## Thinking Path
> - Paperclip helps people manage AI agents and observe their work.
> - The native runner carries provider output into the task transcript.
> - OpenCode sends incremental text in `message.part.delta` events.
> - The driver ignored those events and waited for a full part snapshot.
Accepted chats also waited after lifecycle verification was complete.
> - This pull request forwards each valid chunk as it arrives and
removes unnecessary isolated startup work.
> - Valid chunks reach Paperclip sooner without changing completion or
permission rules. The matched browser experiment below does not
establish a reliable end-to-end latency improvement.
## Linked Issues or Issue Description
**What happened?**
The native OpenCode driver withheld text until OpenCode sent a full
snapshot. A local delayed-provider probe with the pinned OpenCode
1.18.34 runtime showed a 1,496 ms gap between the first native text
delta and the first Paperclip text delta (1,510 ms from provider text).
**Expected behavior**
Forward valid assistant text and reasoning deltas immediately. Preserve
repeated identical tokens, message roles, turn ownership, and final
response selection.
**Steps to reproduce**
Send an empty text part, then text deltas, and withhold the final full
snapshot. The new fixture requires the consumer to acknowledge its first
text delta before releasing the snapshot. The previous driver cannot
pass this handshake.
**Paperclip version or commit**
Baseline: `011e5669bad61c435a4745fb10812bef70376841`. The patch is
rebased onto current master.
**Deployment mode**
Local native OpenCode 1.18.34 on macOS arm64. Live diagnostics use
`openrouter/deepseek/deepseek-v4-flash-0731`. These are narrow
diagnostics, not full Product E2E qualification.
## What Changed
- Keep the macOS verified OpenCode launch pathname until child exit,
with guarded reuse and cleanup on failed launches. This fixes a
reproduced asynchronous executable-lifetime failure.
- Dispatch accepted queued chats immediately after lifecycle readiness
commits, through normal scheduler admission. Preserve ready state if
dispatch fails.
- Validate native OpenCode model access with the real hello probe
without a redundant catalog scan. Keep legacy adapter discovery
unchanged and isolate unspecified native probe directories.
- Map incremental text and reasoning to the existing canonical event
path, using observed part and message identities.
- Keep additive chunks without IDs distinct. Preserve ID-based event
deduplication.
- Clear current streaming part metadata when a new turn starts. Reject
mismatched session/message identities and unknown parts or fields.
- Disable automatic updates, remote model refreshes, and default plugins
in each isolated OpenCode process. Keep assigned MCP tools and default
model reasoning intact.
- Retain the latest cumulative text/reasoning part while its message
role is unknown, including completion metadata after more than 100
chunks.
- Expose `startTurn({ message, reasoningMode: "disabled" })` for one
OpenCode/OpenRouter turn. Carry the selection in the durable command
through Rust and the proxy. An omitted/default option restores provider
defaults on the next turn, including warm and recovered sessions. There
is no environment-level setting or automatic selection policy.
- Group optional Rust turn inputs in `CodexTurnOptions` and dispatch
through `start_turn_with_options`; retain `start_turn` for defaults.
Future turn settings can be added without another feature-specific
method.
- Expose a native-session capability for per-turn reasoning and reject
explicit unsupported selections before dispatch, including direct ACPX
and Codex backends. Runnerd checks the durable selected model as well as
the provider.
- Remove duplicate agent instructions from the shared OpenCode proxy
task envelope for all users. Send one system copy on every turn,
including prepared and resumed turns, because OpenCode reads the latest
user message’s system field. Preserve task constraints and completion
contracts.
- Document startup and streaming behavior. Add regression coverage for
role ordering, repeated chunks, final snapshot deduplication, and stale
turns.
## Verification
### Lower-load browser retry — 2026-10-10
**All 8/8 trials succeeded. In this batch, median Send → first visible
reply fell from 30.586 s to 12.476 s (59.2% lower).** Four fresh-agent
trials per variant, phase order before/after/after/before with two
trials per phase. Every adjacent-phase pair favored the candidate,
although one difference was only 0.301 s. This is evidence for the
readiness/probe changes on this host, not a production percentile or a
guarantee across providers.
| Phase/trial | Variant | Send → reply (s) | Observed ready → run (s) |
Session open → turn start (s) | Model requests |
|---|---|---:|---:|---:|---:|
| 0/0 | before | 45.042 | 25.337 | 3.629 | 2 |
| 0/1 | before | 13.689 | 0.000 | 2.443 | 2 |
| 1/0 | after | 14.696 | 0.000 | 2.526 | 1 |
| 1/1 | after | 13.389 | 0.000 | 2.470 | 2 |
| 2/0 | after | 10.871 | 0.000 | 2.706 | 2 |
| 2/1 | after | 11.564 | 0.004 | 2.443 | 2 |
| 3/0 | before | 41.582 | 21.518 | 2.376 | 2 |
| 3/1 | before | 19.589 | 9.753 | 2.707 | 1 |
Observed ready-to-run median: **15.636 s → 0 s**; zero means execution
began by the first ready observation, not literally zero latency.
Polling interval is nominally 250 ms plus HTTP time.
Session-open-to-turn-start includes controller handling, not just child
startup. All eight ran within the existing startup timeouts; no timeout
or reasoning policy was changed. Host load at fixture creation stayed
**5.47–8.73 on 18 CPUs**, versus 68.9–100.8 in the prior campaign. No
builds/tests ran concurrently with measurement.
Same merged source **b0a0158729a7913882a0e756fe7e27228d72bf53**, release
runner, rebuilt static UI, OpenCode **1.18.34**, model
**openrouter/deepseek/deepseek-v4-flash-0731**, provider-default
reasoning, and empty isolated workspaces in both variants. Only the
readiness worker and explicit-model verification source were toggled;
the launch-lifetime fix and all proxy streaming changes were held
constant. Thus this does not separately measure the original streaming
changes. One browser per phase, two fresh companies/agents/chats per
phase. Measurement begins at capture-phase Send click and ends on
visible Hi text plus two animation frames. Status/thinking is excluded;
emoji can arrive just after the first text. Successful screenshots
inspected. Each variant had three two-request turns using
`paperclip_finish` and one one-request turn; no status lookup was
observed. Reported usage includes settlement after the first visible
reply.
Runner SHA-256
`57f658c220eecd2370ffd3333cd7e5d06d16bb2798af0cf43c84e01c8207c1c3`;
proxy
`bcc02fda2bf35b38a116cd880841aa6c534f6e0b497a96d97369a1e06dcc72ac`;
rebuilt UI tree
`eee238f2eda628c4e8c3660707986da4f8dd9100c814e26938fce3756df2eae4`
(sorted relative path, NUL, binary per-file SHA-256). Worker/probe
variant source hashes are unchanged from the preserved comparison below.
Measured turn cost **$0.00612574**, plus verification probes not
included in that figure. All eight attempts retained; all source/proxy
files restored and test supervisors exited.
Current commit validation: **53 successful CI checks, 4 skipped, zero
failing; Greptile 5/5 on b0a0158729 with no actionable findings.** The
previous 20 targeted post-merge tests passed. No source edit was made
for this rerun. Earlier failed and inconclusive cohorts below remain
historical evidence and are not pooled with this batch.
### Master update and failure diagnosis — 2026-10-09
Merged `origin/master` at `417db14e7d` into this branch without
conflicts; pushed merge commit
`b0a0158729a7913882a0e756fe7e27228d72bf53`. The incoming changes do not
alter OpenCode process startup or its timeout budgets. Historical
measurements below remain attributed to their original commits.
The four last-campaign failures never issued `turn.start`, so these were
**cold-session admission failures, not model replies failing**. Two
retained `session.open` commands eventually completed after controller
timeout/cleanup had begun. The other two ended with the inner
`thread/start` response timeout, and their diagnostics recorded OpenCode
startup retries. Startup event timestamps are buffered publication times
and must not be interpreted as exact process-spawn times.
On the merged source, two credential-free startup-only checks used the
real pinned OpenCode 1.18.34, empty temporary workspaces, a placeholder
key, and **no model turns**:
- Existing pinned executable: spawn at 1.083 s; failed health
attempt/retry at 11.311 s and 21.914 s; third process healthy at 32.210
s; session opened at **35.168 s**.
- Verified private executable path: snapshot preparation took **0.497
s**; process spawned at 1.588 s; healthy at 9.967 s; session opened at
**11.120 s**.
These are sequential diagnostic samples, not evidence that one
executable path is faster. Host load was **56.5–64.5 on 18 logical
CPUs**. The local health wait permits 10 s per attempt and the driver
retries up to three times; the outer controller's cold admission budget
is 30 s, and the Rust facade also waits 30 s for a response. Thus
retries plus setup/session creation can outlast the caller's budget. The
isolated 35.168 s success demonstrates that a session can eventually
open yet fail the app's admission deadline. Heavy load aggravates the
timing; its exact contribution is not isolated. No timeout was increased
and no new model-latency claim is made.
Merge validation: **20/20 targeted lifecycle-policy and heartbeat
run-completion tests passed**, including temporary PostgreSQL cases. The
first sandbox invocation skipped database cases; the authorized local-DB
rerun executed all 20. The package-manager launcher could not verify its
version via the unreachable registry, so validation used the
already-installed Vitest binary. Full CI/review subsequently passed on
this merge commit; see the October 10 retry above. Older results below
apply to their named commits.
### Follow-up: reproduced macOS launch failure — 2026-10-09
The retry exposed a startup bug rather than only host-load noise. The
macOS proxy deleted the private verified executable path immediately
after asynchronous spawn. A credential-free test of the actual pinned
OpenCode `--version` reproduced a fast SIGKILL and a 15-second timeout
in three immediate-cleanup attempts; three deferred-cleanup controls
succeeded. The timeout was killed by the diagnostic's own deadline. This
experiment does not establish the OS-internal reason for the fast
SIGKILL.
Commit `c30451e0ebf3f74e9ef70d37bbe4d9fe7fb56359` retains the private
launch path until child exit, cleans failed spawns, and waits for forced
shutdown before reuse. Source descriptor authentication, ownership,
mode, inode checks, and the prohibition on ambient executable fallback
remain. Overlapping reuse fails closed. The existing synchronous shell
test was changed to exercise the actual asynchronous boundary.
**Verification:** 59 focused proxy/driver tests passed; runner
TypeScript check passed. All six subsequent real OpenCode version
launches succeeded without timeout (4.11, 4.33, 5.73, 6.91, 4.95, 6.70
seconds). The native Rust binary is unchanged from the retry; no model
calls were made by these diagnostics.
Retained interrupted retry: before 42.56/18.69 seconds; after one
180-second timeout (`provider_process_exited` / health SIGKILL) and one
37.33-second success. The latter overlapped the credential-free
diagnostic and is not a clean matched timing. The next phase was stopped
before Send to diagnose the reproduced bug. Reported measured-turn cost:
$0.0016874, verification probes additional. These attempts are not
pooled with other campaigns.
<!-- launch-fixed-proof:start -->
**Completed retry, stopped by the declared failure rule after 6 of 8
planned trials. No reliable end-to-end speedup demonstrated.** At commit
`c30451e0ebf3f74e9ef70d37bbe4d9fe7fb56359`, the launch fix above was
held constant in both variants; only the readiness handoff and
explicit-model verification path changed. Planned phase order:
before/after/after/before, two fresh agents/chats per phase, one new
browser per phase. The second after phase had two consecutive failures,
so the final before phase was not run.
| Phase/trial | Variant | Send → first visible reply | Observed ready →
run | Outcome |
|---|---|---|---|---|
| 0/0 | before | No reply within 180 s | 2.777 s | session.open timeout
|
| 0/1 | before | 47.654 s | 9.383 s | Succeeded |
| 1/0 | after | 50.051 s | 0.087 s | Succeeded |
| 1/1 | after | No reply within 180 s | 0.151 s | session.open timeout |
| 2/0 | after | No reply within 180 s | 3.337 s | session.open timeout |
| 2/1 | after | No reply within 180 s | 1.434 s | session.open timeout |
Both successful screenshots show “Hi 👋”. Timing starts at the browser's
capture-phase Send click and ends at the first visible answer text plus
two animation frames; the first fragment can be “Hi” before the emoji
arrives. Thinking/status text is not counted. All four failures were
`runner_local_connect_failed: PRP command session.open timed out`
(`native_session_interrupted`), before a reply; none reported the
earlier health-stage SIGKILL. They are retained, not discarded as
outliers. One success per variant does not support a speedup estimate or
median comparison. Observed ready-to-run median was **6.080 s before
(n=2) vs 0.793 s after (n=4)**; this is sampled every nominal 250 ms
plus HTTP latency and is a lower bound, not precise tracing. Host load
at fixture creation ranged **68.9–100.8 on 18 logical CPUs**, a
substantial confound that worsened over the campaign. No local
build/test was run concurrently with this campaign.
Provenance: pinned OpenCode **1.18.34**, model
**openrouter/deepseek/deepseek-v4-flash-0731**, default reasoning in
both variants, empty synthetic workspaces and isolated probe homes.
Release runner SHA-256
`57f658c220eecd2370ffd3333cd7e5d06d16bb2798af0cf43c84e01c8207c1c3`;
current proxy SHA-256
`bcc02fda2bf35b38a116cd880841aa6c534f6e0b497a96d97369a1e06dcc72ac`;
built UI tree SHA-256
`7f0c2b7f586cb753408351574b2239e22311944add99af4f6f3562cd6d47bbcb`. This
holds the rebuilt runner and static UI constant. Provider-reported
measured turn cost **$0.00120649**; verification probes are additional.
Including the earlier interrupted retry, this follow-up reports
**$0.00289389** in measured turn usage; missing usage is not assumed
free. Prior cohorts remain separate below.
Validation on `c30451e0e`: **59 focused tests passed**, runner
TypeScript check passed, **6/6 real credential-free pinned OpenCode
launches passed**, fresh Greptile **5/5 with zero unresolved threads**.
CI: **51 success, 4 skipped, 1 failed**. The failed native compilation
job never reached compilation: Docker's auth endpoint timed out during
Buildx setup, then failed the same way on one retry
([job](https://github.com/paperclipai/paperclip/actions/runs/37994181674/job/114039737503)).
Full local checks were not rerun while measuring. The PR remains draft:
the launch defect is reproduced and fixed, but cold session startup
still exceeds the controller's admission budget on this host. Raising
that budget would not establish a faster first response.
<!-- launch-fixed-proof:end -->
### Readiness investigation and live rerun — 2026-10-09
**Measured queue fix; no reliable end-to-end speedup claim. Keep this PR
in draft.** Accepted chats could wait for the periodic queue sweep after
verification had already committed `ready`. The lifecycle worker now
dispatches through the existing scheduler immediately after that commit.
The normal company, pause, budget, concurrency, and task-ownership
checks still apply. Dispatch failure preserves readiness and leaves
recovery to the queue sweep.
Native OpenCode verification also avoids enumerating the full model
catalog before running its real hello request. Identifier validation
remains. Authentication failures, unavailable models, and timeouts still
prevent readiness. An unspecified local probe directory uses an empty
temporary directory.
**Queue-only experiment:** four before and four after attempts, in
before/after/after/before server phases, two fresh agents per phase.
Median observed ready-to-start delay fell from **19.429 s to 0.058 s**.
State polling was nominally 250 ms plus HTTP time, so the latter means
within observation resolution; it is not a precise 58 ms latency claim.
After timings were 100.20, 65.29, 63.78, and 76.97 seconds. Before had
one 59.65-second success and three 120-second response timeouts (one
provider health SIGKILL, one late success, one still running after
settlement and canceled). These censored results do not support a
success-only median speedup comparison. Focused tests overlapped the
last baseline phase, which further limits total-time interpretation.
Reported measured-turn cost: $0.0055383; verification probes and
incomplete/canceled usage are additional.
**Final matched experiment:** built static UI in both variants to avoid
pre-Send Vite compilation; current proxy, release runner, selected
model, default reasoning, and explicitly isolated empty probe
cwd/HOME/XDG held constant. Both worker handoff and model-probe changes
vary. Fresh browser/company/agent/chat per attempt. ABBA order, two
attempts per variant, 180-second response limit declared before the
batch, four-turn bound. Same Send-to-rendered-Hi metric as the earlier
experiment.
| Order | Variant | Send → visible Hi | Created → execution | Observed
ready → execution | Outcome |
| --- | --- | ---: | ---: | ---: | --- |
| 1 | Before | 62.66 s | 23.467 s | 2.830 s | Succeeded |
| 2 | After | >180 s | 14.200 s | Within polling resolution | Provider
health SIGKILL |
| 3 | After | >180 s | 13.877 s | Within polling resolution | Provider
initialization timeout |
| 4 | Before | >180 s | 144.256 s | 14.067 s | Still running after
settlement; canceled |
Only one of four attempts produced a timed reply. **There is no valid
overall speedup estimate from this batch.** The dispatch delay is
removed, but provider startup failures and heavy shared-host load
remain. A recorded host sample was load 93.55 on 18 logical CPUs. This
is a confound, not proof that every failure was caused by host load.
