Compare commits

...

4 Commits

Author SHA1 Message Date
xiaomo eb027e70f4 fix: include step content in continuation prompt (closes #466)
- Add `content: string | null` to RoleStep type
- Resolve contentHash → text for the last step when building ThreadContext
- Update buildAgentPrompt to include <output> tag with step content
- Add 16k content quota with truncation
- Update tests
2026-05-24 13:41:00 +00:00
xiaomo 8fbbbce07e Merge pull request 'chore: cleanup dead code and update CLI docs' (#468) from chore/cleanup-cli-docs into main 2026-05-24 11:42:36 +00:00
xiaoju f115718564 chore: cleanup dead code and update CLI docs
- Remove cmdThreadRunning dead code (CLI uses --status running now)
- Remove step read from README (command not registered)
- Update cli-reference.ts to reflect new four-layer commands

Refs #463
2026-05-24 11:41:02 +00:00
xiaomo 5c0eabda8e Merge pull request 'feat: restructure CLI commands (workflow/thread/step/turn)' (#467) from fix/463-http-methods into main 2026-05-24 11:37:50 +00:00
9 changed files with 179 additions and 43 deletions
@@ -531,13 +531,25 @@ export async function executeThread(
timestamp: nowMs,
parentState: options.parentStateHash,
},
steps: input.steps.map((out, i) => ({
role: out.role,
contentHash: out.contentHash,
meta: out.meta,
refs: out.refs,
timestamp: replayTs?.[i] ?? prefilled?.[i]?.timestamp ?? nowMs + i,
})),
steps: await Promise.all(
input.steps.map(async (out, i) => {
// Resolve content for the last step (most relevant for the next agent).
// Earlier steps only carry meta summaries to avoid bloating the prompt.
const isLast = i === input.steps.length - 1;
let content: string | null = null;
if (isLast) {
content = await getContentMerklePayload(io.cas, out.contentHash);
}
return {
role: out.role,
contentHash: out.contentHash,
content,
meta: out.meta,
refs: out.refs,
timestamp: replayTs?.[i] ?? prefilled?.[i]?.timestamp ?? nowMs + i,
};
}),
),
};
const runtime: WorkflowRuntime = {
@@ -71,6 +71,7 @@ export type RoleStep<M extends RoleMeta> = {
role: K;
meta: M[K];
contentHash: string;
content: string | null;
refs: string[];
timestamp: number;
};
@@ -71,7 +71,8 @@ async function buildRoleStepsFromStates<M extends RoleMeta>(
cas: CasStore,
): Promise<RoleStep<M>[]> {
const steps: RoleStep<M>[] = [];
for (const st of chronologicalStates) {
for (let idx = 0; idx < chronologicalStates.length; idx++) {
const st = chronologicalStates[idx];
if (st.payload.role === END) {
continue;
}
@@ -79,10 +80,13 @@ async function buildRoleStepsFromStates<M extends RoleMeta>(
if (contentParsed === null || contentParsed.kind !== "content") {
throw new Error(`buildThreadContext: expected content node at ${st.payload.content}`);
}
// Resolve full text content for the last step only
const isLast = idx === chronologicalStates.length - 1;
steps.push({
role: st.payload.role,
meta: st.payload.meta,
contentHash: st.payload.content,
content: isLast ? contentParsed.node.payload : null,
refs: [...contentParsed.node.refs],
timestamp: st.payload.timestamp,
} as RoleStep<M>);
@@ -88,6 +88,7 @@ async function advanceOneRound<M extends RoleMeta>(
const step = {
role: next,
contentHash,
content: contentPayload,
meta,
refs,
timestamp: Date.now(),
@@ -30,7 +30,7 @@ describe("buildAgentPrompt", () => {
expect(text).not.toContain("## Tools");
});
test("single step shows hash and meta, and includes tools", async () => {
test("single step shows meta and content, and includes tools", async () => {
const onlyHash = "01HASHSINGLESTEP0000000001";
const ctx: AgentContext = {
start: startTask("user task"),
@@ -42,6 +42,7 @@ describe("buildAgentPrompt", () => {
{
role: "coder",
contentHash: onlyHash,
content: "Here is my implementation of the feature.",
