Bohan Jiang bce0c05856 refactor(agent): drop dead Cursor cost fields (CLI reports no cost) (#5852) ...

MUL-5240

cursor-agent's stream-json never populates total_cost_usd or a per-step
cost — the result event's usage object carries token counts only. Both
fields were speculatively copied from Claude Code's schema in the original
Cursor runtime PR (#1057) and were never read. Verified against the real
CLI (2026.07.20, stream-json and json) plus Cursor's CLI docs.

Remove the two dead fields and document that Cursor spend stays estimated
from the static rate table (no authoritative per-turn cost to carry, unlike
Grok). No behavior change.

Co-authored-by: Bohan-J <bohan@devv.ai>
Co-authored-by: multica-agent <github@multica.ai>

2026-07-24 01:55:07 +08:00

..

testdata

MUL-5231 fix(agent): parse Cursor top-level thinking and tool_call events (#5846)

2026-07-24 01:52:15 +08:00

agent_supported_types_test.go

feat(runtime): add Qwen Code runtime (MUL-5015)

2026-07-21 14:55:08 +08:00

agent_test_executable_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

agent_test.go

feat(runtime): add Qwen Code runtime (MUL-5015)

2026-07-21 14:55:08 +08:00

agent.go

MUL-5228 fix(usage): bill Grok at xAI's reported cost, fix $0 resumed sessions (#5841)

2026-07-24 01:42:08 +08:00

antigravity_test.go

fix: block claude settings flag for antigravity (#4974)

2026-07-06 15:58:38 +08:00

antigravity.go

fix: block claude settings flag for antigravity (#4974)

2026-07-06 15:58:38 +08:00

browser_mcp_config_test.go

MUL-4103: harden Windows browser MCP config (#4976)

2026-07-06 16:14:03 +08:00

browser_mcp_config.go

MUL-4103: harden Windows browser MCP config (#4976)

2026-07-06 16:14:03 +08:00

claude_deadlock_test.go

fix: preflight Claude root/sudo launches with an actionable error (#4944)

2026-07-07 12:19:50 +08:00

claude_test.go

feat(agents): add per-agent runtime skill controls (#5686)

2026-07-22 15:38:38 +08:00

claude.go

feat(agents): add per-agent runtime skill controls (#5686)

2026-07-22 15:38:38 +08:00

codebuddy_test.go

MUL-4824: fail closed on incomplete Claude-style result streams (#5522)

2026-07-16 15:22:46 +08:00

codebuddy.go

fix(daemon): retry with a fresh session only when the resume was actually rejected (MUL-4966) (#5715)

2026-07-21 19:07:46 +08:00

codex_cleanup_unix_test.go

MUL-5155: KAP-1051: diagnose Codex thread/start timeouts fail-closed (#5759)

2026-07-23 15:09:50 +08:00

codex_test.go

MUL-5185: add Codex Fast mode (#5821)

2026-07-23 15:40:18 +08:00

codex.go

MUL-5185: add Codex Fast mode (#5821)

2026-07-23 15:40:18 +08:00

copilot_invocation_other.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

copilot_invocation_test.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

copilot_invocation_windows_test.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

copilot_invocation_windows.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

copilot_invocation.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

copilot_test.go

fix: surface copilot failure details (#2396)

2026-05-11 14:08:33 +08:00

copilot.go

fix(daemon): inactivity-based agent run timeout, no wall-clock guillotine (MUL-3064)

2026-06-05 15:06:07 +08:00

cursor_execute_unix_test.go

MUL-4903 fix(agent): harden Cursor terminal failures (#5559)

2026-07-17 13:09:20 +08:00

cursor_integration_test.go

MUL-5231 fix(agent): parse Cursor top-level thinking and tool_call events (#5846)

2026-07-24 01:52:15 +08:00

cursor_invocation_other.go

fix(agent/cursor): route Windows launcher through PowerShell -File to preserve multi-line prompts (#1709)

2026-04-29 14:00:15 +08:00

cursor_invocation_test.go

fix(agent/cursor): remove obsolete 'chat' subcommand from argv (#3077) (#3092)

2026-05-27 16:40:29 +08:00

cursor_invocation_windows_test.go

fix(agent/cursor): remove obsolete 'chat' subcommand from argv (#3077) (#3092)