Provider-reported measured-turn cost was $0.00032752, with no reported
usage for the other three attempts; verification probes are additional.
Retained earlier setup attempts: one shared-memory startup failure
before model calls, and a separate development-UI batch with a
60.06-second baseline followed by a navigation timeout before Send.
These attempts are retained separately, not counted as successful
response timings. No live attempts were silently dropped.
Provenance: source base `53580f8fbd40b963f3fb7ba5172ff3ede2e9ef1f`,
measured patch committed as `40b54eafb`, then rebased as
`c590770dcc2bb1debce14037935a7031e5c3c1ac`. **These live timings predate
the rebase.** Source and binary hashes are retained below. The inner
harness label `after` selects the identical current proxy in every
attempt; the outer campaign handoff label is the actual before/after
variant. Owned benchmark processes stopped and original proxy restored.
<!-- readiness-check-status:start -->
Post-rebase validation at `c590770dcc2bb1debce14037935a7031e5c3c1ac`:
- Full local `pnpm -r typecheck`: **passed**, including the native
release build (1,098.6 seconds on the loaded host).
- Focused lifecycle and adapter tests: **26 passed**. The 14 database
integration tests did not run locally because their hard-coded 20-second
database setup hook timed out. A retry with a CLI timeout override
encountered the same explicit hook limit. The earlier pre-rebase focused
batch passed 77 tests; these results are not substituted for post-rebase
execution.
- Local `pnpm test:run` was started, then stopped to avoid duplicating
CI on the saturated host. Local `pnpm build` was not run separately.
**Current-head CI passed Typecheck + Release Registry, Build, all
general and serialized test groups, Rust checks, both runner Vitest
groups, and all eight browser E2E shards.** The last general shard
passed 1,179 tests (72 files).
- Fresh [Greptile
review](https://github.com/paperclipai/paperclip/pull/15708#issuecomment-6085742217):
**5/5**, reviewed this exact head, no actionable defect.
- Final CI rollup: **49 success, 4 skipped, 4 failure**. The failures
are [Compile isolated native
Runner](https://github.com/paperclipai/paperclip/actions/runs/37990274515/job/114024329242),
[Docker context
integrity](https://github.com/paperclipai/paperclip/actions/runs/37990274623/job/114024196511),
[Canary Dry
Run](https://github.com/paperclipai/paperclip/actions/runs/37990274623/job/114024196424),
and the dependent `ci / verify` aggregate. All three root failures are
Docker Hub HTTP 429 / unauthenticated pull-rate limits while fetching
Node base images. The native-image job was retried once and hit the same
limit. No source compiler/test failure was reported by those gates. CI
maintainers need authenticated pulls or to rerun after the registry
limit clears.
- Owned benchmark servers stopped. Local validation commands completed
or were stopped. The PR remains a draft: user-visible speed/reliability
is not qualified, and the Docker-dependent CI gates are not green.
<!-- readiness-check-status:end -->
<details><summary>Sanitized readiness evidence with all attempts and
source hashes</summary>
```json
{"campaign":{"order":["before","after","after","before"],"trialsPerPhase":1,"maxMeasuredTurns":4,"maxCampaignUsd":1,"sourceHead":"53580f8fbd40b963f3fb7ba5172ff3ede2e9ef1f","reasoning":"provider default, no override","proxySha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04","purpose":"Final matched comparison of both optimizations; distinct from earlier queue-only campaign.","responseTimeoutMs":180000,"timeoutRationale":"Declared before this final campaign because earlier unchanged baselines sometimes exceeded 120 seconds; earlier timeouts remain retained.","ui":{"mode":"built static UI","treeSha256":"7f0c2b7f586cb753408351574b2239e22311944add99af4f6f3562cd6d47bbcb"},"priorCampaign":"combined-proof stopped after a development-UI navigation timeout before Send; no failed attempts erased."},"complete":true,"statistics":{"before":{"attempted":2,"successfulMeasurements":1,"medianTtfrMs":62657.2000002861,"rangeTtfrMs":[62657.2000002861,62657.2000002861],"medianObservedReadyToRunMs":8448.5,"medianRunStartToVisibleMs":37290.199951171875},"after":{"attempted":2,"successfulMeasurements":0,"medianTtfrMs":null,"rangeTtfrMs":null,"medianObservedReadyToRunMs":0.0,"medianRunStartToVisibleMs":null}},"measuredTurnCostUsd":0.00032752,"costCoverage":"Provider-reported measured chat turns only; harness verification probes are additional and not included.","readinessMetricLimit":"First observed ready state sampled every 250 ms plus HTTP duration; clamped to zero if execution started before the observation. This is a lower bound on ready-to-start delay, not a precise sub-millisecond metric.","results":[{"phase":0,"trial":0,"handoff":"before","ttfrMs":62657.2000002861,"answer":"Hi","statuses":["succeeded"],"error":null,"runErrorCode":null,"providerHealthKilled":false,"queueMs":23467.0,"queuedBeforeObservedReady":true,"observedVerificationMsAfterFixture":26390.0,"observedReadyToRunMs":2830.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":37290.199951171875,"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00032752,"costUsdExact":"0.000327520","inputTokens":26864,"outputTokens":46,"cachedInputTokens":0,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"workerSha256":"02adc7e1162fb60439869cec62b75d8fb22fec71155f80535c8e00211cde8326"},{"phase":1,"trial":0,"handoff":"after","ttfrMs":null,"answer":null,"statuses":["failed"],"error":"TimeoutError: page.waitForFunction: Timeout 180000ms exceeded.","runErrorCode":"provider_process_exited","providerHealthKilled":true,"queueMs":14200.0,"queuedBeforeObservedReady":true,"observedVerificationMsAfterFixture":24028.0,"observedReadyToRunMs":0,"readyAndStartedInSameSample":true,"runStartToVisibleMs":null,"usage":[{}],"workerSha256":"ceffb90a6bc97ffaaf8ec7d0267c7bfa7738d321aaf2a618b5efb9b114bc88e7"},{"phase":2,"trial":0,"handoff":"after","ttfrMs":null,"answer":null,"statuses":["failed"],"error":"TimeoutError: page.waitForFunction: Timeout 180000ms exceeded.","runErrorCode":"provider_initialize_timeout","providerHealthKilled":false,"queueMs":13877.0,"queuedBeforeObservedReady":true,"observedVerificationMsAfterFixture":18107.0,"observedReadyToRunMs":0,"readyAndStartedInSameSample":true,"runStartToVisibleMs":null,"usage":[{}],"workerSha256":"ceffb90a6bc97ffaaf8ec7d0267c7bfa7738d321aaf2a618b5efb9b114bc88e7"},{"phase":3,"trial":0,"handoff":"before","ttfrMs":null,"answer":null,"statuses":["running"],"error":"TimeoutError: page.waitForFunction: Timeout 180000ms exceeded.","runErrorCode":null,"providerHealthKilled":false,"queueMs":144256.0,"queuedBeforeObservedReady":true,"observedVerificationMsAfterFixture":136901.0,"observedReadyToRunMs":14067.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":null,"usage":[{}],"workerSha256":"02adc7e1162fb60439869cec62b75d8fb22fec71155f80535c8e00211cde8326"}],"hostLoadSample":{"at":"2026-10-09T20:48:40.031Z","parallelism":18,"load":[93.546875,82.68017578125,75.9091796875]},"measuredChangesCommit":"40b54eafb","postRebaseCommit":"c590770dcc2bb1debce14037935a7031e5c3c1ac","postRebaseLimit":"Live benchmark predates the rebase. No post-rebase live result is claimed.","variantSourceHashes":{"before":{"server/src/modules/agent-lifecycle/application/worker.ts":"02adc7e1162fb60439869cec62b75d8fb22fec71155f80535c8e00211cde8326","packages/adapters/opencode-local/src/server/test.ts":"4c10bacb55f2c7589e7b5c79d74781206ae075db8955f5b998065d6db3c0335a","server/src/adapters/registry.ts":"4a858763f69947d5745c7b8cb251a62fa404bc9683ade0ffb76282ed12761394"},"after":{"server/src/modules/agent-lifecycle/application/worker.ts":"ceffb90a6bc97ffaaf8ec7d0267c7bfa7738d321aaf2a618b5efb9b114bc88e7","packages/adapters/opencode-local/src/server/test.ts":"cd2ea3d51c3f1b4fb42261be701fb7f6b85704ad8e641e6db73d7c58e47364d3","server/src/adapters/registry.ts":"4a858763f69947d5745c7b8cb251a62fa404bc9683ade0ffb76282ed12761394"}},"model":"openrouter/deepseek/deepseek-v4-flash-0731","prompt":"Reply with Hi and an emoji and nothing else.","runnerBinary":{"profile":"release","sha256":"6134c17debda14a76da69ac9631a2d10dad482ebd58dbc9a4e4480ed652211c4"},"probeIsolation":"Explicit empty cwd and HOME/XDG folders under the synthetic fixture workspace in BOTH variants. No server checkout or ambient provider home is used for the hello request.","comparisonLabelNote":"Inner run.mts variant after selects the identical current proxy in every trial; outer campaign readinessHandoff controls before/after source changes."}
```
Queue-only campaign:
```json
{"campaign":{"order":["before","after","after","before"],"trialsPerPhase":2,"maxMeasuredTurns":8,"maxCampaignUsd":1,"sourceHead":"53580f8fbd40b963f3fb7ba5172ff3ede2e9ef1f","reasoning":"provider default, no override","proxySha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04"},"complete":true,"statistics":{"before":{"attempted":4,"successfulMeasurements":1,"medianTtfrMs":59654.5,"rangeTtfrMs":[59654.5,59654.5],"medianObservedReadyToRunMs":19429.0,"medianRunStartToVisibleMs":8843.5},"after":{"attempted":4,"successfulMeasurements":4,"medianTtfrMs":71128.7000002861,"rangeTtfrMs":[63778.90000009537,100195.59999990463],"medianObservedReadyToRunMs":58.0,"medianRunStartToVisibleMs":26542.849975585938}},"measuredTurnCostUsd":0.0055383,"costCoverage":"Provider-reported measured chat turns only; harness verification probes are additional and not included.","readinessMetricLimit":"First observed ready state sampled every 250 ms plus HTTP duration; clamped to zero if execution started before the observation. This is a lower bound on ready-to-start delay, not a precise sub-millisecond metric.","results":[{"phase":0,"trial":0,"handoff":"before","ttfrMs":59654.5,"answer":"Hi 👋","statuses":["succeeded"],"error":null,"queueMs":50590.0,"observedReadyToRunMs":25709.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":8843.5,"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00087852,"costUsdExact":"0.000878520","inputTokens":25644,"outputTokens":264,"cachedInputTokens":28416,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"workerSha256":"02adc7e1162fb60439869cec62b75d8fb22fec71155f80535c8e00211cde8326"},{"phase":0,"trial":1,"handoff":"before","ttfrMs":null,"answer":null,"statuses":["failed"],"error":"TimeoutError: page.waitForFunction: Timeout 120000ms exceeded.","queueMs":41651.0,"observedReadyToRunMs":14656.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":null,"usage":[{}],"workerSha256":"02adc7e1162fb60439869cec62b75d8fb22fec71155f80535c8e00211cde8326"},{"phase":1,"trial":0,"handoff":"after","ttfrMs":100195.59999990463,"answer":"Hi 🙂","statuses":["succeeded"],"error":null,"queueMs":65893.0,"observedReadyToRunMs":116.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":33243.60009765625,"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00075782,"costUsdExact":"0.000757820","inputTokens":27014,"outputTokens":175,"cachedInputTokens":26368,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"workerSha256":"ceffb90a6bc97ffaaf8ec7d0267c7bfa7738d321aaf2a618b5efb9b114bc88e7"},{"phase":1,"trial":1,"handoff":"after","ttfrMs":65288.60000038147,"answer":"Hi 👋","statuses":["succeeded"],"error":null,"queueMs":43511.0,"observedReadyToRunMs":0,"readyAndStartedInSameSample":true,"runStartToVisibleMs":21227.60009765625,"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00085326,"costUsdExact":"0.000853260","inputTokens":25166,"outputTokens":250,"cachedInputTokens":28160,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"workerSha256":"ceffb90a6bc97ffaaf8ec7d0267c7bfa7738d321aaf2a618b5efb9b114bc88e7"},{"phase":2,"trial":0,"handoff":"after","ttfrMs":63778.90000009537,"answer":"Hi 👋","statuses":["succeeded"],"error":null,"queueMs":39218.0,"observedReadyToRunMs":0,"readyAndStartedInSameSample":true,"runStartToVisibleMs":23479.89990234375,"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.000839,"costUsdExact":"0.000839000","inputTokens":27068,"outputTokens":238,"cachedInputTokens":26368,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"workerSha256":"ceffb90a6bc97ffaaf8ec7d0267c7bfa7738d321aaf2a618b5efb9b114bc88e7"},{"phase":2,"trial":1,"handoff":"after","ttfrMs":76968.80000019073,"answer":"Hi 👋","statuses":["succeeded"],"error":null,"queueMs":46257.0,"observedReadyToRunMs":185.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":29605.800048828125,"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00030582,"costUsdExact":"0.000305820","inputTokens":24694,"outputTokens":32,"cachedInputTokens":1792,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"workerSha256":"ceffb90a6bc97ffaaf8ec7d0267c7bfa7738d321aaf2a618b5efb9b114bc88e7"},{"phase":3,"trial":0,"handoff":"before","ttfrMs":null,"answer":null,"statuses":["succeeded"],"error":"TimeoutError: page.waitForFunction: Timeout 120000ms exceeded.","queueMs":100979.0,"observedReadyToRunMs":3872.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":null,"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00190388,"costUsdExact":"0.001903880","inputTokens":25524,"outputTokens":852,"cachedInputTokens":55808,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"workerSha256":"02adc7e1162fb60439869cec62b75d8fb22fec71155f80535c8e00211cde8326"},{"phase":3,"trial":1,"handoff":"before","ttfrMs":null,"answer":null,"statuses":["running"],"error":"TimeoutError: page.waitForFunction: Timeout 120000ms exceeded.","queueMs":129391.0,"observedReadyToRunMs":24202.0,"readyAndStartedInSameSample":false,"runStartToVisibleMs":null,"usage":[{}],"workerSha256":"02adc7e1162fb60439869cec62b75d8fb22fec71155f80535c8e00211cde8326"}]}
```
</details>
### Matched live browser latency evidence — 2026-10-09
**Conclusion: the overall first-response speedup is not established.**
Twelve successful real browser runs produced a lower after median, but
the updated path won only 3 of 6 adjacent pairs. Median paired
improvement was -0.17 seconds (effectively tied). Do not treat the
deterministic streaming-forwarding improvement as proof that this PR
fixes end-to-end first-response latency.
- **Actual path:** local Paperclip browser → real server/database →
current optimized Rust runner → pinned OpenCode 1.18.34 → OpenRouter
`deepseek/deepseek-v4-flash-0731`. Default reasoning in both variants;
no disabled-reasoning override.
- **Prompt:** `Reply with Hi and an emoji and nothing else.` Fresh
company, agent, chat, and per-turn native provider process for each
trial; same QA fixture instructions and selected model.
- **Comparison:** current product/runner at
`53580f8fbd40b963f3fb7ba5172ff3ede2e9ef1f` held constant. The baseline
substitutes the exact `opencode-app-server-proxy.ts`,
`opencode-proxy-task-envelope.ts`, and `opencode-server-driver.ts`
contents from pre-PR `41fec8c8921f9fb19c13fe11e2c9b71bf1017317`. This
isolates those changed modules; it is not an entire old-checkout
comparison.
- **Metric:** browser capture-phase Send click to a rendered `Hi`
markdown answer plus two animation frames, with a screenshot of the
answer. Thinking, tool labels, and status indicators do not count. This
is a DOM/render measurement, not instrumented compositor pixel timing.
- **Order/bound:** predeclared `before, after, after, before` repeated
three times; six trials per variant; 120-second response timeout; $1
campaign guard. All 12 measured trials returned `Hi` and an emoji and
finished successfully; none omitted.
- **Result:** before median **48.08 s** (37.42–66.40); after median
**42.50 s** (27.68–63.32). The 11.6% lower median alone is not
persuasive evidence of a reliable improvement given the mixed paired
results and broad overlap.
- **Remaining delay:** retained queue timestamps for 10/12 trials show
**9.76–41.65 seconds from run creation to execution start**. This is
before the OpenCode path changed here. Its cause is not established by
this benchmark. The final two queue reads were unavailable after
automatic server shutdown; all twelve primary browser timings were
retained.
- **Cost:** $0.010517369 provider-reported across the 12 measured turns;
$0.011371499 including the successful setup pilot. This is separate from
the older diagnostics listed below.
- **Retained setup attempts:** two failures before Send (composer
locator and transpiler helper); one baseline startup failure before any
observed model request (`SIGKILL` while probing OpenCode health); one
successful current-code pilot whose selector missed the visible reply.
These are retained separately, not silently included/excluded as valid
timings. The measured batch used the corrected selector and the same
release binary for both variants.
