* fix(agent): make cursor stream protocol drift loud instead of silent (MUL-5434)
#6071 reports Cursor tasks that demonstrably read files, ran commands and
called the Multica CLI, yet showed a single blob of agent text with no
reasoning and no tool rows. The run still reported success and tools=0.
`switch evt.Type` in cursor.go had no `default` branch, so any top-level
event type we do not handle was dropped with no counter and no warning.
Renaming only the top-level types of a healthy stream
(`thinking`->`reasoning`, `tool_call`->`tool_calls`), leaving every nested
field untouched, reproduces the report exactly: status=completed, output =
the result text alone, tool_use=0, thinking=0, zero diagnostics. The
existing unknown-subtype warning cannot catch this — it only increments
once the type has already matched — so "no unknown-subtype warning" does
not rule out protocol drift.
Two diagnostic gaps are closed:
- Add the `default` branch with a bounded, content-free tally of unhandled
top-level types, reported once per run as a warning and alongside
tool_use_count in the protocol summary. Type names are normalized through
observedCursorEventType and distinct names are capped at 16 plus an
overflow bucket, so a hostile or noisy stream cannot grow the map or leak
payload into logs. `user` (the CLI echoing our prompt, present in every
recorded run) is explicitly benign so the warning does not fire always.
- Count assistant text separately from the terminal result text. The result
event writes into the same builder, so last_assistant_bytes equalled
result_bytes even when the assistant streamed nothing — erasing the
signal that says "only the final answer arrived". This also aligns cursor
with claude, which already reports assistant bytes only.
Unrecognized events are still never coerced into tool or reasoning
messages; guessing at upstream additions is the failure mode MUL-5231
already fixed once. This is diagnosis only and does not itself restore the
missing tool rows — identifying which upstream shape changed requires a
captured 2026.07.23 stream, and this warning is what makes that
identifiable from a single production log line.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): report cursor unhandled events as evidence, not as a verdict
Addresses the review's must-fix on MUL-5434. The diagnostic was described
as deciding WHY a transcript is empty, which it cannot do:
- "tools=0 with unhandled types" does not establish that a rename ate the
tool rows. Cursor 2026.07.23 also emits transport/control frames, so an
unhandled type only proves the stream carried events we do not parse.
- "tools=0 with no unhandled types" does not establish the agent used no
tools. The CLI may execute tools without handing the updates to its
stream serializer at all — the main branch #6071 has NOT ruled out — a
new shape may be nested inside an event type we already recognize, or
events may be lost to invalid framing or a scanner boundary.
Changes, no behaviour change to messages, status or output:
- Reword the tally doc, the switch default, the warning and the shared
observation struct to state what a non-zero and a zero count each do and
do not establish, and point at the branches that stay open.
- Rename unknown* to unhandled* (fields, log keys, warning text, the
pre-existing subtype counter) so the diagnostic never implies the type is
unrecognized upstream — only that this parser does not handle it.
- Classify `connection` and `retry` explicitly. They join `user` in
cursorNonTranscriptEventTypes, with per-entry provenance recorded: `user`
is confirmed in the recorded 2026.07.20 stream, the control frames are
reported on newer builds and listed defensively. A build that does not
emit them makes the entry inert; one that does must not have a known
control frame reported as an unhandled protocol event.
Tests assert signal presence and that nothing is fabricated, not causality:
the healthy-stream test now carries `connection` / `retry` and additionally
asserts the real thinking/tool rows still arrive, so suppressing the warning
cannot silently suppress the transcript. TestCursorNonTranscriptEventType
also pins that no type the parser handles can enter the suppression list.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Eve <eve@multica-ai.local>
Co-authored-by: multica-agent <github@multica.ai>
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>
Cursor stream-json emits reasoning and tool calls as top-level `thinking` /
`tool_call` events; the parser only looked for them inside assistant messages,
so transcripts showed a single step. Match the top-level events, taking the
tool name from the nested `<name>ToolCall` key and normalizing the packed
call_id. Subtypes are matched explicitly — only `started` opens a tool, only
`completed` closes it, only `delta` carries reasoning — so an unknown/missing
subtype is ignored rather than synthesizing a fake result (which would decrement
the daemon in-flight tool count early and misfire the watchdog) or polluting
reasoning. Covered by a recorded-stream fixture test, an unknown-subtype
regression test, and an opt-in real-CLI smoke test.
* fix(agent/cursor): send prompt on stdin so CLI-like flags cannot be re-tokenised (MUL-4992)
On Windows a Cursor task whose prompt contains CLI-like flags failed in ~2s
with `error: unknown option '-X'` and no agent output (#5649). A pasted build
log such as
go build -ldflags "-X main.version=foo" -o bin/server ./cmd/server
was enough to kill the run.
buildCursorArgs put the whole prompt in argv as the positional after -p.
The official Windows launcher chain ends in `& node.exe index.js $args`
inside cursor-agent.ps1, where PowerShell re-serialises $args onto node's
command line. Under Windows PowerShell 5.1 and pwsh <= 7.2 (Legacy native
argument passing) an argument holding embedded double quotes is not
re-escaped, so the quoted region closes early, node's argv parser re-splits
at the interior spaces, and `-X` reaches commander.js as a standalone flag.
#1709 removed the cmd.exe `%*` re-tokenisation but stopped at the
Go -> PowerShell boundary, one hop before this. Its Windows tests only
compare the argv slice Go builds and never execute a shim, which is why the
gap stayed invisible.
Fix: keep the prompt off every command line. cursor-agent's -p is a boolean
print-mode switch and the prompt is positional; with no positional prompt and
a non-TTY stdin the CLI reads stdin to EOF and uses that as the prompt. So
drop the prompt from argv on all platforms and write it to stdin, leaving
only fixed, content-free flags in argv. No shell or launcher on any platform
can re-tokenise what is not on a command line.
The write runs in its own goroutine: a prompt larger than the pipe buffer
(~64 KiB) blocks mid-write until the child drains it, and the child cannot
drain while nothing reads its stdout. Closing stdin signals end-of-prompt, so
it is closed on both success and error paths, and on cancellation to release
a blocked write. Write failures surface in the result diagnostic, ranked
below explicit agent errors so an early child exit (bad auth, bad flag) is
not masked by the resulting EPIPE.
Tests: a prompt carrying the exact `-ldflags "-X ..."` shape must arrive
byte-for-byte on stdin and appear nowhere in argv; a 512 KiB prompt must not
deadlock; the prompt is written verbatim (the CLI trims it, we do not). Both
new unix tests fail against the pre-fix code. A Windows-tagged test drives a
real PowerShell host through the same .cmd -> -File rewrite.
Closes#5649
Co-authored-by: multica-agent <github@multica.ai>
* test(agent/cursor): prove the Windows launcher fix on both PowerShell hosts in CI
The stdin fix has to hold on the host that actually exhibits the bug.
powershell.exe (5.1) and pwsh <= 7.2 default to Legacy native argument
passing; pwsh >= 7.3 defaults to Standard. A fix verified only on the newer
host would not be a fix for the reporter.
Run the shim probe against every PowerShell host on PATH rather than only the
one defaultPowerShellLookup would select, and hook the windows-tagged launcher
tests into the existing windows-execenv CI job. These tests are windows-tagged
and the backend job runs on ubuntu, so until now they ran nowhere.
Co-authored-by: multica-agent <github@multica.ai>
* test(ci): run Windows launcher tests verbosely so skips are visible
A skipped or unmatched test still reports "ok", which would make the
Windows job look like coverage it is not providing.
Co-authored-by: multica-agent <github@multica.ai>
* test(agent/cursor): close both coverage gaps in the #5649 regression tests
Two tests claimed guarantees they did not actually establish.
Windows: the fake cursor-agent.ps1 called [Console]::In.ReadToEnd() and wrote
the result itself, so it never launched a native child. The official shim ends
in `& node.exe index.js $args`, and that last hop is precisely where the bug
lives -- PowerShell re-serialises $args onto the child command line, and
whether the child inherits stdin was left unproven. The fake ps1 now
re-executes the test binary as a real native child (helper-process idiom),
which records the argv it actually received and drains stdin. Both PowerShell
hosts still run.
Interlock: the large-prompt fake drained stdin before writing any stdout, so
the child always unblocked the parent immediately and the test passed even
against a synchronous write -- it could not fail for the reason it existed.
The fake now floods stdout past pipe capacity *before* reading stdin, creating
the real mutual block. Verified: with the writer made synchronous the test
deadlocks to its 30s timeout, and passes only with the concurrent writer.
Also adds the missing cancellation case: a child that never reads stdin leaves
the writer blocked forever, so cancelling the context must close stdin,
release the writer and settle the run as aborted.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Bohan-J <bohan@devv.ai>
Co-authored-by: multica-agent <github@multica.ai>
Fixes Cursor agent token usage parsing for top-level camelCase, nested camelCase, and legacy nested snake_case result usage shapes. Includes tests for the locally verified nested camelCase stream-json output.
Treats Cursor's stream-json terminal `result` event as the protocol completion boundary so a lingering Cursor worker process can no longer hold the daemon task open after the agent has produced its final result.
- Tighten `cmd.WaitDelay` to 500ms (set before `Start()`)
- Set `resultSeen` and `cancel()` on terminal `result`
- Preserve completed/failed status across the cancellation via two `!resultSeen` guards in the post-loop status decision
- Add unix fake-CLI coverage for success and `is_error` terminal results
Active long-running sessions are no longer killed by a fixed wall-clock deadline. Liveness is delegated to the idle watchdog (MULTICA_AGENT_IDLE_WATCHDOG, default 30m) with a larger in-flight-tool budget (MULTICA_AGENT_TOOL_WATCHDOG, default 2h). MULTICA_AGENT_TIMEOUT is an opt-in absolute cap (default 0 = no cap). The server-side 2.5h sweeper is unchanged as a coarse backstop.
Fixes#3745.
The current cursor-agent CLI no longer has a 'chat' subcommand. The
positional 'chat' argument was silently treated as prompt text, leaking
into the user message (e.g. 'chat <actual prompt>').
Remove 'chat' from buildCursorArgs so the generated argv matches the
current cursor-agent CLI interface.
Fixes#3077
On Windows the official cursor-agent installer ships cursor-agent.cmd whose
body is `powershell ... -File cursor-agent.ps1 %*`. CreateProcess for a .cmd
file goes through cmd.exe, and `%*` in a batch file is expanded by
re-tokenising the original command line, which mangles arguments containing
newlines or other whitespace - most notably a long, multi-line `-p <prompt>`.
The agent then only sees a truncated prompt and fails with "Workspace Trust
Required" or exits 1 immediately.
When LookPath resolves cursor-agent to a .cmd/.bat launcher and a sibling
cursor-agent.ps1 exists, invoke PowerShell directly with `-File <ps1>` so
Go's os/exec passes each argv as a discrete token. This is exactly what the
.cmd does internally; we just skip the cmd.exe re-tokenisation step.
PowerShell host resolution prefers pwsh.exe (PS 7) on PATH, then
powershell.exe on PATH, and finally falls back to
%SystemRoot%\System32\WindowsPowerShell\v1.0.
Platform-specific code is split via build tags
(cursor_invocation_windows.go / cursor_invocation_other.go) so non-Windows
builds carry no Windows-only dependencies. The lookup is exposed as a
package variable to make the Windows path fully unit-testable without
spawning real PowerShell. Five unit tests cover: passthrough on non-launcher
targets, successful rewrite with a multi-line prompt, .exe direct launch
(skip), missing .ps1 (skip), and missing PowerShell host (skip).
The change leaves macOS / Linux behaviour entirely untouched and stays on
the official cursor-agent launch chain - no node.exe direct invocation, no
prompt mutation, no extra flags.
Closes#1297
Made-with: Cursor
* fix(daemon): suppress agent terminal windows on Windows (#1471)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add hideAgentWindow to detectCLIVersion and avoid SysProcAttr overwrite
- Add missing hideAgentWindow(cmd) call in detectCLIVersion (claude.go:554)
so --version checks don't flash console windows on Windows.
- Refactor hideAgentWindow to preserve existing SysProcAttr fields
instead of overwriting the entire struct.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Surface the actual exec path + argv for every agent backend at INFO
so operators can see the exact command without flipping to debug.
Also add the missing log line in pi.go for consistency with the
other nine backends.
* feat(agent): add Cursor Agent CLI runtime support
Add cursor-agent as a new agent backend, following the same pattern as
existing providers. The implementation spawns cursor-agent CLI with
stream-json output, parses JSONL events into the unified Message type,
and supports session resume, usage tracking, and auto-approval (--yolo).
Changes:
- server/pkg/agent/cursor.go: cursorBackend implementation
- server/pkg/agent/cursor_test.go: unit tests for args, parsing, errors
- server/pkg/agent/agent.go: register "cursor" in New() factory
- server/internal/daemon/config.go: probe cursor-agent in PATH
- server/internal/daemon/execenv/context.go: cursor skill discovery path
- server/internal/daemon/execenv/runtime_config.go: AGENTS.md injection
- packages/views/.../provider-logo.tsx: cursor logo in UI
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(agent): address PR review for cursor backend
1. Fix token usage double-counting: usage is now taken exclusively from
"result" events (session totals). Per-message usage in "assistant"
events is intentionally ignored. "step_finish" usage is only used as
fallback when no "result" usage is available.
2. Remove dead code: isCursorUnknownSessionError() and its regex were
defined but never called. Removed along with corresponding test.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(agent): add missing CustomArgs, SystemPrompt, MaxTurns, and debug logging to cursor backend
- Add cursorBlockedArgs and filterCustomArgs support for safe custom arg passthrough
- Add --system-prompt and --max-turns flag support to buildCursorArgs
- Add debug logging of command args before execution (consistent with all other backends)
- Move stdout-close goroutine inside main goroutine (consistent with claude.go pattern)
- Add tests for SystemPrompt/MaxTurns and CustomArgs filtering
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* chore: make daemon uses local profile & update Cursor logo to official brand
- Makefile: make daemon now runs 'daemon start --profile local' for local dev
- Replace Cursor runtime logo with official brand SVG (removed background rect)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(agent): remove unsupported --system-prompt and --max-turns from cursor-agent
cursor-agent CLI does not support these flags. Instructions are already
injected via AGENTS.md and .cursor/skills/ files.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(agent): prevent step_finish + result usage double-counting in cursor
Split usage accumulation into separate stepUsage and resultUsage maps.
After stream ends, use resultUsage if available (session totals from
result event), otherwise fall back to stepUsage (sum of step_finish).
This prevents 2x counting when result.usage already includes totals.
Added table-driven test covering: result-only, step_finish-only,
step_finish+result (no double count), and multi-model scenarios.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* docs(agent): fix misleading comment on cursor -p flag
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Devv <devv@Devvs-Mac-mini.local>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: yushen <ldnvnbl@gmail.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
