Skip to content

docs: say what Agent Relay does with agent readiness - #31896

Merged
BobbyHo merged 18 commits into
mainfrom
bobby/relay-67-e-agent-readiness-docs
Nov 10, 2026
Merged

BobbyHo merged 18 commits into
mainfrom
bobby/relay-67-e-agent-readiness-docs

Conversation

@BobbyHo

@BobbyHo BobbyHo commented Nov 7, 2026 •

Copy link
Copy Markdown
Collaborator

TL;DR

Agent Relay now reads the workspace agent's lifecycle, shows it on its status page, renamed the log line it writes at handoff, and, with coder/agent-relay#155, fails a session about a minute after the agent's startup scripts fail or time out instead of waiting out the 15-minute startup grace (coder/agent-relay#154 and coder/agent-relay#155). The docs still described the relay as ignoring agent readiness, gave template authors no way to size their setup scripts against each pool's budget, did not document the --reap-startup-grace option that sets that budget, and listed a log line the relay no longer writes. This PR updates the setup, troubleshooting, configuration, Cursor and SIEM pages.

Refs https://linear.app/codercom/issue/RELAY-67/start-the-cursor-worker-only-after-the-workspace-agent-is-ready
Refs https://linear.app/codercom/issue/DOCS-1473

How to navigate this PR
  • Docs only, five files. Read docs/agent-relay/setup.md closely and skim the rest.
  • Reading order:
    1. docs/agent-relay/setup.md, section "Start the worker after workspace setup": the opening sentences, the example's timeout, the sentence after the code block, the failed-prerequisite bullet, and the new budget bullet with one sub-bullet per provider.
    2. docs/agent-relay/configuration.md: the new --reap-startup-grace entry, the dispatch_deadline row, and the source note at the top.
    3. docs/agent-relay/troubleshooting.md, "The agent runs commands before the workspace finishes setting up": five added sentences.
    4. docs/agent-relay/cursor.md: two lines that now say the 15-minute limit is a default.
    5. docs/agent-relay/monitoring/siem.md: one string in the Dashboard row.
  • Check that the setup section still reads as the normal way to set up a template, not as a workaround, and that nothing in it names relay internals the template author never sees.
Implementation
  • docs/agent-relay/setup.md
    • The section opens with the effect on the template author: the module starts the worker without waiting for startup scripts, so without an ordering rule the agent can run commands during setup. Earlier drafts described the reaper's lifecycle reads and the status page here. Review moved that out, since the template author never sees either.
    • The example's timeout is now 120 with a # 2 minutes comment, so it fits the smallest default budget below. It was 300.
    • A sentence after the code block points to the coder/agent-relay-claude-code and coder/agent-relay-cursor module READMEs on the registry, which show the rule with a full example as of module version 1.0.1 (docs(agent-relay-cursor, agent-relay-claude-code): order the module after setup registry#1239). The templates those examples came from live in the Agent Relay repository under example/templates (coder/agent-relay#157), which the docs can't link because the repository is private.
    • The failed-prerequisite bullet now covers a timed-out script as well as a failed one, gives the timing per relay version, and describes the Claude Code path in the active voice: Agent Relay hands the work order back once, rebuilds on the redelivery, and fails the session if the second setup fails too.
    • A new budget bullet replaces "keep setup well under 15 minutes". It says the timeout is in seconds and bounds one script, and that the build plus the sum of the setup timeouts must fit the pool's budget. For Cursor that budget is the reaper's startup grace. For Claude Code it is the pool's build budget, and a setup that keeps overrunning it is never served because Anthropic keeps offering the session and each new build reruns setup. There is no retry count on that path, since the one-retry cap only applies after a startup failure.
    • The "Workspace lifecycle" section's 15-minute line now says that limit is the startup grace's default.
  • docs/agent-relay/configuration.md
    • A new --reap-startup-grace entry: type, environment variable, YAML and Helm keys, the 15m0s default, what passing it does to a building workspace and to a built one with no worker, the interaction with dispatch_deadline, and the "must be positive" validation.
    • The dispatch_deadline row for Cursor pools links the 15-minute backstop to that entry and calls it a default.
    • The source note at the top now names v0.15.0 (commit 9b9657817e), the release every option on the page exists in. It named a commit between v0.13.0 and v0.14.0 that predates this option and the keepalive options.
  • docs/agent-relay/troubleshooting.md: the existing entry gains what the operator sees with the rule in place. The session fails about a minute after start_error, or start_timeout when a script reaches its timeout. The reaper's log line carries agent_lifecycle and reason for both cases, with both reason strings quoted. Only Claude Code sessions receive the reason in their error. Cursor users see a fixed message.
  • docs/agent-relay/cursor.md: the "Build deadline" backstop line and the pending row of the lifecycle table now say 15 minutes is the startup grace's default and link to the option. The Prebuilds section says setup reruns on a claim and what a failed setup looks like there.
  • docs/agent-relay/monitoring/siem.md: the Dashboard row's workspace ready, runner handoff becomes workspace built, runner handoff, the line the relay writes since v0.15.0. A SIEM rule built from the old string no longer matches.
  • Not changed: the Monitor page. It doesn't name the handoff line, and its metrics table doesn't list the histogram the new claim_to_agent_ready_seconds sits beside, so adding one without the other would be odd.
  • Release timing: the about-a-minute failure comes from coder/agent-relay#155, which is on the relay's main branch but not in v0.15.0, the latest release. The setup and troubleshooting pages say so: Agent Relay newer than v0.15.0 fails the session about a minute later, and v0.15.0 and older wait out the startup grace before failing a Cursor request and hand a Claude Code work order back as retryable every time, since the one-retry cap is also part of do not merge: Add CLI #155. That matches the wording in the cursor module README on the registry. Everything else on these pages, including the status-page lifecycle, the --reap-startup-grace option and the renamed log line, is in v0.15.0.
  • Claimed prebuilds: the setup, troubleshooting and Cursor pages now say that after a failed setup on a claimed prebuild the status item keeps reporting the prebuild's idle, so Agent Relay neither fails the session nor deletes the workspace. The quick failure only fires on pending, and the module README already documents the gap.
  • These are the two docs follow-ups that DOCS-1473 listed as out of scope, carried here instead of in a new DOCS ticket.
Expected Output
  • A template author reading the setup section learns that the module starts the worker without waiting for setup, and that the ordering rule is what makes it wait.
  • The same section tells them to set a timeout on each setup script, in seconds, and to size the build plus all the timeouts against their pool's budget: the startup grace for Cursor, the build budget for Claude Code.
  • They learn what happens when setup fails or times out: on Agent Relay newer than v0.15.0 the Cursor request fails about a minute later and a Claude Code work order gets one more build before the session fails, while v0.15.0 and older fail the Cursor request after the startup grace and keep rebuilding for Claude Code on every redelivery.
  • They learn that a claimed prebuild with a failed setup keeps reporting idle and is neither failed nor deleted.
  • They learn that a Claude Code setup that keeps overrunning the build budget is never served, because Anthropic keeps re-offering the session and each build reruns setup.
  • An administrator reading the configuration reference finds --reap-startup-grace, its default, and what it bounds, and sees that the 15-minute limits elsewhere in the docs are that default.
  • An operator searching the troubleshooting page for a session that failed right after setup finds both reason strings and the log field to search for, whether the script failed or timed out.
  • An operator building a dashboard from the SIEM page uses the log line the relay actually writes.
Testing
  • make lint/markdown passes with 0 errors over the docs tree.
  • make lint/emdash passes.
  • make fmt/markdown realigned the two tables this PR widened and changed nothing else.
  • Every option field in the --reap-startup-grace entry was checked against the relay's reaper service flag definition at v0.15.0, and both troubleshooting reason strings against the reaper's startup-failure check on the relay's main branch.
  • No manifest or redirect changes, since no page was added, moved or renamed.

Agent Relay now reads the workspace agent's lifecycle on every sweep
and fails a session about a minute after the agent reports that its
startup scripts failed. Update the setup section to say so, link the
example templates that carry the ordering rule, tell operators what a
failed setup looks like in the logs, and name the handoff log line the
relay emits since it was renamed.
@BobbyHo
BobbyHo temporarily deployed to main November 7, 2026 18:03 — with GitHub Actions Inactive
@linear-code

linear-code Bot commented Nov 7, 2026 •

Copy link
Copy Markdown

RELAY-67

DOCS-1473

Comment thread docs/agent-relay/setup.md Resolved
@BobbyHo

BobbyHo commented Nov 7, 2026

Copy link
Copy Markdown
Collaborator Author

/coder-agents-review Please limit the review to P0, P1, and P2 issues only.

