Replace "pending" with "incomplete" in todos output; omit from default view

[jeremy]

Summary

• Rename the user-facing label for incomplete todos from "pending" to "incomplete" in filter values, TUI help hints, empty-state messages, and skill docs
• Accept --status incomplete as the new canonical filter value, keeping pending as a backward-compatible alias
• Normalize "incomplete" → "pending" before passing to the SDK on the single-todolist path (the SDK documents "pending" as the accepted value)
• Omit the completed label entirely for incomplete todos in styled/markdown output — incomplete is the default state, so showing it on every row is noise. "done" still appears when a todo is completed. JSON/agent output is unaffected (raw boolean)

Notes

• The cross-todolist aggregation path fetches todos without a status filter and filters client-side, so it handles both values without SDK involvement
• The empty.NoTodos() change ("incomplete", "pending" case) is forward-looking — no caller currently passes a status context string

Test plan

• bin/ci passes (unit tests, e2e, skill drift, surface snapshot)
• basecamp todos list --status incomplete --in <project> filters correctly
• basecamp todos list --status incomplete --list <id> --in <project> works (single-list path)
• basecamp todos list --status pending --in <project> still works (backward compat)
• Detail view omits "Completed" field for incomplete todos, shows "Completed: done" for completed ones

[github-actions]

⚠️ Potential breaking changes detected:

• Renamed the status flag option value 'pending' to 'incomplete' in todos output, which is a breaking change for scripts or users relying on the previous value.

Review carefully before merging. Consider a major version bump.

[Copilot]

Pull request overview

This PR updates the CLI/TUI/presenter user-facing terminology for not-yet-done todos from “pending” to “incomplete”, while intending to keep pending as a backwards-compatible status filter alias.

Changes:

• Update todo “completed=false” label in the presenter schema from pending → incomplete and adjust presenter tests accordingly.
• Update TUI short-help and empty-state messaging to display “incomplete”.
• Update todos list flag help text and adjust cross-list filtering to treat pending as an alias of incomplete.

Reviewed changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
skills/basecamp/SKILL.md	Updates skill documentation to show --status as completed/incomplete.
internal/tui/workspace/views/todos.go	Updates the TUI toggle hint label from “pending” to “incomplete”.
internal/tui/workspace/views/todos_test.go	Updates TUI hint assertion to “incomplete”.
internal/tui/empty/messages.go	Updates todo empty-state to say “No incomplete todos…”, accepting incomplete and pending contexts.
internal/presenter/schemas/todo.yaml	Changes boolean label for completed=false from “pending” to “incomplete”.
internal/presenter/presenter_test.go	Updates tests to assert “incomplete” output instead of “pending”.
internal/commands/todos.go	Updates --status help text and treats pending as alias of incomplete in the cross-list client-side filter path.

Comments suppressed due to low confidence (1)

internal/commands/todos.go:274

• --status incomplete is now advertised, but the value is passed through to basecamp.TodoListOptions.Status in the single-todolist path (via fetchTodosIncludingGroups). The Basecamp API/SDK status filter appears to only support values like completed (and historically pending), so sending incomplete will likely break basecamp todos list --list ... --status incomplete (server-side filtering) even though the cross-list path applies client-side filtering. Consider normalizing the flag before SDK calls (e.g., map incomplete/pending to empty status or to the API's expected value) and/or validating supported values with a clear usage error.

	cmd.Flags().StringVarP(&flags.status, "status", "s", "", "Filter by status (completed, incomplete)")
	cmd.Flags().BoolVar(&flags.completed, "completed", false, "Show completed todos (shorthand for --status completed)")
	cmd.Flags().BoolVar(&flags.overdue, "overdue", false, "Filter overdue todos")
	cmd.Flags().IntVarP(&flags.limit, "limit", "n", 0, "Maximum number of todos to fetch (0 = default 100)")
	cmd.Flags().BoolVar(&flags.all, "all", false, "Fetch all todos (no limit)")

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: bdd390eae1

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[cubic-dev-ai]

1 issue found across 7 files

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="internal/commands/todos.go">

<violation number="1" location="internal/commands/todos.go:611">
P1: The "incomplete" → "pending" alias is only applied in the `listAllTodos` client-side filter, not in the `fetchTodosIncludingGroups` SDK path. When `--list` is specified, `listTodosInList` passes the raw status to the API — so `--status incomplete --list <id>` sends an unrecognized value to the Basecamp API.

