@prismshadow/penguin-server 0.0.1 → 0.1.1

package/README.md

@@ -37,7 +37,7 @@ pnpm --filter @prismshadow/penguin-server start   # node dist/index.js
 
 - **CSRF**: session cookie is `SameSite=Lax` and writes accept only `Content-Type: application/json`; no CSRF token yet.
 - **No login rate limiting**: add throttling at a reverse proxy for public deployments.
-- **Built-in admin starts as `admin` / `admin123`**: change it immediately (a banner keeps reminding until you do).
+- **Built-in admin starts as `admin` / `penguin-2026`**: change it immediately (a banner keeps reminding until you do).
 - Passwords use `node:crypto` scrypt (`scrypt$N$r$p$salt$hash`, timingSafeEqual); login sessions renew on a 7-day sliding window; the DB stores only the token's sha256.
 - Model credentials live in the Project's hidden 0600 config file; the API always masks them.
 - Behind a reverse proxy, disable response buffering for SSE paths (the server already sends `X-Accel-Buffering: no`) and forward `x-forwarded-proto` to enable Secure cookies.

package/dist/api/types.d.ts

@@ -159,6 +159,13 @@ interface ModelInfo {
      * unset (= treated as supported).
      */
     vision?: boolean;
+    /**
+     * Per-model max output tokens (TOML `max_tokens` annotation; user-only, never preset by the
+     * built-in catalog): when set it wins over the Agent's `system_config.model.max_tokens`;
+     * unset = inherit the Agent value. Lets a small-context model cap its output below the
+     * seeded per-Agent default (32000), which cannot fit into e.g. a 32k context window.
+     */
+    maxTokens?: number;
     pricing?: ModelPricingDto;
     /** Environment variable name to fall back to when api_key is empty (e.g. ANTHROPIC_API_KEY); unset if no known fallback. */
     envKey?: string;
@@ -192,6 +199,8 @@ interface ModelUpdateEntry {
     clientType?: string;
     /** Whether image input (vision/multimodal) is supported; omitted = supported (not persisted). */
     vision?: boolean;
+    /** Per-model max output tokens, a positive integer (wins over the Agent config); omitted = inherit the Agent value (the annotation is cleared). */
+    maxTokens?: number;
     pricing?: ModelPricingDto;
     /** Providing it overwrites and updates createdAt; omitting it keeps the existing value. */
     apiKey?: string;
@@ -222,6 +231,8 @@ interface ModelTestRequest {
     apiKey?: string;
     /** "Clear saved API key" is checked: the test does **not** fall back to the stored key (tests against the current draft). */
     clearApiKey?: boolean;
+    /** Speed-test mode: raises the probe's output cap (16 -> 64 tokens) so TTFT/TPS are measurable; costs a little more quota. */
+    speed?: boolean;
     /**
      * base URL (not secret; the frontend always sends the form's current value): a string
      * means use it, `null` means explicitly clear it (no fallback to the stored value),
@@ -231,10 +242,23 @@ interface ModelTestRequest {
     /** AgentHub client protocol; required for unsaved custom models (otherwise the id can't be auto-routed). */
     clientType?: string;
 }
-/** Connectivity test result: carries round-trip latency when ok, and a reason on failure (truncated raw provider error). */
+/**
+ * Connectivity test result: carries round-trip latency when ok, and a reason on failure
+ * (truncated raw provider error). When streamed content was observed, also carries the
+ * time-to-first-token and, when usage was reported (completed streams), the output rate.
+ */
 interface ModelTestResponse {
     ok: boolean;
     latencyMs?: number;
+    /** Time from request start to the first streamed content (thinking or text), ms. */
+    ttftMs?: number;
+    /**
+     * Output tokens per second over the streaming window (first content -> stream end), 1dp.
+     * Omitted unless the sample is large enough to mean anything: a reply of a few tokens is
+     * dominated by the final chunk's round trip, so the rate it yields tracks network jitter
+     * rather than the model. Callers render TTFT alone in that case.
+     */
+    tps?: number;
     message?: string;
 }
 /** Read-only vault entry display: key name + masked value; plaintext is never sent. */
@@ -277,6 +301,8 @@ interface AgentSummary {
     vaultKeyCount: number;
     /** Schedule count (number of .toml files under agent_state/schedule/, including invalid ones). */
     scheduleCount: number;
+    /** Installed Skill count (number of agent_state/skills/<name>/ directories with a SKILL.md). */
+    skillCount: number;
 }
 interface AgentsResponse {
     agents: AgentSummary[];
@@ -350,7 +376,7 @@ interface SessionInfo {
     approvalMode: ApprovalMode;
     /** Short title auto-generated by the model after the first turn; unset until generated (frontend shows "New Chat"). */
     title?: string;
-    /** Session source (for list badges); unset for user-created sessions. */
+    /** Session source (for list badges/folders), derived from core session_meta — the single source of truth (not stored in the DB); unset for user-created sessions. */
     source?: SessionSource;
     createdAt: string;
     status: SessionStatus;
@@ -379,12 +405,12 @@ interface DirListResponse {
     entries: DirEntryInfo[];
 }
 interface SessionCreateRequest {
-    /** Upstream id of the session's model (paired with provider); defaults to the Project's default Model. */
+    /** Upstream id of the session's model; always sent together with provider. Omit both for the Project's default Model. */
     modelId?: string;
     /**
-     * Provider group for `modelId`; when omitted, resolved via resolveModelRef semantics —
-     * modelId can only be resolved if it's globally unique by exact match in the config;
-     * 0 or multiple matches return 400.
+     * Provider group for `modelId`. A model reference is always a complete
+     * (provider, modelId) pair — the provider is never inferred, so sending one field
+     * without the other returns 400 instead of being resolved.
      */
     provider?: string;
     /** Any existing directory on the server; defaults to auto-creating a temporary Workspace. */
@@ -822,9 +848,9 @@ interface ScheduleItem {
     /** Bound target Session; defaults to creating a new Session each time. */
     sessionId?: string;
     workspace?: string;
-    /** Model for new-Session mode (upstream id, paired with provider); defaults to the Project's default reference. */
+    /** Model for new-Session mode (upstream id, always paired with provider); absent means the Project's default reference. */
     modelId?: string;
-    /** Provider group for `modelId`; when omitted, resolved via resolveModelRef semantics (resolvable only on a unique match). */
+    /** Provider group for `modelId`; present exactly when `modelId` is — a model reference is always a pair. */
     provider?: string;
     status: ScheduleStatus;
     invalidReason?: string;
@@ -852,9 +878,12 @@ interface ScheduleUpsertRequest {
     endAt?: string;
     sessionId?: string;
     workspace?: string;
-    /** Model for new-Session mode (upstream id); defaults to the Project's default reference. */
+    /** Model for new-Session mode (upstream id); always sent together with provider, omit both for the Project's default reference. */
     modelId?: string;
-    /** Provider group for `modelId`; when omitted, validated as uniquely resolvable via resolveModelRef semantics at save/reconciliation time. */
+    /**
+     * Provider group for `modelId`. Both fields are sent as a pair (400 otherwise); the
+     * pair is checked against the Project config at save/reconciliation time.
+     */
     provider?: string;
 }
 interface AgentImportRequest {