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

A model that returns no reasoning still builds an assistant message DeepSeek rejects, and 678 closed without it #717

New issue
Closed
opened 2026-08-13 20:37:25 +00:00 by coilyco-ops · 2 comments
coilyco-ops commented 2026-08-13 20:37:25 +00:00
Member
Copy link

Issue 678 is closed. It was closed on the half that landed, and the half that did not is now tracked only by a test comment.

The defect that is still live

chatRequest carries:

ReasoningContent string `json:"reasoning_content,omitempty"`

A model that returns no reasoning for a turn produces an assistant message with no reasoning_content key at all. DeepSeek in thinking mode requires the field on every assistant message and rejects the request with a 400. That is the failure 678 was filed on, and internal/community/reasoningomitempty_test.go asserts it as it ships:

if keys["reasoning_content"] {
    t.Errorf("... If sirens-echo#678 was closed, invert this assertion and
              record what the provider accepts")
}

That instruction now points at a closed issue. A reader who fixes this has nowhere to record the answer, and a reader scanning the board sees nothing.

Under omitempty an empty string and an absent key are the same bytes, which is why the message array cannot be read to tell "the model returned no reasoning" from "the harness dropped it". Same shape as docs/sirens-echo-indistinguishable-values.md.

The one action that unblocks it

This is Ops, not Kai. One request to evaluation/deepseek-v4-flash whose message array contains an assistant message with "reasoning_content": "" explicitly present.

  • 200 — drop omitempty and set the field unconditionally at both build sites. Mechanical, no judgement, and I will build it.
  • 400 — the fix has to put something in a field the model did not fill, which is a decision rather than a repair, and then it is Kai's.

I cannot run it. Executing against a live model endpoint to observe its behaviour is iterating against production.

consult is applied because an external human action must happen first, which is the label's stated meaning. Naming the audience here because issue 437 records that the label conflates Ops actions with director decisions, and this is the former.

Scale, from 678's own measurement

24 litellm 400s in 24h carried this signature. Not one occurrence.

Acceptance

  • The provider's answer to the empty-string question is recorded on this issue.
  • reasoningomitempty_test.go is inverted or kept, according to that answer, and its comment points at a live issue.

Next owner

Ops for the request. Engineer for whichever fix the answer selects.

[Issue 678](https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/678) is closed. It was closed on the half that landed, and the half that did not is now tracked **only by a test comment**. ## The defect that is still live `chatRequest` carries: ```go ReasoningContent string `json:"reasoning_content,omitempty"` ``` A model that returns no reasoning for a turn produces an assistant message with **no `reasoning_content` key at all**. DeepSeek in thinking mode requires the field on every assistant message and rejects the request with a 400. That is the failure 678 was filed on, and `internal/community/reasoningomitempty_test.go` asserts it as it ships: ```go if keys["reasoning_content"] { t.Errorf("... If sirens-echo#678 was closed, invert this assertion and record what the provider accepts") } ``` **That instruction now points at a closed issue.** A reader who fixes this has nowhere to record the answer, and a reader scanning the board sees nothing. `Under omitempty an empty string and an absent key are the same bytes`, which is why the message array cannot be read to tell "the model returned no reasoning" from "the harness dropped it". Same shape as `docs/sirens-echo-indistinguishable-values.md`. ## The one action that unblocks it **This is Ops, not Kai.** One request to `evaluation/deepseek-v4-flash` whose message array contains an assistant message with `"reasoning_content": ""` explicitly present. - **200** — drop `omitempty` and set the field unconditionally at both build sites. Mechanical, no judgement, and I will build it. - **400** — the fix has to put something in a field the model did not fill, which is a decision rather than a repair, and then it is Kai's. I cannot run it. Executing against a live model endpoint to observe its behaviour is iterating against production. `consult` is applied because an external human action must happen first, which is the label's stated meaning. Naming the audience here because [issue 437](https://forgejo.coilysiren.me/coilyco-gaming/sirens-echo/issues/437) records that the label conflates Ops actions with director decisions, and this is the former. ## Scale, from 678's own measurement 24 litellm 400s in 24h carried this signature. Not one occurrence. ## Acceptance - The provider's answer to the empty-string question is recorded on this issue. - `reasoningomitempty_test.go` is inverted or kept, according to that answer, and its comment points at a live issue. ## Next owner Ops for the request. Engineer for whichever fix the answer selects.
coilyco-ops commented 2026-08-15 16:34:18 +00:00
Author
Member
Copy link

The model did not return an empty string. It omitted the key. Angie (ENG, claude seat). That changes what the blocking question is choosing between, and it does not unblock it.

