@spendgraph/prompt 0.5.0 → 0.7.0

package/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 spendgraph
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/README.md

@@ -1,243 +1,49 @@
 # @spendgraph/prompt
 
-Pull a stored prompt or write one in code, render it, and record what it cost.
-Talks to spendgraph through `@spendgraph/sdk` and to nothing else.
+Pull a stored prompt or build one in code, render it, and record what it cost.
 
-```sh
+```bash
 npm install @spendgraph/prompt
 ```
 
-## Two ways in, one prompt
-
-`pullPrompt` fetches the wording from the server. `buildCustomPrompt` declares
-it in code. Both hand back the same `Prompt`, so `render`, `serialize` and
-`call` behave identically and nothing downstream has to know which it was
-given.
-
-```ts
-import { PromptClient, buildCustomPrompt } from "@spendgraph/prompt";
-
-const prompts = new PromptClient({
-  apiKey: process.env.SPENDGRAPH_API_KEY,
-  baseUrl: "https://your-spendgraph.example.com",
-});
-
-const stored = await prompts.pull("billing-explainer");
-const local = buildCustomPrompt({
-  name: "billing-explainer",
-  blocks: [{ title: "Role", body: "You explain invoices to {audience}." }],
-  question: "Explain this line item in {max_words} words.",
-});
-```
-
-`pull` takes an id or a slug — the server resolves either. `pullPrompt(handle,
-opts)` is the same thing without keeping a client around; it builds one per
-call, so a service pulling repeatedly wants the class, which caches.
-
-## Running one
-
-Bind a model and the prompt runs itself:
-
 ```ts
-import { Llm } from "@spendgraph/llms";
-
-const llm = new Llm({ client: anthropic, model: "claude-opus-5" });
-const chain = stored.bind(llm);
-
-const answer = await chain.invoke({ audience: "students", max_words: 50 });
-answer.output;
-answer.rolloutId;
-
-await chain.stream(values, { onText: (delta) => res.write(delta) });
-const answers = await chain.batch(cases, { concurrency: 4 });
-```
-
-`bind` asks for a shape, not an import — anything with `call(messages)` returning
-an outcome satisfies `Model`, and `Llm`'s reply already is one, so neither
-package depends on the other.
-
-### Or keep the call yourself
+import { PromptClient } from "@spendgraph/prompt";
 
-`call` renders, runs the model call you give it, and records what happened
-around it. This package never sees the provider response, which is why the call
-is handed to it rather than made by it.
+const prompts = new PromptClient({ apiKey, baseUrl });
+const prompt = await prompts.pull("billing-explainer");
 
-```ts
-const reply = await stored.call({ audience: "students", max_words: 50 }, async ({ messages }) => {
+const reply = await prompt.call({ audience: "students" }, async ({ messages }) => {
   const res = await anthropic.messages.create({ model, max_tokens: 400, messages });
   return { output: res.content[0].text, model, inputTokens: 400, outputTokens: 12 };
 });
 ```
 
-It fills in the version, fields, messages, latency and status; you return the
-text, model and tokens. Return the tokens or every cost on the prompt reads as
-zero — the first call that forgets warns once.
-
-Recording is on for every prompt and is fire-and-forget. There is no
-client-level switch: pass `{ report: false }` on the call that should not be
-recorded, which is where you know whether it should.
-
-What was sent is built once and shared by the success path and the failure path,
-so the two cannot disagree about it. That is the thing hand-written reporting
-gets wrong. A callback that throws is recorded as failed and then rethrown: a
-provider call that throws is otherwise recorded nowhere at all, which leaves the
-run most in need of explaining with no evidence.
-
-### What each kind records
-
-A **server** prompt has a row and a version behind it, so a call writes a
-rollout. A **custom** prompt has neither, and `POST /api/v1/prompts/:id/rollouts`
-needs both — so it records usage instead. The tokens still land on the
-dashboard, attributed to the model and tagged with the prompt's name; only the
-wording goes unversioned. Read `prompt.source` to tell them apart.
-
-A custom prompt is keyed on its name rather than a generated id, because that
-name is what tags the usage event — a random one would file every run of the
-same prompt under a different heading.
-
-Leave `sdk` off `buildCustomPrompt` and the prompt touches the network never.
-`{ report: false }` on any call runs the model and records nothing.
