hermes-agent/tui_gateway
alt-glitch e01b04de46 fix(tui): chrome cost from Nous portal headers only (F3)
The status-bar cost segment must show cost ONLY when running against the Nous
portal — per-model cache/input/output pricing is unreliable across the model
long tail, so a guessed figure is worse than none.

- New nous_header_cost_usd(agent): the chrome cost source, derived ONLY from the
  x-nous-credits-* header delta (deliberately ignores the OpenRouter usage.cost
  accumulator). _get_usage now uses it for cost_usd, so a non-Nous session
  reports no cost and the TUI hides the segment.
- The /usage accounting page is unchanged in spirit: it now reads
  real_session_cost_usd(agent) directly (both provider-reported sources) instead
  of the chrome-narrowed _get_usage cost_usd, so OpenRouter cost still shows there.

Tests: new TestNousHeaderCost (header-only, OR-accumulator ignored, clamp,
no-method); updated gateway _get_usage tests for the chrome narrowing; /usage
page test still asserts the full provider-reported figure. 316 gateway + 25 cost
tests green.
2026-06-13 19:17:41 +05:30
..
__init__.py feat: new tui based on ink 2026-04-02 19:07:53 -05:00
entry.py perf(tui): stop slow/dead MCP servers from freezing TUI startup 2026-05-30 02:53:37 -07:00
event_publisher.py chore: address copilot comments 2026-04-24 12:51:04 -04:00
render.py tui: inherit Python-side rendering via gateway bridge 2026-04-05 18:50:41 -05:00
server.py fix(tui): chrome cost from Nous portal headers only (F3) 2026-06-13 19:17:41 +05:30
slash_worker.py tests: pin ink engine in _make_tui_argv npm-bootstrap tests (post-merge semantic fix) 2026-06-12 10:32:40 +05:30
transport.py fix(tui-gateway): harden stdio transport against half-closed pipes + SIGTERM races (#17118) 2026-04-28 17:54:06 -05:00
ws.py tests: pin ink engine in _make_tui_argv npm-bootstrap tests (post-merge semantic fix) 2026-06-12 10:32:40 +05:30