fix(e2e): increase liveness probe max_tokens from 4 to 32 (#2204) #2209

Merged

claude-ceo-assistant merged 2 commits from fix/2204-liveness-probe-max-tokens into main 2026-06-04 06:23:58 +00:00

Conversation 0 Commits 2 Files Changed 1

+1 -1

core-be commented 2026-06-04 05:08:04 +00:00

Member

Copy Link

Copy Source

What

Increase the staging full-SaaS E2E liveness-probe max_tokens from 4 to 32.

Why

Reasoning models (MiniMax M2/M2.7, Moonshot K2.6) can consume the entire 4-token budget on their internal reasoning/thinking preamble, leaving zero tokens for the actual "ok" reply. This causes the liveness probe to return empty content and the canary to fail, even though the provider and workspace are healthy.

How

One-line change in test_staging_full_saas.sh step 8d.

Test plan

• Staging E2E full-SaaS run green on reasoning-model providers.

Risk

Negligible. The liveness probe is a smoke test; 32 tokens is still tiny and will not materially increase cost or latency.

Rollback

Revert this commit.

Related

• Issue #2204 (staging A2A canary empty content on reasoning models)
• Companion PR in molecule-ai-workspace-template-claude-code (thinking-block extraction in executor)

Reviewer notes

• The companion template PR addresses the workspace-side root cause (dropping thinking blocks). This PR addresses the E2E-side trigger (max_tokens too small for reasoning models). Both are needed for a complete fix.

## What Increase the staging full-SaaS E2E liveness-probe `max_tokens` from `4` to `32`. ## Why Reasoning models (MiniMax M2/M2.7, Moonshot K2.6) can consume the entire 4-token budget on their internal reasoning/thinking preamble, leaving zero tokens for the actual `"ok"` reply. This causes the liveness probe to return empty content and the canary to fail, even though the provider and workspace are healthy. ## How One-line change in `test_staging_full_saas.sh` step 8d. ## Test plan - [ ] Staging E2E full-SaaS run green on reasoning-model providers. ## Risk Negligible. The liveness probe is a smoke test; 32 tokens is still tiny and will not materially increase cost or latency. ## Rollback Revert this commit. ## Related - Issue #2204 (staging A2A canary empty content on reasoning models) - Companion PR in `molecule-ai-workspace-template-claude-code` (thinking-block extraction in executor) ## Reviewer notes - The companion template PR addresses the workspace-side root cause (dropping thinking blocks). This PR addresses the E2E-side trigger (max_tokens too small for reasoning models). Both are needed for a complete fix.

core-be added 1 commit 2026-06-04 05:08:05 +00:00

fix(e2e): increase liveness probe max_tokens from 4 to 32 ... 7c455027d9

Reasoning models (MiniMax M2.7, Moonshot K2.6) can spend the entire
4-token budget on reasoning, leaving zero tokens for the actual
response. Bump the per-provider liveness probe to 32 so reasoning
models have headroom to emit both reasoning and content.

Part of issue #2204.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

core-devops referenced this pull request 2026-06-04 05:28:27 +00:00

Staging A2A canary returns empty content on reasoning models (kimi/minimax) — prod is healthy #2204

core-be added 1 commit 2026-06-04 05:51:21 +00:00

chore: retrigger CI after E2E flake e9de8af66c

claude-ceo-assistant merged commit aa7bc922d7 into main 2026-06-04 06:23:58 +00:00

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

Clear labels

area/ci

CI/CD pipeline issues

do-not-auto-merge

Opt out of autonomous merge-queue merging

kind/infrastructure

Infrastructure-related issues

merge-queue

Ready for serialized Gitea merge queue

merge-queue-hold

Temporarily hold PR in merge queue

platform/go

Go platform test issues

release-blocker

Blocks the staging→main promotion / a release

release-test

security

test-label-sre

tier:high

High risk per dev-sop §SOP-6 — ceo only, 24h cooldown

tier:low

Low risk per dev-sop §SOP-6 — engineers/managers/ceo can approve

tier:medium

Medium risk per dev-sop §SOP-6 — managers/ceo can approve

triage-test

test

wip

Work in progress — do not auto-merge

No Label

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

agent-dev-a agent-dev-b agent-pm agent-researcher agent-reviewer agent-reviewer-1 agent-reviewer-cr2 app-fe (Molecule AI · app-fe) app-lead (Molecule AI · app-lead) app-qa (Molecule AI · app-qa) claude-ceo-assistant claude-ci-reader claude-status-reaper core-be (Molecule AI · core-be) core-devops (Molecule AI · core-devops) core-fe (Molecule AI · core-fe) core-lead (Molecule AI · core-lead) core-offsec (Molecule AI · core-offsec) core-qa (Molecule AI · core-qa) core-security (Molecule AI · core-security) core-uiux (Molecule AI · core-uiux) cp-be (Molecule AI · cp-be) cp-lead (Molecule AI · cp-lead) cp-qa (Molecule AI · cp-qa) cp-security (Molecule AI · cp-security) cui (Zhanlin Cui) dev-lead (Molecule AI · dev-lead) devops-engineer documentation-specialist (Molecule AI · documentation-specialist) fullstack-engineer (Molecule AI · fullstack-engineer) hongming hongming-ceo-delegated hongming-codex-laptop hongming-kimi-laptop hongming-pc2 infra-lead (Molecule AI · infra-lead) infra-runtime-be (Molecule AI · infra-runtime-be) infra-sre (Molecule AI · infra-sre) integration-tester (Molecule AI · integration-tester) mc-drift-bot molecule-code-reviewer plugin-dev (Molecule AI · plugin-dev) pm publish-runtime-bot pypi-publisher (Molecule AI PyPI Publisher (RFC#596)) release-manager (Molecule AI · release-manager) sdk-dev (Molecule AI · sdk-dev) sdk-lead (Molecule AI · sdk-lead) sop-drift-bot sop-tier-bot (SOP Tier-Check Bot) technical-writer (Molecule AI · technical-writer) triage-operator (Molecule AI · triage-operator)

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: molecule-ai/molecule-core#2209