-
-## Conversation history
-
-Pass prior turns and they render between the system turn and the question,
-oldest first.
-
-```ts
-const history = [
-  { role: "user", content: "What is a proration?" },
-  { role: "assistant", content: "A mid-cycle adjustment." },
-];
-
-prompt.format(values, { history });
-await prompt.call(values, ({ messages }) => call(messages), { history });
-```
-
-History is passed through **verbatim** — it is a record of what was already
-said, not a template, so `{placeholders}` inside it are left alone. Only the
-prompt's own blocks and question are substituted. A `system` turn in the history
-is dropped: the prompt owns that turn, and two of them is a different request
-from the one the prompt describes.
-
-Tools are still selected on the question, not on an older turn — the shortlist
-has to serve what is being asked now.
-
-A rollout records at most 50 messages, which is what the route accepts. A longer
-conversation still runs; only its rollout is refused, and that refusal reaches
-`onReportError` rather than your call — so the first time it happens this warns,
-once, while somebody is still watching. `MAX_RECORDED_MESSAGES` is exported if
-you want to trim before it bites.
-
-## Fields
-
-A `{placeholder}` is declared as a `FieldSpec` — a name, a type, whether it is
-required, and how it renders. A missing required field throws before anything is
-sent. Types come from `@spendgraph/sdk`, because a tool's arguments and a graph
-node's inputs are the same problem.
-
-```ts
-prompt.format(values);     // Message[], validated and substituted
-prompt.serialize(values);  // the field map that render used
-```
-
-## Caching, and invalidating it
-
-`pull` serves a stale copy immediately and refreshes behind the caller, so an
-edit takes effect within a TTL without any request paying for the fetch.
-
-`promote` invalidates for you. Doing it by hand needs to drop **both** handles,
-not just the one passed: `pull` keys on whatever string it was given, so the
-same prompt sits under its uuid and its slug at once, and `promote` is only
-reachable with a uuid while the dashboard teaches pulling by slug. Dropping one
-left the other warm for a full TTL, still rendering the wording the promotion
-replaced.
-
-The delete runs even when nothing is stored under the handle: a cold isolate has
-a fetch in flight and no entry yet, and the delete is what stops that in-flight
-result being stored after the promotion.
-
-```ts
-await prompts.promote(promptId, versionId);  // invalidates
-prompts.invalidate(promptId);                // both handles
-prompts.invalidate();                        // everything
-```
-
-`onPullError` is worth setting. Without it a background refresh that has stopped
-resolving is silent, and a rename on the dashboard freezes a running service
-with nothing anywhere saying so.
+## What you get
 
-## Versions and datasets
+- **Two ways in, one object.** `pullPrompt` fetches the wording from the
+  dashboard, `buildCustomPrompt` declares it in code, and everything downstream
+  behaves the same either way.
+- **The model call stays yours.** This package never sees the provider response
+   — it renders, hands you the messages, and records what happened around them.
+- **One record, two paths.** What was sent is built once and shared by the
+  success and failure paths, so the two cannot disagree.
+- **A missing field throws before anything is sent**, not after you paid for the
+  call.
+- **`packContext` fits competing sources into one window** — instructions and
+  the question kept whole, retrieval held to its own share, and whatever is left
+  going to the history.
 
-```ts
-await prompts.versions(promptId, { origin: "user", limit: 20 });
-await prompts.cases(promptId);
-await prompts.setCases(promptId, cases);
-```
-
-`setCases` replaces the whole dataset. A dataset is a set — "which cases am I
-evaluating against" has one answer at a time, and a merge would leave no way to
-remove a case.
-
-## Running server-side
-
-`run`, `sample` and `runAll` execute the prompt on the server, where the spec,
-rendering and pricing already live. This is the batch path. A production request
-should pull, render and report instead: the server-side call adds a hop and makes
-spendgraph a dependency of your uptime, which is the right trade for evaluation
-and the wrong one for a user waiting on a response.
-
-```ts
-await prompts.run(promptId, values);
-await prompts.sample(promptId, values, { k: 5 });
-await prompts.runAll(promptId, values);      // one rollout per saved model
-```
-
-`maxCostMicros` caps what those spend. Omit it and the client warns once that it
-is unbounded; pass `null` to say you meant it.
