- Cursor quota exhaustion is now classified separately from context overflow in provider recovery
- Stream-stall retries now use explicit profiles, shared budgets, classifiers, backoff planning, and failure diagnostics
- Anthropic refusal fallback now preserves returned-model pricing
- Reasoning replay, Bedrock redacted reasoning, Z.AI metadata, Azure toolChoice, Google thinking mappings, Kimi cached-token accounting, and Copilot policy-rate handling receive compatibility fixes
- xAI now uses the Responses API path with encrypted reasoning replay, with Grok 4.6 as the refreshed default
- Credential pools now support slot-preserving mutations and slot-specific logout
- OAuth refresh now preserves sibling and pinned credential slots
- Renamed /start-work command to /ulw-execute with hard cutover and no old-name alias
- Compaction no longer assumes provider usage is present
- Truncated summaries are now rejected rather than replayed as complete
- Settings diagnostics now identify exact file and key paths
- State-file permissions, BOM handling, and invalid-settings behavior now have regression coverage
- Extension cleanup after failed extension factories
- Nested skill discovery
- Malformed streamed tool-call arguments
- Corrected toolcall_start metadata
- Branded resume hints
- Cross-platform shell behavior
- start_work configuration key is deprecated in favor of ulw_execute and will emit a warning for one release
From oh-my-openagent
OmO beta.20
Beta.20 is the current beta release of the OmO multi-harness distribution and native edition.
- OmO:
5.0.0-beta.20 - OmO Native:
omo-ai@5.0.0-0.beta.20 - Senpi engine:
@code-yeongyu/senpi@2026.8.25
Senpi 2026.8.25
This release includes the current upstream-integrated Senpi line, including
the upstream RPC queue-clearing surface from upstream/main@a79b37334,
preserved prompt/message ordering, deterministic RPC coverage, and the
fork-specific compatibility repairs recorded after the sync.
Provider recovery is stronger in this release:
- Cursor quota exhaustion is classified separately from context overflow.
- Stream-stall retries use explicit profiles, shared budgets, classifiers, backoff planning, and failure diagnostics.
- Anthropic refusal fallback preserves returned-model pricing.
- OpenAI-compatible reasoning controls and provider-neutral
toolChoiceremain available. - Reasoning replay, Bedrock redacted reasoning, Z.AI metadata, Azure
toolChoice, Google thinking mappings, Kimi cached-token accounting, and Copilot policy-rate handling receive compatibility fixes. - xAI uses the Responses API path with encrypted reasoning replay, with Grok 4.6 as the refreshed default.
Credential and session continuity also improve:
- Credential pools support slot-preserving mutations and slot-specific logout.
- OAuth refresh preserves sibling and pinned credential slots.
- Compaction no longer assumes provider usage is present.
- Truncated summaries are rejected rather than replayed as complete.
- Settings diagnostics identify exact file and key paths.
- State-file permissions, BOM handling, and invalid-settings behavior have regression coverage.
The release also carries extension and CLI fixes for cleanup after failed
extension factories, nested skill discovery, malformed streamed tool-call
arguments, corrected toolcall_start metadata, branded resume hints, and
cross-platform shell behavior.
OmO beta.20
Exact native dependency
omo-ai@5.0.0-0.beta.20 depends exactly on:
@code-yeongyu/senpi: 2026.8.25
The native package is published on npm's beta channel. latest remains the
intentional placeholder, so install the beta tag or the exact prerelease.
Configuration and migration
The unified ~/.omo/omo.jsonc surface remains the cross-harness configuration
contract. Legacy configuration migration is lock- and journal-backed, with
no-clobber diagnostics, migration markers, resumable backups, and dry-run/JSON
modes.
Skill and command migration
| Previous name | Beta.20 name | Migration |
|---|---|---|
/start-work and start-work | /ulw-execute and ulw-execute | Hard cutover; no old-name alias. |
start-work-continuation | ulw-execute-continuation | Update component paths and hooks. |
omo-senpi-start-work-continuation-disabled | omo-senpi-ulw-execute-continuation-disabled | Rename the flag. |
skill_loaded: start-work | skill_loaded: ulw-execute | Update telemetry queries. |
start_work | ulw_execute | Old key reads for one release with a warning; new key wins. |
omo executable | omo-agent-toolkit | Update direct invocations. |
The current native inventory includes mass-ulw, ultrawork, ulw-plan,
ulw-loop, ulw-research, hyperplan, init-deep, dag-library,
onboarding, and give-me-tips. This inventory is not a claim that every
listed skill was introduced in beta.20.
Reliability and orchestration
The beta.20 OmO line includes dependency-frontier DAG admission, honest paused run headers and resume leases, non-blocking reattach paths, reflection run-id collision protection, Bubblewrap degradation, lock-free journal scans and flushes, Atlas cleanup on early exits, surface/install attribution telemetry, and compiled native launcher/asset parity.
Upgrade instructions
Native edition
npm install -g omo-ai@beta
# or:
npm install -g omo-ai@5.0.0-0.beta.20
Multi-harness edition
bun install -g oh-my-openagent@5.0.0-beta.20
# or:
npm install -g oh-my-opencode@5.0.0-beta.20
Replace direct omo invocations with omo-agent-toolkit. Rename
start_work to ulw_execute and use the new continuation-disable flag.
Verification
The release chain was verified in order:
- Senpi release dry-run, release gates, npm publication, and GitHub tag.
- OmO exact dependency/version checks, native payload, generated bundle freshness, frozen install, and package containment checks.
- npm beta metadata for
omo-ai, the wrapper packages, and platform package surfaces. - Rich release content was applied above the generated GitHub changelog while preserving the generated content below it.
Compatibility and known limitations
- This remains a beta release; provider availability and quotas are external.
/start-workhas no compatibility alias.start_workis a one-release compatibility read path and emits a warning.omo-aiis beta-only andlatestremains a placeholder.- Platform smoke jobs may depend on runner/container runtime libraries; their failure does not invalidate the npm package payload when the package gates and platform publication checks pass.
Evidence sources
- Senpi:
v2026.8.24..v2026.8.25,af5f53b0d,a79b37334,99c711255. - OmO:
package.json,packages/omo-native/package.json,CHANGELOG.md,.github/workflows/publish.yml, and theget-unpublished-changesprocedure. - Skill migration:
e3cb1486d,cc57d3908,2aece77f4. - QA evidence:
local-ignore/qa-evidence/beta20/.
Desktop runtime work remains internal QA evidence for this release and is not being exposed as a public Desktop download from the OmO beta release.