refactor: major codebase cleanup - BDD comments, file splitting, bug fixes (#1350)

* style(tests): normalize BDD comments from '// #given' to '// given'

- Replace 4,668 Python-style BDD comments across 107 test files
- Patterns changed: // #given -> // given, // #when -> // when, // #then -> // then
- Also handles no-space variants: //#given -> // given

* fix(rules-injector): prefer output.metadata.filePath over output.title

- Extract file path resolution to dedicated output-path.ts module
- Prefer metadata.filePath which contains actual file path
- Fall back to output.title only when metadata unavailable
- Fixes issue where rules weren't injected when tool output title was a label

* feat(slashcommand): add optional user_message parameter

- Add user_message optional parameter for command arguments
- Model can now call: command='publish' user_message='patch'
- Improves error messages with clearer format guidance
- Helps LLMs understand correct parameter usage

* feat(hooks): restore compaction-context-injector hook

- Restore hook deleted in cbbc7bd0 for session compaction context
- Injects 7 mandatory sections: User Requests, Final Goal, Work Completed,
  Remaining Tasks, Active Working Context, MUST NOT Do, Agent Verification State
- Re-register in hooks/index.ts and main plugin entry

* refactor(background-agent): split manager.ts into focused modules

- Extract constants.ts for TTL values and internal types (52 lines)
- Extract state.ts for TaskStateManager class (204 lines)
- Extract spawner.ts for task creation logic (244 lines)
- Extract result-handler.ts for completion handling (265 lines)
- Reduce manager.ts from 1377 to 755 lines (45% reduction)
- Maintain backward compatible exports

* refactor(agents): split prometheus-prompt.ts into subdirectory

- Move 1196-line prometheus-prompt.ts to prometheus/ subdirectory
- Organize prompt sections into separate files for maintainability
- Update agents/index.ts exports

* refactor(delegate-task): split tools.ts into focused modules

- Extract categories.ts for category definitions and routing
- Extract executor.ts for task execution logic
- Extract helpers.ts for utility functions
- Extract prompt-builder.ts for prompt construction
- Reduce tools.ts complexity with cleaner separation of concerns

* refactor(builtin-skills): split skills.ts into individual skill files

- Move each skill to dedicated file in skills/ subdirectory
- Create barrel export for backward compatibility
- Improve maintainability with focused skill modules

* chore: update import paths and lockfile

- Update prometheus import path after refactor
- Update bun.lock

* fix(tests): complete BDD comment normalization

- Fix remaining #when/#then patterns missed by initial sed
- Affected: state.test.ts, events.test.ts