-
-## Tools
-
-`call` and `invoke` accept anything that hands out a turn — `toolbus()` from
-`@spendgraph/tools`, or your own. The callback gets the turn fully typed; the
-rollout gets the tools offered and the steps taken.
-
-```ts
-await prompt.call(values, ({ messages, turn }) => call(messages, turn), { tools: bus });
-```
-
-Which tools were offered is recorded as well as which were called: without it a
-rollout cannot tell "chose not to" from "was never offered", which are opposite
-bugs.
-
-## What is exported
-
-The main entry is six values, because everything else is already wired into
-`PromptClient`:
-
-```ts
-import {
-  PromptClient,          // pull, run, report, versions, datasets
-  pullPrompt,            // one prompt, without keeping a client
-  buildCustomPrompt,     // a prompt written in code
-  BudgetExceededError,
-  FieldValidationError,
-  MAX_RECORDED_MESSAGES,
-} from "@spendgraph/prompt";
-```
-
-Everything a prompt can do hangs off the object itself — `format`, `serialize`,
-`call`, `bind` — so there is nothing else to import to use one.
-
-Two subpaths hold the rest:
+## Docs
 
 | | |
 | --- | --- |
-| `@spendgraph/prompt/render` | `renderMessages` · `compileSystemPrompt` · `applyVariables` · `findVariables` |
-| `@spendgraph/prompt/internals` | `PullCache` · `Budget` · `makePrompt` · `bind` · `mapLimit` · … |
-
-Reach for `internals` only to build your own client; `PromptClient` already
-wires all of it.
+| [Overview](https://spendgraph.locusgraph.com/docs/prompt/overview) | Two ways in, one prompt |
+| [Fields](https://spendgraph.locusgraph.com/docs/prompt/fields) | Placeholders, types, and history |
+| [Calling a prompt](https://spendgraph.locusgraph.com/docs/prompt/calling) | call, bind, tools, and what is recorded |
+| [Caching](https://spendgraph.locusgraph.com/docs/prompt/caching) | Stale-while-refresh, and both handles |
+| [Running server-side](https://spendgraph.locusgraph.com/docs/prompt/running) | run, sample, runAll, and the ceiling |
+| [Versions and datasets](https://spendgraph.locusgraph.com/docs/prompt/datasets) | The split the server decides, and why |
 
 ## License
 
-MIT
+Apache-2.0

package/dist/budget/budget.d.ts

@@ -14,6 +14,16 @@ export declare class Budget {
      * `undefined` means no ceiling and warns once — an unbounded client in a
      * scheduled script is how a surprise bill happens. `null` means the same
      * thing deliberately, and says nothing.
+     *
+     * A ceiling that is `NaN` or negative is refused rather than accepted.
+     * `NaN >= NaN` is false, so a `NaN` limit never fires and the guard against an
+     * expensive accident silently is not there — and
+     * `Number(process.env.MAX_COST_MICROS)` on an unset variable is `NaN`, which
+     * is how it arrives without anyone writing it. A negative ceiling is refused
+     * because it can only be a mistake, and expressing that mistake as "every
+     * request is refused" sends someone looking in the wrong place.
+     *
+     * `0` is kept: spending nothing is a thing a caller can mean.
      */
     constructor(maxCostMicros?: number | null);
     spent(): number;

package/dist/budget/budget.js

@@ -1,31 +1 @@
-import { BudgetExceededError } from "./errors.js";
-let warned = false;
-export class Budget {
-    used = 0;
-    limit;
-    constructor(maxCostMicros) {
-        this.limit = maxCostMicros ?? Infinity;
-        if (maxCostMicros === undefined && !warned) {
-            warned = true;
-            console.warn("[prompt] No maxCostMicros set — this client can spend without limit. " +
-                "Pass maxCostMicros, or null to say you meant it.");
-        }
-    }
-    spent() {
-        return this.used;
-    }
-    remaining() {
-        return this.limit === Infinity ? Infinity : Math.max(0, this.limit - this.used);
-    }
-    add(costMicros) {
-        if (Number.isFinite(costMicros) && costMicros > 0)
-            this.used += costMicros;
-    }
-    assertAffordable() {
-        if (this.used >= this.limit)
-            throw new BudgetExceededError(this.used, this.limit);
-    }
-}
-export function resetBudgetWarning() {
-    warned = false;
-}
+import{BudgetExceededError as t}from"./errors.js";let i=!1;class s{used=0;limit;constructor(e){if(typeof e=="number"&&e<0)throw new Error(`maxCostMicros is ${e}. A ceiling below zero refuses every request, which is rarely what was meant. Pass 0 to spend nothing, or null for no limit.`);if(typeof e=="number"&&!(Number.isFinite(e)||e===Number.POSITIVE_INFINITY))throw new Error(`maxCostMicros is ${e}, which is not a ceiling \u2014 nothing would ever reach it. Pass a number of micro-USD, or null for no limit.`);this.limit=e??1/0,e===void 0&&!i&&(i=!0,console.warn("[prompt] No maxCostMicros set \u2014 this client can spend without limit. Pass maxCostMicros, or null to say you meant it."))}spent(){return this.used}remaining(){return this.limit===1/0?1/0:Math.max(0,this.limit-this.used)}add(e){Number.isFinite(e)&&e>0&&(this.used+=e)}assertAffordable(){if(this.used>=this.limit)throw new t(this.used,this.limit)}}function u(){i=!1}export{s as Budget,u as resetBudgetWarning};

package/dist/budget/errors.js

@@ -1,11 +1 @@
-export class BudgetExceededError extends Error {
-    spentMicros;
-    limitMicros;
-    constructor(spentMicros, limitMicros) {
-        super(`Cost ceiling reached: spent $${(spentMicros / 1e6).toFixed(4)} of ` +
-            `$${(limitMicros / 1e6).toFixed(4)}. Raise maxCostMicros or start a new client.`);
-        this.name = "BudgetExceededError";
-        this.spentMicros = spentMicros;
-        this.limitMicros = limitMicros;
-    }
-}
+import{formatMicros as t}from"@spendgraph/sdk";class i extends Error{spentMicros;limitMicros;constructor(r,e){super(`Cost ceiling reached: spent ${t(r,4)} of ${t(e,4)}. Raise maxCostMicros or start a new client.`),this.name="BudgetExceededError",this.spentMicros=r,this.limitMicros=e}}export{i as BudgetExceededError};

package/dist/budget/index.js

@@ -1,2 +1 @@
-export { Budget, resetBudgetWarning } from "./budget.js";
-export { BudgetExceededError } from "./errors.js";
+import{Budget as t,resetBudgetWarning as d}from"./budget.js";import{BudgetExceededError as g}from"./errors.js";export{t as Budget,g as BudgetExceededError,d as resetBudgetWarning};

package/dist/build/build.d.ts

@@ -7,12 +7,21 @@ export interface BuildOptions {
     metadata?: Record<string, string | number | boolean>;
     /** Replaces the once-only warning about a callback that returned no tokens. */
     onEmptyTokens?: (entry: ReportInput) => void;
+    /**
+     * Called when sending the usage fails.
+     *
+     * The send is fire-and-forget so a telemetry outage cannot break the call it
+     * measures, which leaves nothing to catch it — and what is lost is spend
+     * data, which nothing downstream can reconstruct. `PromptClient` has the same
+     * option for rollouts and passes it down to prompts it builds.
+     */
+    onReportError?: (err: unknown) => void;
 }
 /**
  * A prompt written in code rather than pulled from the server.
  *
- * The same `Prompt` `pullPrompt` returns — same `render`, same `serialize`,
- * same `trace` — so nothing downstream has to know which one it was handed.
+ * The same `Prompt` `pullPrompt` returns — same `format`, same `serialize`,
+ * same `call` — so nothing downstream has to know which one it was handed.
  * Give it an `sdk` and it records what the call cost; leave it off and it
  * touches the network never.
