Jiayuan Zhang 10c57c0f7a docs: add SWE-bench runner guide ...

Covers the full pipeline: dataset download, agent execution,
result analysis, and official Docker evaluation. Includes
runner options, output format, known limitations, and initial
benchmark results.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-15 18:30:58 +08:00

..

auth

refactor: unify API URL env var to MULTICA_API_URL

2026-02-15 06:31:00 +08:00

channels

…

mobile

…

architecture.drawio

…

cli.md

docs: slim down README and split into topic-specific docs

2026-02-15 03:23:54 +08:00

client-streaming-protocol.md

…

code-stats-report.html

feat(report): add code stats report generator

2026-02-15 04:32:30 +08:00

credentials.md

docs: update credential docs for per-skill .env files

2026-02-15 13:34:51 +08:00

development.md

refactor: unify API URL env var to MULTICA_API_URL

2026-02-15 06:31:00 +08:00

e2e-testing-guide.md

fix(auth): fallback to dev auth.json for E2E tests

2026-02-15 16:37:26 +08:00

exec-approval.md

…

memo.md

…

message-paths.md

…

package-management.md

…

product-capabilities.md

docs: update credential docs for per-skill .env files

2026-02-15 13:34:51 +08:00

rpc.md

…

skills-and-tools.md

docs: slim down README and split into topic-specific docs

2026-02-15 03:23:54 +08:00

subagent-architecture.html

…

swe-bench.md

docs: add SWE-bench runner guide

2026-02-15 18:30:58 +08:00

time-injection.md

docs: slim down README and split into topic-specific docs

2026-02-15 03:23:54 +08:00