2026-08-19 20:18:13 -07:00
package main
fix(ci): move the issue analyst's static instructions out of the workflow
GitHub evaluates a `with:` value holding ${{ }} as one expression and
rejects the whole workflow when it passes 21,000 characters. The analyst
prompt was 19,883; 6eeaaa91 took it to 21,389 and 99d971ff to 23,257, so
since that push the file is invalid: no issue gets an analysis, and every
push records a failed, job-less run named after the file. actionlint does
not check this limit, which is how it shipped.
The static parts - repository context pointer, issue forms, how to
investigate, resuming and maintainer-request modes, evidence discipline,
the severity/confidence/verdict scales, the security exception, labels and
closing, and the comment format - move verbatim to
.github/claude/issue-analyst-instructions.md, which the prompt tells the
analyst to read in full first, as it already does for
issue-analyst-context.md. The prompt keeps everything that needs an
expression or guards the run: the trigger mode, CURRENT ISSUE, the fenced
untrusted data, RULES and the marker. It is now 5,597 characters. The
stale "code changes happen when the maintainer mentions @claude" rule is
replaced: no workflow here changes code, and @claude analyze now exists.
TestBotPromptsFitGitHubExpressionLimit in bot_context_test.go reads every
claude-*.yml and fails on a ${{ }} value over the limit; it is red on
99d971ff (23,257). The instructions file joins the analyst paths pinned by
TestAnalystContextNamesRealPaths, and the file's header now names
everything it pins. actionlint 1.7.7 passes.
2026-10-12 08:05:37 -07:00
// The bot prompts and the files they read (issue-analyst-*.md, REVIEW.md) state
// repo facts no build checks; a stale or oversized one fails silently, so pin them.
2026-08-19 20:18:13 -07:00
import (
"os"
"path/filepath"
"regexp"
"strings"
"testing"
fix(ci): move the issue analyst's static instructions out of the workflow
GitHub evaluates a `with:` value holding ${{ }} as one expression and
rejects the whole workflow when it passes 21,000 characters. The analyst
prompt was 19,883; 6eeaaa91 took it to 21,389 and 99d971ff to 23,257, so
since that push the file is invalid: no issue gets an analysis, and every
push records a failed, job-less run named after the file. actionlint does
not check this limit, which is how it shipped.
The static parts - repository context pointer, issue forms, how to
investigate, resuming and maintainer-request modes, evidence discipline,
the severity/confidence/verdict scales, the security exception, labels and
closing, and the comment format - move verbatim to
.github/claude/issue-analyst-instructions.md, which the prompt tells the
analyst to read in full first, as it already does for
issue-analyst-context.md. The prompt keeps everything that needs an
expression or guards the run: the trigger mode, CURRENT ISSUE, the fenced
untrusted data, RULES and the marker. It is now 5,597 characters. The
stale "code changes happen when the maintainer mentions @claude" rule is
replaced: no workflow here changes code, and @claude analyze now exists.
TestBotPromptsFitGitHubExpressionLimit in bot_context_test.go reads every
claude-*.yml and fails on a ${{ }} value over the limit; it is red on
99d971ff (23,257). The instructions file joins the analyst paths pinned by
TestAnalystContextNamesRealPaths, and the file's header now names
everything it pins. actionlint 1.7.7 passes.
2026-10-12 08:05:37 -07:00
"unicode/utf16"
"github.com/goccy/go-yaml"
2026-08-19 20:18:13 -07:00
)
const (
fix(ci): move the issue analyst's static instructions out of the workflow
GitHub evaluates a `with:` value holding ${{ }} as one expression and
rejects the whole workflow when it passes 21,000 characters. The analyst
prompt was 19,883; 6eeaaa91 took it to 21,389 and 99d971ff to 23,257, so
since that push the file is invalid: no issue gets an analysis, and every
push records a failed, job-less run named after the file. actionlint does
not check this limit, which is how it shipped.
