var MicrosoftWorkspaceConfigSchema = exports_external.object({
   microsoft_client_id: exports_external.string().min(1).optional().describe("Microsoft OAuth application (client) ID from Entra portal " + "(literal string or vault reference e.g. " + "'vault:microsoft-oauth-client-id'). OPTIONAL \u2014 omit it to use " + "switchroom's shipped default Microsoft app (zero-config). " + "Set it only to bring your own Entra app (BYO)."),