2026-05-27 16:40:29 +08:00

cursor_invocation_windows.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

cursor_invocation.go

fix(agent/cursor): route Windows launcher through PowerShell -File to preserve multi-line prompts (#1709)

2026-04-29 14:00:15 +08:00

cursor_stdin_unix_test.go

fix(agent/cursor): send prompt on stdin so CLI-like flags cannot be re-tokenised (MUL-4992) (#5711)

2026-07-21 16:01:04 +08:00

cursor_stdin_windows_test.go

fix(agent/cursor): send prompt on stdin so CLI-like flags cannot be re-tokenised (MUL-4992) (#5711)

2026-07-21 16:01:04 +08:00

cursor_stream_fixture_unix_test.go

MUL-5231 fix(agent): parse Cursor top-level thinking and tool_call events (#5846)

2026-07-24 01:52:15 +08:00

cursor_test.go

refactor(agent): drop dead Cursor cost fields (CLI reports no cost) (#5852)

2026-07-24 01:55:07 +08:00

cursor.go

refactor(agent): drop dead Cursor cost fields (CLI reports no cost) (#5852)

2026-07-24 01:55:07 +08:00

deveco_models.go

feat(agents): add DevEco Code (deveco) runtime agent (MUL-4050) (#4916)

2026-07-14 15:21:45 +08:00

deveco_test.go

feat(agents): add DevEco Code (deveco) runtime agent (MUL-4050) (#4916)

2026-07-14 15:21:45 +08:00

deveco.go

feat(agents): add DevEco Code (deveco) runtime agent (MUL-4050) (#4916)

2026-07-14 15:21:45 +08:00

exec_fixture_unix_test.go

fix(landing): scope landing route to always-light palette (MUL-1277) (#1537)

2026-04-23 01:52:46 +08:00

exec_fixture_windows_test.go

fix(agent/opencode): bypass npm .cmd shim on Windows to preserve multi-line prompts (#1718)

2026-04-27 12:16:56 +08:00

grok_integration_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

grok_test.go

MUL-5228 fix(usage): bill Grok at xAI's reported cost, fix $0 resumed sessions (#5841)

2026-07-24 01:42:08 +08:00

grok.go

MUL-5228 fix(usage): bill Grok at xAI's reported cost, fix $0 resumed sessions (#5841)

2026-07-24 01:42:08 +08:00

handoff_version_test.go

MUL-3416: Issue pre-trigger preview + Handoff Note (#4383)

2026-06-23 13:17:13 +08:00

hermes_test.go

MUL-5228 fix(usage): bill Grok at xAI's reported cost, fix $0 resumed sessions (#5841)

2026-07-24 01:42:08 +08:00

hermes.go

MUL-5228 fix(usage): bill Grok at xAI's reported cost, fix $0 resumed sessions (#5841)

2026-07-24 01:42:08 +08:00

kimi_test.go

fix(agent): clear stale session id when a resumed ACP session is gone [MUL-3216] (#4015)

2026-06-11 14:54:56 +08:00

kimi.go

fix(daemon): retry with a fresh session only when the resume was actually rejected (MUL-4966) (#5715)

2026-07-21 19:07:46 +08:00

kiro_test.go

MUL-4860 fix(acp/kiro): GPT-5.6 Sol completion — object rawOutput + positive-proof guard (follow-up to #5511) (#5515)

2026-07-16 13:36:45 +08:00

kiro.go

fix(daemon): retry with a fresh session only when the resume was actually rejected (MUL-4966) (#5715)

2026-07-21 19:07:46 +08:00

mcp_config.go

feat: redesign agent Skills and MCP capabilities (#5277)

2026-07-12 02:53:17 +08:00

models_test.go

fix(agent): accept ACP configOptions model catalog (kimi-code 0.29) (#5851)

2026-07-24 01:45:24 +08:00

models.go

fix(agent): accept ACP configOptions model catalog (kimi-code 0.29) (#5851)

2026-07-24 01:45:24 +08:00

openclaw_test.go

feat(openclaw): support connecting to existing OpenClaw gateway (#3260) [MUL-3158] (#3664)

2026-06-13 15:33:28 +08:00

openclaw.go

feat(openclaw): support connecting to existing OpenClaw gateway (#3260) [MUL-3158] (#3664)