@BobbyHo
BobbyHo temporarily deployed to main November 9, 2026 16:00 — with GitHub Actions Inactive
@BobbyHo

BobbyHo commented Nov 9, 2026

Copy link
Copy Markdown
Collaborator Author

/coder-agents-review Please limit the review to P0, P1, and P2 issues only.

@coder-agents-review coder-agents-review Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR updates three Agent Relay docs pages for the relay's agent lifecycle reads and early startup failure. As requested, this review covers P0 to P2 only: 3 P2 findings. The two claims about what a failed setup does were checked against origin/bobby/relay-67-b-startup-failure (coder/agent-relay#155); whether that branch has merged was not checked.

Out of scope (needs a ticket or explicit acceptance by a human):

  • coder/agent-relay internal/services/servicecursorworkers/reap.go: a confirmed startup failure has status pending, so the claim fails as retryable and the Cursor user reads "Try again in a few minutes." Retrying rebuilds the same template and the same setup fails again.
  • docs/agent-relay/configuration.md:278: the Workspace reaper section does not document --reap-delay, which postpones provider failure reporting, so readers cannot tell why a startup failure arrives later than about a minute.

🤖 This review was automatically generated with Coder Agents.

Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/troubleshooting.md Resolved
The private agent-relay repository is not reachable by docs readers,
so the example pointer now goes to the module READMEs on the Coder
Registry. A failed setup fails a Cursor request about a minute later,
but a Claude Code work order is retried once on a new workspace first,
and only Claude Code receives the reaper's reason in its error. The
reaper's log line is named so an operator can search for it.
@BobbyHo
BobbyHo temporarily deployed to main November 9, 2026 21:29 — with GitHub Actions Inactive
@BobbyHo

BobbyHo commented Nov 9, 2026

Copy link
Copy Markdown
Collaborator Author

/coder-agents-review Please limit the review to P0, P1, and P2 issues only.

@BobbyHo
BobbyHo temporarily deployed to main November 9, 2026 21:31 — with GitHub Actions Inactive
@BobbyHo
BobbyHo marked this pull request as ready for review November 9, 2026 21:31
@BobbyHo
BobbyHo temporarily deployed to main November 9, 2026 21:31 — with GitHub Actions Inactive

@coder-agents-review coder-agents-review Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR updates three Agent Relay docs pages for the relay's agent lifecycle reads and early startup failure. Within the requested P0 to P2 scope, this round has no new findings. The three P2 findings from the last round (the private-repository link, the Claude Code retry on a first delivery, and where the startup failure reason appears) are fixed in 7169ef2; the new text matches origin/bobby/relay-67-b-startup-failure.

Out of scope (needs a ticket or explicit acceptance by a human):

  • docs/agent-relay/setup.md:257: for Claude Code, build plus setup must fit within the pool's dispatch_deadline (default 5 minutes, counted from work-order issue), but this unchanged line tells authors to keep setup well under 15 minutes, so a 4-minute setup can have its session offered again mid-setup.
  • docs/agent-relay/monitoring/siem.md:226, :227, :233: the rows name workspace build failed, reporting retryable and deleting, workspace build passed the session deadline, reporting retryable and deleting, and delete workspace failed, leaving for reconciliation, but the relay logs workspace build failed, workspace build passed the session deadline, reporting failure, and delete workspace failed, leaving it for the reaper (workspacedispatcher/dispatcher.go:991, :1078, :1159 on the #155 branch), so SIEM rules copied from those rows match nothing.
  • coder/agent-relay internal/workspacereaper/reaper.go:798: after a retryable Claude Code nack the reaper deletes the workspace, while the redelivered work order can try to start a build on that same workspace, so the redelivery may fail with "workspace was deleted before its build could start" instead of getting the one retry the docs describe. Inferred from code, not reproduced.

🤖 This review was automatically generated with Coder Agents.

@BobbyHo
BobbyHo temporarily deployed to main November 9, 2026 23:58 — with GitHub Actions Inactive
The ordering section told every reader to keep setup under 15 minutes.
That is the Cursor startup grace. A Claude Code pool is bounded by the
work order's dispatch_deadline, 5 minutes by default, so the example
timeout of 300 seconds already overran it before the build was counted.
@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 00:09 — with GitHub Actions Inactive
@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 01:59 — with GitHub Actions Inactive
Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
@coderagents

coderagents Bot commented Nov 10, 2026 •

Copy link
Copy Markdown
Contributor

Documentation Check

Blocking

  • docs/agent-relay/setup.md (open) - The Cursor budget bullet names "Agent Relay's startup grace of 15 minutes" as the budget, but the Cursor pool's dispatch_deadline defaults to 10m and the 15-minute delete is a hard backstop; "startup grace" is a new undefined term. Name the pool's dispatch_deadline like the Claude bullet.
  • docs/agent-relay/setup.md (open) - "a workspace whose worker hasn't started" uses "whose" with an inanimate object; use "where the worker hasn't started".
  • docs/agent-relay/setup.md (open) - dispatch_deadline is a pool-config identifier the setup reader doesn't type or receive, and the 5m/15m detail restates the Claude Code build budget; use plain terms and link to the config.
  • docs/agent-relay/setup.md (open) - The Claude Code retry count conflicts: "reruns on every delivery" vs "handed back once" and "retries once" elsewhere.
  • docs/agent-relay/setup.md (open) - "Anthropic redelivers the work order and Agent Relay rebuilds the workspace" describes internal mechanism; lead with the effect on the reader.
  • docs/agent-relay/setup.md (open) - "It reads the workspace agent's lifecycle on every sweep and reports it on the status page, but it doesn't wait for it: the provider module starts the worker as soon as its start script runs." Describes internal mechanism (sweep, status page) the template author neither types nor receives; keep the effect and drop the mechanism.
  • docs/agent-relay/setup.md (open) - "Agent Relay reads the agent's start_error or start_timeout lifecycle and acts about a minute later." Describes internal lifecycle reading and sweep timing; the reader-facing effects are already in the sentences that follow, so cut the sentence.