meta: { files: ["a.ts"] },
refs: [onlyHash],
timestamp: 2,
@@ -52,13 +53,39 @@ describe("buildAgentPrompt", () => {
expect(text).toContain("## Task");
expect(text).toContain("user task");
expect(text).toContain("## Step: coder");
expect(text).toContain(`ContentHash: ${onlyHash}`);
expect(text).toContain('Meta: {"files":["a.ts"]}');
expect(text).toContain("<output>");
expect(text).toContain("Here is my implementation of the feature.");
expect(text).toContain("</output>");
expect(text).toContain("## Tools");
expect(text).toContain("uncaged-workflow thread 01TEST000000000000000000TR");
});
test("two or more steps: previous steps are meta-only; latest step includes hash", async () => {
test("single step with null content omits output tag", async () => {
const onlyHash = "01HASHSINGLESTEP0000000001";
const ctx: AgentContext = {
start: startTask("user task"),
depth: 0,
bundleHash: "TESTHASH00001",
threadId: "01TEST000000000000000000TR",
currentRole: { name: "coder", systemPrompt: "Be helpful." },
steps: [
{
role: "coder",
contentHash: onlyHash,
content: null,
meta: { files: ["a.ts"] },
refs: [onlyHash],
timestamp: 2,
},
],
};
const text = await buildAgentPrompt(ctx);
expect(text).not.toContain("<output>");
expect(text).toContain('Meta: {"files":["a.ts"]}');
});
test("two or more steps: previous steps are meta-only; latest step includes content", async () => {
const plannerHash = "01HASHPLANNER0000000000001";
const coderHash = "01HASHCODER0000000000000001";
const ctx: AgentContext = {
@@ -71,6 +98,7 @@ describe("buildAgentPrompt", () => {
{
role: "planner",
contentHash: plannerHash,
content: null,
meta: { plan: "short" },
refs: [plannerHash],
timestamp: 2,
@@ -78,6 +106,7 @@ describe("buildAgentPrompt", () => {
{
role: "coder",
contentHash: coderHash,
content: "I reviewed the code and found 4 lint issues:\n1. Missing semicolon on line 42\n2. Unused import on line 3",
meta: { done: true },
refs: [coderHash],
timestamp: 3,
@@ -90,10 +119,11 @@ describe("buildAgentPrompt", () => {
expect(text).toContain("### Step 1: planner");
expect(text).toContain('Summary: {"plan":"short"}');
expect(text).toContain("## Latest Step: coder");
expect(text).toContain(`ContentHash: ${coderHash}`);
expect(text).toContain('Meta: {"done":true}');
expect(text).toContain("<output>");
expect(text).toContain("I reviewed the code and found 4 lint issues:");
expect(text).toContain("</output>");
expect(text).toContain("## Tools");
expect(text).toContain("uncaged-workflow thread 01TEST000000000000000000TR");
});
test("parentState null omits Parent Context section", async () => {
@@ -125,7 +155,7 @@ describe("buildAgentPrompt", () => {
expect(text).toContain(`uncaged-workflow cas get ${parentHash}`);
});
test("middle steps show meta summary only and latest shows hash", async () => {
test("middle steps show meta summary only and latest shows content", async () => {
const ha = "01HASHA00000000000000000001";
const hb = "01HASHB00000000000000000001";
const hc = "01HASHC00000000000000000001";
@@ -139,6 +169,7 @@ describe("buildAgentPrompt", () => {
{
role: "a",
contentHash: ha,
content: null,
meta: { n: 1 },
refs: [ha],
timestamp: 2,
@@ -146,6 +177,7 @@ describe("buildAgentPrompt", () => {
{
role: "b",
contentHash: hb,
content: null,
meta: { n: 2 },
refs: [hb],
timestamp: 3,
@@ -153,6 +185,7 @@ describe("buildAgentPrompt", () => {
{
role: "c",
contentHash: hc,
content: "Final output from role c",
meta: { n: 3 },
refs: [hc],
timestamp: 4,
@@ -162,7 +195,35 @@ describe("buildAgentPrompt", () => {
const text = await buildAgentPrompt(ctx);
expect(text).toContain('Summary: {"n":1}');
expect(text).toContain('Summary: {"n":2}');
expect(text).toContain(`ContentHash: ${hc}`);
expect(text).toContain("## Latest Step: c");
expect(text).toContain("<output>");
expect(text).toContain("Final output from role c");
expect(text).toContain("</output>");
});
test("content is truncated when exceeding quota", async () => {
const longContent = "x".repeat(20_000);
const hash = "01HASHLONG000000000000000001";
const ctx: AgentContext = {
start: startTask("task"),
depth: 0,
bundleHash: "TESTHASH00001",
threadId: "01TEST000000000000000000TR",
currentRole: { name: "r", systemPrompt: "S" },
steps: [
{
role: "r",
contentHash: hash,
content: longContent,
meta: {},
refs: [],
timestamp: 2,
},
],
};
const text = await buildAgentPrompt(ctx);
expect(text).toContain("<output>");
expect(text).toContain("... (truncated)");
expect(text.length).toBeLessThan(20_000);
});
});
+1 -3
View File
@@ -16,7 +16,7 @@ workflow → thread → step → turn
- **Workflow** (layer 1): YAML template with roles and routing graph
- **Thread** (layer 2): Single workflow execution instance
- **Step** (layer 3): One moderator→agent→extract cycle
- **Turn** (layer 4): Agent-internal interactions (use `step read` or CAS to inspect)
- **Turn** (layer 4): Agent-internal interactions (use `step show` or CAS to inspect)
This package has no library `src/index.ts` — it is consumed as a CLI binary only.
@@ -72,7 +72,6 @@ uwf thread stop 01ARZ3NDEKTSV4RRFFQ69G5FAV
|---------|-------------|
| `uwf step list <thread-id>` | List all steps in a thread chronologically |
| `uwf step show <step-hash>` | Show step metadata and frontmatter |
| `uwf step read <step-hash> [--before N]` | Read step output as markdown |
| `uwf step fork <step-hash>` | Fork a thread from a specific step |
Examples:
@@ -80,7 +79,6 @@ Examples:
```bash
uwf step list 01ARZ3NDEKTSV4RRFFQ69G5FAV
uwf step show 32GCDE899RRQ3
uwf step read 32GCDE899RRQ3 --before 3
uwf step fork 32GCDE899RRQ3
```
+1 -12
View File
@@ -9,7 +9,6 @@ import type {
AgentConfig,
CasRef,
ModeratorContext,
RunningThreadsOutput,
StartNodePayload,
StartOutput,
StepContext,
@@ -23,12 +22,7 @@ import type {
import { createProcessLogger, generateUlid, type ProcessLogger } from "@uncaged/workflow-util";
import { config as loadDotenv } from "dotenv";
import { parse, stringify } from "yaml";
import {
createMarker,
deleteMarker,
isThreadRunning,
listRunningThreads,
} from "../background/index.js";
import { createMarker, deleteMarker, isThreadRunning } from "../background/index.js";
import {
appendThreadHistory,
createUwfStore,
@@ -1016,8 +1010,3 @@ export async function cmdThreadCancel(
return { thread: threadId, cancelled: true };
}
export async function cmdThreadRunning(storageRoot: string): Promise<RunningThreadsOutput> {
const threads = await listRunningThreads(storageRoot);
return { threads };
}
@@ -0,0 +1,64 @@
import type { AgentContext } from "@uncaged/workflow-runtime";
/** Max characters of step content to include in the prompt. */
const CONTENT_QUOTA = 16_000;
/** Builds the full agent prompt: system instructions plus summarized thread history. */
export async function buildAgentPrompt(ctx: AgentContext): Promise<string> {
const lines: string[] = [];
lines.push(ctx.currentRole.systemPrompt);
lines.push("");
lines.push("## Task");
lines.push(ctx.start.content);
const { steps } = ctx;
if (steps.length === 0) {
return lines.join("\n");
}
if (steps.length === 1) {
const s = steps[0];
lines.push("");
lines.push(`## Step: ${s.role}`);
lines.push("");
lines.push(`Meta: ${JSON.stringify(s.meta)}`);
appendContent(lines, s.content);
} else {
lines.push("");
lines.push("## Previous Steps");
for (let i = 0; i < steps.length - 1; i++) {
const s = steps[i];
lines.push("");
lines.push(`### Step ${i + 1}: ${s.role}`);
lines.push(`Summary: ${JSON.stringify(s.meta)}`);
}
const last = steps[steps.length - 1];
