YeonGyu-Kim f146aeff0f
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>
2026-02-01 16:47:50 +09:00

224 lines
6.9 KiB
TypeScript

import { describe, expect, it } from "bun:test"
import { detectErrorType } from "./index"
describe("detectErrorType", () => {
describe("thinking_block_order errors", () => {
it("should detect 'first block' error pattern", () => {
// given an error about thinking being the first block
const error = {
message: "messages.0: thinking block must not be the first block",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect 'must start with' error pattern", () => {
// given an error about message must start with something
const error = {
message: "messages.5: thinking must start with text or tool_use",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect 'preceeding' error pattern", () => {
// given an error about preceeding block
const error = {
message: "messages.10: thinking requires preceeding text block",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect 'expected/found' error pattern", () => {
// given an error about expected vs found
const error = {
message: "messages.3: thinking block expected text but found tool_use",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect 'final block cannot be thinking' error pattern", () => {
// given an error about final block cannot be thinking
const error = {
message:
"messages.125: The final block in an assistant message cannot be thinking.",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect 'final block' variant error pattern", () => {
// given an error mentioning final block with thinking
const error = {
message:
"messages.17: thinking in the final block is not allowed in assistant messages",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect 'cannot be thinking' error pattern", () => {
// given an error using 'cannot be thinking' phrasing
const error = {
message:
"messages.219: The last block in an assistant message cannot be thinking content",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
})
describe("tool_result_missing errors", () => {
it("should detect tool_use/tool_result mismatch", () => {
// given an error about tool_use without tool_result
const error = {
message: "tool_use block requires corresponding tool_result",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return tool_result_missing
expect(result).toBe("tool_result_missing")
})
})
describe("thinking_disabled_violation errors", () => {
it("should detect thinking disabled violation", () => {
// given an error about thinking being disabled
const error = {
message:
"thinking is disabled for this model and cannot contain thinking blocks",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_disabled_violation
expect(result).toBe("thinking_disabled_violation")
})
})
describe("unrecognized errors", () => {
it("should return null for unrecognized error patterns", () => {
// given an unrelated error
const error = {
message: "Rate limit exceeded",
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return null
expect(result).toBeNull()
})
it("should return null for empty error", () => {
// given an empty error
const error = {}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return null
expect(result).toBeNull()
})
it("should return null for null error", () => {
// given a null error
const error = null
// when detectErrorType is called
const result = detectErrorType(error)
// then should return null
expect(result).toBeNull()
})
})
describe("nested error objects", () => {
it("should detect error in data.error.message path", () => {
// given an error with nested structure
const error = {
data: {
error: {
message:
"messages.163: The final block in an assistant message cannot be thinking.",
},
},
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect error in error.message path", () => {
// given an error with error.message structure
const error = {
error: {
message: "messages.169: final block cannot be thinking",
},
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order
expect(result).toBe("thinking_block_order")
})
it("should detect thinking_block_order even when error message contains tool_use/tool_result in docs URL", () => {
// given Anthropic's extended thinking error with tool_use/tool_result in the documentation text
const error = {
error: {
type: "invalid_request_error",
message:
"messages.1.content.0.type: Expected `thinking` or `redacted_thinking`, but found `text`. " +
"When `thinking` is enabled, a final `assistant` message must start with a thinking block " +
"(preceeding the lastmost set of `tool_use` and `tool_result` blocks). " +
"We recommend you include thinking blocks from previous turns.",
},
}
// when detectErrorType is called
const result = detectErrorType(error)
// then should return thinking_block_order (NOT tool_result_missing)
expect(result).toBe("thinking_block_order")
})
})
})