Add OpenExecutive as the 32nd runtime - #5921
Merged
Merged
Conversation
✅ Drift Bot (ClawMetry): no drift detectedDrift Bot analyzed the changed files against this project's blueprints and requirements and found no drift. |
Contributor
Visual diffComparing 51 of 70 comparison(s) flagged (>1% pixel diff).
Folder: 3b041c6d2058. Full PNGs also attached as a workflow artefact. Generated by visual-diff bot. Pixel diffs >1% flagged; eyeball the table before merging. This check is non-blocking — fail = bot bug, not a code problem. |
✅ Drift Bot (ClawMetry): no drift detectedDrift Bot analyzed the changed files against this project's blueprints and requirements and found no drift. |
OSS half of the OpenExecutive runtime (adapter ships in clawmetry-pro): catalogue + loader spec, labels, landing path, session-prefix sets, probe, declared record (tokens/cost PARTIAL: specialist calls write no usage row), memory catalogue, resume hint, compaction coverage, and an explicit Guard verdict: one API server serves every conversation, so control is unsupported with a human reason rather than the generic string. Also adds muse_code to sync._RUNTIME_PREFIXES and app.js _CM_RT_PREFIXES, which it was missing from, and pins both with a guard. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015D9pee1kCZ8NanY9bZirq4
…ELOG, MODULE_MAP Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015D9pee1kCZ8NanY9bZirq4
vivekchand
force-pushed
the
openexecutive-runtime
branch
from
September 12, 2026 20:42
8aa960e to
3b041c6
Compare
✅ Drift Bot (ClawMetry): no drift detectedDrift Bot analyzed the changed files against this project's blueprints and requirements and found no drift. |
vivekchand
added a commit
that referenced
this pull request
Sep 12, 2026
Claude-Session: https://claude.ai/code/session_015D9pee1kCZ8NanY9bZirq4 Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
3 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds OpenExecutive (SenteLabsAI/OpenExecutive, Apache-2.0, ~4.1k stars) as runtime 32. It is an AI executive team: one Executive persona on FastAPI that routes questions to specialist agents (CFO, CSO, COO, General Counsel, ...), answers over web chat, Slack, email, Telegram, Discord and Google Chat, and runs a scheduler that sends messages on its own later. Pairs with the clawmetry-pro PR carrying the adapter.
Why it fits
Everything is observable from the outside with no vendor cooperation: one SQLite store (
episodic_memory.db) holds sessions, an audit log with per-call token usage, and the queue of outbound sends. The standout signal is that queue: a pending email to the board is visible before it goes out.What changed here (OSS half)
PAID_RUNTIMES,_FAMILY_ADAPTER_SPECS, labels, landing path/runtimes/openexecutive, and every session-prefix set (local_store,routes/usagex2,routes/attention,routes/harness,sync._RUNTIME_PREFIXES, app.js_CM_RT_PREFIXES+ both label maps).muse_codewas missing fromsync._RUNTIME_PREFIXESand app.js_CM_RT_PREFIXES, so its sessions bucketed as openclaw there. Added, and pinned bytest_the_newest_runtimes_are_in_the_backend_and_frontend_prefix_sets.runtime_records+docs/compatibility.mdsay so.unsupported, with a sentence. One API server serves every conversation, channel and the scheduler, so there is no per-conversation process. Newprocess_control.SHARED_PROCESS_RUNTIMESmaps it to a human reason instead of the generic "No signal support for openexecutive". A reopen hint covers the gap.make devwrites to plus/data; memory surfaces the company profile, knowledge base andmcp_servers.json; listed inUNSUPPORTED_COMPACTIONbecause its short-term window drops old turns without recording it.scripts/sync_runtime_count.py, plus the 7 translated taglines the script does not rewrite.Testing
tests/test_openexecutive_runtime_wiring.py(13 tests, registered inci.yml).test_api_runtimes_fallback_lists_both_free_runtimesand bothtest_runtime_tab_capability_paritytests. Not touched here.8b2a9a7(details in the pro PR).Follow-ups
/runtimes/openexecutive(landing PR, merges after the release).Spec: https://factory.8090.ai/project/b415065f-ab2f-4f53-8864-0c009fd098cb/requirements/4868d4ff-75ef-4044-821c-dc5f77bcf072 (Extended Runtime Support, AC-GOV-ERS-010.1-.7) and blueprint section "32nd runtime: OpenExecutive" (ADR-ERS-026..028).
No-PRD: adding a runtime adapter to the existing, documented adapter seam (same as Muse Code #5761); no new product surface beyond one more runtime in the existing catalogue.
🤖 Generated with Claude Code
https://claude.ai/code/session_015D9pee1kCZ8NanY9bZirq4