ci: unbreak Bonk by bumping the pinned OpenCode version - #144
Closed
andre-j3sus wants to merge 2 commits into
Closed
ci: unbreak Bonk by bumping the pinned OpenCode version#144andre-j3sus wants to merge 2 commits into
andre-j3sus wants to merge 2 commits into
Conversation
Bonk has failed on every run since 2026-08-18; the last success was
2026-07-31. Each run creates a session, sends the message, logs a single
"loop { step: 0 }", then emits zero tokens and exits 1 -- the provider never
initializes.
bonk.yml has not changed since it was added, and cloudflare/workers-sdk
fails identically while pinning a March action SHA, so neither this repo's
config nor the action code is the cause. What both broken repos share is the
1.15.13 pin. ask-bonk#226 tracked the same provider-initialization failures
on 2026-08-18 and verified a working run on 1.18.18.
Keeping the version pinned rather than moving to latest, since floating is
what produced this drift in the first place.
|
Model not found: cloudflare-ai-gateway/anthropic/claude-opus-4-8. Did you mean: anthropic/claude-opus-4.5, anthropic/claude-opus-4.6, anthropic/claude-opus-4.7? |
|
@andre-j3sus Bonk workflow failed. Check the logs for details. View workflow run · To retry, trigger Bonk again. |
Bumping OpenCode surfaced the error 1.15.13 was swallowing: Model not found: cloudflare-ai-gateway/anthropic/claude-opus-4-8. Did you mean: anthropic/claude-opus-4.5, anthropic/claude-opus-4.6, anthropic/claude-opus-4.7? The version component is dot-separated, and 4.8 does not exist. Moving to 4.7, the newest the gateway offers.
Collaborator
Author
|
/bonk |
Collaborator
Author
|
Closing to re-open from the same branch: Bonk only triggers on |
This was referenced Aug 24, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Bonk has failed on every run since 2026-08-18. The last success was
2026-07-31 — eight consecutive failures. The failure was silent from the
outside: it posted an empty comment followed by "check the logs for details",
and the logs contained no error either, which is why it went unnoticed for
three weeks.
Two things were wrong, and the first was hiding the second.
The pinned OpenCode 1.15.13 swallowed the underlying error, emitting only
loop { step: 0 }and zero tokens.bonk.ymlhad not been modified since itwas added, and
cloudflare/workers-sdkfails identically while pinning aMarch action SHA, so neither this repo's config nor the action code was the
cause — what both broken repos shared was that pin. ask-bonk#226 tracked the
same provider-initialization failures on 2026-08-18 and verified 1.18.18.
Bumping the pin immediately surfaced the actual fault:
The version component is dot-separated, and 4.8 does not exist. This is
presumably a gateway-side catalog change, since the id resolved until July 31.
Moving to 4.7, the newest offered.
The version stays pinned rather than moving to
latest, since floating is whatproduced this drift. Worth keeping the diagnostic value in mind though: 1.15.13
reported nothing at all, while 1.18.18 named the problem on the first run.