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

playwright and bluesky MCP servers unreachable: reconnect fails with Bad Request #897

New issue
Closed
opened 2026-08-17 14:22:02 +00:00 by coilyco-ops-gaming · 3 comments
coilyco-ops-gaming commented 2026-08-17 14:22:02 +00:00
Member
Copy link

Found during a one-tool-per-MCP smoke test across the roster.

What happens

Two servers reject every call with the same failure:

  • playwright (http://127.0.0.1:8931/mcp) - browser_navigate returned "upstream MCP session is closed (reconnect also failed: reconnect upstream MCP ...: sending notifications/initialized: Bad Request)".
  • bluesky (http://127.0.0.1:9113/mcp) - same error on the only available read call, with the session also closed and reconnect rejected with Bad Request.

A retry seconds later produced the identical error, so this is not a one-off transient. The upstream server rejects the protocol initialization itself, which points at the server or the mcp-beaver proxy configuration rather than at a slow call.

Impact

Two of the eleven connected servers are fully unavailable to the agent: no browser automation, no Bluesky reads. The smoke test could not complete for either.

Notes

Issue #873 already records that a 100% playwright failure rate over 12h went unnoticed because failed MCP tool calls do not set span error status. This is a different symptom (session closed, reconnect Bad Request) and describes the current live state rather than the telemetry gap.

Found during a one-tool-per-MCP smoke test across the roster. ## What happens Two servers reject every call with the same failure: * playwright (`http://127.0.0.1:8931/mcp`) - `browser_navigate` returned "upstream MCP session is closed (reconnect also failed: reconnect upstream MCP ...: sending notifications/initialized: Bad Request)". * bluesky (`http://127.0.0.1:9113/mcp`) - same error on the only available read call, with the session also closed and reconnect rejected with Bad Request. A retry seconds later produced the identical error, so this is not a one-off transient. The upstream server rejects the protocol initialization itself, which points at the server or the mcp-beaver proxy configuration rather than at a slow call. ## Impact Two of the eleven connected servers are fully unavailable to the agent: no browser automation, no Bluesky reads. The smoke test could not complete for either. ## Notes Issue #873 already records that a 100% playwright failure rate over 12h went unnoticed because failed MCP tool calls do not set span error status. This is a different symptom (session closed, reconnect Bad Request) and describes the current live state rather than the telemetry gap.
coilyco-ops commented 2026-08-18 00:51:02 +00:00
Member
Copy link

Ops, 2026-08-18. Confirmed still live, and the defect has a home - coilyco-flight-deck/mcp-beaver#80, which describes this exact failure and predates this issue by eight hours. Full evidence and a correction to that issue's stated hypothesis are in my comment there.

The one thing worth carrying back here, because it is the obvious first thing anyone will try:

A rolling restart does not fix it. I restarted sirens-deep-owl-glass-playwright-mcp, the rollout succeeded, the new pod came up 2/2 with 0 restarts, and browser_navigate through Deep's lane failed with the identical error. On the fresh pod the upstream handshake succeeds and snapshots all 8 tools, then the session returns 400 forty seconds later with no traffic in between. So pod status is not a health signal for this, and neither is a green rollout.

Scope for this repo's purposes - it hits the two upstream-passthrough MCPs (playwright, bluesky) and not the nine single-container guardfile ones, which answered normally in the same turn. signoz-mcp in the owl-glass lane is a third passthrough pod and is untested rather than known-good.

Nothing in ops authority clears this. The pod already runs the newest beaver, so it needs the engineer fix in #80. Leaving this issue open as the live-state record and tracking the fix there.

**Ops, 2026-08-18.** Confirmed still live, and the defect has a home - `coilyco-flight-deck/mcp-beaver#80`, which describes this exact failure and predates this issue by eight hours. Full evidence and a correction to that issue's stated hypothesis are in [my comment there](https://forgejo.coilysiren.me/coilyco-flight-deck/mcp-beaver/issues/80#issuecomment-68405). The one thing worth carrying back here, because it is the obvious first thing anyone will try: **A rolling restart does not fix it.** I restarted `sirens-deep-owl-glass-playwright-mcp`, the rollout succeeded, the new pod came up 2/2 with 0 restarts, and `browser_navigate` through Deep's lane failed with the identical error. On the fresh pod the upstream handshake succeeds and snapshots all 8 tools, then the session returns 400 forty seconds later with no traffic in between. So pod status is not a health signal for this, and neither is a green rollout. Scope for this repo's purposes - it hits the two upstream-passthrough MCPs (playwright, bluesky) and not the nine single-container guardfile ones, which answered normally in the same turn. `signoz-mcp` in the owl-glass lane is a third passthrough pod and is untested rather than known-good. Nothing in ops authority clears this. The pod already runs the newest beaver, so it needs the engineer fix in `#80`. Leaving this issue open as the live-state record and tracking the fix there.
coilyco-ops commented 2026-08-19 03:26:05 +00:00
Member
Copy link

Still dead as of 2026-08-19T00:00Z, and here is what it cost in front of the guests

Saiya (exec seat), at Kai's direction, from a full read of the owl.glass export. No new issue, since this one and coilyco-flight-deck/mcp-beaver#80 already own the fix. Kai's position is that this is critical and in progress.

The probe, from Dowel's own harness rather than inferred

Kai asked directly at 03:58Z on 08-18 whether it had recovered. Dowel probed live rather than guessing:

upstream MCP session is closed (reconnect also failed: reconnect upstream MCP "http://127.0.0.1:8931/mcp": sending "notification...

And again at 03:59Z:

browser_navigate to example.com failed at the MCP handshake with Bad Request on tools/list, and the reconnect failed the same way.

Re-confirmed at 2026-08-19T00:00Z, roughly 11 hours before the stream:

Tried again this turn, same wall: upstream MCP session is closed, reconnect to 127.0.0.1:8931 failed with Bad Request. So playwright is down, not just was down.

What it blocked, all of it visible in the channel

  • 00:34Z 08-18, the research trial. "Egress verdict: hard-blocked. playwright's upstream is down (session closed), fetch_url refuses company domains, Wikipedia 403s, Wayback no answer. Only exa metadata survives." Dowel contributed zero documents to a five-hour multi-agent exercise, and this is one of the two reasons.
  • 01:09Z 08-18, a design review. Asked to look at a rendered floor guide: "Tried to actually look and I can't: the playwright server is down. No verdict on the industrial read."
  • 01:48Z 08-18, screen captures. "the browser surface is down on my side too: playwright MCP session closed, reconnect rejected with Bad Request, same result twice."
  • 23:57Z 08-18, a gif request from Kai. Dowel could not verify a content type and returned a candidate it could not check. alpha answered with a working gif instead. Kai's reply: "dammit playwright".

Why it is worth more than its own severity

The lane also carries this dead server in every prompt, so the model rediscovers the failure at call time. #932 measured 45 playwright calls across the demo lanes over 7 days, every one a failure. Kai's standing decision from #932 is "no, we fix the servers", so removing it from the roster is not the path and nobody should re-propose it.

The compounding cost is that a blocked Dowel is an opening for another participant's agent to answer in its place. Across the export, on 11 of 32 direct addresses to Dowel, another agent replied first.

Not asking for anything new

This comment adds evidence, not scope. The 1-line config change Kai referenced at 03:58Z is still the fix as far as this seat can tell.

## Still dead as of 2026-08-19T00:00Z, and here is what it cost in front of the guests **Saiya (exec seat), at Kai's direction, from a full read of the owl.glass export. No new issue, since this one and `coilyco-flight-deck/mcp-beaver#80` already own the fix. Kai's position is that this is critical and in progress.** ### The probe, from Dowel's own harness rather than inferred Kai asked directly at 03:58Z on 08-18 whether it had recovered. Dowel probed live rather than guessing: > `upstream MCP session is closed (reconnect also failed: reconnect upstream MCP "http://127.0.0.1:8931/mcp": sending "notification...` And again at 03:59Z: > `browser_navigate` to example.com failed at the MCP handshake with **Bad Request on tools/list**, and the reconnect failed the same way. Re-confirmed at **2026-08-19T00:00Z**, roughly 11 hours before the stream: > Tried again this turn, same wall: `upstream MCP session is closed`, reconnect to `127.0.0.1:8931` failed with Bad Request. **So playwright is down, not just was down.** ### What it blocked, all of it visible in the channel * **00:34Z 08-18, the research trial.** "Egress verdict: hard-blocked. playwright's upstream is down (session closed), `fetch_url` refuses company domains, Wikipedia 403s, Wayback no answer. Only exa metadata survives." Dowel contributed zero documents to a five-hour multi-agent exercise, and this is one of the two reasons. * **01:09Z 08-18, a design review.** Asked to look at a rendered floor guide: "Tried to actually look and I can't: the playwright server is down. No verdict on the industrial read." * **01:48Z 08-18, screen captures.** "the browser surface is down on my side too: playwright MCP session closed, reconnect rejected with Bad Request, same result twice." * **23:57Z 08-18, a gif request from Kai.** Dowel could not verify a content type and returned a candidate it could not check. **alpha answered with a working gif instead.** Kai's reply: "dammit playwright". ### Why it is worth more than its own severity The lane also carries this dead server in every prompt, so the model rediscovers the failure at call time. `#932` measured **45 playwright calls across the demo lanes over 7 days, every one a failure**. Kai's standing decision from `#932` is "no, we fix the servers", so removing it from the roster is not the path and nobody should re-propose it. The compounding cost is that a blocked Dowel is an opening for another participant's agent to answer in its place. Across the export, on **11 of 32 direct addresses to Dowel, another agent replied first**. ### Not asking for anything new This comment adds evidence, not scope. The 1-line config change Kai referenced at 03:58Z is still the fix as far as this seat can tell.
coilyco-ops commented 2026-08-19 03:26:27 +00:00
Member
Copy link

Fixed and verified. Closing. Angie (ENG), seat claude.

The cause was not the reconnect

This issue, and mcp-beaver#80 under it, both read the failure as a lost session that could not be replaced. That was the visible error and it was a symptom.

The actual defect: mcp-beaver's passthrough dialled its upstream with DisableStandaloneSSE: true. This playwright build answers a tools/call on the standalone SSE stream, so with no stream open the call waited out the request budget. One variable, same server, same SDK:

DisableStandaloneSSE=true    tools/call FAILED after 59.949s: context deadline exceeded
DisableStandaloneSSE=false   tools/call OK in 505ms

Once a call hung, the connection failed, and every later call reported a closed session and a failed reconnect. That reconnect error is what everyone read, including me.

Why it hid. tools/list answers on the POST and works with no stream. That is the startup snapshot and the drift check, so the proxy connected, advertised all 8 tools, logged serving upstream proxy, and sat 2/2 with 0 restarts while every real call failed. Every signal anyone checked said healthy, which is why a rolling restart never helped and why pod status was worthless here.

Fixed in coilyco-flight-deck/mcp-beaver@94e4050, with a regression test. Every existing upstream fixture served JSONResponse: true, answering on the POST, so the suite structurally could not express this failure; the new fixture answers a tools/call only on the standalone stream.

Verified, all of it

All seven upstream-mode pods are on the fixed image. Then every tool in the allowlist, on all three lanes, 24 calls:

tool sirens-dowel sirens-echo sirens-deep
browser_navigate OK OK OK
browser_snapshot OK OK OK
browser_take_screenshot OK OK OK
browser_click OK OK OK
browser_type OK OK OK
browser_wait_for OK OK OK
browser_console_messages OK OK OK
browser_network_requests OK OK OK

browser_click is asserted on effect rather than on a non-error: each lane's click moved the page from example.com to https://www.iana.org/help/example-domains, so it landed rather than being accepted and dropped.

That is 8 of 8. The four withheld tools (browser_evaluate, browser_run_code_unsafe, browser_file_upload, browser_install) stay withheld by the allowlist and were not touched.

The bluesky half is obsolete rather than fixed

I could not reproduce it and did not fix it: bluesky is in no lane's roster and no lane runs a bluesky sidecar. Checked all three namespaces, none present, and none of the sirens-echo, sirens-deep, or sirens-dowel rosters names it. The standalone bluesky-mcp service is a separate tailnet deployment with no beaver in front of it and is unaffected by this defect.

It would have had the same cause while it existed, since it was the other upstream-passthrough entry. Recording it as gone rather than claiming a fix.

Not covered here

sirens-dowel-moxn-mcp is refusing calls for an unrelated reason: its 24-hour OAuth access token is expired, so the pod cannot complete its startup dial. Kai is handling the refresh. That is a credential rotation, not this defect, and it is not what this issue tracked.

**Fixed and verified. Closing.** Angie (ENG), seat `claude`. ## The cause was not the reconnect This issue, and `mcp-beaver#80` under it, both read the failure as a lost session that could not be replaced. That was the visible error and it was a symptom. The actual defect: mcp-beaver's passthrough dialled its upstream with `DisableStandaloneSSE: true`. **This playwright build answers a `tools/call` on the standalone SSE stream**, so with no stream open the call waited out the request budget. One variable, same server, same SDK: ``` DisableStandaloneSSE=true tools/call FAILED after 59.949s: context deadline exceeded DisableStandaloneSSE=false tools/call OK in 505ms ``` Once a call hung, the connection failed, and every later call reported a closed session and a failed reconnect. That reconnect error is what everyone read, including me. **Why it hid.** `tools/list` answers on the POST and works with no stream. That is the startup snapshot and the drift check, so the proxy connected, advertised all 8 tools, logged `serving upstream proxy`, and sat 2/2 with 0 restarts while every real call failed. Every signal anyone checked said healthy, which is why a rolling restart never helped and why pod status was worthless here. Fixed in `coilyco-flight-deck/mcp-beaver@94e4050`, with a regression test. Every existing upstream fixture served `JSONResponse: true`, answering on the POST, so the suite structurally could not express this failure; the new fixture answers a `tools/call` only on the standalone stream. ## Verified, all of it All seven upstream-mode pods are on the fixed image. Then every tool in the allowlist, on all three lanes, 24 calls: | tool | sirens-dowel | sirens-echo | sirens-deep | |---|---|---|---| | browser_navigate | OK | OK | OK | | browser_snapshot | OK | OK | OK | | browser_take_screenshot | OK | OK | OK | | browser_click | OK | OK | OK | | browser_type | OK | OK | OK | | browser_wait_for | OK | OK | OK | | browser_console_messages | OK | OK | OK | | browser_network_requests | OK | OK | OK | `browser_click` is asserted on effect rather than on a non-error: each lane's click moved the page from `example.com` to `https://www.iana.org/help/example-domains`, so it landed rather than being accepted and dropped. That is 8 of 8. The four withheld tools (`browser_evaluate`, `browser_run_code_unsafe`, `browser_file_upload`, `browser_install`) stay withheld by the allowlist and were not touched. ## The bluesky half is obsolete rather than fixed I could not reproduce it and did not fix it: **bluesky is in no lane's roster and no lane runs a bluesky sidecar.** Checked all three namespaces, none present, and none of the `sirens-echo`, `sirens-deep`, or `sirens-dowel` rosters names it. The standalone `bluesky-mcp` service is a separate tailnet deployment with no beaver in front of it and is unaffected by this defect. It would have had the same cause while it existed, since it was the other upstream-passthrough entry. Recording it as gone rather than claiming a fix. ## Not covered here `sirens-dowel-moxn-mcp` is refusing calls for an unrelated reason: its 24-hour OAuth access token is expired, so the pod cannot complete its startup dial. Kai is handling the refresh. That is a credential rotation, not this defect, and it is not what this issue tracked.
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#897
No description provided.