Go to file
DaiChaoXiong 6257f4f6b8 test(providers): real-endpoint-log regressions for Responses reasoning
Based on the user's actual deepseek-v4-flash debug log (Responses protocol):

- real_log_captures_reasoning_and_tools: replays turn 1 of the real SSE
  (reasoning item + reasoning_text.delta + two function calls) and asserts the
  Done message is [Thinking, ToolCall, ToolCall] with usage mapped
  (input 850 / output 157 / cache-read 768)
- agent_multi_turn_replays_reasoning: drives a 3-turn agent over the real
  protocol (turn 1 + turn 2 from the log, plus a terminating text turn),
  asserting thinking lands in the transcript and the second request's replay
  carries a reasoning item with the captured text and matching call ids

MockTransport gains requests() to inspect all recorded requests.
2026-08-09 22:04:11 +08:00
crates test(providers): real-endpoint-log regressions for Responses reasoning 2026-08-09 22:04:11 +08:00
docs/architecture INIT 2026-07-16 17:59:16 +08:00
examples INIT 2026-07-16 17:59:16 +08:00
.gitignore docs(workspace): whitelist ratatui/crossterm for focus-tui 2026-08-09 21:35:58 +08:00
AGENTS.md docs(workspace): whitelist ratatui/crossterm for focus-tui 2026-08-09 21:35:58 +08:00
Cargo.lock docs(workspace): whitelist ratatui/crossterm for focus-tui 2026-08-09 21:35:58 +08:00
Cargo.toml docs(workspace): whitelist ratatui/crossterm for focus-tui 2026-08-09 21:35:58 +08:00
README.md chore(workspace): sync manifests, docs and lockfile 2026-08-09 21:00:04 +08:00
rust-toolchain.toml INIT 2026-07-16 17:59:16 +08:00

README.md