You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add progress heartbeats for long blocking MCP calls, preserve persistent session project directories across follow-up prompts, and make the Claude live harnesses deterministic with explicit plugin loading.
Co-Authored-By: OpenAI Codex <noreply@openai.com>
Copy file name to clipboardExpand all lines: README.md
+5-2Lines changed: 5 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -33,6 +33,7 @@ Optional environment overrides:
33
33
-`CODEX_SUBAGENTS_JOB_TTL_SECONDS`: completed async job retention window. Defaults to one hour.
34
34
-`CODEX_SUBAGENTS_LOG_LEVEL`: `debug`, `info`, `warn`, `error`, or `silent`. Defaults to `debug`.
35
35
-`CODEX_SUBAGENTS_LOG_MAX_STRING_CHARS`: maximum string payload retained per log field before truncation metadata is used. Defaults to `20000`.
36
+
-`CODEX_SUBAGENTS_PROGRESS_HEARTBEAT_MS`: interval for progress heartbeats on blocking tool calls. Defaults to `10000`.
36
37
37
38
## Spark And Nested Subagents
38
39
@@ -130,7 +131,9 @@ npm run test:claude-desktop
130
131
131
132
`test:claude-real-codex` is the full opt-in live path: Claude Code loads the plugin and calls real Codex through the desktop app binary, including one single agent, one parallel run, and one nested Spark subagent run. It spends both Claude and Codex tokens, so it is intentionally not part of the default suite.
132
133
133
-
`test:claude-autodiscovery` is an opt-in live Claude Code test for automatic tool selection. It gives Claude a natural "ask Codex" request, uses the installed plugin and fake Codex binary, and verifies that Claude chooses the Codex MCP tool without being told the exact tool name.
134
+
`test:claude-real-session` is an opt-in live Claude Code test for daemonless persistent sessions. It loads the symlinked installed plugin, starts a real Codex session, sends a follow-up without `project_dir`, and verifies the session stays pinned to the original project directory.
135
+
136
+
`test:claude-autodiscovery` is an opt-in live Claude Code test for automatic tool selection. It gives Claude a natural "ask Codex" request, loads the local plugin with the fake Codex binary, and verifies that Claude chooses the Codex MCP tool without being told the exact tool name.
134
137
135
138
Run Claude Code with the local plugin:
136
139
@@ -172,7 +175,7 @@ Prefer `start_agent_run` or `start_agents_run` for work that may run longer than
172
175
173
176
Async job snapshots expose partial stdout/stderr and parsed event summaries through `get_agent_run` while work is still running.
174
177
175
-
When a client supports MCP progress tokens, `run_agent`, `run_agents`, `start_agent_run`, `start_agents_run`, `get_agent_run`, `wait_agent_run`, and `cancel_agent_run` send progress notifications. SDK clients should pass an `onprogress` handler and enable timeout reset on progress for long waits.
178
+
When a client supports MCP progress tokens, `run_agent`, `run_agents`, `run_agents_aggregate`, `start_session`, `send_session_prompt`, `start_agent_run`, `start_agents_run`, `get_agent_run`, `wait_agent_run`, and `cancel_agent_run` send progress notifications. SDK clients should pass an `onprogress` handler and enable timeout reset on progress for long waits.
"test:ci": "npm run build && npm test && npm run smoke:mcp && npm run test:reliability && npm run test:stress && npm run test:progress && npm run test:advanced && npm run test:dev-link",
38
39
"test:comprehensive": "npm run build && npm test && npm run smoke:mcp && npm run test:reliability && npm run test:stress && npm run test:progress && npm run test:advanced && npm run test:codex-runtime && npm run validate:plugin && npm run test:claude-desktop",
0 commit comments