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
This commit is contained in:
YeonGyu-Kim
2026-02-01 16:47:50 +09:00
committed by GitHub
parent c83150d9ea
commit f146aeff0f
145 changed files with 10307 additions and 9562 deletions
+39 -39
View File
@@ -40,24 +40,24 @@ describe("start-work hook", () => {
describe("chat.message handler", () => {
test("should ignore non-start-work commands", async () => {
// #given - hook and non-start-work message
// given - hook and non-start-work message
const hook = createStartWorkHook(createMockPluginInput())
const output = {
parts: [{ type: "text", text: "Just a regular message" }],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - output should be unchanged
// then - output should be unchanged
expect(output.parts[0].text).toBe("Just a regular message")
})
test("should detect start-work command via session-context tag", async () => {
// #given - hook and start-work message
// given - hook and start-work message
const hook = createStartWorkHook(createMockPluginInput())
const output = {
parts: [
@@ -68,18 +68,18 @@ describe("start-work hook", () => {
],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - output should be modified with context info
// then - output should be modified with context info
expect(output.parts[0].text).toContain("---")
})
test("should inject resume info when existing boulder state found", async () => {
// #given - existing boulder state with incomplete plan
// given - existing boulder state with incomplete plan
const planPath = join(TEST_DIR, "test-plan.md")
writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [x] Task 2")
@@ -96,19 +96,19 @@ describe("start-work hook", () => {
parts: [{ type: "text", text: "<session-context></session-context>" }],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should show resuming status
// then - should show resuming status
expect(output.parts[0].text).toContain("RESUMING")
expect(output.parts[0].text).toContain("test-plan")
})
test("should replace $SESSION_ID placeholder", async () => {
// #given - hook and message with placeholder
// given - hook and message with placeholder
const hook = createStartWorkHook(createMockPluginInput())
const output = {
parts: [
@@ -119,19 +119,19 @@ describe("start-work hook", () => {
],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "ses-abc123" },
output
)
// #then - placeholder should be replaced
// then - placeholder should be replaced
expect(output.parts[0].text).toContain("ses-abc123")
expect(output.parts[0].text).not.toContain("$SESSION_ID")
})
test("should replace $TIMESTAMP placeholder", async () => {
// #given - hook and message with placeholder
// given - hook and message with placeholder
const hook = createStartWorkHook(createMockPluginInput())
const output = {
parts: [
@@ -142,19 +142,19 @@ describe("start-work hook", () => {
],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - placeholder should be replaced with ISO timestamp
// then - placeholder should be replaced with ISO timestamp
expect(output.parts[0].text).not.toContain("$TIMESTAMP")
expect(output.parts[0].text).toMatch(/\d{4}-\d{2}-\d{2}T/)
})
test("should auto-select when only one incomplete plan among multiple plans", async () => {
// #given - multiple plans but only one incomplete
// given - multiple plans but only one incomplete
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
mkdirSync(plansDir, { recursive: true })
@@ -171,20 +171,20 @@ describe("start-work hook", () => {
parts: [{ type: "text", text: "<session-context></session-context>" }],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should auto-select the incomplete plan, not ask user
// then - should auto-select the incomplete plan, not ask user
expect(output.parts[0].text).toContain("Auto-Selected Plan")
expect(output.parts[0].text).toContain("plan-incomplete")
expect(output.parts[0].text).not.toContain("Multiple Plans Found")
})
test("should wrap multiple plans message in system-reminder tag", async () => {
// #given - multiple incomplete plans
// given - multiple incomplete plans
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
mkdirSync(plansDir, { recursive: true })
@@ -199,20 +199,20 @@ describe("start-work hook", () => {
parts: [{ type: "text", text: "<session-context></session-context>" }],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should use system-reminder tag format
// then - should use system-reminder tag format
expect(output.parts[0].text).toContain("<system-reminder>")
expect(output.parts[0].text).toContain("</system-reminder>")
expect(output.parts[0].text).toContain("Multiple Plans Found")
})
test("should use 'ask user' prompt style for multiple plans", async () => {
// #given - multiple incomplete plans
// given - multiple incomplete plans
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
mkdirSync(plansDir, { recursive: true })
@@ -227,19 +227,19 @@ describe("start-work hook", () => {
parts: [{ type: "text", text: "<session-context></session-context>" }],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should prompt agent to ask user, not ask directly
// then - should prompt agent to ask user, not ask directly
expect(output.parts[0].text).toContain("Ask the user")
expect(output.parts[0].text).not.toContain("Which plan would you like to work on?")
})
test("should select explicitly specified plan name from user-request, ignoring existing boulder state", async () => {
// #given - existing boulder state pointing to old plan
// given - existing boulder state pointing to old plan
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
mkdirSync(plansDir, { recursive: true })
@@ -272,20 +272,20 @@ describe("start-work hook", () => {
],
}
// #when - user explicitly specifies new-plan
// when - user explicitly specifies new-plan
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should select new-plan, NOT resume old-plan
// then - should select new-plan, NOT resume old-plan
expect(output.parts[0].text).toContain("new-plan")
expect(output.parts[0].text).not.toContain("RESUMING")
expect(output.parts[0].text).not.toContain("old-plan")
})
test("should strip ultrawork/ulw keywords from plan name argument", async () => {
// #given - plan with ultrawork keyword in user-request
// given - plan with ultrawork keyword in user-request
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
mkdirSync(plansDir, { recursive: true })
@@ -304,19 +304,19 @@ describe("start-work hook", () => {
],
}
// #when - user specifies plan with ultrawork keyword
// when - user specifies plan with ultrawork keyword
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should find plan without ultrawork suffix
// then - should find plan without ultrawork suffix
expect(output.parts[0].text).toContain("my-feature-plan")
expect(output.parts[0].text).toContain("Auto-Selected Plan")
})
test("should strip ulw keyword from plan name argument", async () => {
// #given - plan with ulw keyword in user-request
// given - plan with ulw keyword in user-request
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
mkdirSync(plansDir, { recursive: true })
@@ -335,19 +335,19 @@ describe("start-work hook", () => {
],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should find plan without ulw suffix
// then - should find plan without ulw suffix
expect(output.parts[0].text).toContain("api-refactor")
expect(output.parts[0].text).toContain("Auto-Selected Plan")
})
test("should match plan by partial name", async () => {
// #given - user specifies partial plan name
// given - user specifies partial plan name
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
mkdirSync(plansDir, { recursive: true })
@@ -366,13 +366,13 @@ describe("start-work hook", () => {
],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "session-123" },
output
)
// #then - should find plan by partial match
// then - should find plan by partial match
expect(output.parts[0].text).toContain("2026-01-15-feature-implementation")
expect(output.parts[0].text).toContain("Auto-Selected Plan")
})
@@ -380,7 +380,7 @@ describe("start-work hook", () => {
describe("session agent management", () => {
test("should update session agent to Atlas when start-work command is triggered", async () => {
// #given
// given
const updateSpy = spyOn(sessionState, "updateSessionAgent")
const hook = createStartWorkHook(createMockPluginInput())
@@ -388,13 +388,13 @@ describe("start-work hook", () => {
parts: [{ type: "text", text: "<session-context></session-context>" }],
}
// #when
// when
await hook["chat.message"](
{ sessionID: "ses-prometheus-to-sisyphus" },
output
)
// #then
// then
expect(updateSpy).toHaveBeenCalledWith("ses-prometheus-to-sisyphus", "atlas")
updateSpy.mockRestore()
})