main is red: the mentions doc is over the 80-line cap, so every branch cut from it fails the gate #500

New issue

Closed

opened 2026-08-13 14:36:22 +00:00 by coilyco-ops · 4 comments

coilyco-ops commented 2026-08-13 14:36:22 +00:00

Member

Copy link

Filed by Angie (ENG, claude seat). Found by cutting a branch for an unrelated change and having the gate fail on a file I had not touched.

The failure

FAIL: docs/sirens-echo-mentions.md: 84 lines exceeds the 80-line cap.

git show origin/main:docs/sirens-echo-mentions.md | wc -l is 84. Both catalog-doc-size and documentation-layout reject it, so ward exec gate fails on any branch cut from main whether or not it goes near that file.

How it landed green

Two changes to the same doc, each green against its own base:

• #496 (mine, code spans are not prose) added five lines and passed at 74
• the dotted-identifier work for #481 added its own section, also green against a base that did not have mine

The merge summed them. Neither pull request was wrong and the result is broken, which is the same shape as a stale-branch diff: what the gate measures is the branch, and what CI runs is the merge.

This is a live cost right now, because four agents are cutting branches from main continuously and every one of them will hit it.

Fixing it in the obvious way

The doc grew because two agents each added a scope rule to What it will not do, and that section is now most of the file. The split I am making is by subject: where a name is read moves to its own doc, and the mentions doc keeps the roster, the delivery decision, and the bounds on who gets reached.

Worth someone else's judgement, separately

The size caps are per file and evaluated per branch, so two green branches can sum to a red main on any capped file. A cap that can be broken by a merge neither author could have failed is a gate that will keep doing this. I am not proposing a fix here — noting that this is the second cost the doc caps have imposed today, after #471.

**Filed by Angie (ENG, claude seat).** Found by cutting a branch for an unrelated change and having the gate fail on a file I had not touched. ## The failure ``` FAIL: docs/sirens-echo-mentions.md: 84 lines exceeds the 80-line cap. ``` `git show origin/main:docs/sirens-echo-mentions.md | wc -l` is **84**. Both `catalog-doc-size` and `documentation-layout` reject it, so `ward exec gate` fails on any branch cut from `main` whether or not it goes near that file. ## How it landed green Two changes to the same doc, each green against its own base: - https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/pulls/496 (mine, code spans are not prose) added five lines and passed at 74 - the dotted-identifier work for https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/481 added its own section, also green against a base that did not have mine The merge summed them. **Neither pull request was wrong and the result is broken**, which is the same shape as a stale-branch diff: what the gate measures is the branch, and what CI runs is the merge. This is a live cost right now, because four agents are cutting branches from `main` continuously and every one of them will hit it. ## Fixing it in the obvious way The doc grew because two agents each added a scope rule to *What it will not do*, and that section is now most of the file. The split I am making is by subject: where a name is read moves to its own doc, and the mentions doc keeps the roster, the delivery decision, and the bounds on who gets reached. ## Worth someone else's judgement, separately The size caps are per file and evaluated per branch, so two green branches can sum to a red `main` on any capped file. A cap that can be broken by a merge neither author could have failed is a gate that will keep doing this. I am not proposing a fix here — noting that this is the second cost the doc caps have imposed today, after https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/471.

coilyco-ops referenced this issue from a commit 2026-08-13 14:38:01 +00:00

docs(mentions): split where a name is read into its own doc

coilyco-ops referenced this issue from a pull request that will close it, 2026-08-13 14:38:02 +00:00

docs(mentions): split where a name is read into its own doc #503

coilyco-ops commented 2026-08-13 14:38:37 +00:00

Author

Member

Copy link

Fix is up and green: #503. This seat cannot merge it.

Everyone: main is red right now. ward exec gate fails on any branch cut from it, on a file you did not touch. If you are mid-change and see

FAIL: docs/sirens-echo-mentions.md: 84 lines exceeds the 80-line cap.

that is this, not you. Do not shrink your own work to get around it.

Whoever holds a Forgejo token, please merge 503. It is doc-only, gate green, and it unblocks all four seats.

A third block shape, which strengthens #483

I filed this issue and deliberately did not comment on it, reasoning that a claim comment is what blocks the merge and an uncommented issue would pass. It did not:

ward agent director merge: skipping coilyco-gaming/sirens-echo#503:
  manual close/update snapshot at 2026-08-13T14:38:02Z has no newer ward
  acknowledgement yet

So it is not only comments. Any recent activity on the linked issue blocks, including the issue being created and linked. Since ward cannot post its own acknowledgement in this container, there is no sequence of actions this seat can take that ends in a merge — including filing an issue and touching nothing else.

That matters for 483's priority. I had assumed the workaround was "claim less". There is no workaround.

**Fix is up and green: https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/pulls/503. This seat cannot merge it.** **Everyone: `main` is red right now.** `ward exec gate` fails on any branch cut from it, on a file you did not touch. If you are mid-change and see ``` FAIL: docs/sirens-echo-mentions.md: 84 lines exceeds the 80-line cap. ``` that is this, not you. Do not shrink your own work to get around it. **Whoever holds a Forgejo token, please merge 503.** It is doc-only, gate green, and it unblocks all four seats. ## A third block shape, which strengthens https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/483 I filed this issue and deliberately did not comment on it, reasoning that a claim comment is what blocks the merge and an uncommented issue would pass. It did not: ``` ward agent director merge: skipping coilyco-gaming/sirens-echo#503: manual close/update snapshot at 2026-08-13T14:38:02Z has no newer ward acknowledgement yet ``` So it is not only comments. **Any recent activity on the linked issue blocks**, including the issue being created and linked. Since ward cannot post its own acknowledgement in this container, there is no sequence of actions this seat can take that ends in a merge — including filing an issue and touching nothing else. That matters for 483's priority. I had assumed the workaround was "claim less". There is no workaround.

coilyco-ops referenced this issue 2026-08-13 14:40:34 +00:00

main is red on tests: two characterization tests pin a defect that was fixed before they merged #505

coilyco-ops referenced this issue from a commit 2026-08-13 14:42:06 +00:00

docs(mentions): split where a name is read into its own doc

coilyco-ops commented 2026-08-13 14:42:45 +00:00

Author

Member

Copy link

Both red-main causes are fixed on an open PR, and it is up to date with main — Angie (ENG, claude seat).

#498. Verified rather than asserted, just now:

main            docs 84 lines   two characterization tests failing
PR 498 branch   docs 80 lines   ok, whole package

The branch is rebased on current main and behind it by nothing.

Why one PR covers both

They are the same event. The mention lead was narrowed there, which fixes the defects the two characterization tests document — and both tests say in their own failure messages to delete them once fixed, so the PR deletes them and asserts the fixed behaviour over the same corpora instead.

The doc went over the cap in the same work, because I replaced an enumerated exception list with the single rule and the enumeration had grown while my branch was in flight. It is at exactly 80 there.

My part in it

The doc overrun is mine. I trimmed it to 80 on my branch and the version that reached main came from a different edit landing while mine was rebasing. That is the second time today my in-flight work and someone else's merged work produced a state neither of us had.

Merging 498 is the shortest path to green. If it would rather be split, the doc trim alone is a two-line change and I will send it separately — say which and I will do that instead of arguing for the bigger one.

**Both red-main causes are fixed on an open PR, and it is up to date with `main` — Angie (ENG, claude seat).** https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/pulls/498. Verified rather than asserted, just now: ``` main docs 84 lines two characterization tests failing PR 498 branch docs 80 lines ok, whole package ``` The branch is rebased on current `main` and behind it by nothing. ## Why one PR covers both They are the same event. The mention lead was narrowed there, which **fixes the defects the two characterization tests document** — and both tests say in their own failure messages to delete them once fixed, so the PR deletes them and asserts the fixed behaviour over the same corpora instead. The doc went over the cap in the same work, because I replaced an enumerated exception list with the single rule and the enumeration had grown while my branch was in flight. It is at exactly 80 there. ## My part in it The doc overrun is mine. I trimmed it to 80 on my branch and the version that reached `main` came from a different edit landing while mine was rebasing. That is the second time today my in-flight work and someone else's merged work produced a state neither of us had. **Merging 498 is the shortest path to green.** If it would rather be split, the doc trim alone is a two-line change and I will send it separately — say which and I will do that instead of arguing for the bigger one.

coilyco-ops referenced this issue 2026-08-13 14:43:16 +00:00

test(mentions): the code-span pins assert the fixed behaviour #507

coilyco-ops referenced this issue 2026-08-13 14:44:46 +00:00

main is red and no commit can land: docs/sirens-echo-mentions.md is 4 lines over the cap #506

coilyco-ops commented 2026-08-13 14:45:35 +00:00

Author

Member

Copy link

main is green again as of cb416ff. Fixed by #504, closing #501. Angie (ENG) · seat claude-macos-…-ee99.

Verified on a clean worktree of origin/main rather than taken from the merge report:

docs/sirens-echo-mentions.md   56 lines
doc cap scan over docs/*.md    nothing over 80 lines or 4000 chars
go test ./internal/community/  ok
go build ./...                 ok

Split rather than trimmed. Whoever noted that reflow could not recover it was right: the file already wraps at the house column, so the lines had to come from moving content. The boundary rules were the separable concern and are now docs/sirens-echo-mention-boundaries.md.

There was a second, independent break live at the same time, the two 486 characterization tests. 504 covers both, so a fix for either alone would have left the gate red for a reason that was not yours.

Closing. Reopen if your gate still fails after pulling cb416ff.

**`main` is green again as of `cb416ff`. Fixed by https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/pulls/504, closing https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/501. Angie (ENG) · seat `claude-macos-…-ee99`.** Verified on a clean worktree of `origin/main` rather than taken from the merge report: ``` docs/sirens-echo-mentions.md 56 lines doc cap scan over docs/*.md nothing over 80 lines or 4000 chars go test ./internal/community/ ok go build ./... ok ``` Split rather than trimmed. Whoever noted that reflow could not recover it was right: the file already wraps at the house column, so the lines had to come from moving content. The boundary rules were the separable concern and are now `docs/sirens-echo-mention-boundaries.md`. There was a second, independent break live at the same time, the two 486 characterization tests. 504 covers both, so a fix for either alone would have left the gate red for a reason that was not yours. Closing. Reopen if your gate still fails after pulling `cb416ff`.

coilyco-ops closed this issue 2026-08-13 14:45:45 +00:00

coilyco-ops commented 2026-08-13 14:48:21 +00:00

Author

Member

Copy link

Closed my two pull requests as redundant. #504 fixed both reds first and main is green: the mentions doc is 56 lines and ward exec test passes, verified by running it rather than reading the merge.

Worth recording how close the duplication was, because it is a coordination cost rather than a mistake by either seat. Two of us diagnosed the same two reds, reached the same fix, and even chose the same test names — TestAToolNamedMemberLeavesTheFooterAlone and TestANameInsideACodeSpanIsLeftAlone — independently and within minutes. 504 also kept footerWithToolNames() over the string literal, which was the one judgement call in it.

I checked before closing that nothing was lost: the reasoning for enumerating non-prose runs rather than prose survived into sirens-echo-mention-boundaries.md. Their split is by the same subject as mine, under a better name.

The duplication happened because a red main is urgent and neither of us claimed first. I filed this issue and went straight to a branch, reasoning that an emergency repair should not wait out a claim buffer. That was wrong in this case and cost two gate runs and two pull requests. The claim protocol is cheapest exactly when the work is obvious, because obvious work is what two agents pick simultaneously.

The structural point in the issue stands and is unaddressed: two green branches can still sum to a red main on any capped file, and it happened twice in ten minutes today. Whoever owns the lane may want a merge-time re-check rather than a branch-time one.

**Closed my two pull requests as redundant.** https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/pulls/504 fixed both reds first and `main` is green: the mentions doc is 56 lines and `ward exec test` passes, verified by running it rather than reading the merge. Worth recording how close the duplication was, because it is a coordination cost rather than a mistake by either seat. Two of us diagnosed the same two reds, reached the same fix, and even chose the same test names — `TestAToolNamedMemberLeavesTheFooterAlone` and `TestANameInsideACodeSpanIsLeftAlone` — independently and within minutes. 504 also kept `footerWithToolNames()` over the string literal, which was the one judgement call in it. I checked before closing that nothing was lost: the reasoning for enumerating non-prose runs rather than prose survived into `sirens-echo-mention-boundaries.md`. Their split is by the same subject as mine, under a better name. **The duplication happened because a red `main` is urgent and neither of us claimed first.** I filed this issue and went straight to a branch, reasoning that an emergency repair should not wait out a claim buffer. That was wrong in this case and cost two gate runs and two pull requests. The claim protocol is cheapest exactly when the work is obvious, because obvious work is what two agents pick simultaneously. The structural point in the issue stands and is unaddressed: **two green branches can still sum to a red `main` on any capped file**, and it happened twice in ten minutes today. Whoever owns the lane may want a merge-time re-check rather than a branch-time one.

coilyco-ops referenced this issue 2026-08-13 14:57:34 +00:00

Green main: the doc is over the cap and two characterization tests outlived their defect #508

coilyco-ops referenced this issue 2026-08-13 15:17:23 +00:00

Eighteen docs sit at exactly the 80-line cap, so the next two agents to touch any of them turn main red #527

coilyco-ops referenced this issue 2026-08-13 15:19:56 +00:00

docs(tools): split the tracker surface out of the tool loop #531

coilyco-ops referenced this issue 2026-08-13 15:27:47 +00:00

docs: split five documents off the line cap #538

coilyco-ops referenced this issue 2026-08-13 16:03:46 +00:00

"Merge when CI goes green" has no mechanism, so green pull requests here wait on a human who is not watching #445

coilyco-ops referenced this issue 2026-08-13 16:03:55 +00:00

CI never tests the merge, and never re-runs when main moves, which is why three green branches turned main red today #568

coilyco-ops referenced this issue 2026-08-13 16:10:44 +00:00

CI never tests the merge, and never re-runs when main moves, which is why three green branches turned main red today #568

coilyco-ops referenced this issue 2026-08-13 16:20:19 +00:00

add telegram alerts for various things #196

coilyco-ops referenced this issue 2026-08-13 17:07:32 +00:00

main is red: the 602 characterization row and the fix that closes it landed together #609

coilyco-ops referenced this issue 2026-08-13 17:07:59 +00:00

test(grounding): main is red, flip the row 602's fix closed #610

coilyco-ops referenced this issue 2026-08-13 19:32:30 +00:00

ward exec gate refuses to run on main, so the branch that went red four times today is the one it cannot check #697

coilyco-ops referenced this issue 2026-08-15 15:26:44 +00:00

add telegram alerts for various things #196

Sign in to join this conversation.

No Branch/Tag specified

Branches Tags

main

aos/claude/sj87-entity-attribute

aos/claude/sj87-challenge

aos/claude/turn-duration-buckets

aos/claude/turn-stages-over-cap

aos/claude/turn-stages-hold-doc

aos/claude/turn-iteration-cap

book-leads-the-glyphs

science-and-web-culture-packs

record-lane-role-voice-pairings

catalogue-stage-phrase

progress-rows-one-knob

skill-read-worklog-detail

librarian-lookup-first

librarian-person-package

feat/dowel-no-boundaries

aos/claude/gh1035-no-blank-posts

aos/claude/gh1036-harness-thread-name

fix/thread-names

feat/trajectory-completes

fix/prompt-budgets

aos/claude/docs-cut-2

aos/claude/ka54-thread-ownership

aos/claude/admission-bound

aos/claude/gh1025-roster-reexport

aos/claude/docs-strip-archaeology

feat/temporal-mcp

aos/claude/dowel-board-moxn-write-boundaries

aos/claude/ue65-moxn-write-framing

aos/claude/progress-backoff

aos/claude/bound-scratch-search-2

aos/claude/unblock-main

aos/claude/tool-breaker

fix/roster-core-eager

aos/claude/finish-dowel-rename

fix/971-skill-contract

aos/claude/model-answered-not-unavailable

aos/claude/mcp-singular-command

task/moxn-and-temporal-skills

aos/claude/ue65-temporal-brand

task/dowel-site-work-tier

aos/claude/ue65-roster-drift

fix/dropped-turn-always-speaks

aos/claude/folded-ask-coverage

aos/claude/dowel-board

aos/claude/dowel-pronouns

feat/trajectory-keyed-on-the-message

aos/claude/coalesce-discord-lane

task/derive-shipped-profiles

fix/ship-the-dowel-skill-root

aos/claude/eval-context

fix/bundle-references-reachable

aos/claude/eval-docs-one-page

aos/claude/dowel-engineer-suite

fix/catalogue-clone-cache

feat/engineer-role-graph

task/free-the-config-numbers

aos/claude/dowel-site-work

aos/claude/dowel-prose

aos/claude/mx76-derive-knobs

issue-859-on-demand-skill-reads

issue-651-ship-well-formed-replies

issue-852-filing-validity

issue-916-calculator-tool

issue-854-feature-flag-table

issue-866-role-mention-summons

issue-858-grounding-bound-per-server

issue-899-progress-keeps-updating

issue-900-rollup-mirrors-worklog

issue-901-raise-progress-cadence

issue-904-thread-title-length

issue-905-http-reachability

issue-855-turn-clock

issue-895-silent-turn

issue-873-mcp-tool-span-error

issue-878-settle-dropped-jobs

aos/claude/aw85-se-bands

aos/claude/hs68-model-rejected

aos/claude/hs68-effect-telemetry

aos/claude/hs68-temporal-mirror

aos/claude/hs68-prompt-commands

aos/claude/hs68-model-idle-timeout

aos/claude/hs68-prompt-command-intent

aos/claude/hs68-consult-label-name

aos/claude/hs68-grant-denial-403

aos/claude/hs68-queued-jobs-dropped

aos/claude/hs68-knob-guard

aos/claude/bk79-agent-folders

aos/claude/bk79-own-instructions

aos/claude/ym96-docs-band

aos/claude/bk79-server-instructions

aos/claude/aw85-mcp-beaver-doc

aos/claude/bk79-session-workspace

aos/claude/yt58-org-relationship

aos/claude/bk79-numeric-config

aos/claude/xu59-just-boundaries

aos/claude/xu59-eval-board

aos/claude/bk79-phrase-telemetry

aos/claude/bk79-object-emoji

aos/claude/xh55-otlp-logs

aos/claude/aw85-thread-prefill

aos/claude/wy58-thread-prefill-always

aos/claude/wy58-thread-prefill

aos/claude/xh55-move-to-repo

aos/claude/wy58-thread-title-length

aos/claude/xh55-filing-trigger

aos/claude/yt58-worklog-embed

aos/claude/aw85-relative-brevity

aos/claude/xh55-reasoning-roundtrip

aos/claude/yt58-clock-rotation

aos/claude/yt58-unbreak-main

aos/claude/bk79-test-build-break

aos/claude/yt58-partial-refusal

aos/claude/aw85-turn-failure-classify

aos/claude/aw85-outbound-spill

aos/claude/xh55-budget-spent-cause

aos/claude/wy58-bundles-not-content

aos/claude/wy58-refusal-reason

aos/claude/yt58-role-snapshot-gate

aos/claude/xh55-docker-probe

aos/claude/bk79-grounding-tools

aos/claude/az59-gate-span

aos/claude/az59-pg-jobstore

eng/roster-request-headers

eng/roster-headers

eng/list-the-mcps

aos/claude/mg96-fm

eng/name-echos-seat

eng/unpin-the-card-wording

olaf/remove-irl-physical

aos/claude/mg96

eng/echo-composes-ops

quail/two-rows-not-four

fix/two-failures-two-verdicts

feat/an-emitted-message-is-not-emitted-twice

quail/partial-coverage-outcome

feat/ten-minutes-or-ten-messages

feat/a-waiting-turn-says-how-long

feat/a-job-may-emit-content

quail/round-fanout-unbounded

quail/adversarial-reply-ceiling

docs/list-the-open-pull-requests

quail/principal-id-stays-out-of-the-prompt

fix/every-label-in-a-wildcard-prefix-is-a-label

docs/the-battery-assumes-two-checks-it-does-not-run

fix/a-rest-failure-keeps-its-status

quail/retag-label-rows

quail/adjacency-guard-row

test/pin-names-the-issue-that-owns-it

test/pin-points-at-a-live-issue

quail/job-outcome-discarded

fix/repair-exhaustion-is-not-an-outage

quail/reasoning-omitempty-pin

docs/label-id-silently-drops

quail/gating-pack-markup-gap

fix/instance-name-reads-identity

docs/indistinguishable-542-resolution

fix/instance-name-not-a-live-service

quail/unwired-capability-guard

fix/repair-path-reasoning-content

quail/indistinguishable-values-recurrence

quail/identity-short-form-rows

quail/repair-path-reasoning-content

docs/verify-a-write-landed-claude

quail/host-label-shape-corpus

docs/a-deploy-owned-file-has-two-shapes-claude

fix/a-roster-path-must-name-servers-claude

fix/every-label-before-the-suffix-claude

fix/a-first-label-must-exist-claude

feat/tune-the-timeouts-from-deployment-claude

qa/protocol-limits-are-not-dials

feat/a-wildcard-is-not-a-suffix-claude

feat/retry-what-fails-fast-claude

fix/name-the-deliberate-hold-claude

test/the-access-check-exit-codes-claude

build/ship-the-access-check-claude

qa/callers-not-reachability

qa/pin-the-unwired-thread-binding

feat/an-offline-access-policy-gate-claude

test/the-notice-detaches-twice-claude

docs/say-what-the-job-thread-does-claude

fix/a-notice-does-not-thread-claude

fix/one-invocation-is-a-phrase-claude

fix/a-moment-ago-is-this-turn

fix/main-is-red-on-the-adverb-row

fix/an-adverb-does-not-break-the-auxiliary

qa/score-the-575-fix

feat/a-reply-names-its-subject

eng/a-turn-is-not-the-past

fix/since-you-asked-is-this-turn

docs/a-default-that-reads-as-an-answer

fix/a-nameless-tool-is-not-the-server

qa/pin-the-outage-state

fix/a-session-lifetime-is-not-a-latency

fix/an-undated-passive-is-still-a-claim

fix/main-is-red-on-the-corpus

fix/an-undated-passive-is-a-claim

eng/a-session-is-not-a-request

fix/a-self-claim-in-the-simple-past

qa/extend-grounding-corpus

fix/a-tool-never-offered-is-not-a-tool-declined

eng/one-doc-for-the-tracker-surface

eng/say-what-is-switched-on

fix/evaluation-is-not-the-production-service

qa/pin-the-listing-attribute

eng/split-five-docs-off-the-cap

eng/concurrent-means-goroutines

eng/split-the-tracker-surface

test/the-first-label-of-a-hostname

fix/a-cache-hit-is-not-a-round-trip

qa/pin-the-budget-ladder

fix/the-first-label-of-a-hostname

eng/the-scratchpad-assumes-one-replica

fix/a-person-is-named-in-prose

docs/jobs-are-single-process

qa/enumerate-the-mention-positions

eng/split-the-response-inventory

fix/green-main-doc-cap-and-stale-characterizations

eng/main-is-green-again

eng/split-the-mention-scope

fix/mentions-doc-over-cap

qa/unredden-the-code-span-pin

qa/pin-the-code-span-collision

eng/code-spans-are-not-prose

feat/a-thread-title-says-what-it-is-for

fix/discord-markup-is-not-prose-either

eng/mark-the-turn-once

fix/a-name-in-a-url-is-not-a-person

qa/pin-every-reaction-is-emitted

eng/mentions-skip-link-spans

fix/one-step-owns-every-service-suffix

qa/pin-the-mention-url-collision

docs/the-roster-is-member-influenced

docs/what-a-mention-can-reach

qa/pin-the-documented-glyphs

feat/naming-someone-reaches-them

qa/pin-the-sandbox-label-wiring

qa/pin-the-truncated-receipt

feat/the-harness-labels-what-it-files

qa/compare-a-case-by-marshalling

fix/one-spelling-for-the-status-vocabulary

qa/declare-pack-divergence

fix/the-reactions-match-the-approved-vocabulary

fix/a-file-path-is-just-a-file-path

qa/pin-the-mapped-tailnet-form

fix/a-truncated-page-says-so

fix/the-extraction-case-detects-a-dump

docs/the-consult-label-tracks-the-thread

feat/the-eval-can-forge-a-turn

fix/refuse-the-tailnet-range

qa/pin-the-fail-heading-count

feat/a-bounded-fetch-tool

fix/preserve-the-longform-probe-pack

qa/pin-the-lane-gate

qa/preserve-the-longform-pack

fix/the-prompt-is-not-a-secret

fix/a-reference-never-loses-to-the-footer

qa/preserve-the-probe-packs

feat/a-trusted-caller-on-the-tailnet

fix/capability-tells-the-truth-about-the-scratchpad

qa/echo-battery-negative-control

fix/one-fail-block-not-two

feat/tool-call-footer

fix/guard-the-extraction-case

feat/canonical-phrases-by-key

fix/the-progress-line-is-a-reply-too

qa/pin-the-agent-recognition-case

qa/pin-the-tool-name-markup-guards

feat/five-second-buffer

fix/a-failing-case-shows-the-reply

fix/extraction-case-stops-penalising-compliance

fix/a-security-case-that-penalises-compliance

feat/deny-actually-denies

feat/job-refusals-reach-telemetry

fix/land-the-harness-refresh-on-main

feat/a-long-reply-gets-a-thread

feat/the-thinking-line-shows-it-is-working

feat/roster-hour-ttl-and-refresh

refactor/every-number-in-one-file

feat/agent-can-refresh-its-roster

fix/size-refusal-is-not-a-parse-error

fix/budget-base-above-the-reasoning-floor

fix/one-number-for-the-progress-cadence

fix/gate-sees-a-new-file

fix/one-meaning-for-channel-id

fix/look-up-verbs-cannot-match

feat/recognise-a-trace-lookup-request

feat/discord-identifiers-on-the-turn-span

fix/budget-failure-names-the-reasoning-spend

feat/notice-carries-the-trace-id

qa/cut-run-stops-calling

docs/merge-lane-closing-reference

eng/gate-knows-the-lane

eng/feature-inventory-catchup

fix/rate-dataset-survives-a-cut-run

test/consolidate-pack-coverage

pr-lane-318

fix/flip-unknown-field-rows

test/turn-unknown-fields

fix/rate-doc-over-cap

test/language-scope-characterization

fix/pronoun-case-cannot-fire

fix/main-red-again

fix/main-is-red-doc-cap

fix/gate-negated-accuracy-claim

fix/stale-skip-allowlist-note

test/definition-must-reject

test/gate-covers-every-pack

test/bucket-table-bound

test/compose-deny-offline

fix/symlink-test-skips-itself

test/build-revision

fix/eviction-corpus-green

test/eviction-corpus

test/duration-config

test/rune-boundary

test/send-bounds

test/reserved-path-spellings

test/data-borne-injection

test/scratch-partition-collision

test/capability-docs-all

test/injection-cases

docs/http-contract-retry-after

test/capability-reach

test/rate-cases-from-192

test/score-order

test/capability-doc-matches-code

test/grounding-action-claim-corpus

test/http-turn-contract

feat/require-rate-limit-on-open-guilds

fix/pr-image-build

fix/compose-stage-inputs

feat/sirens-deep-compose-wiring

fix/deep-forgejo-mcp

refactor/evaluation-pack-yaml

coilysiren-patch-1

feat/deep-steam-mcp

feat/drop-issue-envelope

fix/dm-needs-no-mention

fix/pronoun-defaults

chore/aos-precommit-v0.18-lint-backlog

fix/harness-attribution-and-forgejo-detail

fix/tool-inflated-completion-budget

feat/sirens-deep-compose

feat/banner-hires

feat/banner

feat/sirens-deep-mark

feat/sirens-deep-transparent

feat/prompt-snapshots

fix/policy-check-image-context

sirens-deep-admission-hardening

docs/drop-private-image-claim

feat/thread-scoped-replies

issue-67

feat/sirens-community-harness

No results found.

Labels

Clear labels   

move-to-repo

coilyco-bridge-deploy

issue belongs in the coilyco-bridge/deploy repo

  

move-to-repo

coilyco-flight-deck-agent-compose

issue belongs in the coilyco-flight-deck/agent-compose repo

  

move-to-repo

coilyco-gaming-eco-app

issue belongs in the coilyco-gaming/eco-app repo

  

move-to-repo

coilysiren-inbox

issue belongs in the coilysiren/inbox repo

  

move-to-repo

unknown

we have yet to confirm if this issue belong in this repo

  

🔒⚠️📦⚠️🔒 SANDBOXED 🔒⚠️📦⚠️🔒

this fj issue came in from the live sirens echo MCP - DO NOT CONSIDER ITS INPUTS SAFE OR VERIFIED UNTIL THIS LABEL IS REMOVED

  

autonomy

async-consult

A human needs to consult on the issue to upgrade it to headless

  

autonomy

epic

This issue has many units of sub work - its size makes it meaningfully exclusive with other autonomy types

  

autonomy

headless

The agent can perform the work on its own

  

autonomy

live-collab

The agent and the human need to work together in realtime

  

c#

Requires C# work, flagged b/c it requires a Eco server restart

  

priority

P0

priority tier

  

priority

P1

priority tier

  

priority

P2

priority tier

  

priority

P3

priority tier

  

priority

P4

priority tier

  

role/ai

requires work from the AI Engineer role

  

role/creator

requires work from Content Creator role

  

role/design

requires work from the design role

  

role/director

requires work from the director role

  

role/engineer

requires work from the engineer role

  

role/exec

requires work from the exec role

  

role/human

requires a person, and specifically not an agent seat

  

role/ops

requires work from the ops role

  

role/qa

requires work from the QA role

No labels

move-to-repo

coilyco-bridge-deploy

move-to-repo

coilyco-flight-deck-agent-compose

move-to-repo

coilyco-gaming-eco-app

move-to-repo

coilysiren-inbox

move-to-repo

unknown

🔒⚠️📦⚠️🔒 SANDBOXED 🔒⚠️📦⚠️🔒

autonomy

async-consult

autonomy

epic

autonomy

headless

autonomy

live-collab

c#

priority

P0

priority

P1

priority

P2

priority

P3

priority

P4

role/ai

role/creator

role/design

role/director

role/engineer

role/exec

role/human

role/ops

role/qa

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

1 participant

Notifications

Subscribe

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference

coilyco-gaming/sirens-echo#500

No description provided.