Joao MouraandClaude Opus 5.5 2d83f10c26 fix(cli): AGENTS.md starts the login while evaluating, and stops after three rounds ...

"No account is needed to evaluate: don't wait on a login" made logged-out
agents treat the login as optional: setting up a project, half of them
stopped starting it. Evaluation loops also ran on without reporting. The
file now says to start the login hand-off and evaluate without waiting for
it, and to stop when the goal gate passes or after three rounds, reporting
the first and latest grades with both report links. A guard pins both.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-20 06:44:28 -07:00

..

authentication

chore(cli): drop self-explanatory comments

2026-05-26 01:05:25 -07:00

deploy

deploy push reads AMP's comparison refusal by its code (#8161)

2026-10-14 16:52:50 -03:00

enterprise

refactor: extract CLI into standalone crewai-cli package

2026-05-06 20:46:46 +08:00

experimental

fix(cli): crewai eval says why before it asks, and its help says when it asks (#8301)

2026-10-20 10:39:18 +05:30

organization

refactor: extract CLI into standalone crewai-cli package

2026-05-06 20:46:46 +08:00

skills

feat(skills)!: promote Skills Repository out of experimental (#6579)

2026-07-17 14:21:15 +00:00

tools

feat(cli): rewrite the scaffolded AGENTS.md and fail PRs that teach coding agents less (#8298)

2026-10-20 10:28:47 +05:30

triggers

refactor: extract CLI into standalone crewai-cli package

2026-05-06 20:46:46 +08:00

__init__.py

refactor: extract CLI into standalone crewai-cli package

2026-05-06 20:46:46 +08:00

conftest.py

feat(cli): crewai eval runs the crew itself, so a coding agent gets a verdict from one command (#8270)

2026-10-19 04:11:15 -03:00

test_checkpoint_telemetry.py

feat(telemetry): track checkpoint runtime and CLI usage (#7348)

2026-09-09 22:13:11 +05:30

test_cli.py

feat(cli): crewai deploy push --force, and why AMP held a push back (#8150)

2026-10-14 09:58:28 -03:00

test_click_compatibility.py

chore: widen click dependency constraint to allow 8.2+

2026-06-02 00:06:25 -07:00

test_config.py

fix: enforce owner-only permissions on credential files (#6242)

2026-06-26 01:36:48 +08:00

test_constants.py

[OSS-129] Map GPT-5.6 family to the official 1.05M context window (#7012)

2026-08-24 19:03:48 +00:00

test_create_crew.py

fix(cli): AGENTS.md starts the login while evaluating, and stops after three rounds

2026-10-20 06:44:28 -07:00

test_create_flow.py

feat(cli): rewrite the scaffolded AGENTS.md and fail PRs that teach coding agents less (#8298)

2026-10-20 10:28:47 +05:30

test_create_unified.py

feat(cli): unify scaffolding under crewai create <resource> (#6821)

2026-08-05 16:41:27 +00:00

test_crew_run_tui.py

feat(cli): crewai eval runs the crew itself, so a coding agent gets a verdict from one command (#8270)

2026-10-19 04:11:15 -03:00

test_crew_test.py

chore(cli): drop self-explanatory comments

2026-05-26 01:05:25 -07:00

test_flow_commands.py

Validate declarative flow definition paths (#6311)

2026-06-23 19:28:35 -07:00

test_git.py

Support ZIP deployment fallback and JSON crew project env runs (#6166)

2026-06-15 18:46:54 -03:00

test_input_prompt.py

fix(cli): keep runtime input prompts on stderr (#8297)

2026-10-20 07:56:30 +00:00

test_install_crew.py

Require explicit CrewAI project definitions (#6358)

2026-06-26 12:07:03 -07:00

test_kickoff_flow.py

feat(cli): crewai eval runs the crew itself, so a coding agent gets a verdict from one command (#8270)

2026-10-19 04:11:15 -03:00

test_model_catalog.py

fix(cli): key model-catalog cache by exact API key, shorten TTL, skip Ollama (#6468)

2026-07-07 18:47:19 -07:00

test_plus_api.py

fix(core): send AMP requests through the proxy the environment names (#8186)

2026-10-19 12:28:26 -03:00

test_run_crew.py

fix(core): send AMP requests through the proxy the environment names (#8186)

2026-10-19 12:28:26 -03:00

test_run_declarative_flow.py

feat(cli): crewai eval runs the crew itself, so a coding agent gets a verdict from one command (#8270)

2026-10-19 04:11:15 -03:00

test_scaffold_gitignore.py

feat(tracing): record the last traced run for crewai eval instead of printing it (#7648)

2026-09-21 17:28:25 +00:00

test_settings_command.py

chore(cli): drop self-explanatory comments

2026-05-26 01:05:25 -07:00

test_token_manager.py

fix: enforce owner-only permissions on credential files (#6242)

2026-06-26 01:36:48 +08:00

test_trace_consent_session.py

fix(tracing): turning tracing on is the answer, and an Evaluate button in the TUI (#7765)

2026-09-28 11:28:52 -07:00

test_train_crew.py

fix(cli): correct train filename error message (#7903)

2026-10-06 18:46:20 +00:00

test_tui_picker.py

Filter platform actions while selecting them (#7991)

2026-10-15 10:00:00 +05:30

test_update_crew.py

fix(cli): overwrite stale poetry.lock backup on windows (#7463)

2026-09-15 15:37:03 +00:00

test_utils.py

Implement DMN mode support in crew creation and execution (#6194)

2026-06-16 19:48:31 -03:00

test_version.py

Fix JSON crew version pin (#6342)

2026-06-26 05:19:14 -03:00