The static parts - repository context pointer, issue forms, how to
investigate, resuming and maintainer-request modes, evidence discipline,
the severity/confidence/verdict scales, the security exception, labels and
closing, and the comment format - move verbatim to
.github/claude/issue-analyst-instructions.md, which the prompt tells the
analyst to read in full first, as it already does for
issue-analyst-context.md. The prompt keeps everything that needs an
expression or guards the run: the trigger mode, CURRENT ISSUE, the fenced
untrusted data, RULES and the marker. It is now 5,597 characters. The
stale "code changes happen when the maintainer mentions @claude" rule is
replaced: no workflow here changes code, and @claude analyze now exists.
TestBotPromptsFitGitHubExpressionLimit in bot_context_test.go reads every
claude-*.yml and fails on a ${{ }} value over the limit; it is red on
99d971ff (23,257). The instructions file joins the analyst paths pinned by
TestAnalystContextNamesRealPaths, and the file's header now names
everything it pins. actionlint 1.7.7 passes.
2026-10-12 08:05:37 -07:00
analystContextPath = ".github/claude/issue-analyst-context.md"
analystInstructionsPath = ".github/claude/issue-analyst-instructions.md"
reviewPath = "REVIEW.md"
ciWorkflowPath = ".github/workflows/ci.yml"
2026-08-19 20:18:13 -07:00
)
func readRepoFile ( t * testing . T , path string ) string {
t . Helper ( )
b , err := os . ReadFile ( path )
if err != nil {
t . Fatalf ( "read %s: %v" , path , err )
}
return string ( b )
}
// section returns the text between two markers, so a table is matched only
// inside the heading that owns it.
func section ( t * testing . T , doc , from , to string ) string {
t . Helper ( )
i := strings . Index ( doc , from )
if i < 0 {
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
t . Fatalf ( "%s no longer contains the heading %q" , analystContextPath , from )
2026-08-19 20:18:13 -07:00
}
rest := doc [ i + len ( from ) : ]
2026-08-23 12:51:39 -07:00
if before , _ , ok := strings . Cut ( rest , to ) ; ok {
return before
2026-08-19 20:18:13 -07:00
}
return rest
}
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
func TestAnalystContextLocaleFileCount ( t * testing . T ) {
doc := readRepoFile ( t , analystContextPath )
2026-08-19 20:18:13 -07:00
m := regexp . MustCompile ( "`internal/web/translation/` \\((\\d+) files\\)" ) . FindStringSubmatch ( doc )
if m == nil {
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
t . Fatalf ( "%s no longer states the locale file count as \"`internal/web/translation/` (N files)\"" , analystContextPath )
2026-08-19 20:18:13 -07:00
}
files , err := filepath . Glob ( "internal/web/translation/*.json" )
if err != nil {
t . Fatalf ( "glob locales: %v" , err )
}
if got := len ( files ) ; m [ 1 ] != itoa ( got ) {
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
t . Errorf ( "%s claims %s locale files, internal/web/translation/ holds %d; update the claim and every prompt that relies on it" , analystContextPath , m [ 1 ] , got )
2026-08-19 20:18:13 -07:00
}
}
func itoa ( n int ) string {
if n == 0 {
return "0"
}
var b [ ] byte
for n > 0 {
b = append ( [ ] byte { byte ( '0' + n % 10 ) } , b ... )
n /= 10
}
return string ( b )
}
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
func TestAnalystContextNamesRealCIJobs ( t * testing . T ) {
doc := readRepoFile ( t , analystContextPath )
2026-08-19 20:18:13 -07:00
ci := readRepoFile ( t , ciWorkflowPath )
table := section ( t , doc , "## What CI runs" , "**What CI does NOT prove.**" )
rows := regexp . MustCompile ( "(?m)^\\| `([a-z0-9-]+)` \\|" ) . FindAllStringSubmatch ( table , - 1 )
if len ( rows ) < 5 {
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
t . Fatalf ( "expected the CI table in %s to list at least 5 jobs, found %d" , analystContextPath , len ( rows ) )
2026-08-19 20:18:13 -07:00
}
for _ , r := range rows {
t . Run ( r [ 1 ] , func ( t * testing . T ) {
if ! strings . Contains ( ci , "\n " + r [ 1 ] + ":\n" ) {
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
t . Errorf ( "%s describes a CI job %q that %s does not define" , analystContextPath , r [ 1 ] , ciWorkflowPath )
2026-08-19 20:18:13 -07:00
}
} )
}
}
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
func TestAnalystContextNamesRealPaths ( t * testing . T ) {
fix(ci): move the issue analyst's static instructions out of the workflow
GitHub evaluates a `with:` value holding ${{ }} as one expression and
rejects the whole workflow when it passes 21,000 characters. The analyst
prompt was 19,883; 6eeaaa91 took it to 21,389 and 99d971ff to 23,257, so
since that push the file is invalid: no issue gets an analysis, and every
push records a failed, job-less run named after the file. actionlint does
not check this limit, which is how it shipped.