- **Limits:** local development server and headless Chromium on macOS
arm64, small sample, variable queue timing/provider routing/cache. This
does not qualify production/cloud performance or isolate the
contributions of each changed module. Server, browser, and owned runs
were stopped; original proxy build artifact restored; no product source
files changed for this experiment.
| Pair | Before: Send → visible Hi | After: Send → visible Hi | Faster
variant |
| --- | ---: | ---: | --- |
| 1 | 66.40 s | 27.68 s | After |
| 2 | 37.42 s | 28.00 s | After |
| 3 | 39.75 s | 55.22 s | Before |
| 4 | 47.32 s | 63.32 s | Before |
| 5 | 48.85 s | 29.79 s | After |
| 6 | 51.31 s | 61.07 s | Before |
<details>
<summary>Sanitized measurement records, source/binary hashes, usage, and
retained attempt classification</summary>
```json
{"manifest":{"candidate":"53580f8fbd40b963f3fb7ba5172ff3ede2e9ef1f","baseline":"41fec8c8921f9fb19c13fe11e2c9b71bf1017317","comparison":"Same current product and runner; replace the three OpenCode proxy/driver source modules with exact pre-PR contents for baseline. Reasoning uses defaults in both.","model":"openrouter/deepseek/deepseek-v4-flash-0731","prompt":"Reply with Hi and an emoji and nothing else.","samplesPerVariant":6,"order":["before","after","after","before","before","after","after","before","before","after","after","before"],"maxTurnMs":120000,"maxCostUsd":1,"variants":{"before":{"sources":{"src/cli/opencode-app-server-proxy.ts":"e9b46c937d7ce3b51dc44181a2a3ad82befda9ebe184adf80c0a6b30da140fd6","src/cli/opencode-proxy-task-envelope.ts":"fc23f8a515c2c4d1551f6b95e5b38e6254849dec23f7396e76b646e170a6e006","src/drivers/opencode/opencode-server-driver.ts":"99de415e8fc3bb5fb6f8d7512d751c4c37d2aa77a18b0546b9fb232f1a6fb6c5"},"bundleSha256":"6dd8726e72545341f6772e54ec5aeb6264dec74db67290df44930d87135efb6b"},"after":{"sources":{"src/cli/opencode-app-server-proxy.ts":"fa800e9bccce02f05f1af83e225d3b5a1300d0a7d4c35ac548f400d6c0a83f79","src/cli/opencode-proxy-task-envelope.ts":"5c387614fc9832322686326b8482eb00d88699d491b05cf59cadcd94a41194ea","src/drivers/opencode/opencode-server-driver.ts":"a944f3bf7f1bf897daec3a5dc2aa34ee9d1a2133efcb3cf150b002095a0ec586"},"bundleSha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04"}},"runnerBinary":{"profile":"release","sha256":"6134c17debda14a76da69ac9631a2d10dad482ebd58dbc9a4e4480ed652211c4"},"metric":"Browser Send capture-phase click to visible Hi answer, sampled on animation frames, plus two paint opportunities. Excludes reasoning/tool/status text.","setupAttempts":["setup-failure-1","setup-failure-2","startup-failure-3","pilot-selector-failure"]},"summary":{"before":{"attempts":6,"measured":6,"medianMs":48083.050000190735,"minMs":37420.5,"maxMs":66397.69999980927,"totalCostUsd":0.004945229,"toolCalls":[4,1,0,0,0,1]},"after":{"attempts":6,"measured":6,"medianMs":42504.049999952316,"minMs":27680.099999904633,"maxMs":63320.90000009537,"totalCostUsd":0.00557214,"toolCalls":[0,1,0,4,0,1]},"medianReductionPercent":11.602841334350234,"medianPairedImprovementMs":-168.59999990463257,"reportedCampaignCostUsdIncludingPilot":0.011371498999999998},"pairs":[{"indices":[0,1],"beforeMs":66397.69999980927,"afterMs":27680.099999904633,"improvementMs":38717.59999990463},{"indices":[2,3],"beforeMs":37420.5,"afterMs":27997,"improvementMs":9423.5},{"indices":[4,5],"beforeMs":39751.60000038147,"afterMs":55217.199999809265,"improvementMs":-15465.599999427795},{"indices":[6,7],"beforeMs":47318.90000009537,"afterMs":63320.90000009537,"improvementMs":-16002.0},{"indices":[8,9],"beforeMs":48847.2000002861,"afterMs":29790.900000095367,"improvementMs":19056.300000190735},{"indices":[10,11],"beforeMs":51311.7000002861,"afterMs":61072.40000009537,"improvementMs":-9760.699999809265}],"trials":[{"index":0,"variant":"before","startedAt":"2026-10-09T19:15:23.172Z","measurementError":null,"ttfrMs":66397.69999980927,"domMs":66390.59999990463,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.002612595,"costUsdExact":"0.002612595","inputTokens":55962,"outputTokens":1344,"cachedInputTokens":83456,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6dd8726e72545341f6772e54ec5aeb6264dec74db67290df44930d87135efb6b","toolCalls":["paperclip_get_task_context","paperclip_comment_on_task","paperclip_finish","paperclip_finish"],"eventCounts":{"turn.started":1,"tool.execution.started":4,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:15:58.194Z","turn.submitted":"2026-10-09T19:15:58.311Z","turn.started":"2026-10-09T19:15:59.063Z","firstTextDelta":"2026-10-09T19:16:36.039Z","turn.completed":"2026-10-09T19:16:36.118Z"},"completedRunDurationsMs":[42915.0]},{"index":1,"variant":"after","startedAt":"2026-10-09T19:16:36.598Z","measurementError":null,"ttfrMs":27680.099999904633,"domMs":27636.599999904633,"answer":"Hi","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00030429,"costUsdExact":"0.000304290","inputTokens":26845,"outputTokens":28,"cachedInputTokens":0,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04","toolCalls":[],"eventCounts":{"turn.started":1,"item.delta":3,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:17:00.717Z","turn.submitted":"2026-10-09T19:17:00.841Z","turn.started":"2026-10-09T19:17:01.508Z","firstTextDelta":"2026-10-09T19:17:05.934Z","turn.completed":"2026-10-09T19:17:06.205Z"},"completedRunDurationsMs":[14435.0]},{"index":2,"variant":"after","startedAt":"2026-10-09T19:17:08.762Z","measurementError":null,"ttfrMs":27997,"domMs":27984.599999904633,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00101016,"costUsdExact":"0.001010160","inputTokens":27544,"outputTokens":366,"cachedInputTokens":26624,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04","toolCalls":["paperclip_finish"],"eventCounts":{"turn.started":1,"tool.execution.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:17:26.192Z","turn.submitted":"2026-10-09T19:17:26.305Z","turn.started":"2026-10-09T19:17:26.936Z","firstTextDelta":"2026-10-09T19:17:40.688Z","turn.completed":"2026-10-09T19:17:40.826Z"},"completedRunDurationsMs":[17763.0]},{"index":3,"variant":"before","startedAt":"2026-10-09T19:17:41.376Z","measurementError":null,"ttfrMs":37420.5,"domMs":37364.40000009537,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.000693018,"costUsdExact":"0.000693018","inputTokens":24236,"outputTokens":282,"cachedInputTokens":27648,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6dd8726e72545341f6772e54ec5aeb6264dec74db67290df44930d87135efb6b","toolCalls":["paperclip_finish"],"eventCounts":{"turn.started":1,"tool.execution.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:18:12.381Z","turn.submitted":"2026-10-09T19:18:12.616Z","turn.started":"2026-10-09T19:18:13.441Z","firstTextDelta":"2026-10-09T19:18:21.746Z","turn.completed":"2026-10-09T19:18:22.262Z"},"completedRunDurationsMs":[29216.0]},{"index":4,"variant":"before","startedAt":"2026-10-09T19:18:23.000Z","measurementError":null,"ttfrMs":39751.60000038147,"domMs":39705.7000002861,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.000265747,"costUsdExact":"0.000265747","inputTokens":26123,"outputTokens":77,"cachedInputTokens":0,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6dd8726e72545341f6772e54ec5aeb6264dec74db67290df44930d87135efb6b","toolCalls":[],"eventCounts":{"turn.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:19:01.000Z","turn.submitted":"2026-10-09T19:19:01.163Z","turn.started":"2026-10-09T19:19:01.893Z","firstTextDelta":"2026-10-09T19:19:07.169Z","turn.completed":"2026-10-09T19:19:07.384Z"},"completedRunDurationsMs":[15843.0]},{"index":5,"variant":"after","startedAt":"2026-10-09T19:19:10.050Z","measurementError":null,"ttfrMs":55217.199999809265,"domMs":55204.89999961853,"answer":"Hi 🙂","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00030421,"costUsdExact":"0.000304210","inputTokens":4294,"outputTokens":28,"cachedInputTokens":22543,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04","toolCalls":[],"eventCounts":{"turn.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:19:59.877Z","turn.submitted":"2026-10-09T19:19:59.990Z","turn.started":"2026-10-09T19:20:00.713Z","firstTextDelta":"2026-10-09T19:20:07.290Z","turn.completed":"2026-10-09T19:20:07.658Z"},"completedRunDurationsMs":[15104.0]},{"index":6,"variant":"after","startedAt":"2026-10-09T19:20:09.550Z","measurementError":null,"ttfrMs":63320.90000009537,"domMs":63313.09999990463,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00260723,"costUsdExact":"0.002607230","inputTokens":137971,"outputTokens":951,"cachedInputTokens":1024,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04","toolCalls":["paperclip_comment_on_task","paperclip_get_task_context","paperclip_comment_on_task","paperclip_finish"],"eventCounts":{"turn.started":1,"tool.execution.started":4,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:20:59.730Z","turn.submitted":"2026-10-09T19:20:59.859Z","turn.started":"2026-10-09T19:21:00.501Z","firstTextDelta":"2026-10-09T19:21:19.416Z","turn.completed":"2026-10-09T19:21:19.608Z"},"completedRunDurationsMs":[26519.0]},{"index":7,"variant":"before","startedAt":"2026-10-09T19:21:20.519Z","measurementError":null,"ttfrMs":47318.90000009537,"domMs":47246.800000190735,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.000257965,"costUsdExact":"0.000257965","inputTokens":4700,"outputTokens":71,"cachedInputTokens":21407,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6dd8726e72545341f6772e54ec5aeb6264dec74db67290df44930d87135efb6b","toolCalls":[],"eventCounts":{"turn.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:22:03.924Z","turn.submitted":"2026-10-09T19:22:04.439Z","turn.started":"2026-10-09T19:22:04.772Z","firstTextDelta":"2026-10-09T19:22:09.915Z","turn.completed":"2026-10-09T19:22:10.343Z"},"completedRunDurationsMs":[16702.0]},{"index":8,"variant":"before","startedAt":"2026-10-09T19:22:11.124Z","measurementError":null,"ttfrMs":48847.2000002861,"domMs":48802.59999990463,"answer":"Hi 🎉","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.000327654,"costUsdExact":"0.000327654","inputTokens":44796,"outputTokens":32,"cachedInputTokens":0,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6dd8726e72545341f6772e54ec5aeb6264dec74db67290df44930d87135efb6b","toolCalls":[],"eventCounts":{"turn.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:22:57.182Z","turn.submitted":"2026-10-09T19:22:57.281Z","turn.started":"2026-10-09T19:22:57.988Z","firstTextDelta":"2026-10-09T19:23:02.915Z","turn.completed":"2026-10-09T19:23:03.035Z"},"completedRunDurationsMs":[9541.0]},{"index":9,"variant":"after","startedAt":"2026-10-09T19:23:03.579Z","measurementError":null,"ttfrMs":29790.900000095367,"domMs":29748.800000190735,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00034054,"costUsdExact":"0.000340540","inputTokens":24710,"outputTokens":59,"cachedInputTokens":1792,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04","toolCalls":[],"eventCounts":{"turn.started":1,"item.delta":2,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:23:28.840Z","turn.submitted":"2026-10-09T19:23:28.954Z","turn.started":"2026-10-09T19:23:29.666Z","firstTextDelta":"2026-10-09T19:23:35.306Z","turn.completed":"2026-10-09T19:23:35.531Z"},"completedRunDurationsMs":[12732.0]},{"index":10,"variant":"after","startedAt":"2026-10-09T19:23:37.247Z","measurementError":null,"ttfrMs":61072.40000009537,"domMs":61061.300000190735,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00100571,"costUsdExact":"0.001005710","inputTokens":25307,"outputTokens":368,"cachedInputTokens":28160,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6691475ed55f10179ec6ee0023a1f6462982f763848da7cd5b1d0baf38633b04","toolCalls":["paperclip_finish"],"eventCounts":{"turn.started":1,"tool.execution.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:24:33.721Z","turn.submitted":"2026-10-09T19:24:33.832Z","turn.started":"2026-10-09T19:24:34.601Z","firstTextDelta":"2026-10-09T19:24:43.135Z","turn.completed":"2026-10-09T19:24:43.278Z"},"completedRunDurationsMs":[17387.0]},{"index":11,"variant":"before","startedAt":"2026-10-09T19:24:44.710Z","measurementError":null,"ttfrMs":51311.7000002861,"domMs":51300.5,"answer":"Hi 👋","runCount":1,"statuses":["succeeded"],"usage":[{"model":"openrouter/deepseek/deepseek-v4-flash-0731","costUsd":0.00078825,"costUsdExact":"0.000788250","inputTokens":24316,"outputTokens":356,"cachedInputTokens":27648,"cacheWriteTokens":0,"usageSource":"per_run","costStatus":"reported"}],"bundleSha256":"6dd8726e72545341f6772e54ec5aeb6264dec74db67290df44930d87135efb6b","toolCalls":["paperclip_finish"],"eventCounts":{"turn.started":1,"tool.execution.started":1,"item.delta":1,"turn.completed":1},"eventTimes":{"session.started":"2026-10-09T19:25:31.347Z","turn.submitted":"2026-10-09T19:25:31.463Z","turn.started":"2026-10-09T19:25:32.208Z","firstTextDelta":"2026-10-09T19:25:39.405Z","turn.completed":"2026-10-09T19:25:39.563Z"},"completedRunDurationsMs":[15446.0]}],"additionalAttempts":[{"attempt":"setup-1","stage":"before_send","result":"non-editable composer locator","modelRequestObserved":false},{"attempt":"setup-2","stage":"before_send","result":"transpiler helper absent in browser","modelRequestObserved":false},{"attempt":"startup-pilot-before","runnerProfile":"debug","result":"no visible reply within 120s; OpenCode health startup SIGKILL; retained infrastructure failure","modelRequestObserved":false},{"attempt":"selector-pilot-after","runnerProfile":"debug","result":"Hi reply succeeded; browser selector missed it; no valid TTFR","providerReportedCostUsd":0.00085413}],"queueTimingCoverage":{"measuredTrials":10,"totalTrials":12,"records":[{"index":0,"runs":[{"createdAt":"2026-10-09T19:15:28.998Z","startedAt":"2026-10-09T19:15:53.558Z","queuedMs":24560.0}]},{"index":1,"runs":[{"createdAt":"2026-10-09T19:16:38.520Z","startedAt":"2026-10-09T19:16:54.157Z","queuedMs":15637.0}]},{"index":2,"runs":[{"createdAt":"2026-10-09T19:17:10.587Z","startedAt":"2026-10-09T19:17:23.561Z","queuedMs":12974.0}]},{"index":3,"runs":[{"createdAt":"2026-10-09T19:17:43.807Z","startedAt":"2026-10-09T19:17:53.564Z","queuedMs":9757.0}]},{"index":4,"runs":[{"createdAt":"2026-10-09T19:18:28.113Z","startedAt":"2026-10-09T19:18:54.011Z","queuedMs":25898.0}]},{"index":5,"runs":[{"createdAt":"2026-10-09T19:19:12.343Z","startedAt":"2026-10-09T19:19:53.993Z","queuedMs":41650.0}]},{"index":6,"runs":[{"createdAt":"2026-10-09T19:20:14.258Z","startedAt":"2026-10-09T19:20:53.866Z","queuedMs":39608.0}]},{"index":7,"runs":[{"createdAt":"2026-10-09T19:21:23.019Z","startedAt":"2026-10-09T19:21:54.298Z","queuedMs":31279.0}]},{"index":8,"runs":[{"createdAt":"2026-10-09T19:22:14.671Z","startedAt":"2026-10-09T19:22:53.933Z","queuedMs":39262.0}]},{"index":9,"runs":[{"createdAt":"2026-10-09T19:23:06.155Z","startedAt":"2026-10-09T19:23:23.941Z","queuedMs":17786.0}]}],"limitation":"The server shut down before a final API read; queue timing is retained for the first ten trials only."},"conclusion":"No reliable end-to-end speedup established. The after median is lower, but only three of six adjacent matched pairs were faster; median paired improvement is approximately zero. The deterministic streaming-forwarding fix remains separately supported.","limitations":["Local dev server and headless Chromium on macOS arm64; six fresh chats per variant; not a production/cloud latency guarantee.","Current product and current release runner held constant; only three OpenCode modules replaced by their exact pre-PR contents for baseline.","Default model reasoning unchanged; no no-reasoning override or decision policy.","Upstream routing/cache and queue time vary; trials run serially in predeclared counterbalanced ABBA order.","Render proxy: capture-phase Send click to visible nonempty Hi markdown, then two animation frames; screenshot verifies the rendered answer. This is not instrumented compositor pixel timing.","Two setup-only failures, one startup failure, and one invalid-measurement successful pilot are retained separately, not silently treated as successful timings."],"reproducibility":{"harnessSha256":"f93996b306c7d31c19bfcb9cc197653f867944ffb900d81a23a34f831e17c0c5","variantBuilderSha256":"4e88a7bbdc0de5d72601194ebe3b96d9c6f6eda5a33d8e0f00cf2d5d14db34c2","analyzerSha256":"2d129177a1b8033f768aad3c82dc8fff70ba0ba76e7270b2d8612ee760d4aaf4"}}
```
</details>
- Latest options-struct refactor: 33 provider tests and 86 backend tests
passed. Four port-dependent fixtures initially failed inside the sandbox
and passed with loopback access. Latest check snapshot: 51 successes, 4
skips, and 2 failures (`ci / e2e` and `ci / e2e shard (5/8)`). This
latency experiment does not make the PR merge-ready.
- Focused TypeScript suites passed: OpenCode driver, per-turn reasoning,
prepared-context recovery, proxy envelope, live sessions, Codex context
control, and native instruction measurements. The real runnerd/proxy
integration test confirms disabled followed by default in the same
session. A stale staged binary initially hid the new parameter;
rebuilding the release runner resolved it.
- Capability-guard regression suites passed all 53 tests; the real
runner/proxy boundary still accepts the per-turn selection. Both
OpenRouter and non-OpenRouter real runner/proxy cases passed, along with
62 existing OpenCode fixture tests. Runner TypeScript build passed after
the final correction.
- Affected Rust modules passed: 33 provider tests and 86 durable backend
tests. Malformed or unsupported reasoning selections do not dispatch a
provider turn or poison admission state.
- Pinned OpenCode 1.18.34 with a local OpenRouter-compatible fixture
sent three successive provider requests with reasoning omitted,
`enabled: false`, then omitted. Each request contained one copy of the
agent instructions. No paid provider call was needed.
- The reconstructed first-turn task envelope shrank from 4,356 to 460
characters. This is a payload-size measurement, not a claimed token or
latency reduction. Existing stored conversation history is not
rewritten.
- Prior head `8c07fe2e70267a7c8a3118f1071eca73ecdc6c8a`: all 53 checks
passed, with four intentional skips. Greptile is 5/5 with no open
findings. One bounded retry cleared first-test timeouts, a legacy
signoff lease failure, and CI runner shutdowns. The timed-out suites
also passed locally (14 auth-signal tests, 40 device-login tests, and
the runner resume case).
- Known reported diagnostic usage totals about $0.0029. Two prematurely
closed baseline warm-turn attempts are excluded from latency comparisons
and their usage is not fully captured; background provider usage is also
not fully accounted. No further paid runs are active.
- `pnpm -r typecheck`: passed. Runner TypeScript typechecks and build
also passed after the review correction.
- `pnpm test:run`: attempted and stopped after a reproducible failure in
the untouched Codex recovery test `archives a damaged prior epoch before
completing guarded same-task replacement with real runnerd`
(`server/src/services/native-runtime/native-session-resume.test.ts:1072`).
It returns `needs_review` / failed instead of done / succeeded,
including when rerun alone. The broad local suite is not green. The two
initial collection failures disappeared after building; their isolated
rerun passed all 1,565 tests.
- `pnpm build`: passed.
- Pinned real OpenCode plus a delayed local provider: first native delta
to Paperclip delta fell from 1,496 ms to less than 1 ms at millisecond
measurement resolution. This isolates forwarding delay, not
network/model inference.
- Two live driver samples after the patch reached first text in
2.28–2.62 seconds including session startup. Baseline first responses
took 12.37–13.43 seconds. Small unmatched samples had different
reasoning/cache outcomes, so these are observations, not an attributed
speedup ratio.
- Full compiled runnerd protocol diagnostic: completed with `Hi 👋`;
first assistant delta at 9.19 seconds and cleanup complete at 9.44
seconds. The seeded mock-control-plane harness used 27,512 input tokens
across two provider requests, split into 13,521 and 13,991. The extra
`answer_status_question` call posted `Hi 👋` to the mock task in 12 ms,
then caused another model request. A reconstruction contains 25 tools
(35.3k JSON characters), 12.8k system characters, and a 4.4k task
envelope; 3.9k instruction characters appear in both system and task
context. Provider-reported cost was $0.00073976; the pricing-table
estimate was $0.00395332. This is one integration diagnostic, not a
production latency claim.
- A separate full-runner sample with existing lazy tool discovery also
completed, but took 14.64 seconds through cleanup and called
`paperclip_finish`. Its usage ledger recorded 12,888 input and 11,776
cached-input tokens, with $0.00096344 provider-reported cost. This did
not establish a latency improvement, so the default tool exposure was
not changed.
- Four direct OpenRouter requests separately measured default reasoning
at 2.45/3.90 seconds to first text and disabled reasoning at 0.66/0.53
seconds. Default reasoning remains unchanged; disabling it requires the
explicit per-turn option.
## Risks
- Immediate readiness dispatch changes scheduling timing. It uses
existing admission checks and preserves the periodic sweep as recovery.
- Native model verification relies on the real request rather than
catalog enumeration. The final live batch had provider startup failures;
overall speed and reliability are not qualified.
- Incremental chunks without IDs cannot safely be deduplicated by
content. Repeated identical chunks are valid. Known-ID duplicates remain
suppressed.
- OpenCode uses its bundled model catalog plus the explicit
selected-model entry. New remote catalog metadata will not refresh
during isolated startup.
- Default provider plugins are disabled. This runner supplies
credentials and assigned MCP tools through its own controlled
configuration.
- Disabled reasoning is supported only on the OpenCode/OpenRouter path
and requires a compatible model. It applies to one turn and is not an
automatic latency policy.
- The matched live browser sample is small and does not establish a
reliable end-to-end improvement. It includes local queueing/startup and
browser rendering, but does not qualify production or remote sandbox
latency.
## Model Used
OpenAI GPT-6 (Codex). Tool use, code editing, and command execution were
used. The session does not expose a more specific model ID or
context-window size. Live diagnostic target: DeepSeek
`deepseek/deepseek-v4-flash-0731` through OpenRouter and OpenCode
1.18.34.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
<!-- Write all pull request text in Simplified Technical English
(ASD-STE100). -->
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Task descriptions, comments, continuation data, skills, and
execution rules enter several agent adapters.
> - The same source can be rendered by more than one automatic input
carrier.
> - Failed resumes can also rebuild input from stale or compact context.
> - This pull request gives each Paperclip-owned source one delivery
owner and preserves the required transport boundaries.
> - It adds deterministic adapter, interaction, runner, and browser
tests for these boundaries.
> - The benefit is more predictable context delivery with explicit
evidence for later live qualification.
## Linked Issues or Issue Description
Related: #13144 removes a duplicate environment payload and bounds wake
lists. Related: #11360 addresses Hermes resume behavior. This pull
request preserves compatible active-session formats while repairing
context ownership and stale question creation.
**What happened?**
Task descriptions and comments could enter more than one automatic
context block. Native transports could wrap a complete model input in a
second task envelope. Some legacy and gateway adapters could omit the
owned assignment on ordinary tasks or rebuild a failed resume with stale
compact context. A continuation could also request a question after
newer human comments had arrived.
**Expected behavior**
Each task or comment source has one automatic model-facing owner.
Distinct comment IDs and repeated wording remain distinct. Fresh
fallback attempts rebuild the required full context. A question request
is rejected when newer queued human direction makes it stale. Harness
access policy remains owned by execution configuration.
**Steps to reproduce**
1. Build a task with a description and current comments.
2. Capture the actual adapter or runner input.
3. Compare source ownership and task-envelope nesting.
4. Queue a human comment before a continuation requests a question.
5. Trigger a failed resume and inspect the fresh retry input.
6. Run the focused adapter, interaction, runner, and browser checks.
## What Changed
- Add shared prompt-section selection at the provider-attempt boundary.
- Deliver owned assignment context through native, legacy CLI, ACP,
gateway, cloud, Pi, Kimi, Grok, Gemini, OpenCode, Cursor, OpenClaw, and
Hermes paths.
- Rebuild full or compact context after resume recovery changes the
attempt. Add native and Claude ACP tests of actual recovery requests.
- Preserve custom templates, loaded instruction files, execution
policies, and older active-session formats.
