Fix ?. + chained || literal fallback parsing to preserve left-to-right short-circuit semantics

[Copilot]

source?.path || "A" || "B" was resolving to "B" instead of "A" in cases where the safe pull produced undefined. The parser was collapsing chained || alternatives in a way that lost first-truthy behavior for literal fallbacks.

• Problem scope

  • Safe navigation (?.) correctly converts source errors to undefined, but chained || literal fallbacks were not preserving authored short-circuit order.
  • This caused later literals to override earlier truthy literals in some parsed wire shapes.

• Parser behavior update (packages/bridge-parser/src/parser/parser.ts)

  • While collecting nullAlt (||) alternatives for a wire:
    • Stop processing additional alternatives once a truthy literal fallback is encountered.
    • Clear a previously captured literal fallback when a later source/control alt is parsed, so stale falsy literals do not survive chain continuation.

• Regression coverage (packages/bridge/test/coalesce-cost.test.ts)

  • Added an end-to-end case for chained literals after safe navigation to ensure first-truthy fallback wins.
  • Added an additional mixed-chain regression to confirm strict left-to-right semantics across || and ??:
    • const.lorem.kala || const.lorem.ipsums?.mees || "B" ?? "C" resolves to "B".

version 1.5
const lorem = {
  "ipsum": "dolor sit amet",
  "consetetur": 8.9
}

bridge Query.lookup {
  with const
  with output as o

  o.label <- const.lorem.ipsums?.kala || "A" || "B"
}

Expected result for o.label: "A".

• Release metadata
  • Added a user-facing changeset for this fix:
    • .changeset/tough-cups-smoke.md
    • patch bumps for @stackables/bridge and @stackables/bridge-parser.

> [!WARNING]
>
>

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

[changeset-bot]

🦋 Changeset detected

Latest commit: 9d0f23d

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 2 packages

Name	Type
@stackables/bridge	Patch
@stackables/bridge-parser	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[cloudflare-workers-and-pages]

Deploying with    Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	bridge	9d0f23d	Commit Preview URL Branch Preview URL	Mar 05 2026, 05:47 PM

[aarne]

@copilot

version 1.5
const lorem = {
"ipsum": "dolor sit amet",
"consetetur": 8.9
}

bridge Query.lookup {
with const
with output as o

o.label <- const.lorem.kala || const.lorem.ipsums?.mees || "B" ?? "C"
}

now the answer is B, right?

|| and ?? chain is always processed strictly from left to right.

=====

you forgot to add a changeset as this needs to be released to users also

[Copilot]

@copilot

version 1.5
...

Yes — with strict left-to-right evaluation, that expression resolves to "B" (|| chain yields "B", then ?? "C" does not apply). I added a regression test for this exact case and added the missing user-facing changeset in commit 9d0f23d.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• api.open-meteo.com
  • Triggering command: /opt/hostedtoolcache/node/24.14.0/x64/bin/node /opt/hostedtoolcache/node/24.14.0/x64/bin/node --heap-prof-interval=524288 --cpu-prof-interval=1000 --test-coverage-functions=0 --test-concurrency=0 --inspect-publish-uid=stderr,http --inspect-port=127.0.0.1:9229 --experimental-transform-types --report-signal=SIGUSR2 --test-coverage-lines=0 --test-isolation=process --conditions=source --tls-cipher-list=TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256:TLS_AES_128_GCM_SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-SHA est/*.test.ts (dns block)
• dummyjson.com
  • Triggering command: /opt/hostedtoolcache/node/24.14.0/x64/bin/node /opt/hostedtoolcache/node/24.14.0/x64/bin/node --heap-prof-interval=524288 --cpu-prof-interval=1000 --test-coverage-functions=0 --test-concurrency=0 --inspect-publish-uid=stderr,http --inspect-port=127.0.0.1:9229 --experimental-transform-types --report-signal=SIGUSR2 --test-coverage-lines=0 --test-isolation=process --conditions=source --tls-cipher-list=TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256:TLS_AES_128_GCM_SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-SHA est/*.test.ts (dns block)
• nominatim.openstreetmap.org
  • Triggering command: /opt/hostedtoolcache/node/24.14.0/x64/bin/node /opt/hostedtoolcache/node/24.14.0/x64/bin/node --heap-prof-interval=524288 --cpu-prof-interval=1000 --test-coverage-functions=0 --test-concurrency=0 --inspect-publish-uid=stderr,http --inspect-port=127.0.0.1:9229 --experimental-transform-types --report-signal=SIGUSR2 --test-coverage-lines=0 --test-isolation=process --conditions=source --tls-cipher-list=TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256:TLS_AES_128_GCM_SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-SHA est/*.test.ts (dns block)
• transport.opendata.ch
  • Triggering command: /opt/hostedtoolcache/node/24.14.0/x64/bin/node /opt/hostedtoolcache/node/24.14.0/x64/bin/node --heap-prof-interval=524288 --cpu-prof-interval=1000 --test-coverage-functions=0 --test-concurrency=0 --inspect-publish-uid=stderr,http --inspect-port=127.0.0.1:9229 --experimental-transform-types --report-signal=SIGUSR2 --test-coverage-lines=0 --test-isolation=process --conditions=source --tls-cipher-list=TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256:TLS_AES_128_GCM_SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-SHA est/*.test.ts (dns block)
• v6.db.api.bahn.guru
  • Triggering command: /opt/hostedtoolcache/node/24.14.0/x64/bin/node /opt/hostedtoolcache/node/24.14.0/x64/bin/node --heap-prof-interval=524288 --cpu-prof-interval=1000 --test-coverage-functions=0 --test-concurrency=0 --inspect-publish-uid=stderr,http --inspect-port=127.0.0.1:9229 --experimental-transform-types --report-signal=SIGUSR2 --test-coverage-lines=0 --test-isolation=process --conditions=source --tls-cipher-list=TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256:TLS_AES_128_GCM_SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-SHA est/*.test.ts (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

[github-actions]

Bencher Report

Branch	copilot/fix-query-output-logics
Testbed	ubuntu-latest

Click to view all benchmark results

Benchmark	Latency	Benchmark Result nanoseconds (ns) (Result Δ%)	Upper Boundary nanoseconds (ns) (Limit %)
compiled: absolute baseline (passthrough, no tools)	📈 view plot 🚷 view threshold	0.00 ns (-0.22%) Baseline: 0.00 ns	0.00 ns (91.81%)
compiled: array + tool-per-element 10	📈 view plot 🚷 view threshold	0.01 ns (+0.11%) Baseline: 0.01 ns	0.01 ns (94.09%)
compiled: array + tool-per-element 100	📈 view plot 🚷 view threshold	0.03 ns (-4.62%) Baseline: 0.03 ns	0.04 ns (89.83%)
compiled: chained 3-tool fan-out	📈 view plot 🚷 view threshold	0.00 ns (-0.41%) Baseline: 0.00 ns	0.00 ns (92.89%)
compiled: flat array 10 items	📈 view plot 🚷 view threshold	0.00 ns (-0.77%) Baseline: 0.01 ns	0.01 ns (92.75%)
compiled: flat array 100 items	📈 view plot 🚷 view threshold	0.01 ns (-1.32%) Baseline: 0.01 ns	0.01 ns (93.28%)
compiled: flat array 1000 items	📈 view plot 🚷 view threshold	0.07 ns (-1.60%) Baseline: 0.07 ns	0.07 ns (93.85%)
compiled: nested array 10x10	📈 view plot 🚷 view threshold	0.02 ns (-0.43%) Baseline: 0.02 ns	0.02 ns (93.77%)
compiled: nested array 20x10	📈 view plot 🚷 view threshold	0.03 ns (+0.26%) Baseline: 0.03 ns	0.04 ns (94.89%)
compiled: nested array 5x5	📈 view plot 🚷 view threshold	0.01 ns (-1.05%) Baseline: 0.01 ns	0.01 ns (93.16%)
compiled: short-circuit (overdefinition bypass)	📈 view plot 🚷 view threshold	0.00 ns (-0.53%) Baseline: 0.00 ns	0.00 ns (91.65%)
compiled: simple chain (1 tool)	📈 view plot 🚷 view threshold	0.00 ns (-0.28%) Baseline: 0.00 ns	0.00 ns (91.84%)
exec: absolute baseline (passthrough, no tools)	📈 view plot 🚷 view threshold	0.00 ns (+5.81%) Baseline: 0.00 ns	0.00 ns (86.02%)
exec: array + tool-per-element 10	📈 view plot 🚷 view threshold	0.08 ns (+1.90%) Baseline: 0.08 ns	0.10 ns (76.37%)
exec: array + tool-per-element 100	📈 view plot 🚷 view threshold	0.71 ns (+4.07%) Baseline: 0.68 ns	0.93 ns (75.82%)
exec: chained 3-tool fan-out	📈 view plot 🚷 view threshold	0.02 ns (+15.15%) Baseline: 0.01 ns	0.02 ns (84.82%)
exec: flat array 10 items	📈 view plot 🚷 view threshold	0.01 ns (-8.56%) Baseline: 0.02 ns	0.04 ns (40.29%)
exec: flat array 100 items	📈 view plot 🚷 view threshold	0.07 ns (-24.26%) Baseline: 0.10 ns	0.32 ns (23.14%)
exec: flat array 1000 items	📈 view plot 🚷 view threshold	0.68 ns (-30.92%) Baseline: 0.98 ns	3.87 ns (17.58%)
exec: nested array 10x10	📈 view plot 🚷 view threshold	0.12 ns (-16.58%) Baseline: 0.15 ns	0.39 ns (31.40%)
exec: nested array 20x10	📈 view plot 🚷 view threshold	0.24 ns (-17.60%) Baseline: 0.29 ns	0.79 ns (29.90%)
exec: nested array 5x5	📈 view plot 🚷 view threshold	0.05 ns (-8.32%) Baseline: 0.05 ns	0.11 ns (44.21%)
exec: short-circuit (overdefinition bypass)	📈 view plot 🚷 view threshold	0.00 ns (+6.96%) Baseline: 0.00 ns	0.00 ns (94.22%)
exec: simple chain (1 tool)	📈 view plot 🚷 view threshold	0.01 ns (+13.62%) Baseline: 0.01 ns	0.01 ns (87.46%)
parse: large bridge (20 handles x 5 wires)	📈 view plot 🚷 view threshold	1.19 ns (+20.09%) Baseline: 0.99 ns	1.36 ns (87.16%)
parse: simple bridge	📈 view plot 🚷 view threshold	0.04 ns (+26.25%) Baseline: 0.03 ns	0.05 ns (88.59%)

🐰 View full continuous benchmarking report in Bencher