f146aeff0f
* 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>
233 lines
6.9 KiB
TypeScript
233 lines
6.9 KiB
TypeScript
import { describe, expect, test } from "bun:test"
|
|
import { createSisyphusJuniorAgentWithOverrides, SISYPHUS_JUNIOR_DEFAULTS } from "./sisyphus-junior"
|
|
|
|
describe("createSisyphusJuniorAgentWithOverrides", () => {
|
|
describe("honored fields", () => {
|
|
test("applies model override", () => {
|
|
// given
|
|
const override = { model: "openai/gpt-5.2" }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.model).toBe("openai/gpt-5.2")
|
|
})
|
|
|
|
test("applies temperature override", () => {
|
|
// given
|
|
const override = { temperature: 0.5 }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.temperature).toBe(0.5)
|
|
})
|
|
|
|
test("applies top_p override", () => {
|
|
// given
|
|
const override = { top_p: 0.9 }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.top_p).toBe(0.9)
|
|
})
|
|
|
|
test("applies description override", () => {
|
|
// given
|
|
const override = { description: "Custom description" }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.description).toBe("Custom description")
|
|
})
|
|
|
|
test("applies color override", () => {
|
|
// given
|
|
const override = { color: "#FF0000" }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.color).toBe("#FF0000")
|
|
})
|
|
|
|
test("appends prompt_append to base prompt", () => {
|
|
// given
|
|
const override = { prompt_append: "Extra instructions here" }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.prompt).toContain("You work ALONE")
|
|
expect(result.prompt).toContain("Extra instructions here")
|
|
})
|
|
})
|
|
|
|
describe("defaults", () => {
|
|
test("uses default model when no override", () => {
|
|
// given
|
|
const override = {}
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.model).toBe(SISYPHUS_JUNIOR_DEFAULTS.model)
|
|
})
|
|
|
|
test("uses default temperature when no override", () => {
|
|
// given
|
|
const override = {}
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.temperature).toBe(SISYPHUS_JUNIOR_DEFAULTS.temperature)
|
|
})
|
|
})
|
|
|
|
describe("disable semantics", () => {
|
|
test("disable: true causes override block to be ignored", () => {
|
|
// given
|
|
const override = {
|
|
disable: true,
|
|
model: "openai/gpt-5.2",
|
|
temperature: 0.9,
|
|
}
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then - defaults should be used, not the overrides
|
|
expect(result.model).toBe(SISYPHUS_JUNIOR_DEFAULTS.model)
|
|
expect(result.temperature).toBe(SISYPHUS_JUNIOR_DEFAULTS.temperature)
|
|
})
|
|
})
|
|
|
|
describe("constrained fields", () => {
|
|
test("mode is forced to subagent", () => {
|
|
// given
|
|
const override = { mode: "primary" as const }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.mode).toBe("subagent")
|
|
})
|
|
|
|
test("prompt override is ignored (discipline text preserved)", () => {
|
|
// given
|
|
const override = { prompt: "Completely new prompt that replaces everything" }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.prompt).toContain("You work ALONE")
|
|
expect(result.prompt).not.toBe("Completely new prompt that replaces everything")
|
|
})
|
|
})
|
|
|
|
describe("tool safety (task/delegate_task blocked, call_omo_agent allowed)", () => {
|
|
test("task and delegate_task remain blocked, call_omo_agent is allowed via tools format", () => {
|
|
// given
|
|
const override = {
|
|
tools: {
|
|
task: true,
|
|
delegate_task: true,
|
|
call_omo_agent: true,
|
|
read: true,
|
|
},
|
|
}
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
const tools = result.tools as Record<string, boolean> | undefined
|
|
const permission = result.permission as Record<string, string> | undefined
|
|
if (tools) {
|
|
expect(tools.task).toBe(false)
|
|
expect(tools.delegate_task).toBe(false)
|
|
// call_omo_agent is NOW ALLOWED for subagents to spawn explore/librarian
|
|
expect(tools.call_omo_agent).toBe(true)
|
|
expect(tools.read).toBe(true)
|
|
}
|
|
if (permission) {
|
|
expect(permission.task).toBe("deny")
|
|
expect(permission.delegate_task).toBe("deny")
|
|
// call_omo_agent is NOW ALLOWED for subagents to spawn explore/librarian
|
|
expect(permission.call_omo_agent).toBe("allow")
|
|
}
|
|
})
|
|
|
|
test("task and delegate_task remain blocked when using permission format override", () => {
|
|
// given
|
|
const override = {
|
|
permission: {
|
|
task: "allow",
|
|
delegate_task: "allow",
|
|
call_omo_agent: "allow",
|
|
read: "allow",
|
|
},
|
|
} as { permission: Record<string, string> }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override as Parameters<typeof createSisyphusJuniorAgentWithOverrides>[0])
|
|
|
|
// then - task/delegate_task blocked, but call_omo_agent allowed for explore/librarian spawning
|
|
const tools = result.tools as Record<string, boolean> | undefined
|
|
const permission = result.permission as Record<string, string> | undefined
|
|
if (tools) {
|
|
expect(tools.task).toBe(false)
|
|
expect(tools.delegate_task).toBe(false)
|
|
expect(tools.call_omo_agent).toBe(true)
|
|
}
|
|
if (permission) {
|
|
expect(permission.task).toBe("deny")
|
|
expect(permission.delegate_task).toBe("deny")
|
|
expect(permission.call_omo_agent).toBe("allow")
|
|
}
|
|
})
|
|
})
|
|
|
|
describe("prompt composition", () => {
|
|
test("base prompt contains discipline constraints", () => {
|
|
// given
|
|
const override = {}
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
expect(result.prompt).toContain("Sisyphus-Junior")
|
|
expect(result.prompt).toContain("You work ALONE")
|
|
expect(result.prompt).toContain("BLOCKED ACTIONS")
|
|
})
|
|
|
|
test("prompt_append is added after base prompt", () => {
|
|
// given
|
|
const override = { prompt_append: "CUSTOM_MARKER_FOR_TEST" }
|
|
|
|
// when
|
|
const result = createSisyphusJuniorAgentWithOverrides(override)
|
|
|
|
// then
|
|
const baseEndIndex = result.prompt!.indexOf("Dense > verbose.")
|
|
const appendIndex = result.prompt!.indexOf("CUSTOM_MARKER_FOR_TEST")
|
|
expect(baseEndIndex).not.toBe(-1) // Guard: anchor text must exist in base prompt
|
|
expect(appendIndex).toBeGreaterThan(baseEndIndex)
|
|
})
|
|
})
|
|
})
|