Skip to content

Update the sandbox limit to 25, document self-service Hermes updates and rewrite the CrewAI guide for the built-in provider - #40

Merged
ats3v merged 5 commits into
mainfrom
sandbox-limit-25
Oct 12, 2026
Merged

ats3v merged 5 commits into
mainfrom
sandbox-limit-25

Conversation

@ats3v

@ats3v ats3v commented Oct 12, 2026 •

Copy link
Copy Markdown
Member

Summary

This PR carries three independent doc updates.

Sandbox limit: 5 → 25

The per-account cap on active sandboxes goes from 5 to 25. This updates the three places that stated the old number:

  • sandboxes/overview.mdx, Limits and quotas: "up to 25 non-stopped sandboxes per account"
  • sandboxes/overview.mdx, Errors table: "Over the 25-active-sandboxes cap"
  • integrations/crewai.mdx: "Note the account limit of 25 active sandboxes"

Only the number changes. Going over the cap still returns a 429 (RateLimitError / TooManySandboxesError), and stopped sandboxes still don't count toward it.

A search of the whole repo, including api-reference/openapi.json, found no other place that states the limit.

Hosted Hermes-Agent: self-service updates

The platform no longer upgrades Hermes-Agent instances in place. The customer connects over SSH and runs the update command that the dashboard's Update action shows. Three places described the old flow, and each fix has its own commit:

  • New Updating section in agents/hermes-agent.mdx (28146a5). It gives the SSH steps and the update command, worded like the dashboard dialog, and links the upstream releases. It suggests a backup first, since hermes update pulls upstream main. It also notes that the version shown in the dashboard doesn't change after a self-update, and that hermes --version shows what is running.
  • Update bullet in agents/introduction.mdx, Manage an instance (3634067). It said every framework upgrades in place. It now says that applies to OpenClaw, and that for Hermes-Agent Update shows the commands to run.
  • HTTP API in agents/introduction.mdx (4f4d5f1). POST /v1/agents/{instance_id}/update now returns 409 for Hermes-Agent instances, with the command to run. A line under the example says so.

The command is written out in full (git -C /opt/hermes/src remote set-branches origin main && hermes update) rather than as a bare hermes update. The git part is needed on older instances that haven't been restarted since the change, and it is harmless on the rest.

These stay unchanged because they are still correct:

  • agents/openclaw.mdx: OpenClaw still upgrades in place.
  • The note and FAQ entry on DeepInfra's admin SSH access "(updates and backup restores for example)": still true for OpenClaw.
  • The API reference: it is loaded live from api.deepinfra.com/openapi.json, so it picks up the 409 on its own.

CrewAI: built-in DeepInfra provider

crewai 1.15.27 (2026-10-09) ships DeepInfra as a native OpenAI-compatible provider (crewAIInc/crewAI#7459): LLM(model="deepinfra/<org>/<model>") reads DEEPINFRA_API_KEY and needs neither a base URL nor LiteLLM. integrations/crewai.mdx is rewritten around that (9958ffe):

  • Configuration collapses to LLM(model="deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731") in all three examples, replacing the custom_openai=True / base_url / api_key block. DEEPINFRA_BASE_URL is documented for proxies.
  • The @llm workaround note is removed. A plain llm: deepinfra/... string now works in agents.yaml, so the page shows that snippet instead.
  • Install line pins crewai>=1.15.27; the "Tested with" note moves from 1.15.21 to 1.15.27.
  • Tips: the LiteLLM tip becomes an "Older CrewAI versions" fallback (custom_openai=True + base_url, which still works on current versions); a new tip covers the org/model id check, which now raises a ValueError at construction; the context-window tip stays, because the native provider still assumes 8,192 tokens for DeepInfra ids.

Unchanged on purpose:

  • Knowledge and memory keep the openai embedder with api_base pointed at DeepInfra. The native DeepInfra embeddings provider (crewAIInc/crewAI#7978) is not merged yet; this section should switch to it once it ships.
  • Sandbox section and the model table: all six ids are current in the catalog and none is deprecated.

Verification: every Python block in the page was extracted and run verbatim against api.deepinfra.com with crewai 1.15.27, plus a @CrewBase crew configured only through agents.yaml, structured outputs (response_format and output_pydantic), streaming, and the DEEPINFRA_BASE_URL override.

Not in this PR

The fleet-wide cap is also going up, but the docs never give that number, so the Fleet capacity bullet is unchanged.

ats3v added 4 commits October 12, 2026 11:22
Hosted Hermes-Agent instances are no longer upgraded in place by the
platform: the customer connects over SSH and runs the update command that
the dashboard's Update action shows. Add an Updating section with that
command, worded like the dashboard, and note that the version shown in the
dashboard does not change after a self-update.
The Update action still upgrades OpenClaw in place, but for Hermes-Agent it
now shows the SSH and update commands to run instead. Say so in the Hosted
Agents introduction and link the Hermes-Agent steps.
The backend refuses to update Hermes-Agent instances in place and answers
409 with the command to run over SSH. Say so under the HTTP API example.
@ats3v ats3v changed the title Update the per-account sandbox limit from 5 to 25 Update the per-account sandbox limit to 25 and document self-service Hermes updates Oct 12, 2026
crewai 1.15.27 (released 2026-10-09) ships DeepInfra as a native
OpenAI-compatible provider (crewAIInc/crewAI#7459), so
LLM(model="deepinfra/<org>/<model>") reads DEEPINFRA_API_KEY and needs
neither a base URL nor LiteLLM.

- Configuration collapses to the one-line LLM(model="deepinfra/...") in
  all three examples; DEEPINFRA_BASE_URL is documented for proxies.
- Drop the @llm workaround note: a plain `llm: deepinfra/...` string now
  works in agents.yaml, so show that snippet instead.
- Pin the install line to crewai>=1.15.27 and bump the "Tested with" note.
- Tips: replace the LiteLLM tip with an "Older CrewAI versions" fallback
  (custom_openai=True + base_url), add the org/model id check that now
  raises a ValueError at construction, and keep the context-window tip
  since the native provider still assumes 8,192 tokens for DeepInfra ids.

The embeddings section keeps the `openai` embedder pointed at DeepInfra:
the native DeepInfra embeddings provider (crewAIInc/crewAI#7978) is not
merged yet.

Every Python block in the page was run verbatim against api.deepinfra.com
with crewai 1.15.27, including the YAML crew path, structured outputs,
streaming and the knowledge example.
@ats3v ats3v changed the title Update the per-account sandbox limit to 25 and document self-service Hermes updates Update the sandbox limit to 25, document self-service Hermes updates and rewrite the CrewAI guide for the built-in provider Oct 12, 2026
@ats3v
ats3v merged commit ed3ee3c into main Oct 12, 2026
1 check passed
@ats3v
ats3v deleted the sandbox-limit-25 branch October 12, 2026 10:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants