coilyco-gaming/sirens-echo
Watch
3
0
Code Issues 150 Pull requests Projects Releases Packages 2 Wiki Activity Actions

Dowel's skill root opts out of progressive disclosure entirely: all six references are inline, 24KB every turn #993

New issue
Closed
opened 2026-08-18 22:36:37 +00:00 by coilyco-ops · 4 comments
coilyco-ops commented 2026-08-18 22:36:37 +00:00
Member
Copy link

Found while checking whether .agents/skills/sirens-dowel needed updating for the lane's MCP surface. It did not - references/tool-surfaces.md is accurate 12/12 against the live roster on coilyco-bridge/deploy main, and it correctly declares itself a map rather than an inventory with the offered tool list winning on conflict. Nothing to fix there.

This is the thing I found instead.

Every reference in the root is inline: always

SKILL.md                    1,935
coilyco-suite.md            3,906
dowel-provenance.md         3,838
moxn-knowledge-base.md      4,013
site-work.md                4,566
temporal.md                 3,081
tool-surfaces.md            2,758
                           ------
total inline               24,097 bytes, every turn

The two shared roots the same definition loads use the tier split #927 built:

coilyco-general    entry 2,504    deferred 5,717
coilyco-org        entry   673    deferred 1,380

So the lane with the largest prompt is the one root that carries everything inline.

Not all of it is wrong

#927 records the rule and it is right: "a model that has to choose to read its own boundaries may not". dowel-provenance.md is the identity and placement answer, and placement is the fact a probe most wants wrong, which the root's own closing paragraph explains. tool-surfaces.md prevents a question being turned away for want of noticing a tool. Both earn inline on that reasoning.

Three of them look like the long tail

  • site-work.md (4,566). The root says "Read references/site-work.md before touching a page", which is a conditional. A conditional is what the deferred tier exists for.
  • coilyco-suite.md (3,906) and temporal.md (3,081). Subject matter rather than boundaries. A turn that never reaches those subjects pays for them anyway.

Deferring those three is roughly 11.5KB off every turn, at the cost of one read_skill round on turns that actually go there.

Why it is worth a decision rather than drift

This is #932's lane, at a 32.9s median turn. 11.5KB is not the headline there, and I am not claiming it is. The point is that each inline: always looked reasonable on its own and the total was never decided by anyone. That is how the tier split stops being a split.

Kai's own guidance on #927 was "keep the highest-traffic references inline and move the long tail, rather than moving everything on principle". This root moved nothing.

What would close it

A deliberate answer to one question per reference: must Dowel never fail to know this, or does it need it only when the subject comes up? Inline the first kind, defer the second, and record why on the file rather than in a thread.

I did not change anything. This is a judgment call about what the demo agent must never fail to know, and that belongs to Kai or the AI seat rather than to me, especially inside the August 19 freeze (#929).

Evidence for the broader question on #968, which is currently an empty stub asking whether progressive disclosure is actually working. This is one concrete answer: on the shared roots yes, on this root it was opted out of.

Related: #927, #932, #968, #859.

Found while checking whether `.agents/skills/sirens-dowel` needed updating for the lane's MCP surface. **It did not** - `references/tool-surfaces.md` is accurate 12/12 against the live roster on `coilyco-bridge/deploy` main, and it correctly declares itself a map rather than an inventory with the offered tool list winning on conflict. Nothing to fix there. This is the thing I found instead. ## Every reference in the root is `inline: always` ``` SKILL.md 1,935 coilyco-suite.md 3,906 dowel-provenance.md 3,838 moxn-knowledge-base.md 4,013 site-work.md 4,566 temporal.md 3,081 tool-surfaces.md 2,758 ------ total inline 24,097 bytes, every turn ``` The two shared roots the same definition loads use the tier split #927 built: ``` coilyco-general entry 2,504 deferred 5,717 coilyco-org entry 673 deferred 1,380 ``` So the lane with the largest prompt is the one root that carries everything inline. ## Not all of it is wrong #927 records the rule and it is right: "a model that has to *choose* to read its own boundaries may not". `dowel-provenance.md` is the identity and placement answer, and placement is the fact a probe most wants wrong, which the root's own closing paragraph explains. `tool-surfaces.md` prevents a question being turned away for want of noticing a tool. Both earn inline on that reasoning. ## Three of them look like the long tail * **`site-work.md`** (4,566). The root says "Read `references/site-work.md` **before touching a page**", which is a conditional. A conditional is what the deferred tier exists for. * **`coilyco-suite.md`** (3,906) and **`temporal.md`** (3,081). Subject matter rather than boundaries. A turn that never reaches those subjects pays for them anyway. Deferring those three is roughly **11.5KB off every turn**, at the cost of one `read_skill` round on turns that actually go there. ## Why it is worth a decision rather than drift This is #932's lane, at a 32.9s median turn. 11.5KB is not the headline there, and I am not claiming it is. The point is that **each `inline: always` looked reasonable on its own and the total was never decided by anyone**. That is how the tier split stops being a split. Kai's own guidance on #927 was "keep the highest-traffic references inline and move the long tail, rather than moving everything on principle". This root moved nothing. ## What would close it A deliberate answer to one question per reference: **must Dowel never fail to know this, or does it need it only when the subject comes up?** Inline the first kind, defer the second, and record why on the file rather than in a thread. I did not change anything. This is a judgment call about what the demo agent must never fail to know, and that belongs to Kai or the AI seat rather than to me, especially inside the August 19 freeze (#929). Evidence for the broader question on #968, which is currently an empty stub asking whether progressive disclosure is actually working. This is one concrete answer: on the shared roots yes, on this root it was opted out of. Related: #927, #932, #968, #859.
coilyco-ops commented 2026-08-18 22:46:23 +00:00
Author
Member
Copy link

Correcting my own list, and adding the repo-wide picture that makes the scope clear.

temporal.md does not belong in my long-tail list

The root says so explicitly, and I quoted the file names out of it without reading the sentence around them:

Two of them carry a standing instruction to reach for them rather than answer from recall. The shared knowledge base has references/moxn-knowledge-base.md, and Temporal has references/temporal.md. Both are already in this prompt, so on either subject there is nothing to fetch first and a remembered answer is a choice.

That is #927's own criterion, not subject matter. An instruction saying "do not answer this from memory" cannot be behind a fetch the model has to choose to make, because the failure mode is exactly the model not choosing. Both earn inline, and moxn-knowledge-base.md earns it for the same reason. I had temporal.md in the wrong column.

The corrected list is two files, not three

  • site-work.md (4,566) - the root's own pointer is "before touching a page", a conditional, which is what the deferred tier is for.
  • coilyco-suite.md (3,906) - what Kai ships and how to mention it. Subject matter, and the only one of the six carrying no standing instruction and no boundary.

Roughly 8.5KB off every turn rather than the 11.5KB I claimed.

Repo-wide, so the scope is not guessed

Seventeen reference files exist. Ten are inline:

INLINE    coilyco-general/references/capability.md          3,659
INLINE    coilyco-org/references/organizations.md           1,380
INLINE    sirens-echo-knowledge/references/boundaries.md    1,005
INLINE    sirens-echo-knowledge/references/capability.md    3,907
INLINE    sirens-dowel/references/*                        22,162  (six files)

The four outside sirens-dowel are precisely the four #927 justified when it built the split. sirens-dowel contributes six of the ten, and is the only root added since.

So this is not a fleet-wide annotation pass. The rest of the repo is already tiered deliberately, with reasons on the record. This is two files on one root, and the action is removing inline: always rather than attaching anything, since deferred is the default and inline is the opt-out.

Correcting my own list, and adding the repo-wide picture that makes the scope clear. ## `temporal.md` does not belong in my long-tail list The root says so explicitly, and I quoted the file names out of it without reading the sentence around them: > Two of them carry **a standing instruction to reach for them rather than answer from recall**. The shared knowledge base has `references/moxn-knowledge-base.md`, and Temporal has `references/temporal.md`. Both are already in this prompt, so on either subject there is nothing to fetch first and **a remembered answer is a choice**. That is #927's own criterion, not subject matter. An instruction saying "do not answer this from memory" cannot be behind a fetch the model has to choose to make, because the failure mode is exactly the model not choosing. Both earn inline, and `moxn-knowledge-base.md` earns it for the same reason. I had `temporal.md` in the wrong column. ## The corrected list is two files, not three * **`site-work.md`** (4,566) - the root's own pointer is "before touching a page", a conditional, which is what the deferred tier is for. * **`coilyco-suite.md`** (3,906) - what Kai ships and how to mention it. Subject matter, and the only one of the six carrying no standing instruction and no boundary. Roughly **8.5KB** off every turn rather than the 11.5KB I claimed. ## Repo-wide, so the scope is not guessed Seventeen reference files exist. Ten are inline: ``` INLINE coilyco-general/references/capability.md 3,659 INLINE coilyco-org/references/organizations.md 1,380 INLINE sirens-echo-knowledge/references/boundaries.md 1,005 INLINE sirens-echo-knowledge/references/capability.md 3,907 INLINE sirens-dowel/references/* 22,162 (six files) ``` The four outside `sirens-dowel` are precisely the four #927 justified when it built the split. **`sirens-dowel` contributes six of the ten**, and is the only root added since. So this is not a fleet-wide annotation pass. The rest of the repo is already tiered deliberately, with reasons on the record. This is two files on one root, and the action is **removing** `inline: always` rather than attaching anything, since deferred is the default and inline is the opt-out.
coilyco-ops commented 2026-08-19 04:02:44 +00:00
Author
Member
Copy link

Decision: demote the long tail, keep the two standing-instruction files inline.

Kai's decision, 2026-08-19, recorded by Saiya (exec seat) during a P0 review.

Keep inline: always on moxn-knowledge-base.md and temporal.md. The root itself states why, and the correction comment above makes the same point: both carry a standing instruction to reach for them rather than answer from recall. On a Temporal livestream, an agent answering about Temporal from recall instead of the file is the exact failure that instruction exists to prevent.

Tier the other four onto the disclosure split the shared roots already use: coilyco-suite.md, dowel-provenance.md, site-work.md, tool-surfaces.md.

That is roughly 13KB off a 24KB inline block, on a lane whose prefix cost is the surviving explanation of the latency Kai called fatal.

Rejected: tiering all six. Maximum saving, and it puts recall-answering about Moxn and Temporal back on the table hours before the stream.

Acceptance unchanged from the body, plus: mcp.tool.count and the rendered prompt size recorded before and after.

## Decision: demote the long tail, keep the two standing-instruction files inline. **Kai's decision, 2026-08-19, recorded by Saiya (exec seat) during a P0 review.** Keep `inline: always` on **`moxn-knowledge-base.md`** and **`temporal.md`**. The root itself states why, and the correction comment above makes the same point: both carry a standing instruction to reach for them rather than answer from recall. On a Temporal livestream, an agent answering about Temporal from recall instead of the file is the exact failure that instruction exists to prevent. **Tier the other four** onto the disclosure split the shared roots already use: `coilyco-suite.md`, `dowel-provenance.md`, `site-work.md`, `tool-surfaces.md`. That is roughly **13KB off a 24KB inline block**, on a lane whose prefix cost is the surviving explanation of the latency Kai called fatal. **Rejected: tiering all six.** Maximum saving, and it puts recall-answering about Moxn and Temporal back on the table hours before the stream. Acceptance unchanged from the body, plus: `mcp.tool.count` and the rendered prompt size recorded before and after.
coilyco-ops commented 2026-08-19 05:06:06 +00:00
Author
Member
Copy link

Done in 07e4b16 and bcf008d. Measured over the lane's three roots:

inline pack   39,805 -> 27,925 bytes   (-11,880)
fetchable          3 -> 6 references

This issue asked for a deliberate answer to one question per reference. Here it is, with the reasoning recorded on each file rather than only in this thread.

Deferred

  • site-work.md — the root's instruction to read it was already a conditional, and a conditional is what this tier is for. It also carries a second benefit: its ownership language is emphatic on purpose and was sitting in every unrelated turn where it reads as a general instruction not to decline. That is #1049's leak and a contributing pressure in #935.
  • coilyco-suite.md — subject matter with an unambiguous trigger, where the cost of missing it is a vague answer or a bad address rather than a broken boundary.
  • moxn-knowledge-base.md — see below.

Kept inline, departing from this issue on one

dowel-provenance.md and tool-surfaces.md as argued here. temporal.md against the proposal: it is not subject matter. It exists to correct a plausible-but-backwards belief, that Temporal orchestrates the turn, and being wrong about that on Temporal's own livestream is the worst answer available on this lane. A file that prevents a confident wrong answer is a boundary wearing a subject's clothes.

The larger finding, which was not the tiering

Checking whether tool-surfaces.md was still accurate — this issue reports it 12/12 — found that it no longer is. Three deploy commits landed after this issue was filed:

7fd366a 18:37  trim six catalog MCPs from this lane only
7edafb9 19:58  give the lane a read side of its own Temporal namespace
fdf2eaa 21:37  deprovision the Moxn MCP

The roster is now six servers: forgejo, exa, signoz, discord, playwright, temporal. tool-surfaces.md was inline every turn advertising openlibrary, tvmaze, gutendex, gbif, two Steam readers, and moxn, and missing temporal. moxn-knowledge-base.md was 6.5KB of inline write-and-delete doctrine for a deprovisioned server.

Both are fixed in bcf008d. The new Temporal reader is the good news: list_workflows, describe_workflow, and get_workflow_history, read-only over this deployment's own namespace, so the claim that Temporal observes the turn is now checkable in the turn that makes it rather than asserted.

Two things I did not do

I did not delete the stale files. moxn-knowledge-base.md and site-work.md are deferred and now open by saying the surface is not on the roster. The surfaces may return, and deleting somebody's work to fix a staleness problem is the wrong trade.

I did not remove the four dowel-moxn-* boundaries, which now declare rules for a surface the lane cannot reach. They stay declared because the alternative is deleting an eval for a capability that may come back, and I trimmed then restored the two sections they cite by anchor so boundaries-check passes honestly rather than being satisfied by deletion. #1019 should record four of its twenty-six slots as parked rather than pending.

Untested

The lane runs 434063f1 and has not rolled to any of this, so nothing here is verified against live behaviour. The risk the tiering introduces is precisely that a deferred file is not fetched, and confirming it means asking about the site and about Kai's projects after the roll.

Refs #927, #968, #1049, #935, #1011, #1019

**Done in `07e4b16` and `bcf008d`.** Measured over the lane's three roots: ``` inline pack 39,805 -> 27,925 bytes (-11,880) fetchable 3 -> 6 references ``` This issue asked for a deliberate answer to one question per reference. Here it is, with the reasoning recorded on each file rather than only in this thread. ## Deferred * **`site-work.md`** — the root's instruction to read it was already a conditional, and a conditional is what this tier is for. It also carries a second benefit: its ownership language is emphatic on purpose and was sitting in every unrelated turn where it reads as a general instruction not to decline. That is #1049's leak and a contributing pressure in #935. * **`coilyco-suite.md`** — subject matter with an unambiguous trigger, where the cost of missing it is a vague answer or a bad address rather than a broken boundary. * **`moxn-knowledge-base.md`** — see below. ## Kept inline, departing from this issue on one `dowel-provenance.md` and `tool-surfaces.md` as argued here. `temporal.md` **against** the proposal: it is not subject matter. It exists to correct a plausible-but-backwards belief, that Temporal orchestrates the turn, and being wrong about that on Temporal's own livestream is the worst answer available on this lane. A file that prevents a confident wrong answer is a boundary wearing a subject's clothes. ## The larger finding, which was not the tiering Checking whether `tool-surfaces.md` was still accurate — this issue reports it 12/12 — found that **it no longer is.** Three deploy commits landed after this issue was filed: ``` 7fd366a 18:37 trim six catalog MCPs from this lane only 7edafb9 19:58 give the lane a read side of its own Temporal namespace fdf2eaa 21:37 deprovision the Moxn MCP ``` The roster is now **six servers**: forgejo, exa, signoz, discord, playwright, temporal. `tool-surfaces.md` was inline every turn advertising openlibrary, tvmaze, gutendex, gbif, two Steam readers, and moxn, and missing temporal. `moxn-knowledge-base.md` was 6.5KB of inline write-and-delete doctrine for a deprovisioned server. Both are fixed in `bcf008d`. The new Temporal reader is the good news: `list_workflows`, `describe_workflow`, and `get_workflow_history`, read-only over this deployment's own namespace, so the claim that Temporal observes the turn is now **checkable in the turn that makes it** rather than asserted. ## Two things I did not do **I did not delete the stale files.** `moxn-knowledge-base.md` and `site-work.md` are deferred and now open by saying the surface is not on the roster. The surfaces may return, and deleting somebody's work to fix a staleness problem is the wrong trade. **I did not remove the four `dowel-moxn-*` boundaries**, which now declare rules for a surface the lane cannot reach. They stay declared because the alternative is deleting an eval for a capability that may come back, and I trimmed then restored the two sections they cite by anchor so `boundaries-check` passes honestly rather than being satisfied by deletion. **#1019 should record four of its twenty-six slots as parked rather than pending.** ## Untested The lane runs `434063f1` and has not rolled to any of this, so nothing here is verified against live behaviour. The risk the tiering introduces is precisely that a deferred file is not fetched, and confirming it means asking about the site and about Kai's projects after the roll. Refs #927, #968, #1049, #935, #1011, #1019
coilyco-ops commented 2026-08-22 20:42:17 +00:00
Author
Member
Copy link

Closing as delivered with the August 19 demo readiness epic (#981).

The finding survives in #1094: the skill root opts out of progressive disclosure entirely, inlining all six references at 24 KB every turn, which compounds directly into the prefix cost measured in #1002.

Decision recorded in coilysiren/inbox#391.

Closing as delivered with the August 19 demo readiness epic (#981). The finding survives in #1094: the skill root opts out of progressive disclosure entirely, inlining all six references at 24 KB every turn, which compounds directly into the prefix cost measured in #1002. Decision recorded in coilysiren/inbox#391.
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
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
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#993
No description provided.