Design notes

  • The prior "two different models of the provider's budget" note is resolved: both bullets now name the budget and link to the configurable value. A pre-existing naming split remains where the Claude Code build budget is called both "build budget" (section heading, setup.md) and "spawn budget" (configuration.md, claude-code.md prose); both names predate this change, so it is adjacent, not introduced here.
Findings for agents
- id: accuracy-1
  persona: accuracy
  class: wrong
  blocking: true
  file: docs/agent-relay/setup.md
  line: 258
  quote: "  - For a Cursor pool, keep them well under Agent Relay's startup grace of 15 minutes, after which it deletes a workspace whose worker hasn't started."
  evidence:
    - docs/agent-relay/cursor.md:197
    - docs/agent-relay/cursor.md:200
  rule: null
  problem: The Cursor budget bullet names "Agent Relay's startup grace of 15 minutes" as the budget, but the Cursor pool's actual budget is its dispatch_deadline, default 10m and at most 15m. "startup grace" was a new undefined term.
  fix: Name the pool's dispatch_deadline (10m default, at most 15) like the sibling Claude Code bullet.
  verified: true
- id: consistency-2
  persona: consistency
  class: rule
  blocking: true
  file: docs/agent-relay/setup.md
  line: 260
  quote: "    Past it, Anthropic redelivers the work order and Agent Relay rebuilds the workspace, so setup that can't fit reruns on every delivery and the session is never served."
  evidence:
    - docs/agent-relay/setup.md:254
    - docs/agent-relay/troubleshooting.md:106
  rule: docs/.style/style-guide/word-choice.md#one-term-per-concept
  problem: The Claude Code retry count conflicts: "reruns on every delivery" vs "handed back once" (setup.md:254) and "retries once" (troubleshooting.md:106).
  fix: State the trigger and count together, reusing the same wording as the other two places.
  verified: true
- id: audience-1
  persona: audience
  class: rule
  blocking: true
  file: docs/agent-relay/setup.md
  line: 218
  quote: "It reads the workspace agent's lifecycle on every sweep and reports it on the status page, but it doesn't wait for it: the provider module starts the worker as soon as its start script runs."
  evidence:
    - docs/.style/content-guidelines.md#describe-the-current-version-for-the-end-user
  rule: docs/.style/content-guidelines.md#describe-the-current-version-for-the-end-user
  problem: The sentence describes Agent Relay's sweep/status-page mechanism, which the setup reader neither types nor receives; the reader-facing effect follows in the next sentence.
  fix: "The provider module starts the worker as soon as its start script runs, without waiting for the workspace to be set up."
  verified: true
- id: audience-2
  persona: audience
  class: rule
  blocking: true
  file: docs/agent-relay/setup.md
  line: 252
  quote: "Agent Relay reads the agent's `start_error` or `start_timeout` lifecycle and acts about a minute later."
  evidence:
    - docs/.style/content-guidelines.md#describe-the-current-version-for-the-end-user
  rule: docs/.style/content-guidelines.md#describe-the-current-version-for-the-end-user
  problem: The sentence describes internal lifecycle reading and sweep timing; the reader-facing effects are stated in the sentences that follow.
  fix: Remove the sentence so the bullet goes straight to the effect.
  verified: true
- id: language-1
  persona: language
  class: rule
  blocking: true
  file: docs/agent-relay/setup.md
  line: 258
  quote: "after which it deletes a workspace whose worker hasn't started."
  evidence:
    - docs/.style/style-guide/word-choice.md#whose-for-people-not-things
  rule: docs/.style/style-guide/word-choice.md#whose-for-people-not-things
  problem: "Whose" is used with the inanimate object "workspace"; the rule requires "where the worker hasn't started".
  fix: "after which it deletes a workspace where the worker hasn't started."
  verified: true
- id: learner-1
  persona: learner
  class: suggestion
  blocking: false
  file: docs/agent-relay/setup.md
  line: 257
  quote: "  The build and setup together must fit the provider's budget:"
  evidence:
    - docs/agent-relay/setup.md:229
    - docs/agent-relay/setup.md:256-260
  rule: null
  problem: The reader can't translate the 5m/15m budgets into a coder_script timeout value.
  fix: State the units and that the coder_script timeout is in seconds and bounds one script.
  verified: true
- id: language-4
  persona: language
  class: suggestion
  blocking: false
  file: docs/agent-relay/setup.md
  line: 258
  quote: "keep them well under Agent Relay's startup grace of 15 minutes"
  evidence:
    - docs/.style/style-guide/word-choice.md#avoid-weasel-words
  rule: docs/.style/style-guide/word-choice.md#avoid-weasel-words
  problem: "well under" is a hedged degree qualifier.
  fix: "keep them under the pool's `dispatch_deadline`, 10 minutes by default and at most 15"
  verified: true
- id: audience-3
  persona: audience
  class: suggestion
  blocking: false
  file: docs/agent-relay/setup.md
  line: 229
  quote: "  timeout      = 120"
  evidence:
    - docs/templates/extending-templates/script-ordering.md
  rule: null
  problem: The coder_script timeout is in seconds, but the example gives a bare 120 directly above budget guidance in minutes.
  fix: "  timeout      = 120  # 2 minutes"
  verified: true
- id: language-5
  persona: language
  class: suggestion
  blocking: false
  file: docs/agent-relay/configuration.md
  line: 309
  quote: "A short grace can cut off slow agent connections and slow worker startups."
  evidence:
    - docs/.style/style-guide/word-choice.md#choose-words-that-have-one-meaning
  rule: docs/.style/style-guide/word-choice.md#choose-words-that-have-one-meaning
  problem: "can" is used for a possible adverse outcome; the rule maps "might" to possibility.
  fix: "A short grace might cut off slow agent connections and slow worker startups."
  verified: true

Automated review via Coder Agents. Reply to a finding's thread with the reason if the finding is wrong.

Say that the coder_script timeout is in seconds and bounds one script,
name the Cursor budget as the reaper's startup grace and the Claude Code
budget as the pool's build budget with links to both, state the single
redelivery, and document --reap-startup-grace on the configuration page.
@BobbyHo

BobbyHo commented Nov 10, 2026

Copy link
Copy Markdown
Collaborator Author

Thanks for the review. All six inline threads are addressed in 981c5a3; the version one stays open until the next relay tag. The four 15-minute lines outside the diff (cursor.md, setup.md, configuration.md) are fixed in this PR too, and the description is rewritten to match the branch.

@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 16:03 — with GitHub Actions Inactive
@Emyrk

Emyrk commented Nov 10, 2026

Copy link
Copy Markdown
Member

Active-voice pass on the latest diff: the earlier passive sentence about handing the Claude Code work order back is already active. Two passive turns remain in docs/agent-relay/setup.md:259-260: “counted from when Anthropic issues the work order” and “the session is never served.” Could we make the actors explicit, for example, “The budget starts when Anthropic issues the work order” and “no worker serves the session”? The SIEM entry is a literal log string, so it should stay unchanged.

