feat: replace $START _ status with new/resume semantics
#102
@@ -0,0 +1,9 @@
|
||||
---
|
||||
"@united-workforce/cli": minor
|
||||
"@united-workforce/util": patch
|
||||
---
|
||||
|
||||
feat: replace $START `_` status with `new`/`resume` semantics
|
||||
|
||||
BREAKING: All workflow YAML files must update `$START._` to `$START.new` + `$START.resume`.
|
||||
The `resume` edge prompt replaces the previously hardcoded resume message in the CLI.
|
||||
@@ -264,7 +264,8 @@ roles:
|
||||
|
||||
graph:
|
||||
$START:
|
||||
_: { role: "bootstrap", prompt: "Set up the Docker container and verify uwf is runnable." }
|
||||
new: { role: "bootstrap", prompt: "Set up the Docker container and verify uwf is runnable." }
|
||||
resume: { role: "bootstrap", prompt: "Review the previous run output and continue the walkthrough." }
|
||||
bootstrap:
|
||||
pass: { role: "config-and-registry", prompt: "Container {{{containerName}}} is ready. Validate config and workflow registration." }
|
||||
fail: { role: "$END", prompt: "Bootstrap failed: {{{error}}}. No container was created." }
|
||||
|
||||
@@ -227,7 +227,8 @@ roles:
|
||||
required: [$status, error]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: "planner", prompt: "Analyze the issue and produce an implementation plan." }
|
||||
new: { role: "planner", prompt: "Analyze the issue and produce an implementation plan." }
|
||||
resume: { role: "planner", prompt: "Review the previous run output and continue the work." }
|
||||
planner:
|
||||
insufficient_info: { role: "$SUSPEND", prompt: "信息不足,需要补充:{{{reason}}}" }
|
||||
ready: { role: "developer", prompt: "Implement the TDD test spec (CAS hash: {{{plan}}}) in repo {{{repoPath}}}. Repo remote: {{{repoRemote}}}." }
|
||||
|
||||
@@ -35,6 +35,7 @@ roles:
|
||||
required: [$status, thesis, keyPoints]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: "analyst", prompt: "Analyze the topic in the task and produce a structured summary with key points." }
|
||||
new: { role: "analyst", prompt: "Analyze the topic in the task and produce a structured summary with key points." }
|
||||
resume: { role: "analyst", prompt: "Review the previous analysis output and continue with additional context." }
|
||||
analyst:
|
||||
done: { role: "$END", prompt: "Analysis complete. Finish the workflow." }
|
||||
|
||||
@@ -53,7 +53,8 @@ roles:
|
||||
required: [$status, argument]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: "against", prompt: "Present your opening argument against the proposition." }
|
||||
new: { role: "against", prompt: "Present your opening argument against the proposition." }
|
||||
resume: { role: "against", prompt: "Review the previous debate output and continue the argument against the proposition." }
|
||||
against:
|
||||
conceded: { role: "$END", prompt: "The against side conceded. Debate over." }
|
||||
continue: { role: "for", prompt: "Counter the opposing argument: {{{argument}}}" }
|
||||
|
||||
@@ -25,6 +25,7 @@ roles:
|
||||
required: [$status, summary]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: "fixer", prompt: "Fix the code issue described in the task prompt." }
|
||||
new: { role: "fixer", prompt: "Fix the code issue described in the task prompt." }
|
||||
resume: { role: "fixer", prompt: "Review the previous run output and continue fixing the code issue." }
|
||||
fixer:
|
||||
done: { role: "$END", prompt: "Fix complete." }
|
||||
|
||||
@@ -215,7 +215,8 @@ roles:
|
||||
required: [$status, error]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: "planner", prompt: "Analyze the issue and produce an implementation plan." }
|
||||
new: { role: "planner", prompt: "Analyze the issue and produce an implementation plan." }
|
||||
resume: { role: "planner", prompt: "Review the previous run output and continue the work." }
|
||||
planner:
|
||||
insufficient_info: { role: "$SUSPEND", prompt: "信息不足,需要补充:{{{reason}}}" }
|
||||
ready: { role: "developer", prompt: "Implement the TDD test spec (CAS hash: {{{plan}}}) in repo {{{repoPath}}}." }
|
||||
|
||||
@@ -58,7 +58,10 @@ describe("C1: adapter JSON round-trip integration", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Do the work", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Do the work", location: null },
|
||||
resume: { role: "worker", prompt: "Resume the work", location: null },
|
||||
},
|
||||
worker: { done: { role: "$END", prompt: "completed", location: null } },
|
||||
},
|
||||
});
|
||||
|
||||
@@ -45,10 +45,14 @@ roles:
|
||||
$status: { type: string, enum: ["done"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: roleA
|
||||
prompt: "Do A"
|
||||
location: null
|
||||
resume:
|
||||
role: roleA
|
||||
prompt: "Resume A"
|
||||
location: null
|
||||
roleA:
|
||||
ready:
|
||||
role: roleB
|
||||
@@ -107,10 +111,14 @@ roles:
|
||||
$status: { type: string, enum: ["done"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: roleA
|
||||
prompt: "Do A"
|
||||
location: null
|
||||
resume:
|
||||
role: roleA
|
||||
prompt: "Resume A"
|
||||
location: null
|
||||
roleA:
|
||||
pass:
|
||||
role: roleB
|
||||
@@ -150,10 +158,14 @@ roles:
|
||||
$status: { type: string, enum: ["done"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: worker
|
||||
prompt: "Work"
|
||||
location: null
|
||||
resume:
|
||||
role: worker
|
||||
prompt: "Resume work"
|
||||
location: null
|
||||
worker:
|
||||
done:
|
||||
role: $END
|
||||
|
||||
@@ -36,7 +36,8 @@ roles:
|
||||
required: [$status]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: analyst, prompt: 'Analyze the task' }
|
||||
new: { role: analyst, prompt: 'Analyze the task' }
|
||||
resume: { role: analyst, prompt: 'Review the previous run output and continue the work.' }
|
||||
analyst:
|
||||
analyzed: { role: developer, prompt: 'Implement the change' }
|
||||
developer:
|
||||
|
||||
@@ -25,7 +25,8 @@ roles:
|
||||
required: [$status]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: planner, prompt: 'Plan the task' }
|
||||
new: { role: planner, prompt: 'Plan the task' }
|
||||
resume: { role: planner, prompt: 'Review the previous run output and continue the work.' }
|
||||
planner:
|
||||
ready: { role: worker, prompt: 'Do the work' }
|
||||
worker:
|
||||
|
||||
@@ -28,7 +28,8 @@ roles:
|
||||
required: [$status]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: developer, prompt: 'Implement the change' }
|
||||
new: { role: developer, prompt: 'Implement the change' }
|
||||
resume: { role: developer, prompt: 'Review the previous run output and continue the work.' }
|
||||
developer:
|
||||
review_needed: { role: reviewer, prompt: 'Review the change' }
|
||||
reviewer:
|
||||
|
||||
@@ -27,7 +27,8 @@ roles:
|
||||
required: [$status]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: planner, prompt: 'Plan the task' }
|
||||
new: { role: planner, prompt: 'Plan the task' }
|
||||
resume: { role: planner, prompt: 'Review the previous run output and continue the work.' }
|
||||
planner:
|
||||
ready: { role: worker, prompt: 'Work on branch {{{branch}}} in {{{repoPath}}}' }
|
||||
worker:
|
||||
|
||||
@@ -18,7 +18,8 @@ roles:
|
||||
required: [$status]
|
||||
graph:
|
||||
$START:
|
||||
_: { role: planner, prompt: 'Analyze the task' }
|
||||
new: { role: planner, prompt: 'Analyze the task' }
|
||||
resume: { role: planner, prompt: 'Review the previous run output and continue the work.' }
|
||||
planner:
|
||||
insufficient_info: { role: '$SUSPEND', prompt: 'Need more info: {{{reason}}}' }
|
||||
ready: { role: '$END', prompt: 'Done' }
|
||||
|
||||
@@ -5,7 +5,12 @@ import { evaluate } from "../moderator/evaluate.js";
|
||||
|
||||
const solveIssueGraph: WorkflowPayload["graph"] = {
|
||||
$START: {
|
||||
_: { role: "planner", prompt: "Start planning from the issue in the task.", location: null },
|
||||
new: { role: "planner", prompt: "Start planning from the issue in the task.", location: null },
|
||||
resume: {
|
||||
role: "planner",
|
||||
prompt: "Review the previous run output and continue the work.",
|
||||
location: null,
|
||||
},
|
||||
},
|
||||
planner: {
|
||||
planned: { role: "developer", prompt: "Implement the plan: {{plan}}", location: null },
|
||||
@@ -20,8 +25,8 @@ const solveIssueGraph: WorkflowPayload["graph"] = {
|
||||
};
|
||||
|
||||
describe("evaluate", () => {
|
||||
test("$START → first role (unit status _)", () => {
|
||||
const result = evaluate(solveIssueGraph, "$START", { $status: "_" });
|
||||
test("$START → first role (status new)", () => {
|
||||
const result = evaluate(solveIssueGraph, "$START", { $status: "new" });
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: {
|
||||
@@ -32,6 +37,18 @@ describe("evaluate", () => {
|
||||
});
|
||||
});
|
||||
|
||||
test("$START → first role (status resume)", () => {
|
||||
const result = evaluate(solveIssueGraph, "$START", { $status: "resume" });
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: {
|
||||
role: "planner",
|
||||
prompt: "Review the previous run output and continue the work.",
|
||||
location: null,
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
test("status-based routing (reviewer rejected → developer)", () => {
|
||||
const result = evaluate(solveIssueGraph, "reviewer", {
|
||||
$status: "rejected",
|
||||
@@ -95,7 +112,7 @@ describe("evaluate", () => {
|
||||
});
|
||||
|
||||
test("missing role in graph → error", () => {
|
||||
const result = evaluate(solveIssueGraph, "unknown-role", { $status: "_" });
|
||||
const result = evaluate(solveIssueGraph, "unknown-role", { $status: "new" });
|
||||
expect(result.ok).toBe(false);
|
||||
if (!result.ok) {
|
||||
expect(result.error.message).toBe('no transitions defined for role "unknown-role"');
|
||||
|
||||
@@ -253,7 +253,10 @@ describe("thread read timing", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "go", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "go", location: null },
|
||||
resume: { role: "worker", prompt: "resume", location: null },
|
||||
},
|
||||
worker: { done: { role: "$END", prompt: "", location: null } },
|
||||
},
|
||||
});
|
||||
@@ -319,7 +322,10 @@ describe("thread read timing", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "go", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "go", location: null },
|
||||
resume: { role: "worker", prompt: "resume", location: null },
|
||||
},
|
||||
worker: { done: { role: "$END", prompt: "", location: null } },
|
||||
},
|
||||
});
|
||||
|
||||
@@ -57,10 +57,14 @@ roles:
|
||||
$status: { type: string, enum: ["ready"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: planner
|
||||
prompt: "Plan the work"
|
||||
location: null
|
||||
resume:
|
||||
role: planner
|
||||
prompt: "Resume the work"
|
||||
location: null
|
||||
planner:
|
||||
ready:
|
||||
role: $END
|
||||
@@ -113,10 +117,14 @@ roles:
|
||||
$status: { type: string, enum: ["ready"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: planner
|
||||
prompt: "Plan"
|
||||
location: null
|
||||
resume:
|
||||
role: planner
|
||||
prompt: "Resume"
|
||||
location: null
|
||||
planner:
|
||||
ready:
|
||||
role: $END
|
||||
@@ -156,10 +164,14 @@ roles:
|
||||
$status: { type: string, enum: ["ready"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: planner
|
||||
prompt: "Plan"
|
||||
location: null
|
||||
resume:
|
||||
role: planner
|
||||
prompt: "Resume"
|
||||
location: null
|
||||
planner:
|
||||
ready:
|
||||
role: $END
|
||||
|
||||
@@ -70,7 +70,10 @@ async function setupSuspendedThread(mode: MockAgentMode): Promise<{
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start work", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start work", location: null },
|
||||
resume: { role: "worker", prompt: "Resume the work", location: null },
|
||||
},
|
||||
worker: {
|
||||
needs_input: {
|
||||
role: "$SUSPEND",
|
||||
@@ -233,7 +236,10 @@ describe("uwf thread resume", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start", location: null },
|
||||
resume: { role: "worker", prompt: "Resume", location: null },
|
||||
},
|
||||
worker: { done: { role: "$END", prompt: "Done", location: null } },
|
||||
},
|
||||
});
|
||||
@@ -479,7 +485,10 @@ describe("uwf thread resume - completed threads", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start work", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start work", location: null },
|
||||
resume: { role: "worker", prompt: "Resume the work", location: null },
|
||||
},
|
||||
worker: { done: { role: "reviewer", prompt: "Review the work", location: null } },
|
||||
reviewer: { done: { role: "$END", prompt: "Done", location: null } },
|
||||
},
|
||||
@@ -610,7 +619,7 @@ echo '${adapterJson}'
|
||||
expect(cliOutput.done).toBe(false);
|
||||
|
||||
const capturedPrompt = await readFile(promptCapturePath, "utf8");
|
||||
expect(capturedPrompt).toContain("Previous run completed");
|
||||
expect(capturedPrompt).toContain("Resume the work");
|
||||
expect(capturedPrompt).toContain("Additional context");
|
||||
|
||||
const storeModule = await import("../store.js");
|
||||
@@ -640,7 +649,10 @@ echo '${adapterJson}'
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start", location: null },
|
||||
resume: { role: "worker", prompt: "Resume", location: null },
|
||||
},
|
||||
worker: { done: { role: "$END", prompt: "Done", location: null } },
|
||||
},
|
||||
});
|
||||
@@ -688,7 +700,10 @@ echo '${adapterJson}'
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start", location: null },
|
||||
resume: { role: "worker", prompt: "Resume", location: null },
|
||||
},
|
||||
worker: { done: { role: "$END", prompt: "Done", location: null } },
|
||||
},
|
||||
});
|
||||
|
||||
@@ -34,10 +34,14 @@ roles:
|
||||
$status: { type: string, enum: ["ready"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: planner
|
||||
prompt: "Plan the work"
|
||||
location: null
|
||||
resume:
|
||||
role: planner
|
||||
prompt: "Resume the work"
|
||||
location: null
|
||||
planner:
|
||||
ready:
|
||||
role: $END
|
||||
@@ -66,10 +70,14 @@ roles:
|
||||
question: { type: string }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: worker
|
||||
prompt: "Start work"
|
||||
location: null
|
||||
resume:
|
||||
role: worker
|
||||
prompt: "Resume work"
|
||||
location: null
|
||||
worker:
|
||||
needs_input:
|
||||
role: $SUSPEND
|
||||
|
||||
@@ -57,10 +57,14 @@ roles:
|
||||
$status: { type: string, enum: ["ready"] }
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: planner
|
||||
prompt: "Plan the work"
|
||||
location: null
|
||||
resume:
|
||||
role: planner
|
||||
prompt: "Resume the work"
|
||||
location: null
|
||||
planner:
|
||||
ready:
|
||||
role: $END
|
||||
|
||||
@@ -58,7 +58,10 @@ describe("suspend step CAS chain and threads.yaml metadata", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start work", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start work", location: null },
|
||||
resume: { role: "worker", prompt: "Resume work", location: null },
|
||||
},
|
||||
worker: {
|
||||
needs_input: {
|
||||
role: "$SUSPEND",
|
||||
|
||||
@@ -55,7 +55,10 @@ describe("suspended thread display", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start work", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start work", location: null },
|
||||
resume: { role: "worker", prompt: "Resume work", location: null },
|
||||
},
|
||||
worker: {
|
||||
needs_input: {
|
||||
role: "$SUSPEND",
|
||||
@@ -162,7 +165,10 @@ describe("suspended thread display", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start work", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start work", location: null },
|
||||
resume: { role: "worker", prompt: "Resume work", location: null },
|
||||
},
|
||||
worker: {
|
||||
needs_input: {
|
||||
role: "$SUSPEND",
|
||||
@@ -248,7 +254,10 @@ describe("suspended thread display", () => {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "Start work", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "Start work", location: null },
|
||||
resume: { role: "worker", prompt: "Resume work", location: null },
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
|
||||
@@ -51,7 +51,10 @@ function makeWorkflow(overrides?: Partial<WorkflowPayload>): WorkflowPayload {
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "writer", prompt: "Begin writing", location: null } },
|
||||
$START: {
|
||||
new: { role: "writer", prompt: "Begin writing", location: null },
|
||||
resume: { role: "writer", prompt: "Review previous output and continue", location: null },
|
||||
},
|
||||
writer: { done: { role: "reviewer", prompt: "Review this: {{{plan}}}", location: null } },
|
||||
reviewer: {
|
||||
approved: { role: "$END", prompt: "Done: {{{summary}}}", location: null },
|
||||
@@ -135,27 +138,38 @@ describe("Suite 2: Graph Structure", () => {
|
||||
expect(errors.some((e) => e.includes("$START must be defined in graph"))).toBe(true);
|
||||
});
|
||||
|
||||
test("2.2 $START has multiple status keys", () => {
|
||||
test("2.2 $START missing resume edge", () => {
|
||||
const wf = makeWorkflow();
|
||||
wf.graph.$START = {
|
||||
_: { role: "writer", prompt: "Begin", location: null },
|
||||
other: { role: "reviewer", prompt: "Also", location: null },
|
||||
new: { role: "writer", prompt: "Begin", location: null },
|
||||
};
|
||||
const errors = validateWorkflow(wf);
|
||||
expect(
|
||||
errors.some((e) => e.includes('$START must have exactly one edge with status "_"')),
|
||||
errors.some((e) => e.includes('$START must have edges with statuses "new" and "resume"')),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
test("2.3 $START edge uses non-_ status", () => {
|
||||
test("2.3 $START missing new edge", () => {
|
||||
const wf = makeWorkflow();
|
||||
wf.graph.$START = { ready: { role: "writer", prompt: "Begin", location: null } };
|
||||
wf.graph.$START = {
|
||||
resume: { role: "writer", prompt: "Resume", location: null },
|
||||
};
|
||||
const errors = validateWorkflow(wf);
|
||||
expect(
|
||||
errors.some((e) => e.includes('$START must have exactly one edge with status "_"')),
|
||||
errors.some((e) => e.includes('$START must have edges with statuses "new" and "resume"')),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
test("2.3b $START with new and resume passes", () => {
|
||||
const wf = makeWorkflow();
|
||||
wf.graph.$START = {
|
||||
new: { role: "writer", prompt: "Begin", location: null },
|
||||
resume: { role: "writer", prompt: "Resume", location: null },
|
||||
};
|
||||
const errors = validateWorkflow(wf);
|
||||
expect(errors.some((e) => e.includes("$START must have edges"))).toBe(false);
|
||||
});
|
||||
|
||||
test("2.4 $END has outgoing edges", () => {
|
||||
const wf = makeWorkflow();
|
||||
wf.graph.$END = { _: { role: "writer", prompt: "Loop", location: null } };
|
||||
@@ -193,15 +207,18 @@ describe("Suite 2: Graph Structure", () => {
|
||||
});
|
||||
|
||||
describe("Suite 3: Status-Edge Consistency", () => {
|
||||
test("3.1 user role using _ graph key is rejected", () => {
|
||||
test("3.1 user role using _ graph key is treated as an unknown status", () => {
|
||||
// "_" is no longer special-cased — it's just a status key that does not
|
||||
// match the role's $status enum, so it surfaces as extra/missing keys.
|
||||
const wf = makeWorkflow();
|
||||
wf.graph.writer = { _: { role: "reviewer", prompt: "Review", location: null } };
|
||||
const errors = validateWorkflow(wf);
|
||||
expect(
|
||||
errors.some((e) =>
|
||||
e.includes('role "writer" must use explicit $status keys in graph, not "_"'),
|
||||
),
|
||||
).toBe(true);
|
||||
expect(errors.some((e) => e.includes('role "writer" graph has extra status keys: _'))).toBe(
|
||||
true,
|
||||
);
|
||||
expect(errors.some((e) => e.includes('role "writer" graph is missing status keys: done'))).toBe(
|
||||
true,
|
||||
);
|
||||
});
|
||||
|
||||
test("3.2 user role graph key not matching $status enum", () => {
|
||||
@@ -240,13 +257,16 @@ describe("Suite 3: Status-Edge Consistency", () => {
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
test("3.5 multi-exit role with _ key", () => {
|
||||
test("3.5 multi-exit role with _ key is treated as an unknown status", () => {
|
||||
const wf = makeWorkflow();
|
||||
wf.graph.reviewer = { _: { role: "$END", prompt: "Done", location: null } };
|
||||
const errors = validateWorkflow(wf);
|
||||
expect(errors.some((e) => e.includes('role "reviewer" graph has extra status keys: _'))).toBe(
|
||||
true,
|
||||
);
|
||||
expect(
|
||||
errors.some((e) =>
|
||||
e.includes('role "reviewer" must use explicit $status keys in graph, not "_"'),
|
||||
e.includes('role "reviewer" graph is missing status keys: approved, rejected'),
|
||||
),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
@@ -38,7 +38,10 @@ function makeMinimalPayload(name: string, description: string): WorkflowPayload
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: { _: { role: "worker", prompt: "start working", location: null } },
|
||||
$START: {
|
||||
new: { role: "worker", prompt: "start working", location: null },
|
||||
resume: { role: "worker", prompt: "resume working", location: null },
|
||||
},
|
||||
worker: { done: { role: "$END", prompt: "done", location: null } },
|
||||
},
|
||||
};
|
||||
|
||||
@@ -911,7 +911,7 @@ function resolveEvaluateArgs(
|
||||
chain: ChainState,
|
||||
): { lastRole: string; lastOutput: EvaluateLastOutput } {
|
||||
if (chain.headIsStart) {
|
||||
return { lastRole: START_ROLE, lastOutput: { [STATUS_KEY]: "_" } };
|
||||
return { lastRole: START_ROLE, lastOutput: { [STATUS_KEY]: "new" } };
|
||||
}
|
||||
|
||||
const lastStep = chain.stepsNewestFirst[0];
|
||||
@@ -1037,7 +1037,6 @@ function archiveThread(uwf: UwfStore, threadId: ThreadId, _workflow: CasRef, _he
|
||||
completeThread(uwf.varStore, threadId, "completed");
|
||||
}
|
||||
|
||||
// biome-ignore lint/complexity/noExcessiveCognitiveComplexity: orchestration function with inherent branching
|
||||
export async function cmdThreadResume(
|
||||
storageRoot: string,
|
||||
threadId: ThreadId,
|
||||
@@ -1101,7 +1100,7 @@ export async function cmdThreadResume(
|
||||
|
||||
// status === "completed"
|
||||
const workflow = loadWorkflowPayload(uwf, workflowHash);
|
||||
const startResult = evaluate(workflow.graph, START_ROLE, {});
|
||||
const startResult = evaluate(workflow.graph, START_ROLE, { [STATUS_KEY]: "resume" });
|
||||
if (!startResult.ok) {
|
||||
fail(`failed to evaluate $START: ${startResult.error.message}`);
|
||||
}
|
||||
@@ -1113,11 +1112,7 @@ export async function cmdThreadResume(
|
||||
}
|
||||
|
||||
const startRole = startResult.value.role;
|
||||
const completedPromptPrefix = "Previous run completed. Resuming with additional context.";
|
||||
const completedResumePrompt =
|
||||
supplement !== null && supplement !== ""
|
||||
? `${completedPromptPrefix}\n\n${supplement}`
|
||||
: completedPromptPrefix;
|
||||
const completedResumePrompt = buildResumePrompt(startResult.value.prompt, supplement);
|
||||
|
||||
const updatedEntry = { ...entry, status: "idle" as const, completedAt: null };
|
||||
setThread(uwf.varStore, threadId, updatedEntry);
|
||||
|
||||
@@ -6,11 +6,11 @@ describe("Edge prompt template variable resolution", () => {
|
||||
test("returns error when rendered prompt is empty string", () => {
|
||||
const graph = {
|
||||
$START: {
|
||||
_: { role: "classifier", prompt: "{{{userPrompt}}}", location: null },
|
||||
new: { role: "classifier", prompt: "{{{userPrompt}}}", location: null },
|
||||
},
|
||||
};
|
||||
|
||||
const result = evaluate(graph, "$START", {});
|
||||
const result = evaluate(graph, "$START", { $status: "new" });
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
if (!result.ok) {
|
||||
@@ -22,11 +22,11 @@ describe("Edge prompt template variable resolution", () => {
|
||||
test("returns error when rendered prompt is whitespace-only", () => {
|
||||
const graph = {
|
||||
$START: {
|
||||
_: { role: "classifier", prompt: " {{{userPrompt}}} ", location: null },
|
||||
new: { role: "classifier", prompt: " {{{userPrompt}}} ", location: null },
|
||||
},
|
||||
};
|
||||
|
||||
const result = evaluate(graph, "$START", {});
|
||||
const result = evaluate(graph, "$START", { $status: "new" });
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
if (!result.ok) {
|
||||
@@ -38,11 +38,11 @@ describe("Edge prompt template variable resolution", () => {
|
||||
test("succeeds when all template variables resolve to non-empty values", () => {
|
||||
const graph = {
|
||||
$START: {
|
||||
_: { role: "classifier", prompt: "{{{userPrompt}}}", location: null },
|
||||
new: { role: "classifier", prompt: "{{{userPrompt}}}", location: null },
|
||||
},
|
||||
};
|
||||
|
||||
const result = evaluate(graph, "$START", { userPrompt: "Fix the bug" });
|
||||
const result = evaluate(graph, "$START", { $status: "new", userPrompt: "Fix the bug" });
|
||||
|
||||
expect(result.ok).toBe(true);
|
||||
if (result.ok) {
|
||||
@@ -53,11 +53,11 @@ describe("Edge prompt template variable resolution", () => {
|
||||
test("succeeds with static (no-variable) prompt", () => {
|
||||
const graph = {
|
||||
$START: {
|
||||
_: { role: "classifier", prompt: "Classify this input", location: null },
|
||||
new: { role: "classifier", prompt: "Classify this input", location: null },
|
||||
},
|
||||
};
|
||||
|
||||
const result = evaluate(graph, "$START", {});
|
||||
const result = evaluate(graph, "$START", { $status: "new" });
|
||||
|
||||
expect(result.ok).toBe(true);
|
||||
if (result.ok) {
|
||||
@@ -68,11 +68,11 @@ describe("Edge prompt template variable resolution", () => {
|
||||
test("succeeds when prompt has mix of static text and unresolved variables", () => {
|
||||
const graph = {
|
||||
$START: {
|
||||
_: { role: "classifier", prompt: "Please handle: {{{userPrompt}}}", location: null },
|
||||
new: { role: "classifier", prompt: "Please handle: {{{userPrompt}}}", location: null },
|
||||
},
|
||||
};
|
||||
|
||||
const result = evaluate(graph, "$START", {});
|
||||
const result = evaluate(graph, "$START", { $status: "new" });
|
||||
|
||||
expect(result.ok).toBe(true);
|
||||
if (result.ok) {
|
||||
@@ -83,11 +83,11 @@ describe("Edge prompt template variable resolution", () => {
|
||||
test("returns error when ALL variables missing and no static text remains", () => {
|
||||
const graph = {
|
||||
$START: {
|
||||
_: { role: "classifier", prompt: "{{{a}}}{{{b}}}", location: null },
|
||||
new: { role: "classifier", prompt: "{{{a}}}{{{b}}}", location: null },
|
||||
},
|
||||
};
|
||||
|
||||
const result = evaluate(graph, "$START", {});
|
||||
const result = evaluate(graph, "$START", { $status: "new" });
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
});
|
||||
|
||||
@@ -6,10 +6,7 @@ import type { EvaluateResult, Result } from "./types.js";
|
||||
// Disable HTML escaping — prompts are plain text, not HTML.
|
||||
mustache.escape = (text: string) => text;
|
||||
|
||||
const START_ROLE = "$START";
|
||||
const SUSPEND_ROLE = "$SUSPEND";
|
||||
// $START is a special entry node with no agent output — it always uses this key.
|
||||
const START_STATUS = "_";
|
||||
|
||||
type LastOutput = Record<string, unknown>;
|
||||
|
||||
@@ -21,9 +18,7 @@ export function evaluate(
|
||||
lastOutput: LastOutput,
|
||||
): Result<EvaluateResult, Error> {
|
||||
let status: string;
|
||||
if (lastRole === START_ROLE) {
|
||||
status = START_STATUS;
|
||||
} else if (typeof lastOutput[STATUS_KEY] === "string") {
|
||||
if (typeof lastOutput[STATUS_KEY] === "string") {
|
||||
status = lastOutput[STATUS_KEY] as string;
|
||||
} else {
|
||||
return {
|
||||
|
||||
@@ -97,9 +97,9 @@ function checkGraphStructure(payload: WorkflowPayload, errors: string[]): void {
|
||||
if (!graphNodes.has("$START")) {
|
||||
errors.push("$START must be defined in graph");
|
||||
} else {
|
||||
const startKeys = Object.keys(payload.graph.$START);
|
||||
if (startKeys.length !== 1 || startKeys[0] !== "_") {
|
||||
errors.push('$START must have exactly one edge with status "_"');
|
||||
const startKeys = new Set(Object.keys(payload.graph.$START));
|
||||
if (!startKeys.has("new") || !startKeys.has("resume")) {
|
||||
errors.push('$START must have edges with statuses "new" and "resume"');
|
||||
}
|
||||
}
|
||||
|
||||
@@ -190,22 +190,13 @@ function checkOneOfDiscriminant(
|
||||
}
|
||||
}
|
||||
|
||||
/** Check status-edge consistency for a user role. "_" is reserved for $START and rejected here. */
|
||||
/** Check status-edge consistency for a user role. */
|
||||
function checkStatusEdges(
|
||||
roleName: string,
|
||||
graphKeys: Set<string>,
|
||||
statusSet: Set<string>,
|
||||
errors: string[],
|
||||
): void {
|
||||
if (graphKeys.has("_")) {
|
||||
errors.push(`role "${roleName}" must use explicit $status keys in graph, not "_"`);
|
||||
return;
|
||||
}
|
||||
if (statusSet.has("_")) {
|
||||
errors.push(`role "${roleName}" $status enum must use explicit values, not "_"`);
|
||||
return;
|
||||
}
|
||||
|
||||
const extraKeys = [...graphKeys].filter((k) => !statusSet.has(k));
|
||||
const missingKeys = [...statusSet].filter((k) => !graphKeys.has(k));
|
||||
if (extraKeys.length > 0) {
|
||||
|
||||
@@ -57,13 +57,13 @@ function isGraph(value: unknown): boolean {
|
||||
if (!isRecord(value)) {
|
||||
return false;
|
||||
}
|
||||
return Object.entries(value).every(([node, statusMap]) => {
|
||||
return Object.values(value).every((statusMap) => {
|
||||
if (!isRecord(statusMap)) {
|
||||
return false;
|
||||
}
|
||||
return Object.entries(statusMap).every(([status, target]) => {
|
||||
// "_" is only valid as a status key for the $START entry node.
|
||||
if (status === "_" && node !== "$START") {
|
||||
// "_" is no longer a valid status key anywhere — $START uses "new"/"resume".
|
||||
if (status === "_") {
|
||||
return false;
|
||||
}
|
||||
return isTarget(target);
|
||||
|
||||
@@ -16,7 +16,8 @@ The graph is a nested map: \`Record<Role | "$START", Record<Status, Target>>\`.
|
||||
\`\`\`yaml
|
||||
graph:
|
||||
$START:
|
||||
_: { role: planner, prompt: "Analyze the issue." }
|
||||
new: { role: planner, prompt: "Analyze the issue." }
|
||||
resume: { role: planner, prompt: "Review the previous run output and continue." }
|
||||
planner:
|
||||
ready: { role: developer, prompt: "Implement the plan (CAS hash: {{{plan}}})." }
|
||||
insufficient_info: { role: $END, prompt: "Not enough info." }
|
||||
@@ -41,7 +42,7 @@ Edge prompts use triple-brace Mustache syntax (\`{{{field}}}\`) to interpolate v
|
||||
|
||||
## Special Nodes
|
||||
|
||||
- \`$START\` — entry point; uses status key \`_\` (unconditional) since there is no previous output
|
||||
- \`$START\` — entry point; uses status keys \`new\` (first start) and \`resume\` (resuming a completed thread)
|
||||
- \`$END\` — terminal node; thread completes when reached and is moved to history
|
||||
|
||||
## Integration with Steps
|
||||
|
||||
@@ -40,7 +40,8 @@ roles: # named actors
|
||||
|
||||
graph: # status-based routing
|
||||
$START:
|
||||
_: { role: planner, prompt: "Analyze the issue." }
|
||||
new: { role: planner, prompt: "Analyze the issue." }
|
||||
resume: { role: planner, prompt: "Review the previous run output and continue." }
|
||||
planner:
|
||||
ready: { role: developer, prompt: "Implement {{{plan}}}." }
|
||||
failed: { role: $END, prompt: "Failed: {{{error}}}" }
|
||||
@@ -113,7 +114,7 @@ graph[role][$status] → { role: nextRole, prompt: edgePrompt }
|
||||
|
||||
| Node | Purpose |
|
||||
|------|---------|
|
||||
| \`$START\` | Entry point — status key is always \`_\` (unconditional) |
|
||||
| \`$START\` | Entry point — status keys \`new\` (first start) and \`resume\` (resuming a completed thread) |
|
||||
| \`$END\` | Terminal — thread completes and is archived |
|
||||
|
||||
### Edge Prompts
|
||||
@@ -178,7 +179,7 @@ ocas get <output-hash>
|
||||
1. Every \`$status\` value in a role's frontmatter has a matching edge in the graph
|
||||
2. Every field referenced in edge prompts (\`{{{field}}}\`) exists in the source role's schema
|
||||
3. Every role referenced in the graph exists in \`roles\`
|
||||
4. \`$START\` has exactly one edge with key \`_\`
|
||||
4. \`$START\` has edges with keys \`new\` and \`resume\`
|
||||
5. At least one path leads to \`$END\`
|
||||
6. No orphan roles (defined but never routed to)
|
||||
|
||||
|
||||
@@ -32,7 +32,8 @@ roles: # named actors in the workflow
|
||||
|
||||
graph: # status-based routing (nested map)
|
||||
$START:
|
||||
_: { role: planner, prompt: "Analyze the issue." }
|
||||
new: { role: planner, prompt: "Analyze the issue." }
|
||||
resume: { role: planner, prompt: "Review the previous run output and continue." }
|
||||
planner:
|
||||
ready: { role: developer, prompt: "Implement plan {{{plan}}}." }
|
||||
insufficient_info: { role: $END, prompt: "Not enough info." }
|
||||
@@ -70,10 +71,10 @@ Record<Role | "$START", Record<Status, { role: string, prompt: string }>>
|
||||
| Level | Key | Value |
|
||||
|-------|-----|-------|
|
||||
| Outer | Role name or \`$START\` | Status map for that role |
|
||||
| Inner | \`$status\` value (or \`_\` for unconditional) | Target: \`{ role, prompt }\` |
|
||||
| Inner | \`$status\` value | Target: \`{ role, prompt }\` |
|
||||
|
||||
### Special Nodes
|
||||
- \`$START\` — entry point; uses status key \`_\` (unconditional, no previous output)
|
||||
- \`$START\` — entry point; uses status keys \`new\` (first start) and \`resume\` (resuming a completed thread)
|
||||
- \`$END\` — terminal node; thread completes when reached
|
||||
|
||||
### Edge Prompts
|
||||
|
||||
@@ -21,9 +21,12 @@ graph:
|
||||
role: package-metadata
|
||||
prompt: Biome setup failed ({{{reason}}}), but continue. Standardize package metadata for repo at {{{repoPath}}}.
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: workspace
|
||||
prompt: Set up bun workspace structure for repo at {{{repoPath}}}.
|
||||
resume:
|
||||
role: workspace
|
||||
prompt: Review the previous run output and continue setting up the bun workspace structure for repo at {{{repoPath}}}.
|
||||
release:
|
||||
done:
|
||||
role: testing
|
||||
|
||||
@@ -283,9 +283,12 @@ roles:
|
||||
- error
|
||||
graph:
|
||||
$START:
|
||||
_:
|
||||
new:
|
||||
role: planner
|
||||
prompt: Analyze the issue and produce an implementation plan.
|
||||
resume:
|
||||
role: planner
|
||||
prompt: Review the previous run output and continue the work.
|
||||
planner:
|
||||
insufficient_info:
|
||||
role: $SUSPEND
|
||||
|
||||
Reference in New Issue
Block a user