Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(tui): add /status session diagnostics

Browse Source
This commit is contained in:
ZiyaZhang
2026-07-22 03:10:14 -07:00
parent 988dd70e7c
commit 280207c824
13 changed files with 316 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/tui-agent/README.md
View File

@@ -17,7 +17,7 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem
The `todo_write` task tracker is opt-in and not in the shipped config: add `@deepseek-ai/dsh-tool-todo` to `cordis.yml` (or a personal-config overlay under `~/.dsh`) to expose it. Once loaded, the model records a whole-list plan to the session log and the TUI renders it.
The TUI renders Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and — when `todo_write` is loaded — the latest plan. Long tool bodies keep a head/tail preview; Ctrl+O expands or collapses every card. Enter submits or steers while the agent runs, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `/model` opens a keyboard selector for the current provider catalog; use Up/Down and Enter, or `/model <model>` and `/model <provider>/<model>` for direct selection. `ask_user_question` opens a wide bottom-left keyboard panel with batch progress and numbered options.
The TUI renders Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and — when `todo_write` is loaded — the latest plan. Long tool bodies keep a head/tail preview; Ctrl+O expands or collapses every card. Enter submits or steers while the agent runs, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `/status` expands the current session's identity, activity counts, exact token/cache buckets, context use, and timestamps without interrupting a running turn. `/model` opens a keyboard selector for the current provider catalog; use Up/Down and Enter, or `/model <model>` and `/model <provider>/<model>` for direct selection. `ask_user_question` opens a wide bottom-left keyboard panel with batch progress and numbered options.
### Resuming a prior session

14
examples/tui-agent/tests/tui-keyless-smoke.e2e.ts
View File

@@ -101,8 +101,10 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
// provider's tool-less title call; the scripted adapter answers it, the
// accepted title lands in the log, and the TUI renders the terminal
// window title as `<session title> — <configured title>` via OSC 0.
// Gating /exit on it keeps the assertion race-free.
{ waitFor: 'scripted session title — DeepSeek Harness', send: '/exit\r' },
// Gating /status on it keeps the assertion race-free; the diagnostics
// card is then exercised through the same real Loader/PTY composition.
{ waitFor: 'scripted session title — DeepSeek Harness', send: '/status\r' },
{ waitFor: 'Session diagnostics', send: '/exit\r' },
],
})
expect(output).toContain('I need one decision before I continue.')
@@ -114,6 +116,14 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
expect(output).not.toContain('\u009B31mMODEL_C1')
expect(output).toContain('Safe')
expect(output).toContain('\u001B]0;scripted session title — DeepSeek Harness\u0007')
expect(output).toContain('Session diagnostics')
expect(output).toContain('Title')
expect(output).toContain('scripted session title')
expect(output).toContain('Model')
expect(output).toContain('tui-scripted/tui-scripted-model-pro')
expect(output).toContain('KV cache hit')
expect(output).toContain('Context')
expect(output).toContain('128,000')
expect(output).toContain('\u001B[?2004l')
}, LOADER_SMOKE_TEST_TIMEOUT_MS)