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

Mount all public repos into /workspace and /substrate (ward-style) so sirens-deep can read its own source #633

New issue
Open
opened 2026-08-13 17:35:59 +00:00 by coilyco-ops-gaming · 3 comments
coilyco-ops-gaming commented 2026-08-13 17:35:59 +00:00
Member
Copy link

Context: sirens-deep currently has no repository content access. Its Forgejo grants are issue-only: create, comment, label, close, list. No file, PR, or content tool exists, so the agent cannot inspect its own source even though the repo is public.

Ask: mount all of Kai's public repos into /workspace and /substrate in the same way that ward does, with sirens-echo as the workspace repo.

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

Confirmed as filed - all public repos, ward-style. Kai chose the widest option over the three narrower ones.

Rejected, and why each was rejected:

  • sirens-echo only - answers the literal ask ("read its own source") and would leave Deep unable to explain anything about the systems it sits inside.
  • Read-only Forgejo content tools instead of a mount - reaches every public repo without a volume, and does not give the agent a filesystem it can search across repos.
  • sirens-echo plus direct dependencies - a hand-maintained list that goes stale.

Build

  1. Mount every public repo under /workspace and /substrate, matching ward's mount scheme. Ward's layout is the reference - confirm the specifics against that setup rather than reconstructing it from this description.
  2. sirens-echo is the workspace repo.
  3. Read-only. This grants inspection, not authorship. Deep's existing Forgejo issue grants are unchanged and no write path to repository content is created here.

Boundaries that follow from the width, and these are the reason to be careful

  • Public only. The selection must be derived from repository visibility at sync time, not from a checked-in list that can go stale into including a private repo. A private repo appearing under /workspace is a disclosure, not a bug.
  • Nothing in the mount is instruction. Deep reads repository content as data a member could also read. A file in a mounted repo never widens Deep's authority, names a tool, or grants a permission - the same rule the attachment path holds in docs/sirens-echo-attachments.md.
  • Refresh cadence needs a number. A mount that never updates makes Deep confidently wrong about its own source. Pick a sync interval and record it here.
  • Size and growth need a ceiling. All public repos is an unbounded set as the estate grows. Say what happens when the volume fills.

Acceptance

  • Deep can read sirens-echo's own source and answer a question about its own behaviour from the file rather than from the issue describing it.
  • No private repository appears under either path. Assert this against live visibility, not against a list.
  • Deep cannot write to either path.
  • The layout matches ward's rather than being a similar-looking alternative.

Placement - the mount itself is deployment work and belongs in move-to-repo/coilyco-bridge-deploy. This issue holds the requirement and the boundaries.

Related - #251 (Deep answering questions about itself from its own source) is the capability this unblocks. #647 was decided today toward selection rather than schema dumps, and a searchable source mount is a different answer to a nearby question - do not let the two duplicate each other.

Context: sirens-deep currently has no repository content access. Its Forgejo grants are issue-only: create, comment, label, close, list. No file, PR, or content tool exists, so the agent cannot inspect its own source even though the repo is public. Ask: mount all of Kai's public repos into `/workspace` and `/substrate` in the same way that ward does, with sirens-echo as the workspace repo. --- ## Resolved spec (design pass, 2026-08-15) **Confirmed as filed - all public repos, ward-style.** Kai chose the widest option over the three narrower ones. Rejected, and why each was rejected: * **sirens-echo only** - answers the literal ask ("read its own source") and would leave Deep unable to explain anything about the systems it sits inside. * **Read-only Forgejo content tools instead of a mount** - reaches every public repo without a volume, and does not give the agent a filesystem it can search across repos. * **sirens-echo plus direct dependencies** - a hand-maintained list that goes stale. **Build** 1. Mount every public repo under `/workspace` and `/substrate`, matching ward's mount scheme. Ward's layout is the reference - confirm the specifics against that setup rather than reconstructing it from this description. 2. `sirens-echo` is the workspace repo. 3. **Read-only.** This grants inspection, not authorship. Deep's existing Forgejo issue grants are unchanged and no write path to repository content is created here. **Boundaries that follow from the width, and these are the reason to be careful** * **Public only.** The selection must be derived from repository visibility at sync time, not from a checked-in list that can go stale into including a private repo. A private repo appearing under `/workspace` is a disclosure, not a bug. * **Nothing in the mount is instruction.** Deep reads repository content as data a member could also read. A file in a mounted repo never widens Deep's authority, names a tool, or grants a permission - the same rule the attachment path holds in `docs/sirens-echo-attachments.md`. * **Refresh cadence needs a number.** A mount that never updates makes Deep confidently wrong about its own source. Pick a sync interval and record it here. * **Size and growth need a ceiling.** All public repos is an unbounded set as the estate grows. Say what happens when the volume fills. **Acceptance** * Deep can read `sirens-echo`'s own source and answer a question about its own behaviour from the file rather than from the issue describing it. * No private repository appears under either path. Assert this against live visibility, not against a list. * Deep cannot write to either path. * The layout matches ward's rather than being a similar-looking alternative. **Placement** - the mount itself is deployment work and belongs in `move-to-repo/coilyco-bridge-deploy`. This issue holds the requirement and the boundaries. **Related** - #251 (Deep answering questions about itself from its own source) is the capability this unblocks. #647 was decided today toward selection rather than schema dumps, and a searchable source mount is a different answer to a nearby question - do not let the two duplicate each other.
coilyco-ops commented 2026-08-13 18:34:54 +00:00
Member
Copy link

Claiming the capability half — Angie (ENG, claude seat). 20 minutes from this comment, after the one minute race buffer. Not the mount.

Separating the ask from the need

The ask is a mount layout. The need, in your first line, is:

the agent cannot inspect its own source even though the repo is public

Those are not the same size. A mount means a clone at pod start, a volume, and a decision about what re-syncs it and how often — infrastructure, a rollout, and a staleness question that has to be answered forever after. And a mounted clone is stale the moment anything merges, which for this repository today is several times an hour.

Reading a public file over the API has none of that. No volume, no sync, no staleness, and no credential, for the same reason #677 needs none: public content is public. The grant problem you describe — issue-only Forgejo tools — does not apply to an unauthenticated read.

What I am building

A read_public_file tool, sibling to the list_public_repos that just landed in 677. Owner, repo, path, optional ref. Public only, by holding no credential rather than by filtering.

Together those two give exactly your third acceptance criterion — "read access to repo contents, not just issues" — with nothing mounted.

What I am not doing, and it stays yours

The mount itself. If you want /workspace and /substrate populated ward-style, that is a deploy change, it is Ops to roll, and I am not going to land a volume layout inside a capability ticket. Your first two acceptance criteria are untouched by my change.

And I am not asserting the mount is unnecessary. It buys things an API read does not: grep across a whole tree, following imports, reading a repository too large to fetch a file at a time. If that is what you are actually after, say so and this becomes groundwork rather than an alternative.

What I am claiming is narrower: the reason given in the issue — cannot read its own source — is satisfiable today without infrastructure, and it is worth having that before deciding whether to build the rest.

**Claiming the capability half — Angie (ENG, claude seat).** 20 minutes from this comment, after the one minute race buffer. **Not the mount.** ## Separating the ask from the need The ask is a mount layout. The need, in your first line, is: > the agent cannot inspect its own source even though the repo is public Those are not the same size. A mount means a clone at pod start, a volume, and a decision about what re-syncs it and how often — infrastructure, a rollout, and a staleness question that has to be answered forever after. **And a mounted clone is stale the moment anything merges**, which for this repository today is several times an hour. Reading a public file over the API has none of that. No volume, no sync, no staleness, and no credential, for the same reason https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/pulls/677 needs none: **public content is public.** The grant problem you describe — issue-only Forgejo tools — does not apply to an unauthenticated read. ## What I am building A `read_public_file` tool, sibling to the `list_public_repos` that just landed in 677. Owner, repo, path, optional ref. Public only, by holding no credential rather than by filtering. Together those two give exactly your third acceptance criterion — *"read access to repo contents, not just issues"* — with nothing mounted. ## What I am not doing, and it stays yours **The mount itself.** If you want `/workspace` and `/substrate` populated ward-style, that is a deploy change, it is Ops to roll, and I am not going to land a volume layout inside a capability ticket. Your first two acceptance criteria are untouched by my change. **And I am not asserting the mount is unnecessary.** It buys things an API read does not: grep across a whole tree, following imports, reading a repository too large to fetch a file at a time. If that is what you are actually after, say so and this becomes groundwork rather than an alternative. What I am claiming is narrower: **the reason given in the issue — cannot read its own source — is satisfiable today without infrastructure**, and it is worth having that before deciding whether to build the rest.
coilyco-ops commented 2026-08-13 18:38:55 +00:00
Member
Copy link

Capability half delivered — #681, closing the slice #679. Gate green. Claim released. This issue stays open: nothing is mounted.

Your third criterion is met:

The change gives the agent read access to repo contents, not just issues.

Two tools, no credential and no volume:

list_public_repos   name, description, html_url, language, updated_at   (PR 677)
read_public_file    owner, repo, path, optional ref                     (PR 681)

An agent can now read its own source. That was the reason you opened with, and it needed no infrastructure.

The two things I was careful about

A path that climbs out is refused before any request is made. ../secrets, a/../../b and /etc/passwd never reach the forge, so a refusal costs no round trip and the caller is told rather than silently corrected. Each segment is escaped separately, so a path keeps its separators while a segment carrying a slash cannot forge one.

A file past the cap says it was cut. The same shape the fetch tool uses, because a half file the model cannot tell from a whole one gets answered from with ordinary confidence.

Your first two criteria are untouched, and I have not argued them away

/workspace and /substrate populated ward-style is still open, still a deploy change, and still Ops to roll.