Coder Agents on behalf of @Emyrk.

@Emyrk Emyrk left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just comments on language. Overall LG and need to get the new flag in

@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 16:08 — with GitHub Actions Inactive
@Emyrk

Emyrk commented Nov 10, 2026

Copy link
Copy Markdown
Member

A few accuracy notes on the current wording:

  • The “about a minute” failure in setup.md:251-252 and troubleshooting.md:105-109 is not in the latest released Agent Relay (v0.15.0). Its reaper does not inspect start_error/start_timeout before the startup grace; that check landed after the release in agent-relay#155. This is already tracked in the open version thread, and I agree it should remain open until a release includes the behavior or the docs name the version where it starts.
  • Even on agent-relay main, the quick-failure check requires agent_relay_status=pending (internal/workspacereaper/lifecycle.go:96-109). A claimed prebuild can retain idle if an ordered prerequisite fails before the worker runs, so the unconditional “about a minute” outcome does not cover that case. Could we qualify the guidance for claimed prebuilds?
  • In setup.md:259-260, one attempt exceeding the Claude Code budget does not prove that no later attempt can serve the session. Could we scope that consequence to setup that consistently exceeds the budget? “The budget starts when Anthropic issues the work order” is an accurate active-voice replacement for “counted from ...”.

Coder Agents on behalf of @Emyrk.

The budget starts when Anthropic issues the work order, and a setup
that overruns it means no worker ever serves the session.
@BobbyHo

BobbyHo commented Nov 10, 2026

Copy link
Copy Markdown
Collaborator Author

Fixed in 25dfbca. Both sentences are active now, and the first matches the Build budget wording on the Claude Code page. SIEM string untouched.

@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 16:21 — with GitHub Actions Inactive
@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 16:29 — with GitHub Actions Inactive
… claimed prebuilds

Agent Relay newer than v0.15.0 fails a session about a minute after a
setup script fails; v0.15.0 and older wait out the startup grace. A
claimed prebuild keeps reporting the prebuild's idle after a failed
setup, so the quick failure never fires there. A Claude Code setup is
only never served when it keeps overrunning the budget.
@BobbyHo

BobbyHo commented Nov 10, 2026

Copy link
Copy Markdown
Collaborator Author

Fixed in e763311. Both pages now give the timing per relay version, matching the cursor module README. The claimed-prebuild case is stated on the setup, troubleshooting and Cursor pages, and the Claude Code sentence is scoped to setup that keeps overrunning the budget.

@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 16:56 — with GitHub Actions Inactive

@nickvigilante nickvigilante left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approved with changes. Thanks for this!


One issue is inline, in two places: the Claude Code one-retry cap came with dd726ff (#155) and isn't in v0.15.0, so the v0.15.0 sentences need to say that those versions keep handing Claude Code work orders back as retryable.

Checked and correct: the version scoping (main publishes :unstable, so newer than v0.15.0 is installable), the claimed-prebuild behavior (the module's status script keeps the prebuild's idle until the worker starts, and the reaper keeps idle workspaces), the startup-grace links and defaults in cursor.md, configuration.md, and setup.md, the timed-out setup strings, and the v0.15.0 source note.

Comment thread docs/agent-relay/troubleshooting.md Resolved
Comment thread docs/agent-relay/setup.md Resolved
The one-retry cap on Claude Code work orders arrived with the quick
failure in agent-relay#155, so v0.15.0 and older hand a pending runner
back as retryable on every redelivery and rerun the setup each time.
@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 17:27 — with GitHub Actions Inactive
@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 17:27 — with GitHub Actions Inactive
@BobbyHo
BobbyHo enabled auto-merge (squash) November 10, 2026 17:31
@BobbyHo
BobbyHo merged commit a0b595b into main Nov 10, 2026
32 of 33 checks passed
@BobbyHo
BobbyHo deleted the bobby/relay-67-e-agent-readiness-docs branch November 10, 2026 17:33
@BobbyHo
BobbyHo temporarily deployed to main November 10, 2026 17:33 — with GitHub Actions Inactive
@github-actions github-actions Bot locked and limited conversation to collaborators Nov 10, 2026

This branch was previously deployed

1 inactive deployment
main — d9bd5a30 Deployed Nov 10, 2026 by BobbyHo via cla #253598
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants