coilyco-gaming/sirens-echo
Watch
3
0
Code Issues 153 Pull requests Projects Releases Packages 2 Wiki Activity Actions

Restrict Echo (not Deep) from weighing in extensively on general information topics that can just be linked to wikipedia #605

New issue
Closed
opened 2026-08-13 16:58:32 +00:00 by coilysiren · 5 comments
coilysiren commented 2026-08-13 16:58:32 +00:00
Owner
Copy link

its already providing wiki links, it just gives too long of a preamble before them

A recent algebra question produced a two-paragraph intro before the wiki link. Kai wants that down to one or two sentences.

Resolved spec (design pass, 2026-08-15)

Scope, decided 2026-08-13 - Echo only, not Deep. Encyclopedia-shaped topics only. Eco and community questions keep full answers, unchanged. A structural "link first, then a note" inversion and a hard sentence cap were both rejected.

Mechanism, decided 2026-08-15 - a sharper doctrine line, and nothing else. No evaluation case, no production length check.

Rejected, and why each was rejected:

  • Evaluation case with max_reply_words - declined for this ticket. It measures rather than enforces, and Kai is not buying a measurement here.
  • Both a new line and a case - declined for the same reason.
  • Production length check - declined. A genuinely long correct answer that cites a source would trip it, and per the closed-target-set rule a check that can fire on a correct reply does not survive.

Build

The existing line in .agents/skills/sirens-echo-community/SKILL.md:14 is "Start with the requested information." That line is already there and was already ignored, so the replacement must say something the current one does not. Restating it more firmly is the failure mode to avoid.

The instruction must carry all three of these, because the current line carries none of them:

  1. The topic test - encyclopedia-shaped versus Eco and community. This is the load-bearing half. Get it wrong toward encyclopedia and Echo becomes terse about Eco, which is the one thing it should be expansive about.
  2. The shape - lead with the link, then at most two sentences, for encyclopedia-shaped topics only.
  3. The non-restriction - Echo still answers these questions. General-knowledge explainers are explicitly not a denylist category, per #227.

Acceptance

  • An encyclopedia-shaped question ("what is algebra", "who was Ada Lovelace") gets the link plus at most two sentences.
  • An Eco question gets a full answer with no brevity pressure. Check this one explicitly, since it is the failure direction that costs the most.
  • No new validator and no new evaluation case ship with this. Verification is by eye, which is what "sharper doctrine line only" buys.

Related - #213 and #222 set the link-out regime, and this is the brevity half of it not being followed. #607 widens Deep in the opposite direction. Echo goes deep on Eco and links out on everything else, Deep is the broad one, and neither should drift toward the other.

its already providing wiki links, it just gives too long of a preamble before them A recent algebra question produced a two-paragraph intro before the wiki link. Kai wants that down to one or two sentences. --- ## Resolved spec (design pass, 2026-08-15) **Scope, decided 2026-08-13** - Echo only, not Deep. Encyclopedia-shaped topics only. Eco and community questions keep full answers, unchanged. A structural "link first, then a note" inversion and a hard sentence cap were both rejected. **Mechanism, decided 2026-08-15** - a sharper doctrine line, and nothing else. No evaluation case, no production length check. Rejected, and why each was rejected: * Evaluation case with `max_reply_words` - declined for this ticket. It measures rather than enforces, and Kai is not buying a measurement here. * Both a new line and a case - declined for the same reason. * Production length check - declined. A genuinely long correct answer that cites a source would trip it, and per the closed-target-set rule a check that can fire on a correct reply does not survive. **Build** The existing line in `.agents/skills/sirens-echo-community/SKILL.md:14` is "Start with the requested information." That line is already there and was already ignored, so **the replacement must say something the current one does not**. Restating it more firmly is the failure mode to avoid. The instruction must carry all three of these, because the current line carries none of them: 1. The topic test - encyclopedia-shaped versus Eco and community. This is the load-bearing half. Get it wrong toward encyclopedia and Echo becomes terse about Eco, which is the one thing it should be expansive about. 2. The shape - lead with the link, then at most two sentences, for encyclopedia-shaped topics only. 3. The non-restriction - Echo still answers these questions. General-knowledge explainers are explicitly not a denylist category, per #227. **Acceptance** * An encyclopedia-shaped question ("what is algebra", "who was Ada Lovelace") gets the link plus at most two sentences. * An Eco question gets a full answer with no brevity pressure. Check this one explicitly, since it is the failure direction that costs the most. * No new validator and no new evaluation case ship with this. Verification is by eye, which is what "sharper doctrine line only" buys. **Related** - #213 and #222 set the link-out regime, and this is the brevity half of it not being followed. #607 widens Deep in the opposite direction. Echo goes deep on Eco and links out on everything else, Deep is the broad one, and neither should drift toward the other.
coilysiren changed title from Restrict Echo (not Deep) from weighing in on general information topics that can just be linked to wikipedia to Restrict Echo (not Deep) from weighing in extensively on general information topics that can just be linked to wikipedia 2026-08-13 16:59:03 +00:00
coilysiren commented 2026-08-13 16:59:41 +00:00
Author
Owner
Copy link

a recent algebra Q resulted in a 2 paragraph into before the wiki link. I would like that down to 1 or 2 sentences

a recent algebra Q resulted in a 2 paragraph into before the wiki link. I would like that down to 1 or 2 sentences
coilyco-ops commented 2026-08-13 19:05:27 +00:00
Member
Copy link

The rule you are asking for already exists in Echo's doctrine and is not holding. Angie (ENG, claude seat). Not claiming — the fix is doctrine and @Lucia's, but the lever inventory is mine and it is short.

It is already written

.agents/skills/sirens-echo-community/SKILL.md:14:

Start with the requested information. Use concise, factual, impersonal …

That is your "down to 1 or 2 sentences", in the file Echo loads every turn. So this is not a missing instruction. Adding a second sentence saying the same thing more firmly is the cheapest-looking fix and the one least likely to work, because the first one is already there and was ignored.

What could enforce it, and what cannot

Nothing in production bounds reply length except Discord's own cap.

discordReplyLimit   1990 runes, a platform limit, not a style bound
MaxReplyWords       evaluation-only: evaluation.go:46, checked by
                    checkReplyLength at evaluation.go:359

MaxReplyWords is exactly the shape of your ask — "every volunteered justification is words", per its own comment — but it grades an evaluation case. It does not reach a live turn.

So there are three real options, and they are not equal

A sharper doctrine line. Cheapest, and it is what the existing line already tried. If it is taken, it should say something the current line does not — lead with the link, then at most two sentences is a different instruction from start with the requested information, and testable by eye.

An evaluation case with max_reply_words. Turns "too long" into a number that a run reports. Your algebra question is a ready-made case. This is the one I would build, and it is engineering rather than doctrine. It measures rather than enforces, which is the honest description.

A production bound. I would argue against it. A check on preamble length before a link would fire on correct replies — a genuinely long answer that happens to cite a source is not a defect — and per the closed target set a check that can fire on a correct reply does not survive.

What I would want before building the case

The algebra reply itself, or its trace. You saw two paragraphs; a case needs the question and a word count to pick a bound that is tight enough to catch it and loose enough to pass a good answer. Guessing the bound is how a case ends up either permanently red or permanently green.

If you paste the question, I will write the case. If Lucia takes the doctrine half first, the case is how anyone knows whether it worked.

**The rule you are asking for already exists in Echo's doctrine and is not holding. Angie (ENG, claude seat). Not claiming — the fix is doctrine and @Lucia's, but the lever inventory is mine and it is short.** ## It is already written `.agents/skills/sirens-echo-community/SKILL.md:14`: > **Start with the requested information.** Use concise, factual, impersonal … That is your *"down to 1 or 2 sentences"*, in the file Echo loads every turn. **So this is not a missing instruction.** Adding a second sentence saying the same thing more firmly is the cheapest-looking fix and the one least likely to work, because the first one is already there and was ignored. ## What could enforce it, and what cannot **Nothing in production bounds reply length except Discord's own cap.** ``` discordReplyLimit 1990 runes, a platform limit, not a style bound MaxReplyWords evaluation-only: evaluation.go:46, checked by checkReplyLength at evaluation.go:359 ``` `MaxReplyWords` is exactly the shape of your ask — *"every volunteered justification is words"*, per its own comment — but it grades an evaluation case. It does not reach a live turn. ## So there are three real options, and they are not equal **A sharper doctrine line.** Cheapest, and it is what the existing line already tried. If it is taken, it should say something the current line does not — *lead with the link, then at most two sentences* is a different instruction from *start with the requested information*, and testable by eye. **An evaluation case with `max_reply_words`.** Turns "too long" into a number that a run reports. Your algebra question is a ready-made case. This is the one I would build, and it is engineering rather than doctrine. **It measures rather than enforces**, which is the honest description. **A production bound.** I would argue against it. A check on preamble length before a link would fire on correct replies — a genuinely long answer that happens to cite a source is not a defect — and per [the closed target set](https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/src/branch/main/docs/sirens-echo-battery.md) a check that can fire on a correct reply does not survive. ## What I would want before building the case **The algebra reply itself, or its trace.** You saw two paragraphs; a case needs the question and a word count to pick a bound that is tight enough to catch it and loose enough to pass a good answer. Guessing the bound is how a case ends up either permanently red or permanently green. If you paste the question, I will write the case. If Lucia takes the doctrine half first, the case is how anyone knows whether it worked.
coilyco-ops commented 2026-08-13 22:48:01 +00:00
Member
Copy link

Decided — scoped narrowly: Echo only, general-knowledge topics only

Recorded by Delphi (design seat, standing in for exec). Kai's decision, 2026-08-13.

The restriction applies to Echo and not Deep, and only to topics that are genuinely encyclopedia-shaped. Eco questions keep full answers.

Kai rejected a structural "link first, then a note" inversion and rejected a hard sentence cap.

What this is and is not

Not a new boundary. Echo still answers these questions — Kai explicitly rejected making general-knowledge explainers a denylist category (#227) and the link-out regime already says answer briefly and link (#213, #222).

This is that rule not being followed. Your note: "its already providing wiki links, it just gives too long of a preamble before them." The link-out decision landed; the brevity half did not.

The hard part is the scope test, not the length

Kai's choice puts the weight on which topics qualify. Echo must distinguish:

  • Encyclopedia-shaped — "what is algebra", "who was Ada Lovelace". Brief answer, then the link.
  • Eco and community — full answers, unchanged. This is Echo's domain and the restriction must not touch it.

That boundary is the whole design. Get it wrong toward encyclopedia and Echo becomes terse about Eco, which is the one thing it should be expansive about.

Echo, not Deep. Deep is being generalized to a broad gaming/entertainment/tech harness (#607) and keeps its latitude.

The split this creates between the two agents, worth stating

Echo goes deep on Eco and links out on everything else. Deep is the broad one.

That falls out of two decisions made today without either being designed for the other — 605 narrowing Echo's general-knowledge register, 607 widening Deep's. It is a coherent division of labour and worth naming so neither drifts toward the other.

Note

The measured baseline in #175 covers boundary responses. This is the ordinary-response side and has no baseline — worth measuring preamble length before and after, or there is no way to tell whether it worked.

## Decided — scoped narrowly: Echo only, general-knowledge topics only Recorded by Delphi (design seat, standing in for exec). Kai's decision, 2026-08-13. **The restriction applies to Echo and not Deep, and only to topics that are genuinely encyclopedia-shaped.** Eco questions keep full answers. Kai rejected a structural "link first, then a note" inversion and rejected a hard sentence cap. ### What this is and is not **Not a new boundary.** Echo still answers these questions — Kai explicitly rejected making general-knowledge explainers a denylist category (https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/227) and the link-out regime already says answer briefly and link (https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/213, https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/222). **This is that rule not being followed.** Your note: *"its already providing wiki links, it just gives too long of a preamble before them."* The link-out decision landed; the brevity half did not. ### The hard part is the scope test, not the length Kai's choice puts the weight on **which topics qualify**. Echo must distinguish: - **Encyclopedia-shaped** — *"what is algebra"*, *"who was Ada Lovelace"*. Brief answer, then the link. - **Eco and community** — full answers, unchanged. This is Echo's domain and the restriction must not touch it. **That boundary is the whole design.** Get it wrong toward encyclopedia and Echo becomes terse about Eco, which is the one thing it should be expansive about. **Echo, not Deep.** Deep is being generalized to a broad gaming/entertainment/tech harness (https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/607) and keeps its latitude. ### The split this creates between the two agents, worth stating **Echo goes deep on Eco and links out on everything else. Deep is the broad one.** That falls out of two decisions made today without either being designed for the other — 605 narrowing Echo's general-knowledge register, 607 widening Deep's. It is a coherent division of labour and worth naming so neither drifts toward the other. ### Note The measured baseline in https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/175 covers boundary responses. **This is the ordinary-response side and has no baseline** — worth measuring preamble length before and after, or there is no way to tell whether it worked.
coilyco-ops commented 2026-08-19 04:48:14 +00:00
Member
Copy link

Landed in 1ea685b, in sirens-echo-community/SKILL.md under the existing link section.

Implements the 2026-08-15 resolved spec and adds nothing to it. That spec is unusually clear about what it did not want, and every rejection is honoured: no evaluation case, no max_reply_words, no production length check, no link-first structural inversion, no hard sentence cap. A sharper doctrine line and nothing else.

The line:

On an encyclopedia-shaped question the link is the answer. Where the substance of the question is the contents of a listed reference page, give one or two sentences and the link, and stop. Not a summary of the page, not a definition followed by its key components, not a survey of the field. The member asked what a thing is and the page they can open says it better and at their own length.

The three "not" clauses are the shapes from #222's transcript rather than invented ones: that reply gave a definition, then key components as a list, then a paragraph on what algebra enables and what it underpins. Naming the shapes does the work a sentence count would have done, without being the cap that was rejected.

Scoped as decided on 2026-08-13. It lands in sirens-echo-community, which only Echo loads, so Deep and Dowel are untouched. The closing paragraph then states what it does not narrow: Eco, community, and deployment questions keep their full answers, because for those no page already says it. Without that, this reads as a general instruction to be terse and collides with the community answers that are supposed to be thorough, which is the failure mode in #1049.

What is owed

Nothing measurable was added, by design, so confirming this works means someone asking Echo an encyclopedia question against a build carrying 1ea685b and reading the preamble length. #222 supplies a ready-made prompt for that.

Refs #222, #1049

**Landed in `1ea685b`**, in `sirens-echo-community/SKILL.md` under the existing link section. Implements the 2026-08-15 resolved spec and adds nothing to it. That spec is unusually clear about what it did not want, and every rejection is honoured: no evaluation case, no `max_reply_words`, no production length check, no link-first structural inversion, no hard sentence cap. A sharper doctrine line and nothing else. The line: > **On an encyclopedia-shaped question the link is the answer.** Where the substance of the question is the contents of a listed reference page, give one or two sentences and the link, and stop. Not a summary of the page, not a definition followed by its key components, not a survey of the field. The member asked what a thing is and the page they can open says it better and at their own length. The three "not" clauses are the shapes from #222's transcript rather than invented ones: that reply gave a definition, then key components as a list, then a paragraph on what algebra enables and what it underpins. Naming the shapes does the work a sentence count would have done, without being the cap that was rejected. **Scoped as decided on 2026-08-13.** It lands in `sirens-echo-community`, which only Echo loads, so Deep and Dowel are untouched. The closing paragraph then states what it does not narrow: Eco, community, and deployment questions keep their full answers, because for those no page already says it. Without that, this reads as a general instruction to be terse and collides with the community answers that are supposed to be thorough, which is the failure mode in #1049. ## What is owed Nothing measurable was added, by design, so confirming this works means someone asking Echo an encyclopedia question against a build carrying `1ea685b` and reading the preamble length. #222 supplies a ready-made prompt for that. Refs #222, #1049
coilyco-ops commented 2026-08-19 09:16:21 +00:00
Member
Copy link

Verified on main: 1ea685b ships the resolved spec's doctrine line in sirens-echo-community/SKILL.md (the encyclopedia-shaped topic test, the one-or-two-sentences-plus-link shape, and the explicit non-restriction), and per the spec nothing else shipped with it - no eval case, no length check. Acceptance is by eye per the spec, so nothing further blocks this issue. Closing as landed.

Verified on main: 1ea685b ships the resolved spec's doctrine line in sirens-echo-community/SKILL.md (the encyclopedia-shaped topic test, the one-or-two-sentences-plus-link shape, and the explicit non-restriction), and per the spec nothing else shipped with it - no eval case, no length check. Acceptance is by eye per the spec, so nothing further blocks this issue. Closing as landed.
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
2 participants
Notifications
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#605
No description provided.