The static parts - repository context pointer, issue forms, how to
investigate, resuming and maintainer-request modes, evidence discipline,
the severity/confidence/verdict scales, the security exception, labels and
closing, and the comment format - move verbatim to
.github/claude/issue-analyst-instructions.md, which the prompt tells the
analyst to read in full first, as it already does for
issue-analyst-context.md. The prompt keeps everything that needs an
expression or guards the run: the trigger mode, CURRENT ISSUE, the fenced
untrusted data, RULES and the marker. It is now 5,597 characters. The
stale "code changes happen when the maintainer mentions @claude" rule is
replaced: no workflow here changes code, and @claude analyze now exists.
TestBotPromptsFitGitHubExpressionLimit in bot_context_test.go reads every
claude-*.yml and fails on a ${{ }} value over the limit; it is red on
99d971ff (23,257). The instructions file joins the analyst paths pinned by
TestAnalystContextNamesRealPaths, and the file's header now names
everything it pins. actionlint 1.7.7 passes.
2026-10-12 08:05:37 -07:00
// REVIEW.md briefs the review job the way the two issue-analyst files brief
// the analyst, so all three get their paths pinned.
2026-08-19 20:18:13 -07:00
// internal/web/dist and frontend/node_modules are build output: absent from a
// fresh clone, created by `make dist-stub` and `npm ci`.
generated := map [ string ] bool {
"internal/web/dist/" : true ,
"frontend/node_modules" : true ,
"frontend/src/generated/" : true ,
}
seen := map [ string ] bool { }
refactor(ci): replace the in-house review lanes with the official code-review skill
The four pull_request_target review jobs in claude-bot.yml (Senior
Developer / QA / Tester / Arbiter and their shared rubric) are replaced by
a single review job running the official code-review plugin - the same
skill behind Anthropic's hosted Code Review and the review workflow
/install-github-app generates. The hosted service needs a Team/Enterprise
organisation, so the plugin runs in CI on the maintainer's subscription
instead: inline findings on PR open and ready-for-review, plus manual
(re-)review when the owner or a collaborator comments "@claude review".
The official example triggers on pull_request, but GitHub withholds
secrets from fork runs and essentially every 3x-ui pull request is from a
fork, so the job keeps the lanes' pull_request_target posture: the
workspace is the base revision and nothing from the pull request is
checked out or executed.
What the lanes uniquely knew is distilled into REVIEW.md, handed to the
skill via --append-system-prompt and pinned by bot_context_test.go the way
repo-context.md is: the runtime.Runtime dispatch rule, migration and
upgrade safety, the four-step route contract chain including the unchecked
docs copy, the i18n rule, the three link implementations, and the
wire-format verification bar. The mention job now ignores "@claude
review" comments on pull requests so the review trigger does not also
wake the generic bot, and the lane-only rubric file goes with the lanes.
The remaining prompts also lose their tone micro-rules (no emoji, no
exclamation marks, no filler) and the workflow's comment banners are
removed.
2026-08-20 06:08:04 -07:00
counts := map [ string ] int { }
fix(ci): move the issue analyst's static instructions out of the workflow
GitHub evaluates a `with:` value holding ${{ }} as one expression and
rejects the whole workflow when it passes 21,000 characters. The analyst
prompt was 19,883; 6eeaaa91 took it to 21,389 and 99d971ff to 23,257, so
since that push the file is invalid: no issue gets an analysis, and every
push records a failed, job-less run named after the file. actionlint does
not check this limit, which is how it shipped.
The static parts - repository context pointer, issue forms, how to
investigate, resuming and maintainer-request modes, evidence discipline,
the severity/confidence/verdict scales, the security exception, labels and
closing, and the comment format - move verbatim to
.github/claude/issue-analyst-instructions.md, which the prompt tells the
analyst to read in full first, as it already does for
issue-analyst-context.md. The prompt keeps everything that needs an
expression or guards the run: the trigger mode, CURRENT ISSUE, the fenced
untrusted data, RULES and the marker. It is now 5,597 characters. The
stale "code changes happen when the maintainer mentions @claude" rule is
replaced: no workflow here changes code, and @claude analyze now exists.
TestBotPromptsFitGitHubExpressionLimit in bot_context_test.go reads every
claude-*.yml and fails on a ${{ }} value over the limit; it is red on
99d971ff (23,257). The instructions file joins the analyst paths pinned by
TestAnalystContextNamesRealPaths, and the file's header now names
everything it pins. actionlint 1.7.7 passes.
2026-10-12 08:05:37 -07:00
for _ , src := range [ ] string { analystContextPath , analystInstructionsPath , reviewPath } {
refactor(ci): replace the in-house review lanes with the official code-review skill
The four pull_request_target review jobs in claude-bot.yml (Senior
Developer / QA / Tester / Arbiter and their shared rubric) are replaced by
a single review job running the official code-review plugin - the same
skill behind Anthropic's hosted Code Review and the review workflow
/install-github-app generates. The hosted service needs a Team/Enterprise
organisation, so the plugin runs in CI on the maintainer's subscription
instead: inline findings on PR open and ready-for-review, plus manual
(re-)review when the owner or a collaborator comments "@claude review".
The official example triggers on pull_request, but GitHub withholds
secrets from fork runs and essentially every 3x-ui pull request is from a
fork, so the job keeps the lanes' pull_request_target posture: the
workspace is the base revision and nothing from the pull request is
checked out or executed.
What the lanes uniquely knew is distilled into REVIEW.md, handed to the
skill via --append-system-prompt and pinned by bot_context_test.go the way
repo-context.md is: the runtime.Runtime dispatch rule, migration and
upgrade safety, the four-step route contract chain including the unchecked
docs copy, the i18n rule, the three link implementations, and the
wire-format verification bar. The mention job now ignores "@claude
review" comments on pull requests so the review trigger does not also
wake the generic bot, and the lane-only rubric file goes with the lanes.
The remaining prompts also lose their tone micro-rules (no emoji, no
exclamation marks, no filler) and the workflow's comment banners are
removed.
2026-08-20 06:08:04 -07:00
for _ , m := range regexp . MustCompile ( "`([^`]+)`" ) . FindAllStringSubmatch ( readRepoFile ( t , src ) , - 1 ) {
p := m [ 1 ]
if ! regexp . MustCompile ( ` ^(internal|frontend|docs|tools|\.github)/ ` ) . MatchString ( p ) ||
strings . ContainsAny ( p , "*{ " ) || generated [ p ] || seen [ p ] {
continue
2026-08-19 20:18:13 -07:00
}
refactor(ci): replace the in-house review lanes with the official code-review skill
The four pull_request_target review jobs in claude-bot.yml (Senior
Developer / QA / Tester / Arbiter and their shared rubric) are replaced by
a single review job running the official code-review plugin - the same
skill behind Anthropic's hosted Code Review and the review workflow
/install-github-app generates. The hosted service needs a Team/Enterprise
organisation, so the plugin runs in CI on the maintainer's subscription
instead: inline findings on PR open and ready-for-review, plus manual
(re-)review when the owner or a collaborator comments "@claude review".
The official example triggers on pull_request, but GitHub withholds
secrets from fork runs and essentially every 3x-ui pull request is from a
fork, so the job keeps the lanes' pull_request_target posture: the
workspace is the base revision and nothing from the pull request is
checked out or executed.
What the lanes uniquely knew is distilled into REVIEW.md, handed to the
skill via --append-system-prompt and pinned by bot_context_test.go the way
repo-context.md is: the runtime.Runtime dispatch rule, migration and
upgrade safety, the four-step route contract chain including the unchecked
docs copy, the i18n rule, the three link implementations, and the
wire-format verification bar. The mention job now ignores "@claude
review" comments on pull requests so the review trigger does not also
wake the generic bot, and the lane-only rubric file goes with the lanes.
The remaining prompts also lose their tone micro-rules (no emoji, no
exclamation marks, no filler) and the workflow's comment banners are
removed.
2026-08-20 06:08:04 -07:00
seen [ p ] = true
counts [ src ] ++
t . Run ( p , func ( t * testing . T ) {
if _ , err := os . Stat ( strings . TrimSuffix ( p , "/" ) ) ; err != nil {
t . Errorf ( "%s names %q, which does not exist; the bot prompts trust this file" , src , p )
}
} )
}
2026-08-19 20:18:13 -07:00
}
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
if counts [ analystContextPath ] < 20 {
t . Errorf ( "expected the bot context to name at least 20 repository paths, found %d - has the file been gutted?" , counts [ analystContextPath ] )
2026-08-19 20:18:13 -07:00
}
}
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
func TestAnalystContextSkipGatesExist ( t * testing . T ) {
doc := readRepoFile ( t , analystContextPath )
2026-08-19 20:18:13 -07:00
table := section ( t , doc , "**What CI does NOT prove.**" , "Mutation testing" )
// [A-Z0-9_] and not [A-Z_]: XRAY_E2E_BINARY carries a digit, and excluding it
// silently dropped that gate from the check instead of failing.
gates := regexp . MustCompile ( "`((?:XUI|XRAY)_[A-Z0-9_]+)`" ) . FindAllStringSubmatch ( table , - 1 )
if len ( gates ) < 5 {
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
t . Fatalf ( "expected at least 5 skip-gate variables in %s, found %d" , analystContextPath , len ( gates ) )
2026-08-19 20:18:13 -07:00
}
var sources [ ] string
err := filepath . WalkDir ( "internal" , func ( path string , d os . DirEntry , err error ) error {
if err != nil {
return err
}
if ! d . IsDir ( ) && strings . HasSuffix ( path , ".go" ) {
sources = append ( sources , path )
}
return nil
} )
if err != nil {
t . Fatalf ( "walk internal: %v" , err )
}
for _ , g := range gates {
t . Run ( g [ 1 ] , func ( t * testing . T ) {
for _ , f := range sources {
if strings . Contains ( readRepoFile ( t , f ) , g [ 1 ] ) {
return
}
}
refactor(ci): add an adversarial pass and name the analyst briefing
REVIEW.md told the reviewer which repository rules to check but never to try
breaking the change, so the conditions this panel actually meets went
unexamined. "Try to break it" adds six, each tied to a mechanism here rather
than to a generic checklist: an upgrade over an operator's existing rows and
the rollback that reads them again, a restart that drops in-memory state under
the cron jobs, a sub-node racing the master on the same row, an operation
applied twice, an inbound or client at the empty and the thousand end, and a
dependency that is down. It closes with the gate that running a case is not
reporting it - each one still has to clear the verification bar below it, so
the section cannot become a licence for hypotheticals.
repo-context.md said nothing about which bot reads it. Only the issue analyst
does, since the review job's briefing moved inline in acf3603d, so it becomes
issue-analyst-context.md and its title names the analyst instead of "the Claude
bot". bot_context_test.go pins that path in a constant, so the rename carries
through the constant, the four test names and the two comments that named the
old file - one of which still said "the bot prompts", plural.
Backticks come off mtg-multi in the new section: the same test file reads any
hyphenated backticked token in REVIEW.md as a CI job name, and fails on one
ci.yml does not define.
2026-09-08 12:29:21 -07:00
t . Errorf ( "%s lists %s as a test skip gate, but no .go file under internal/ reads it" , analystContextPath , g [ 1 ] )
2026-08-19 20:18:13 -07:00
} )
}
}
feat(ci): give the review bot a severity scale and a tally
REVIEW.md said what blocks and what does not, but never how to mark a finding,
so every review invented its own shape and none carried a severity. It now
names the three markers the hosted Code Review service uses - Important, Nit,
Pre-existing - and keys them to what the pull request did rather than to how
alarming a defect looks alone: a defect it introduces or worsens is Important,
one it merely brought into view is Pre-existing and cannot be a reason to hold
it. Pre-existing was missing entirely, and checking what this panel emits means
reading far outside the diff, so those findings had nowhere to go except a
wrong Important or silence.
The volume cap said how many and never which. It now collapses a nit repeated
across files into one finding, prefers a nit in code the pull request wrote
over one in code it only moved, caps pre-existing findings at three, and states
that Important findings are never capped - a section listing two caps otherwise
reads as licence to trim what matters. The review opens with a tally so the
author sees the shape before the detail.
Two contradictions went with it. The file told the reviewer to skip what CI
enforces and then to check that a new i18n key reaches all 13 locales, which
i18n-dead-keys.test.ts pins in both directions - the rule moves to "Do not
report" with the reason. "Anything CI already enforces: npm audit" overstated
what runs; CI audits production dependencies at high and above, so a
dev-dependency advisory is out of scope by design.
The reviewer could not read its own CI. Only postgres-durable-first runs
against PostgreSQL, and XRAY_E2E_BINARY and XUI_SCALE_TEST are set by no job,
so a dialect or migration change can carry a wall of green while the paths it
touches never executed. That belongs to the verification bar, next to the rule
that a behaviour claim needs a file:line citation, and "CI passed" now needs a
run actually read. Also names the two house choices no linter defends: neither
golangci-lint nor oxlint rejects a testify or Tailwind import.
Both kinds of claim rot on a rename, so a test pins them the way
repo-context.md's claims are already pinned - the CI jobs REVIEW.md names must
exist in ci.yml, the skip gates it calls unset must stay unset, and the locale
count must match the directory.
The review itself moves from high to max effort, and the prompt records why it
names REVIEW.md at all: the code-review skill reads CLAUDE.md on its own but
not REVIEW.md, so dropping that clause would silently stop the file applying.
Drops a CLAUDE.md reference to tools/seedperf/, which no longer exists - the
review reads that file as project context, so a stale path there misleads it.
2026-08-20 18:19:33 -07:00
// REVIEW.md tells the reviewer which CI job proves what, and which skip gates
// mean a green run proved nothing. Both go stale silently on a rename.
func TestReviewNamesRealCIJobsAndGates ( t * testing . T ) {
doc := readRepoFile ( t , reviewPath )
ci := readRepoFile ( t , ciWorkflowPath )
// Hyphenated only: a single-word job name is indistinguishable from prose.
jobs := regexp . MustCompile ( "`([a-z0-9]+(?:-[a-z0-9]+)+)`" ) . FindAllStringSubmatch ( doc , - 1 )
if len ( jobs ) < 2 {
t . Fatalf ( "expected %s to name at least 2 CI jobs in backticks, found %d" , reviewPath , len ( jobs ) )
}
for _ , j := range jobs {
t . Run ( j [ 1 ] , func ( t * testing . T ) {
if ! strings . Contains ( ci , "\n " + j [ 1 ] + ":\n" ) {
t . Errorf ( "%s names a CI job %q that %s does not define" , reviewPath , j [ 1 ] , ciWorkflowPath )
}
} )
}
for _ , g := range regexp . MustCompile ( "`((?:XUI|XRAY)_[A-Z0-9_]+)`" ) . FindAllStringSubmatch ( doc , - 1 ) {
t . Run ( g [ 1 ] , func ( t * testing . T ) {
if strings . Contains ( ci , g [ 1 ] ) {
t . Errorf ( "%s claims %s is never set in CI, but %s sets it" , reviewPath , g [ 1 ] , ciWorkflowPath )
}
} )
}
}
// The i18n rule is the one REVIEW.md states as a number, so it is the one that
// goes wrong silently when a locale is added.
func TestReviewLocaleFileCount ( t * testing . T ) {
doc := readRepoFile ( t , reviewPath )
m := regexp . MustCompile ( ` (\d+) locale files ` ) . FindStringSubmatch ( doc )
if m == nil {
t . Fatalf ( "%s no longer states the i18n rule as \"N locale files\"" , reviewPath )
}
files , err := filepath . Glob ( "internal/web/translation/*.json" )
if err != nil {
t . Fatalf ( "glob locales: %v" , err )
}
if got := len ( files ) ; m [ 1 ] != itoa ( got ) {
t . Errorf ( "%s tells the reviewer to expect %s locale files, internal/web/translation/ holds %d" , reviewPath , m [ 1 ] , got )
}
}
fix(ci): move the issue analyst's static instructions out of the workflow
GitHub evaluates a `with:` value holding ${{ }} as one expression and
rejects the whole workflow when it passes 21,000 characters. The analyst
prompt was 19,883; 6eeaaa91 took it to 21,389 and 99d971ff to 23,257, so
since that push the file is invalid: no issue gets an analysis, and every
push records a failed, job-less run named after the file. actionlint does
not check this limit, which is how it shipped.
The static parts - repository context pointer, issue forms, how to
investigate, resuming and maintainer-request modes, evidence discipline,
the severity/confidence/verdict scales, the security exception, labels and
closing, and the comment format - move verbatim to
.github/claude/issue-analyst-instructions.md, which the prompt tells the
analyst to read in full first, as it already does for
issue-analyst-context.md. The prompt keeps everything that needs an
expression or guards the run: the trigger mode, CURRENT ISSUE, the fenced
untrusted data, RULES and the marker. It is now 5,597 characters. The
stale "code changes happen when the maintainer mentions @claude" rule is
replaced: no workflow here changes code, and @claude analyze now exists.
TestBotPromptsFitGitHubExpressionLimit in bot_context_test.go reads every
claude-*.yml and fails on a ${{ }} value over the limit; it is red on
99d971ff (23,257). The instructions file joins the analyst paths pinned by
TestAnalystContextNamesRealPaths, and the file's header now names
everything it pins. actionlint 1.7.7 passes.
2026-10-12 08:05:37 -07:00
// GitHub rejects the whole workflow once a value holding ${{ }} passes 21,000
// characters, so every trigger fails with no job to read; actionlint misses it.
func TestBotPromptsFitGitHubExpressionLimit ( t * testing . T ) {
const limit = 21000
files , err := filepath . Glob ( ".github/workflows/claude-*.yml" )
if err != nil || len ( files ) == 0 {
t . Fatalf ( "glob bot workflows: %v (%d files)" , err , len ( files ) )
}
checked := 0
for _ , path := range files {
var wf struct {
Jobs map [ string ] struct {
Steps [ ] struct {
With map [ string ] any ` yaml:"with" `
} ` yaml:"steps" `
} ` yaml:"jobs" `
}
if err := yaml . Unmarshal ( [ ] byte ( readRepoFile ( t , path ) ) , & wf ) ; err != nil {
t . Fatalf ( "parse %s: %v" , path , err )
}
for job , j := range wf . Jobs {
for _ , step := range j . Steps {
for key , v := range step . With {
s , ok := v . ( string )
if ! ok || ! strings . Contains ( s , "${{" ) {
continue
}
checked ++
// GitHub counts .NET string length: UTF-16 code units.
if n := len ( utf16 . Encode ( [ ] rune ( s ) ) ) ; n > limit {
t . Errorf ( "%s job %s with.%s is %d characters; GitHub rejects the workflow over %d" , path , job , key , n , limit )
}
}
}
}
}
if checked == 0 {
t . Fatal ( "no ${{ }} value found in the bot workflows: the parse no longer reaches the prompts" )
}
}