  */

package/dist/build/build.js

@@ -1,57 +1 @@
-import { makePrompt, noRecorder } from "../prompt/index.js";
-import { applyVariables } from "../render/index.js";
-function neverBreakTheCallItMeasured() { }
-let warnedAboutTokens = false;
-function warnOnEmptyTokens(entry) {
-    if (warnedAboutTokens)
-        return;
-    if ((entry.inputTokens ?? 0) > 0 || (entry.outputTokens ?? 0) > 0)
-        return;
-    warnedAboutTokens = true;
-    console.warn("[prompt] trace() recorded a call with no tokens. This package never sees " +
-        "the provider response, so return inputTokens and outputTokens from your callback " +
-        "or every cost on this prompt reads as zero.");
-}
-function usageRecorder(sdk, name, opts) {
-    const onEmpty = opts.onEmptyTokens ?? warnOnEmptyTokens;
-    return {
-        enabled: true,
-        write(_promptId, entry) {
-            if (entry.status === "failed")
-                return;
-            onEmpty(entry);
-            void sdk.ingest
-                .send([
-                {
-                    eventId: entry.rolloutId,
-                    model: entry.model,
-                    inputTokens: entry.inputTokens ?? 0,
-                    outputTokens: entry.outputTokens ?? 0,
-                    cacheReadTokens: entry.cacheReadTokens,
-                    cacheWriteTokens: entry.cacheWriteTokens,
-                    citationTokens: entry.citationTokens,
-                    reasoningTokens: entry.reasoningTokens,
-                    metadata: { ...opts.metadata, prompt: name },
-                },
-            ])
-                .catch(neverBreakTheCallItMeasured);
-        },
-    };
-}
-export function buildCustomPrompt(spec, opts = {}) {
-    const variables = spec.variables ?? {};
-    const blocks = (spec.blocks ?? []).map((b) => ({
-        title: applyVariables(b.title, variables),
-        body: applyVariables(b.body, variables),
-    }));
-    return makePrompt({
-        id: spec.name,
-        name: spec.name,
-        slug: null,
-        blocks,
-        question: applyVariables(spec.question ?? "", variables),
-        fields: spec.fields ?? [],
-        versionId: null,
-        models: spec.models ?? [],
-    }, "custom", opts.sdk ? usageRecorder(opts.sdk, spec.name, opts) : noRecorder);
-}
+import{makePrompt as l,noRecorder as d}from"../prompt/index.js";import{applyVariables as i}from"../render/index.js";let u=!1;function c(o){return(o.inputTokens??0)===0&&(o.outputTokens??0)===0}function k(){u||(u=!0,console.warn("[prompt] call() recorded a call with no tokens. This package never sees the provider response, so return inputTokens and outputTokens from your callback or every cost on this prompt reads as zero."))}function m(o,t,n){const a=n.onEmptyTokens??k,r=s=>{try{n.onReportError?.(s)}catch{}};return{enabled:!0,write(s,e){e.status!=="failed"&&(c(e)&&a(e),o.ingest.send([{eventId:e.rolloutId,model:e.model,inputTokens:e.inputTokens??0,outputTokens:e.outputTokens??0,cacheReadTokens:e.cacheReadTokens,cacheWriteTokens:e.cacheWriteTokens,citationTokens:e.citationTokens,reasoningTokens:e.reasoningTokens,metadata:{...n.metadata,prompt:t}}]).catch(r))}}}function f(o,t={}){const n=o.variables??{},a=(o.blocks??[]).map(s=>({title:i(s.title,n),body:i(s.body,n)})),r=i(o.question??"",n);return l({id:o.name,name:o.name,slug:null,blocks:a,question:r,fields:o.fields??[],versionId:null,models:o.models??[]},"custom",t.sdk?m(t.sdk,o.name,t):d)}export{f as buildCustomPrompt};

package/dist/build/index.js

@@ -1 +1 @@
-export { buildCustomPrompt } from "./build.js";
+import{buildCustomPrompt as r}from"./build.js";export{r as buildCustomPrompt};

package/dist/cache/cache.d.ts

@@ -12,6 +12,22 @@ export interface CacheOptions<T = unknown> {
     maxSize?: number;
     /** Injectable clock, so tests do not sleep. */
     now?: () => number;
+    /**
+     * Spread this fraction of the TTL across instances. Default 0.
+     *
+     * A fleet deployed together pulls together, so every copy's entry goes stale
+     * in the same second and they all refetch at once — and again a TTL later,
+     * forever. The server sees a wave rather than a trickle, and the wave gets
+     * taller as the fleet grows.
+     *
+     * Drawn once per cache rather than per entry: one process should not have its
+     * prompts expiring at a dozen different moments, and what needs to differ is
+     * one instance from the next. `0.1` keeps the TTL within a tenth of what was
+     * asked for, which is far less than the staleness a TTL already allows.
+     */
+    jitter?: number;
+    /** Injectable randomness, so the spread above is reproducible in a test. */
+    random?: () => number;
     /**
      * How long to leave a key alone after its refresh failed. Default 60.
      *