mirror of
https://github.com/openclaw/openclaw.git
synced 2026-10-03 09:39:25 +00:00
docs: illustrate the 2026.9.1 release page (#152988)
* docs: illustrate the 2026.9.1 release page Add ten GitHub-hosted release illustrations with exact published UI captures and clearly labeled concepts. Preserve the original release narrative and legacy raw changelog. Co-authored-by: steipete <58493+steipete@users.noreply.github.com> * docs: illustrate the 2026.9.1 release page OpenClaw-Publication: 0f3e84b4-9780-4918-b3db-543ba839d01d Co-authored-by: steipete <58493+steipete@users.noreply.github.com> --------- Co-authored-by: steipete <58493+steipete@users.noreply.github.com>
This commit is contained in:
RoboClaw
GitHub
parent
ec13f837c4
commit
df7ee5e4f9
1 changed files with 40 additions and 0 deletions
|
|
@ -27,6 +27,10 @@ On a fresh local install, the recommended Quick Start path can reuse verified Cl
|
|||
|
||||
On a headless machine, the same path provides a one-time authenticated dashboard link and an SSH tunnel template instead of exposing reusable Gateway credentials. Custom setup, remote Gateway onboarding, and non-interactive setup keep their existing paths when Quick Start is not the right fit.
|
||||
|
||||
|
||||
|
||||
_Quick Start reuses usable AI access while leaving service installation for later. Conceptual illustration, not a screenshot. Conceptual flow, not a terminal capture. Headless setup provides a one-time dashboard link and an SSH tunnel template._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -152,6 +156,10 @@ Completed Mermaid fences now render as diagrams directly in chat, with the exact
|
|||
|
||||
The renderer is lazy-loaded and isolated from the rest of the page, and model-authored output is reduced to passive SVG before display. Incomplete fences remain code, while invalid, oversized, or externally dependent diagrams fall back to readable source with an error instead of being treated as a successful render.
|
||||
|
||||
|
||||
|
||||
_A proposed Harbor welcome route renders from Mermaid inside the published conversation. Published 2026.9.1 interface with fictional Harbor data; no live task execution._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -171,6 +179,10 @@ Returning to existing work is steadier too. Dashboards and background tasks stay
|
|||
|
||||
New Session can also prepare a suggested name after an eligible draft sits briefly idle without delaying Start. Chat and New Session load lighter payloads and reuse display preferences for the connected Gateway, while account footers show when that Gateway is suspending or suspended and clear when work admission returns.
|
||||
|
||||
|
||||
|
||||
_The draft, agent workspace, model, and effort controls stay together on New Session. Published 2026.9.1 interface with fictional Harbor data; no live task execution._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -493,6 +505,10 @@ When an interactive update gets far enough to fail operationally, OpenClaw can n
|
|||
|
||||
That investigation does not get authority to retry the update, repair state, or restart the Gateway on its own, and a successful investigation does not turn the original update into a success. JSON, `--yes`, background, and managed-service runs remain diagnostic-only, preserving the original exit result while printing the next commands for an operator to use.
|
||||
|
||||
|
||||
|
||||
_A bounded, sanitized failure record carries useful context into the triage conversation. Conceptual illustration, not a screenshot. Conceptual flow. JSON, --yes, background, and managed-service runs remain diagnostic-only._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -718,6 +734,10 @@ Built-in Memory now has an explicit `openclaw memory reset` path that discards o
|
|||
|
||||
Full reindexes are safer around that path. Replacement caches are bounded before publication, failed full rebuilds leave the previously published cache intact, a memory change during automatic maintenance gets one retry against current content, and abandoned workspace locks can recover after process-ID reuse. Recovery messages identify whether an incompatible index belongs to OpenClaw or configuration, warn when an explicit rebuild may contact a paid embedding provider, and retain the unreadable source path; ordinary replies remain available while a legacy index is repaired in the background, and combined memory and wiki searches continue to show the affected agent's repair instructions.
|
||||
|
||||
|
||||
|
||||
_The explicit memory reset path removes rebuildable search data while keeping durable sources. Conceptual illustration, not a screenshot. Conceptual boundary. Confirmation is required; non-interactive use requires --yes. A later rebuild may use a paid embedding provider._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -863,6 +883,10 @@ Signed-in teammates on a shared Gateway can create, import, update, and reuse sk
|
|||
|
||||
ZIP imports now reserve room across profiles as well. One person with many unfinished uploads cannot occupy every pending slot, while existing uploads can still finish and linked or merged identities continue to share one allowance. Each session also keeps the immutable skill revision that was selected, including its supporting files and executable permissions, as work moves through local, sandbox, cloud, or node workers.
|
||||
|
||||
|
||||
|
||||
_The real library distinguishes private, shared, and team-owned Harbor skills. Published 2026.9.1 interface with fictional Harbor data; no live task execution._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -928,6 +952,10 @@ The Android app now brings the pieces people reach for during a normal conversat
|
|||
|
||||
That work also keeps the app usable on narrow screens and with larger text, and it gives an actionable Providers and Models route before sending with an explicitly selected model whose authentication is unavailable. That check still follows the availability reported by the connected Gateway and is scoped to explicitly selected models.
|
||||
|
||||
|
||||
|
||||
_The 9.1 native experience brings everyday conversation controls into reachable places. Conceptual illustration, not a screenshot. Conceptual feature map—not an Android screenshot. No current native UI is presented as historical 9.1 evidence._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -1137,6 +1165,10 @@ The Control UI now gathers the main model, utility model, first fallback, thinki
|
|||
|
||||
Reasoning choices now stay attached to the runtime that actually owns them. Eligible Sol and Terra turns keep Ultra through supported child-session boundaries, configured native Codex models show the effort levels their account advertises, and Luna remains capped at Max. Anthropic Fable 5.1 joins the shared API and Claude CLI catalogs, supported local Ollama routes remain selectable, and status views keep an authored context cap when a model runs through a provider alias.
|
||||
|
||||
|
||||
|
||||
_Model, utility model, fallback, thinking, and Fast Mode share the Defaults card. Published 2026.9.1 interface with fictional Harbor data; no live task execution._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -1387,6 +1419,10 @@ Older schedules are handled more carefully too. Upgrades that have not yet compl
|
|||
|
||||
Operators who do not want stale reminders, digests, or model calls after downtime can enable `cron.skipMissedJobs: true`. On startup, OpenClaw advances overdue recurring schedules to their next future occurrence and saves that decision before normal scheduling resumes. The setting is opt-in, so leaving it unset or false preserves the existing catch-up behavior, and one-time jobs are not skipped.
|
||||
|
||||
|
||||
|
||||
_With cron.skipMissedJobs enabled, downtime does not trigger a backlog of recurring garden reminders. Conceptual illustration, not a screenshot. Conceptual timeline. This is opt-in: unset or false retains the existing catch-up behavior._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
@ -2124,6 +2160,10 @@ Installations with large saved-session histories also keep less conversation dat
|
|||
|
||||
Discord and Telegram turns on large SQLite session stores no longer wait for full-store maintenance before dispatch; bounded cleanup continues afterward.
|
||||
|
||||
|
||||
|
||||
_Four fictional Harbor conversations populate the real session catalog; no benchmark is implied. Published 2026.9.1 interface with fictional Harbor data; no live task execution._
|
||||
|
||||
<details class="release-source-toggle">
|
||||
<summary>Sources and complete change list</summary>
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue