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
+30 -30
View File
@@ -64,89 +64,89 @@ const mockContext: ToolContext = {
describe("skill tool - synchronous description", () => {
it("includes available_skills immediately when skills are pre-provided", () => {
// #given
// given
const loadedSkills = [createMockSkill("test-skill")]
// #when
// when
const tool = createSkillTool({ skills: loadedSkills })
// #then
// then
expect(tool.description).toContain("<available_skills>")
expect(tool.description).toContain("test-skill")
})
it("includes all pre-provided skills in available_skills immediately", () => {
// #given
// given
const loadedSkills = [
createMockSkill("playwright"),
createMockSkill("frontend-ui-ux"),
createMockSkill("git-master"),
]
// #when
// when
const tool = createSkillTool({ skills: loadedSkills })
// #then
// then
expect(tool.description).toContain("playwright")
expect(tool.description).toContain("frontend-ui-ux")
expect(tool.description).toContain("git-master")
})
it("shows no-skills message immediately when empty skills are pre-provided", () => {
// #given / #when
// given / #when
const tool = createSkillTool({ skills: [] })
// #then
// then
expect(tool.description).toContain("No skills are currently available")
})
})
describe("skill tool - agent restriction", () => {
it("allows skill without agent restriction to any agent", async () => {
// #given
// given
const loadedSkills = [createMockSkill("public-skill")]
const tool = createSkillTool({ skills: loadedSkills })
const context = { ...mockContext, agent: "any-agent" }
// #when
// when
const result = await tool.execute({ name: "public-skill" }, context)
// #then
// then
expect(result).toContain("public-skill")
})
it("allows skill when agent matches restriction", async () => {
// #given
// given
const loadedSkills = [createMockSkill("restricted-skill", { agent: "sisyphus" })]
const tool = createSkillTool({ skills: loadedSkills })
const context = { ...mockContext, agent: "sisyphus" }
// #when
// when
const result = await tool.execute({ name: "restricted-skill" }, context)
// #then
// then
expect(result).toContain("restricted-skill")
})
it("throws error when agent does not match restriction", async () => {
// #given
// given
const loadedSkills = [createMockSkill("sisyphus-only-skill", { agent: "sisyphus" })]
const tool = createSkillTool({ skills: loadedSkills })
const context = { ...mockContext, agent: "oracle" }
// #when / #then
// when / #then
await expect(tool.execute({ name: "sisyphus-only-skill" }, context)).rejects.toThrow(
'Skill "sisyphus-only-skill" is restricted to agent "sisyphus"'
)
})
it("throws error when context agent is undefined for restricted skill", async () => {
// #given
// given
const loadedSkills = [createMockSkill("sisyphus-only-skill", { agent: "sisyphus" })]
const tool = createSkillTool({ skills: loadedSkills })
const contextWithoutAgent = { ...mockContext, agent: undefined as unknown as string }
// #when / #then
// when / #then
await expect(tool.execute({ name: "sisyphus-only-skill" }, contextWithoutAgent)).rejects.toThrow(
'Skill "sisyphus-only-skill" is restricted to agent "sisyphus"'
)
@@ -167,7 +167,7 @@ describe("skill tool - MCP schema display", () => {
describe("formatMcpCapabilities with inputSchema", () => {
it("displays tool inputSchema when available", async () => {
// #given
// given
const mockToolsWithSchema: McpTool[] = [
{
name: "browser_type",
@@ -202,10 +202,10 @@ describe("skill tool - MCP schema display", () => {
getSessionID: () => sessionID,
})
// #when
// when
const result = await tool.execute({ name: "test-skill" }, mockContext)
// #then
// then
// Should include inputSchema details
expect(result).toContain("browser_type")
expect(result).toContain("inputSchema")
@@ -217,7 +217,7 @@ describe("skill tool - MCP schema display", () => {
})
it("displays multiple tools with their schemas", async () => {
// #given
// given
const mockToolsWithSchema: McpTool[] = [
{
name: "browser_navigate",
@@ -260,10 +260,10 @@ describe("skill tool - MCP schema display", () => {
getSessionID: () => sessionID,
})
// #when
// when
const result = await tool.execute({ name: "playwright-skill" }, mockContext)
// #then
// then
expect(result).toContain("browser_navigate")
expect(result).toContain("browser_click")
expect(result).toContain("url")
@@ -271,7 +271,7 @@ describe("skill tool - MCP schema display", () => {
})
it("handles tools without inputSchema gracefully", async () => {
// #given
// given
const mockToolsMinimal: McpTool[] = [
{
name: "simple_tool",
@@ -295,16 +295,16 @@ describe("skill tool - MCP schema display", () => {
getSessionID: () => sessionID,
})
// #when
// when
const result = await tool.execute({ name: "simple-skill" }, mockContext)
// #then
// then
expect(result).toContain("simple_tool")
// Should not throw, should handle gracefully
})
it("formats schema in a way LLM can understand for skill_mcp calls", async () => {
// #given
// given
const mockTools: McpTool[] = [
{
name: "query",
@@ -336,10 +336,10 @@ describe("skill tool - MCP schema display", () => {
getSessionID: () => sessionID,
})
// #when
// when
const result = await tool.execute({ name: "db-skill" }, mockContext)
// #then
// then
// Should provide enough info for LLM to construct valid skill_mcp call
expect(result).toContain("sqlite")
expect(result).toContain("query")