Normalize early in `runTodosList`, before either code path is entered.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[Copilot]

Pull request overview

Updates the Basecamp CLI/TUI todo status terminology by renaming the user-facing “pending” label to “incomplete”, while keeping pending as a backward-compatible --status alias and normalizing to the SDK’s expected value where needed.

Changes:

• Renamed todo completion label output from “pending” → “incomplete” (presenter schema + related rendering tests).
• Added --status incomplete handling, including single-todolist normalization to pending for SDK/API calls and cross-todolist client-side filtering for both values.
• Updated TUI help hints, empty-state copy, skill docs, and added/updated tests for the new status behavior.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
skills/basecamp/SKILL.md	Updates documented --status values to use “incomplete”.
internal/tui/workspace/views/todos_test.go	Updates TUI ShortHelp expectation to “incomplete”.
internal/tui/workspace/views/todos.go	Updates the TUI ShortHelp hint label from “pending” to “incomplete”.
internal/tui/empty/messages.go	Updates empty-state messaging to say “No incomplete todos…”, supporting both context strings.
internal/presenter/schemas/todo.yaml	Changes boolean label for completed=false from “pending” to “incomplete”.
internal/presenter/presenter_test.go	Updates presenter rendering tests to expect “incomplete” output.
internal/commands/todos_test.go	Adds tests ensuring --status incomplete normalizes to pending for single-list SDK calls and filters client-side in cross-list mode.
internal/commands/todos.go	Updates CLI flag help text and implements single-list status normalization + cross-list alias-aware filtering.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Updates the CLI/TUI todo terminology and filtering so users see and can query for “incomplete” todos instead of “pending”, while keeping pending working as a backward-compatible alias and ensuring the single-todolist SDK call still receives the SDK-supported status value.

Changes:

• Renames user-facing “pending” wording to “incomplete” in CLI help/docs and TUI hints/empty states.
• Adds/validates behavior for --status incomplete (including normalization to pending before SDK calls on the single-list path).
• Updates presenter schema/tests and command tests to reflect the new status naming and filtering behavior.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
skills/basecamp/SKILL.md	Updates user documentation for --status flag terminology.
internal/tui/workspace/views/todos_test.go	Adjusts TUI help tests to expect “incomplete”.
internal/tui/workspace/views/todos.go	Updates the TUI short-help hint label from “pending” to “incomplete”.
internal/tui/empty/messages.go	Updates empty-state copy to say “No incomplete todos…”, while accepting both contexts.
internal/presenter/schemas/todo.yaml	Changes how incomplete status is rendered in the todo schema (completed=false label).
internal/presenter/presenter_test.go	Updates presenter tests around boolean labels and todo detail/markdown output expectations.
internal/commands/todos_test.go	Adds tests verifying --status incomplete normalization and cross-list client-side filtering.
internal/commands/todos.go	Updates --status help text, normalizes incomplete→pending for SDK calls, and treats both values equivalently in client-side filtering.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[cubic-dev-ai]

1 issue found across 3 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="internal/presenter/schemas/todo.yaml">

<violation number="1" location="internal/presenter/schemas/todo.yaml:33">
P2: The `completed` false-label is now an empty string, so incomplete todos will display a blank status in the detail view. The previous value was already `"incomplete"`, which matches the PR's stated goal. If the intent is to show "incomplete" in the detail view (per the test plan), this should be preserved rather than blanked.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}