2026-06-13 15:33:28 +08:00

opencode_cancel_unix_test.go

fix(agent): terminate opencode process group before closing stdout (#4533) (#4541)

2026-06-25 00:41:25 +08:00

opencode_mcp_test.go

feat(agent): consume OpenCode mcp_config via OPENCODE_CONFIG_CONTENT (#3098)

2026-05-30 18:08:21 +08:00

opencode_mcp.go

feat(agent): consume OpenCode mcp_config via OPENCODE_CONFIG_CONTENT (#3098)

2026-05-30 18:08:21 +08:00

opencode_test.go

fix(agent): fail opencode runs whose stream ends without a terminal signal (#5238)

2026-07-15 16:40:59 +08:00

opencode.go

fix(agent): fail opencode runs whose stream ends without a terminal signal (#5238)

2026-07-15 16:40:59 +08:00

pi_invocation_other.go

MUL-2708: fix(agent): preserve multi-line Pi prompt on Windows by bypassing the .cmd shim (#3417)

2026-05-28 12:36:16 +08:00

pi_invocation_test.go

MUL-2708: fix(agent): preserve multi-line Pi prompt on Windows by bypassing the .cmd shim (#3417)

2026-05-28 12:36:16 +08:00

pi_invocation_windows_test.go

MUL-2708: fix(agent): preserve multi-line Pi prompt on Windows by bypassing the .cmd shim (#3417)

2026-05-28 12:36:16 +08:00

pi_invocation_windows.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

pi_invocation.go

MUL-2708: fix(agent): preserve multi-line Pi prompt on Windows by bypassing the .cmd shim (#3417)

2026-05-28 12:36:16 +08:00

pi_test.go

fix(agent): pi agent final output excludes intermediate steps (#4894) (MUL-4030)

2026-07-06 15:34:22 +08:00

pi.go

fix(agent): pi agent final output excludes intermediate steps (#4894) (MUL-4030)

2026-07-06 15:34:22 +08:00

proc_other.go

MUL-5155: KAP-1051: diagnose Codex thread/start timeouts fail-closed (#5759)

2026-07-23 15:09:50 +08:00

proc_windows_test.go

MUL-5155: KAP-1051: diagnose Codex thread/start timeouts fail-closed (#5759)

2026-07-23 15:09:50 +08:00

proc_windows.go

MUL-5155: KAP-1051: diagnose Codex thread/start timeouts fail-closed (#5759)

2026-07-23 15:09:50 +08:00

qoder_test.go

MUL-3305: feat(agent): add qoder CLI as a choice of agent provider. (#2461)

2026-06-22 18:55:45 +08:00

qoder.go

fix(daemon): retry with a fresh session only when the resume was actually rejected (MUL-4966) (#5715)

2026-07-21 19:07:46 +08:00

qwen_test.go

MUL-5141: fix(agent): inject --yolo in Qwen headless runs so shell/edit/write tools are available (#5752)

2026-07-22 13:35:59 +08:00

qwen.go

MUL-5141: fix(agent): inject --yolo in Qwen headless runs so shell/edit/write tools are available (#5752)

2026-07-22 13:35:59 +08:00

real_agent_smoke_integration_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

stderr_tail.go

MUL-4903 fix(agent): harden Cursor terminal failures (#5559)

2026-07-17 13:09:20 +08:00

stream_json_final_output_test.go

MUL-4903 fix(agent): harden Cursor terminal failures (#5559)

2026-07-17 13:09:20 +08:00

stream_json_result.go

MUL-4903 fix(agent): harden Cursor terminal failures (#5559)

2026-07-17 13:09:20 +08:00

thinking_test.go

MUL-5185: add Codex Fast mode (#5821)

2026-07-23 15:40:18 +08:00

thinking.go

MUL-5185: add Codex Fast mode (#5821)

2026-07-23 15:40:18 +08:00

traecli_integration_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

traecli_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

traecli.go

fix(daemon): retry with a fresh session only when the resume was actually rejected (MUL-4966) (#5715)

2026-07-21 19:07:46 +08:00

version_test.go

feat(runtime): add Qwen Code runtime (MUL-5015)

2026-07-21 14:55:08 +08:00

version.go

feat(runtime): add Qwen Code runtime (MUL-5015)

2026-07-21 14:55:08 +08:00