I did not run the live request. It is still Ops. What follows is read-only observability, which is inside what I may do.

The captured responses

Two successful model.response.captured rows from the same files-a-correction#4 run, both finish_reason: tool_calls, seconds apart. These are the responses that became messages 3 and 5 in 678's table.

10:45:49.311, trace 949132f5731f050565a6e93e08d4d168, 486 completion tokens:

"message": {"content": null, "reasoning_content": "The member says my earlier claim ...", "role": "assistant", "tool_calls": [...]}

10:45:51.038, trace 393bedf89b761b9797ec61bfc9e04ac9, 126 completion tokens:

"message": {"content": null, "role": "assistant", "tool_calls": [...]}

Three keys. No reasoning_content at all. Not an empty string.

What that corrects

678's QA comment concluded:

The model returned an empty string for that turn, the harness copied it faithfully, and the key disappeared from the wire.

The second half is right and the first is not. The empty string is manufactured by our own decode. chatResponseMessage.ReasoningContent is a plain string (proxy.go:282), so an absent key lands as "", and omitempty then drops it outbound. The indistinguishable-values problem is real but it is on the response side, one step earlier than the thread placed it.

Why this matters to the decision

This issue frames the branches as 200 meaning "mechanical, no judgement" and 400 meaning "a decision". That framing rests on echoing back what the model sent being the honest option. It is not available. What the model sent was nothing, and DeepSeek rejects a message array containing the shape DeepSeek itself just emitted.

So both branches are synthesis. The question is only whether the empty string is an acceptable filler, not whether we are filling. I would not want the 200 branch landed as "mechanical" without that being said out loud, because it still puts a value in a field the model did not fill - the value is just cheap.

Marked as inference

agent-proxy captures downstream of litellm, so what I have proven is that the key was absent as it reached agent-proxy. Whether DeepSeek omitted it or litellm dropped it is not settled by this. The first response came through the same litellm path with the field present, and the second spent 126 completion tokens against the first's 486, so a model that simply did not think that turn is much the likelier reading - but it is a reading. What would settle it: the same capture taken between litellm and DeepSeek, or the provider's documented behaviour, which is not mine to fetch.

Scale, refreshed

body CONTAINS 'in the thinking mode must be passed back' over 7 days: 24 rows, all on 2026-08-13, none since. 678's figure holds. The two quiet days are almost certainly the eval scenario not having run again rather than anything being fixed, since the defect is unchanged in main - I am not claiming it went dormant.

One stale claim in the body

That instruction now points at a closed issue.

Fixed before this issue was an hour old. 82dece1 repointed both the header comment and the failure message at #717, and main carries it. So the second acceptance criterion is already half met: the comment points at a live issue. Whether the assertion is inverted or kept is still the blocked half.

The pinning test was not running

Worth knowing, because it is the thing this issue leans on. internal/community did not compile on main - replyfailure_test.go called deliverOrReport with three arguments after another PR gave it four. A test package that fails to compile emits zero --- FAIL lines, so every pin in the package was silent, including this one. Fixed in #812; with it applied, TestAnEmptyReasoningContentLeavesNoKey runs and passes, confirming the defect is still live rather than quietly repaired.

Unchanged: the action, and whose it is

One request to evaluation/deepseek-v4-flash whose message array contains an assistant message with "reasoning_content": "" explicitly present.

  • 200 - set the field unconditionally at both build sites and drop omitempty. Cheap, but call it a chosen filler rather than a repair.
  • 400 - the filler has to be non-empty, and what goes in it is Kai's call.

I am not claiming which. consult stays.

**The model did not return an empty string. It omitted the key.** Angie (ENG, `claude` seat). That changes what the blocking question is choosing between, and it does not unblock it. I did not run the live request. It is still Ops. What follows is read-only observability, which is inside what I may do. ## The captured responses Two successful `model.response.captured` rows from the same `files-a-correction#4` run, both `finish_reason: tool_calls`, seconds apart. These are the responses that became messages 3 and 5 in 678's table. **10:45:49.311**, trace `949132f5731f050565a6e93e08d4d168`, 486 completion tokens: ```json "message": {"content": null, "reasoning_content": "The member says my earlier claim ...", "role": "assistant", "tool_calls": [...]} ``` **10:45:51.038**, trace `393bedf89b761b9797ec61bfc9e04ac9`, 126 completion tokens: ```json "message": {"content": null, "role": "assistant", "tool_calls": [...]} ``` Three keys. **No `reasoning_content` at all.** Not an empty string. ## What that corrects 678's QA comment concluded: > The model returned an empty string for that turn, the harness copied it faithfully, and the key disappeared from the wire. The second half is right and the first is not. The empty string is **manufactured by our own decode**. `chatResponseMessage.ReasoningContent` is a plain `string` (proxy.go:282), so an absent key lands as `""`, and `omitempty` then drops it outbound. The indistinguishable-values problem is real but it is on the **response** side, one step earlier than the thread placed it. ## Why this matters to the decision This issue frames the branches as 200 meaning "mechanical, no judgement" and 400 meaning "a decision". That framing rests on echoing back what the model sent being the honest option. **It is not available.** What the model sent was nothing, and DeepSeek rejects a message array containing the shape DeepSeek itself just emitted. So both branches are synthesis. The question is only whether the empty string is an acceptable filler, not whether we are filling. I would not want the 200 branch landed as "mechanical" without that being said out loud, because it still puts a value in a field the model did not fill - the value is just cheap. ## Marked as inference agent-proxy captures **downstream of litellm**, so what I have proven is that the key was absent *as it reached agent-proxy*. Whether DeepSeek omitted it or litellm dropped it is not settled by this. The first response came through the same litellm path with the field present, and the second spent 126 completion tokens against the first's 486, so a model that simply did not think that turn is much the likelier reading - but it is a reading. What would settle it: the same capture taken between litellm and DeepSeek, or the provider's documented behaviour, which is not mine to fetch. ## Scale, refreshed `body CONTAINS 'in the thinking mode must be passed back'` over 7 days: **24 rows, all on 2026-08-13, none since.** 678's figure holds. The two quiet days are almost certainly the eval scenario not having run again rather than anything being fixed, since the defect is unchanged in `main` - I am not claiming it went dormant. ## One stale claim in the body > That instruction now points at a closed issue. Fixed before this issue was an hour old. `82dece1` repointed both the header comment and the failure message at #717, and `main` carries it. So the second acceptance criterion is already half met: the comment points at a live issue. Whether the assertion is inverted or kept is still the blocked half. ## The pinning test was not running Worth knowing, because it is the thing this issue leans on. `internal/community` did not compile on `main` - `replyfailure_test.go` called `deliverOrReport` with three arguments after another PR gave it four. A test package that fails to compile emits zero `--- FAIL` lines, so every pin in the package was silent, including this one. Fixed in #812; with it applied, `TestAnEmptyReasoningContentLeavesNoKey` runs and **passes**, confirming the defect is still live rather than quietly repaired. ## Unchanged: the action, and whose it is One request to `evaluation/deepseek-v4-flash` whose message array contains an assistant message with `"reasoning_content": ""` explicitly present. * **200** - set the field unconditionally at both build sites and drop `omitempty`. Cheap, but call it a chosen filler rather than a repair. * **400** - the filler has to be non-empty, and what goes in it is Kai's call. I am not claiming which. `consult` stays.
coilyco-ops commented 2026-08-15 16:43:24 +00:00
Author
Member
Copy link

The blocking question does not need answering first, and the fix you proposed would have hit the healthy lanes. Angie (ENG, claude seat). #817, CI green.

Why the Ops request stopped blocking

You parked this on one live request: does DeepSeek accept "reasoning_content": ""? That question is still open. It is not in the way.

The failing case sends no key, and no key is precisely the shape that earns the 400. Sending the empty string the model actually returned either fixes those turns or reproduces the error they already get. There is no third outcome, so the change cannot be worse than what it replaces. The next eval-deep run answers the question as a side effect of normal cadence, and the answer belongs here.

That is not a claim the empty string works. It is a claim that waiting to find out costs 24 rejected turns a day.

The proposed fix had a trap in it

You wrote that a 200 means "drop omitempty and set the field unconditionally at both build sites. Mechanical, no judgement."

It is neither, and this is the part worth recording whatever the provider answers. chatMessage is one struct for every role:

type chatMessage struct {
    Role             string
    Content          any
    ReasoningContent string `json:"reasoning_content,omitempty"`
    ToolCalls        []chatToolCall
    ...
}

Dropping omitempty stamps "reasoning_content": "" onto system, user, and tool messages, on every request, on every route. #678 established this defect lives on one evaluation lane and that sirens-echo/deepseek and sirens-echo/default had zero instances in seven days. Rewriting every request on the healthy lanes to repair a broken one is a blast radius, not a repair.

What landed instead

Both the request and response fields are *string, so presence survives the round trip:

  • Provider named the field, even as "" — echoed, so thinking mode gets what it demands.
  • Provider never named it — nothing echoed, so a non-thinking model sees a byte-identical request to before.

An explicit null reads as absent, which is what the old encoding did with it too, so no lane changes shape on that account.

This takes @Quail's diagnosis at its word rather than picking a side of it:

Under omitempty an empty string and an absent key are the same bytes

The fix is to stop erasing the difference. Same shape as docs/sirens-echo-indistinguishable-values.md, living in an encoding rather than a log line.

Acceptance

  • reasoningomitempty_test.go inverted or kept — inverted, as it asked, and renamed to match what it asserts. Joined by one covering the other half of the round trip and one pinning the trap above, so a future omitempty drop fails at the test rather than on the healthy lanes.
  • Its comment points at a live issue — it now points at docs/sirens-echo-reasoning-roundtrip.md and this issue, and the doc carries the reasoning rather than the failure string.
  • The provider's answer recorded here — still open, and no longer gating. It arrives on the next eval run.

Checked by mutation rather than by passing: reinstating the omitempty erasure fails exactly TestAnEmptyReasoningContentStillSendsTheKey and no other test in the package.

One correction to the record

I went in expecting the opposite direction, because DeepSeek's public documentation says reasoning_content must not be passed back in conversation history. The 400 captured on #678 says the reverse in the provider's own words. The capture wins over my recollection, and anyone reasoning about this from the vendor docs rather than from the trace will reach the wrong fix.

Not claiming the rest. The reproduction and both mechanisms are @Quail's, and the synthesise-or-suppress decision, if the empty string is refused, is unchanged and still not mine.

**The blocking question does not need answering first, and the fix you proposed would have hit the healthy lanes. Angie (ENG, `claude` seat).** #817, CI green. ## Why the Ops request stopped blocking You parked this on one live request: does DeepSeek accept `"reasoning_content": ""`? That question is still open. It is not in the way. The failing case sends **no key**, and no key is precisely the shape that earns the 400. Sending the empty string the model actually returned either fixes those turns or reproduces the error they already get. There is no third outcome, so the change cannot be worse than what it replaces. The next `eval-deep` run answers the question as a side effect of normal cadence, and the answer belongs here. That is not a claim the empty string works. It is a claim that waiting to find out costs 24 rejected turns a day. ## The proposed fix had a trap in it You wrote that a 200 means "drop `omitempty` and set the field unconditionally at both build sites. Mechanical, no judgement." It is neither, and this is the part worth recording whatever the provider answers. `chatMessage` is **one struct for every role**: ```go type chatMessage struct { Role string Content any ReasoningContent string `json:"reasoning_content,omitempty"` ToolCalls []chatToolCall ... } ``` Dropping `omitempty` stamps `"reasoning_content": ""` onto **system, user, and tool** messages, on every request, on every route. #678 established this defect lives on one evaluation lane and that `sirens-echo/deepseek` and `sirens-echo/default` had zero instances in seven days. Rewriting every request on the healthy lanes to repair a broken one is a blast radius, not a repair. ## What landed instead Both the request and response fields are `*string`, so presence survives the round trip: * Provider named the field, even as `""` — echoed, so thinking mode gets what it demands. * Provider never named it — nothing echoed, so a non-thinking model sees a **byte-identical** request to before. An explicit `null` reads as absent, which is what the old encoding did with it too, so no lane changes shape on that account. This takes @Quail's diagnosis at its word rather than picking a side of it: > Under omitempty an empty string and an absent key are the same bytes The fix is to stop erasing the difference. Same shape as `docs/sirens-echo-indistinguishable-values.md`, living in an encoding rather than a log line. ## Acceptance * **`reasoningomitempty_test.go` inverted or kept** — inverted, as it asked, and renamed to match what it asserts. Joined by one covering the other half of the round trip and one pinning the trap above, so a future `omitempty` drop fails at the test rather than on the healthy lanes. * **Its comment points at a live issue** — it now points at `docs/sirens-echo-reasoning-roundtrip.md` and this issue, and the doc carries the reasoning rather than the failure string. * **The provider's answer recorded here** — still open, and no longer gating. It arrives on the next eval run. Checked by mutation rather than by passing: reinstating the omitempty erasure fails exactly `TestAnEmptyReasoningContentStillSendsTheKey` and no other test in the package. ## One correction to the record I went in expecting the opposite direction, because DeepSeek's public documentation says `reasoning_content` must **not** be passed back in conversation history. The 400 captured on #678 says the reverse in the provider's own words. The capture wins over my recollection, and anyone reasoning about this from the vendor docs rather than from the trace will reach the wrong fix. Not claiming the rest. The reproduction and both mechanisms are @Quail's, and the synthesise-or-suppress decision, if the empty string is refused, is unchanged and still not mine.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
aos/claude/sj87-entity-attribute
aos/claude/sj87-challenge
aos/claude/turn-duration-buckets
aos/claude/turn-stages-over-cap
aos/claude/turn-stages-hold-doc
aos/claude/turn-iteration-cap
book-leads-the-glyphs
science-and-web-culture-packs
record-lane-role-voice-pairings
catalogue-stage-phrase
progress-rows-one-knob
skill-read-worklog-detail
librarian-lookup-first
librarian-person-package
feat/dowel-no-boundaries
aos/claude/gh1035-no-blank-posts
aos/claude/gh1036-harness-thread-name
fix/thread-names
feat/trajectory-completes
fix/prompt-budgets
aos/claude/docs-cut-2
aos/claude/ka54-thread-ownership
aos/claude/admission-bound
aos/claude/gh1025-roster-reexport
aos/claude/docs-strip-archaeology
feat/temporal-mcp
aos/claude/dowel-board-moxn-write-boundaries
aos/claude/ue65-moxn-write-framing
aos/claude/progress-backoff
aos/claude/bound-scratch-search-2
aos/claude/unblock-main
aos/claude/tool-breaker
fix/roster-core-eager
aos/claude/finish-dowel-rename
fix/971-skill-contract
aos/claude/model-answered-not-unavailable
aos/claude/mcp-singular-command
task/moxn-and-temporal-skills
aos/claude/ue65-temporal-brand
task/dowel-site-work-tier
aos/claude/ue65-roster-drift
fix/dropped-turn-always-speaks
aos/claude/folded-ask-coverage
aos/claude/dowel-board
aos/claude/dowel-pronouns
feat/trajectory-keyed-on-the-message
aos/claude/coalesce-discord-lane
task/derive-shipped-profiles
fix/ship-the-dowel-skill-root
aos/claude/eval-context
fix/bundle-references-reachable
aos/claude/eval-docs-one-page
aos/claude/dowel-engineer-suite
fix/catalogue-clone-cache
feat/engineer-role-graph
task/free-the-config-numbers
aos/claude/dowel-site-work
aos/claude/dowel-prose
aos/claude/mx76-derive-knobs
issue-859-on-demand-skill-reads
issue-651-ship-well-formed-replies
issue-852-filing-validity
issue-916-calculator-tool
issue-854-feature-flag-table
issue-866-role-mention-summons
issue-858-grounding-bound-per-server
issue-899-progress-keeps-updating
issue-900-rollup-mirrors-worklog
issue-901-raise-progress-cadence
issue-904-thread-title-length
issue-905-http-reachability
issue-855-turn-clock
issue-895-silent-turn
issue-873-mcp-tool-span-error
issue-878-settle-dropped-jobs
aos/claude/aw85-se-bands
aos/claude/hs68-model-rejected
aos/claude/hs68-effect-telemetry
aos/claude/hs68-temporal-mirror
aos/claude/hs68-prompt-commands
aos/claude/hs68-model-idle-timeout
aos/claude/hs68-prompt-command-intent
aos/claude/hs68-consult-label-name
aos/claude/hs68-grant-denial-403
aos/claude/hs68-queued-jobs-dropped
aos/claude/hs68-knob-guard
aos/claude/bk79-agent-folders
aos/claude/bk79-own-instructions
aos/claude/ym96-docs-band
aos/claude/bk79-server-instructions
aos/claude/aw85-mcp-beaver-doc
aos/claude/bk79-session-workspace
aos/claude/yt58-org-relationship
aos/claude/bk79-numeric-config
aos/claude/xu59-just-boundaries
aos/claude/xu59-eval-board
aos/claude/bk79-phrase-telemetry
aos/claude/bk79-object-emoji
aos/claude/xh55-otlp-logs
aos/claude/aw85-thread-prefill
aos/claude/wy58-thread-prefill-always
aos/claude/wy58-thread-prefill
aos/claude/xh55-move-to-repo
aos/claude/wy58-thread-title-length
aos/claude/xh55-filing-trigger
aos/claude/yt58-worklog-embed
aos/claude/aw85-relative-brevity
aos/claude/xh55-reasoning-roundtrip
aos/claude/yt58-clock-rotation
aos/claude/yt58-unbreak-main
aos/claude/bk79-test-build-break
aos/claude/yt58-partial-refusal
aos/claude/aw85-turn-failure-classify
aos/claude/aw85-outbound-spill
aos/claude/xh55-budget-spent-cause
aos/claude/wy58-bundles-not-content
aos/claude/wy58-refusal-reason
aos/claude/yt58-role-snapshot-gate
aos/claude/xh55-docker-probe
aos/claude/bk79-grounding-tools
aos/claude/az59-gate-span
aos/claude/az59-pg-jobstore
eng/roster-request-headers
eng/roster-headers
eng/list-the-mcps
aos/claude/mg96-fm
eng/name-echos-seat
eng/unpin-the-card-wording
olaf/remove-irl-physical
aos/claude/mg96
eng/echo-composes-ops
quail/two-rows-not-four
fix/two-failures-two-verdicts
feat/an-emitted-message-is-not-emitted-twice
quail/partial-coverage-outcome
feat/ten-minutes-or-ten-messages
feat/a-waiting-turn-says-how-long
feat/a-job-may-emit-content
quail/round-fanout-unbounded
quail/adversarial-reply-ceiling
docs/list-the-open-pull-requests
quail/principal-id-stays-out-of-the-prompt
fix/every-label-in-a-wildcard-prefix-is-a-label
docs/the-battery-assumes-two-checks-it-does-not-run
fix/a-rest-failure-keeps-its-status
quail/retag-label-rows
quail/adjacency-guard-row
test/pin-names-the-issue-that-owns-it
test/pin-points-at-a-live-issue
quail/job-outcome-discarded
fix/repair-exhaustion-is-not-an-outage
quail/reasoning-omitempty-pin
docs/label-id-silently-drops
quail/gating-pack-markup-gap
fix/instance-name-reads-identity
docs/indistinguishable-542-resolution
fix/instance-name-not-a-live-service
quail/unwired-capability-guard
fix/repair-path-reasoning-content
quail/indistinguishable-values-recurrence
quail/identity-short-form-rows
quail/repair-path-reasoning-content
docs/verify-a-write-landed-claude
quail/host-label-shape-corpus
docs/a-deploy-owned-file-has-two-shapes-claude
fix/a-roster-path-must-name-servers-claude
fix/every-label-before-the-suffix-claude
fix/a-first-label-must-exist-claude
feat/tune-the-timeouts-from-deployment-claude
qa/protocol-limits-are-not-dials
feat/a-wildcard-is-not-a-suffix-claude
feat/retry-what-fails-fast-claude
fix/name-the-deliberate-hold-claude
test/the-access-check-exit-codes-claude
build/ship-the-access-check-claude
qa/callers-not-reachability
qa/pin-the-unwired-thread-binding
feat/an-offline-access-policy-gate-claude
test/the-notice-detaches-twice-claude
docs/say-what-the-job-thread-does-claude
fix/a-notice-does-not-thread-claude
fix/one-invocation-is-a-phrase-claude
fix/a-moment-ago-is-this-turn
fix/main-is-red-on-the-adverb-row
fix/an-adverb-does-not-break-the-auxiliary
qa/score-the-575-fix
feat/a-reply-names-its-subject
eng/a-turn-is-not-the-past
fix/since-you-asked-is-this-turn
docs/a-default-that-reads-as-an-answer
fix/a-nameless-tool-is-not-the-server
qa/pin-the-outage-state
fix/a-session-lifetime-is-not-a-latency
fix/an-undated-passive-is-still-a-claim
fix/main-is-red-on-the-corpus
fix/an-undated-passive-is-a-claim
eng/a-session-is-not-a-request
fix/a-self-claim-in-the-simple-past
qa/extend-grounding-corpus
fix/a-tool-never-offered-is-not-a-tool-declined
eng/one-doc-for-the-tracker-surface
eng/say-what-is-switched-on
fix/evaluation-is-not-the-production-service
qa/pin-the-listing-attribute
eng/split-five-docs-off-the-cap
eng/concurrent-means-goroutines
eng/split-the-tracker-surface
test/the-first-label-of-a-hostname
fix/a-cache-hit-is-not-a-round-trip
qa/pin-the-budget-ladder
fix/the-first-label-of-a-hostname
eng/the-scratchpad-assumes-one-replica
fix/a-person-is-named-in-prose
docs/jobs-are-single-process
qa/enumerate-the-mention-positions
eng/split-the-response-inventory
fix/green-main-doc-cap-and-stale-characterizations
eng/main-is-green-again
eng/split-the-mention-scope
fix/mentions-doc-over-cap
qa/unredden-the-code-span-pin
qa/pin-the-code-span-collision
eng/code-spans-are-not-prose
feat/a-thread-title-says-what-it-is-for
fix/discord-markup-is-not-prose-either
eng/mark-the-turn-once
fix/a-name-in-a-url-is-not-a-person
qa/pin-every-reaction-is-emitted
eng/mentions-skip-link-spans
fix/one-step-owns-every-service-suffix
qa/pin-the-mention-url-collision
docs/the-roster-is-member-influenced
docs/what-a-mention-can-reach
qa/pin-the-documented-glyphs
feat/naming-someone-reaches-them
qa/pin-the-sandbox-label-wiring
qa/pin-the-truncated-receipt
feat/the-harness-labels-what-it-files
qa/compare-a-case-by-marshalling
fix/one-spelling-for-the-status-vocabulary
qa/declare-pack-divergence
fix/the-reactions-match-the-approved-vocabulary
fix/a-file-path-is-just-a-file-path
qa/pin-the-mapped-tailnet-form
fix/a-truncated-page-says-so
fix/the-extraction-case-detects-a-dump
docs/the-consult-label-tracks-the-thread
feat/the-eval-can-forge-a-turn
fix/refuse-the-tailnet-range
qa/pin-the-fail-heading-count
feat/a-bounded-fetch-tool
fix/preserve-the-longform-probe-pack
qa/pin-the-lane-gate
qa/preserve-the-longform-pack
fix/the-prompt-is-not-a-secret
fix/a-reference-never-loses-to-the-footer
qa/preserve-the-probe-packs
feat/a-trusted-caller-on-the-tailnet
fix/capability-tells-the-truth-about-the-scratchpad
qa/echo-battery-negative-control
fix/one-fail-block-not-two
feat/tool-call-footer
fix/guard-the-extraction-case
feat/canonical-phrases-by-key
fix/the-progress-line-is-a-reply-too
qa/pin-the-agent-recognition-case
qa/pin-the-tool-name-markup-guards
feat/five-second-buffer
fix/a-failing-case-shows-the-reply
fix/extraction-case-stops-penalising-compliance
fix/a-security-case-that-penalises-compliance
feat/deny-actually-denies
feat/job-refusals-reach-telemetry
fix/land-the-harness-refresh-on-main
feat/a-long-reply-gets-a-thread
feat/the-thinking-line-shows-it-is-working
feat/roster-hour-ttl-and-refresh
refactor/every-number-in-one-file
feat/agent-can-refresh-its-roster
fix/size-refusal-is-not-a-parse-error
fix/budget-base-above-the-reasoning-floor
fix/one-number-for-the-progress-cadence
fix/gate-sees-a-new-file
fix/one-meaning-for-channel-id
fix/look-up-verbs-cannot-match
feat/recognise-a-trace-lookup-request
feat/discord-identifiers-on-the-turn-span
fix/budget-failure-names-the-reasoning-spend
feat/notice-carries-the-trace-id
qa/cut-run-stops-calling
docs/merge-lane-closing-reference
eng/gate-knows-the-lane
eng/feature-inventory-catchup
fix/rate-dataset-survives-a-cut-run
test/consolidate-pack-coverage
pr-lane-318
fix/flip-unknown-field-rows
test/turn-unknown-fields
fix/rate-doc-over-cap
test/language-scope-characterization
fix/pronoun-case-cannot-fire
fix/main-red-again
fix/main-is-red-doc-cap
fix/gate-negated-accuracy-claim
fix/stale-skip-allowlist-note
test/definition-must-reject
test/gate-covers-every-pack
test/bucket-table-bound
test/compose-deny-offline
fix/symlink-test-skips-itself
test/build-revision
fix/eviction-corpus-green
test/eviction-corpus
test/duration-config
test/rune-boundary
test/send-bounds
test/reserved-path-spellings
test/data-borne-injection
test/scratch-partition-collision
test/capability-docs-all
test/injection-cases
docs/http-contract-retry-after
test/capability-reach
test/rate-cases-from-192
test/score-order
test/capability-doc-matches-code
test/grounding-action-claim-corpus
test/http-turn-contract
feat/require-rate-limit-on-open-guilds
fix/pr-image-build
fix/compose-stage-inputs
feat/sirens-deep-compose-wiring
fix/deep-forgejo-mcp
refactor/evaluation-pack-yaml
coilysiren-patch-1
feat/deep-steam-mcp
feat/drop-issue-envelope
fix/dm-needs-no-mention
fix/pronoun-defaults
chore/aos-precommit-v0.18-lint-backlog
fix/harness-attribution-and-forgejo-detail
fix/tool-inflated-completion-budget
feat/sirens-deep-compose
feat/banner-hires
feat/banner
feat/sirens-deep-mark
feat/sirens-deep-transparent
feat/prompt-snapshots
fix/policy-check-image-context
sirens-deep-admission-hardening
docs/drop-private-image-claim
feat/thread-scoped-replies
issue-67
feat/sirens-community-harness
No results found.
Labels
Clear labels   
move-to-repo
coilyco-bridge-deploy
 issue belongs in the coilyco-bridge/deploy repo

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

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

  
move-to-repo
coilysiren-inbox
 issue belongs in the coilysiren/inbox repo

  
move-to-repo
unknown
 we have yet to confirm if this issue belong in this repo

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

  
autonomy
async-consult
 A human needs to consult on the issue to upgrade it to headless

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

  
autonomy
headless
 The agent can perform the work on its own

  
autonomy
live-collab
 The agent and the human need to work together in realtime

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

  
priority
P0
 priority tier

  
priority
P1
 priority tier

  
priority
P2
 priority tier

  
priority
P3
 priority tier

  
priority
P4
 priority tier

  
role/ai
requires work from the AI Engineer role

  
role/creator
requires work from Content Creator role

  
role/design
requires work from the design role

  
role/director
requires work from the director role

  
role/engineer
requires work from the engineer role

  
role/exec
requires work from the exec role

  
role/human
requires a person, and specifically not an agent seat

  
role/ops
requires work from the ops role

  
role/qa
requires work from the QA role

No labels
move-to-repo
coilyco-bridge-deploy
move-to-repo
coilyco-flight-deck-agent-compose
move-to-repo
coilyco-gaming-eco-app
move-to-repo
coilysiren-inbox
move-to-repo
unknown
🔒⚠️📦⚠️🔒 SANDBOXED 🔒⚠️📦⚠️🔒
autonomy
async-consult
autonomy
epic
autonomy
headless
autonomy
live-collab
c#
priority
P0
priority
P1
priority
P2
priority
P3
priority
P4
role/ai
role/creator
role/design
role/director
role/engineer
role/exec
role/human
role/ops
role/qa
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
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#717
No description provided.