lines.push("");
lines.push(`## Latest Step: ${last.role}`);
lines.push("");
lines.push(`Meta: ${JSON.stringify(last.meta)}`);
appendContent(lines, last.content);
}
lines.push("");
lines.push("## Tools");
lines.push(
`Use \`uncaged-workflow thread ${ctx.threadId}\` to read full details of any previous step.`,
);
return lines.join("\n");
}
function appendContent(lines: string[], content: string | null | undefined): void {
if (content === null || content === undefined || content.trim() === "") {
return;
}
const truncated =
content.length > CONTENT_QUOTA
? `${content.slice(0, CONTENT_QUOTA)}\n... (truncated)`
: content;
lines.push("");
lines.push("<output>");
lines.push(truncated);
lines.push("</output>");
}
+19 -13
View File
@@ -15,7 +15,7 @@ uwf setup --provider <name> --base-url <url> \\
## Workflow Commands
\`\`\`
uwf workflow put <file> # register a workflow from YAML file
uwf workflow add <file> # register a workflow from YAML file
uwf workflow show <id> # show workflow by name or CAS hash
uwf workflow list # list all registered workflows
\`\`\`
@@ -24,20 +24,27 @@ uwf workflow list # list all registered workflows
\`\`\`
uwf thread start <workflow> -p <prompt> # create a thread (no execution)
uwf thread step <thread-id> # execute one moderator→agent→extract cycle
uwf thread exec <thread-id> # execute one moderator→agent→extract cycle
[--agent <cmd>] # override agent command
[-c, --count <number>] # run multiple steps (default: 1)
[--background] # run in background
uwf thread show <thread-id> # show thread head pointer
uwf thread list # list active threads
[--all] # include archived threads
uwf thread kill <thread-id> # terminate and archive a thread
uwf thread steps <thread-id> # list all steps in a thread
uwf thread list # list threads
[--status <status>] # filter: idle, running, or completed
uwf thread read <thread-id> # render thread context as markdown
[--quota <chars>] # max output characters (default 32000)
[--before <step-hash>] # load steps before this hash (exclusive)
[--start] # include start step in output
uwf thread fork <step-hash> # fork a thread from a specific step
uwf thread step-details <step-hash> # dump full detail node of a step as YAML
uwf thread stop <thread-id> # stop background execution (keep thread active)
uwf thread cancel <thread-id> # cancel thread (stop + move to history)
\`\`\`
## Step Commands
\`\`\`
uwf step list <thread-id> # list all steps in a thread
uwf step show <step-hash> # show details of a specific step
uwf step fork <step-hash> # fork a thread from a specific step
\`\`\`
## CAS Commands
@@ -78,10 +85,9 @@ uwf -V, --version # print version
## Key Concepts
- **Workflow**: YAML definition with roles, conditions, and a routing graph; stored as a CAS node identified by its XXH64 hash.
- **Thread**: A single workflow execution (ULID). State is an immutable CAS chain; active threads are indexed in \`threads.yaml\`.
- **Step**: One moderator→agent→extract cycle. Run \`uwf thread step\` repeatedly until \`$END\`.
- **CAS**: Content-Addressed Storage — all nodes are immutable and identified by hash.
- **Role**: Named actor with goal, capabilities, procedure, output, and frontmatter schema; the moderator routes between roles.
- **Edge Prompt**: Required instruction on each graph edge — the moderator's dispatch message to the agent.
- **Thread**: A running instance of a workflow; points to a chain of CAS step nodes.
- **Step**: One moderator→agent→extract cycle; stored as a CAS node with output + detail refs.
- **Turn**: Agent-internal interaction (within a single step); stored per-turn in the detail node.
- **CAS**: Content-addressable store; every artifact (workflows, steps, details, turns) is hashed.
`;
}