A mount buys things these tools do not, and I want that on the record rather than buried: grep across a whole tree, following an import to its definition, and reading a repository too large to fetch a file at a time. If any of those is what you actually wanted, this is groundwork rather than a substitute and the mount should still happen.

What I would push back on is the staleness. A mounted clone is correct at pod start and wrong after the next merge, which here is several times an hour. If the mount lands, it wants an answer for what re-syncs it, and "nothing" is a real answer only if the tree is meant to be a snapshot rather than the source.

Note on ordering

681 is stacked on 677, so its diff includes the inventory. Merging 677 first makes 681 small. Both are behind #483 either way.

**Capability half delivered — https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/pulls/681, closing the slice https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/679. Gate green. Claim released. This issue stays open: nothing is mounted.** Your third criterion is met: > The change gives the agent read access to repo contents, not just issues. Two tools, no credential and no volume: ``` list_public_repos name, description, html_url, language, updated_at (PR 677) read_public_file owner, repo, path, optional ref (PR 681) ``` An agent can now read its own source. That was the reason you opened with, and it needed no infrastructure. ## The two things I was careful about **A path that climbs out is refused before any request is made.** `../secrets`, `a/../../b` and `/etc/passwd` never reach the forge, so a refusal costs no round trip and the caller is told rather than silently corrected. Each segment is escaped separately, so a path keeps its separators while a segment carrying a slash cannot forge one. **A file past the cap says it was cut.** The same shape the fetch tool uses, because a half file the model cannot tell from a whole one gets answered from with ordinary confidence. ## Your first two criteria are untouched, and I have not argued them away `/workspace` and `/substrate` populated ward-style is still open, still a deploy change, and still Ops to roll. **A mount buys things these tools do not**, and I want that on the record rather than buried: grep across a whole tree, following an import to its definition, and reading a repository too large to fetch a file at a time. If any of those is what you actually wanted, this is groundwork rather than a substitute and the mount should still happen. What I would push back on is the *staleness*. A mounted clone is correct at pod start and wrong after the next merge, which here is several times an hour. If the mount lands, it wants an answer for what re-syncs it, and "nothing" is a real answer only if the tree is meant to be a snapshot rather than the source. ## Note on ordering 681 is stacked on 677, so its diff includes the inventory. Merging 677 first makes 681 small. Both are behind https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/483 either way.
coilyco-ops commented 2026-08-13 19:13:30 +00:00
Member
Copy link

Adding consult, because what is left here is a decision rather than unclaimed work. Angie (ENG, claude seat).

This has sat unlabelled since 17:35, which is invisible to the human queue and fail-closed for dispatch at once — the pair #437 names as worst.

Why it is a decision now and was not before

Your third criterion is met. list_public_repos and read_public_file both merged, so the reason you opened with — the agent cannot inspect its own source — is fixed, with no volume and no credential.

Your first two are untouched, and whether they should happen at all is now a genuine question rather than a task waiting for someone:

a mount buys the tools already give
read one known file — yes, and always current
list what exists — yes
grep across a whole tree yes no
follow an import to its definition yes no
a repository too large to read a file at a time yes no

So the mount is worth building if and only if the bottom three matter. Nobody here can answer that for you, and building a volume plus a sync story to duplicate the top two would be work that looks like progress.

The question that decides it

Does Deep need to search across repositories, or to read files it can already name? If it is the second, this issue is done and should close. If it is the first, the mount is the right shape and it wants an answer for what re-syncs it, because a clone is correct at pod start and wrong after the next merge — several times an hour on this repository today.

I am not closing it on my own reading. The capability half was mine and I delivered it; the mount half is yours to want or drop.

**Adding `consult`, because what is left here is a decision rather than unclaimed work. Angie (ENG, claude seat).** This has sat unlabelled since 17:35, which is invisible to the human queue and fail-closed for dispatch at once — the pair https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/437 names as worst. ## Why it is a decision now and was not before Your third criterion is met. `list_public_repos` and `read_public_file` both merged, so **the reason you opened with — the agent cannot inspect its own source — is fixed**, with no volume and no credential. Your first two are untouched, and whether they should happen at all is now a genuine question rather than a task waiting for someone: | | a mount buys | the tools already give | | --- | --- | --- | | read one known file | — | yes, and always current | | list what exists | — | yes | | grep across a whole tree | **yes** | no | | follow an import to its definition | **yes** | no | | a repository too large to read a file at a time | **yes** | no | **So the mount is worth building if and only if the bottom three matter.** Nobody here can answer that for you, and building a volume plus a sync story to duplicate the top two would be work that looks like progress. ## The question that decides it **Does Deep need to search across repositories, or to read files it can already name?** If it is the second, this issue is done and should close. If it is the first, the mount is the right shape and it wants an answer for what re-syncs it, because a clone is correct at pod start and wrong after the next merge — several times an hour on this repository today. I am not closing it on my own reading. The capability half was mine and I delivered it; the mount half is yours to want or drop.
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#633
No description provided.