- Record continuation source metadata and reject stale question creation
under the issue-row lock.
- Add explicit Product E2E context-integrity profiles, prerequisite
gates, credential-isolation checks, and report fixtures.
- Bypass service-worker forwarding for same-origin Vite development
modules. A real Chromium test fails with resource exhaustion before the
repair and passes after it. Production asset caching keeps its existing
policy.
- Add browser diagnostics and service-worker module-loading regressions.
- Add an explicit zero-retry eval option. The default retry behavior
remains unchanged. Each campaign records its effective policy.
- Remove the model-facing working-directory sentence from four prompt
builders. Existing workspace, sandbox, permission, and custom-template
configuration remains unchanged.
- Align the everyday workflow assertion with the current 47-entry
catalog.
Compared with current upstream master, the branch carries the
context-ownership implementation and its tests, the explicit
context-integrity catalog and evidence harness, and the focused browser
regression checks.
## Verification
**Merge assessment:** focused regression evidence supports merge. This
is not full completion of the original broad qualification matrix. The
maintainer has authorized merge after fresh verification of the master
integration.
- Current head: `bbd52f82114eabf09bc7b1a7e97d54a5b43bbc00`. This
integrates current master `2f585ef26a1814fa209715242d1ca791b63e4c4e`.
All 14 conflicts are resolved. Cancellation checks, workspace
finalization, native Grok support, and both sets of tests are retained.
- Current-head Greptile: **5/5**, with no blocking findings. The review
names this exact commit. All **59 reported checks are terminal: 55
successful, 4 skipped, zero pending or failing**. This includes the full
root general and serialized suites, separate runner checks, typecheck,
build, canary, browser E2E, Docker, and security checks. The successful
legacy security status is included in that total.
- After integration: workspace typecheck and full build passed. Separate
runner checks passed: **2,160 TypeScript tests (10 skipped), 582 Rust
tests, and 39 preparation checks**. Other passing checks include 621
Product E2E harness units, 376 focused shared/adapter tests, 160
real-database/API tests, 86 Hermes tests, 18 browser-support checks, and
Product E2E typechecking. The complete root suite passed in CI. The
duplicate local monolithic root run was stopped after that CI result; it
is not counted as a completed local pass.
- New native recovery coverage retains full assignment, completion
contract, and explicit skill selection after safe replacement, for old
and prepared input formats. Full native session test file: **136/136
passed**.
- New Claude ACP coverage captures actual fresh, resumed, and
missing-session fallback requests. It verifies one assignment copy,
comment order, identical text under distinct comment IDs, and full
fallback context. Full file: **33/33 passed**. Both affected TypeScript
checks passed.
- Existing deterministic tests cover source revisions, approval and
trust boundaries, completion validation, custom templates, compatible
sessions, standalone driver wrapping, and maintained adapter transport
requests.
- Provider-free browser support: **17/17 passed** after the master
merge. Service-worker unit tests: **33/33 passed**. The module-overload
regression failed before the repair and passed after it in real
Chromium.
### Fresh live comparisons
The new batch ran exactly four Product E2E attempts. **All four passed
on the first attempt; no retries.** Each has six terminal matchers plus
the existing browser lifecycle and invariant checks.
| Exact case ID | Control | Candidate |
|---|---|---|
| `core-compatibility.runner-codex.local.plan-revise-accept` | Passed |
Passed |
|
`local-session-integrity.runner-acpx-claude.local.structured-question-restart-resume`
| Passed | Passed |
The plan case checks a revised canonical plan and revision-bound
approval before completion. The question case restarts the server before
submitting the answer, then verifies the continuation completes.
Control source is `dfa4e1bda8d50a1a01746603251a9128dbe9d0d6`. Candidate
source is `79fcdb5dece501d28064ea9da306603881b46f0c`. They use identical
frozen definitions and provider versions: Codex `0.156.0` with
`gpt-5.6-sol`; ACPX `0.13.1` / Claude ACP `0.73.0` with
`claude-sonnet-5`. The September 24 head added master browser recovery
and test-only changes. The September 28 head also integrates newer
master changes, including cancellation, workspace finalization, and
native Grok. These are frozen-source live results, not exact-head live
runs.
The candidate received one description copy where the control initially
received three. The submitted initial plan envelopes were 7,969 versus
19,097 characters. Question envelopes were 7,592 versus 18,919. These
are structural measurements, not whole-provider token or dollar savings.
### Earlier evidence and failed attempts
- The preceding fresh batch has four effective passing pairs: OpenCode
comment continuation and assigned skill, native Codex comment
continuation, and native Claude comment continuation. It retains **11
attempts: eight passed and three failed**.
- Original failures remain recorded: missing local PostgreSQL library
links before task creation; host-sleep cleanup after task/page checks
passed; and a Claude **control** session-open rejection before a model
turn. Setup was repaired identically on both worktrees. The permitted
unchanged infrastructure retries passed. The underlying Claude provider
startup error was not retained and remains unknown.
- Older R2 retains **17 passes and one failure** across 18 attempts,
including eight both-pass native/legacy Codex/Claude pairs. Its OpenCode
blank-page failure led to the service-worker repair. R2 is historical
evidence: master changed the native fixed prompt and removed duplicate
wake environment data afterward.
- The September 24 CI run initially failed one unrelated preview
readiness test (`ECONNREFUSED` on its local fixture). Its test and
production code match master. Isolated local verification passed **28
tests, 3 skipped**. One unchanged CI retry passed the full shard: **831
passed, 1 skipped**, including all **31 preview-exposure tests**. The
aggregate CI gate passed afterward. The precise startup cause remains
unknown; a port race is a hypothesis, not a proved cause.
### Limits
The original wider profile/workflow matrix, repeated trials, and remote
Daytona qualification are incomplete. These results support a focused
merge recommendation, not statistical equivalence or universal harness
qualification. Some usage receipts are missing in both variants, so no
token or dollar savings are claimed. The $500 ceiling was preserved
using conservative allowances; failed attempts and unknown charges
remain in the ledger.
Reproduce the focused additions with `pnpm exec vitest run
packages/adapters/claude-local/src/server/acp.test.ts` and `pnpm
--filter @paperclipai/paperclip-runner exec vitest run
src/native-session-runtime.test.ts`. Full checks use `pnpm -r
typecheck`, `pnpm test:run`, `pnpm build`, and the separate runner
checks. Paid evals require the frozen definitions, profiles, and
credentials; do not use `--all` as a substitute for the selected cases.
## Risks
- Context placement changes can affect model behavior. Deterministic
checks cover the selected paths, but live qualification remains
incomplete.
- The stale-question guard can reject a request when queued human
comments arrived during the run. This is intended.
- New stored inputs and model envelopes retain compatibility readers for
older active sessions.
- Custom templates may intentionally repeat content.
- Removing a model-facing working-directory sentence does not change
filesystem, command, sandbox, or permission configuration.
- The worker bypass applies only to same-origin development module
paths. Cache-policy tests preserve private-response handling and
production asset caching. Mounted HTTP fixture changes remain test-only.
- This PR does not claim measured token savings or statistical
equivalence across every harness.
## Model Used
OpenAI Codex, exact model gpt-6-astra, with repository tools and code
execution. Bounded supporting work used gpt-5.6-luna and gpt-6-luna. The
serving context-window size is not exposed in this task.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have described the issue in-PR using the required issue fields
- [x] I have not referenced internal/instance-local Paperclip issues or
links
- [x] My branch name describes the change and contains no internal
ticket id
- [x] I have run the focused local checks and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect these changes
- [x] I have considered and documented risks above
- [x] All current-head Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
for the current head
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner provides a durable execution boundary for supported
providers.
> - The current production runtime supports Codex but cannot execute
OpenCode sessions.
> - OpenCode needs a qualified transport, strict input mapping, and
normalized events.
> - This pull request adds the OpenCode runtime as one isolated provider
unit.
> - The benefit is a reviewable provider expansion that does not weaken
the existing Codex path.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting: packages/paperclip-runner and the Codex-local adapter
configuration contract.
**Problem or motivation**
Paperclip Runner has provider-neutral contracts, but the production
backend factory cannot start a qualified OpenCode session. This blocks
OpenCode from using the durable runner path.
**Proposed solution**
Add the qualified OpenCode app-server proxy, driver, MCP bridge,
backend, fixtures, and factory wiring. Keep existing Codex behavior
unchanged.
**Alternatives considered**
Keeping OpenCode only on the direct adapter path would avoid this
runtime work, but it would not provide durable runner recovery or
normalized provider events.
**Roadmap alignment**
ROADMAP.md does not list a conflicting provider-runtime project. This
change extends the existing Paperclip Runner architecture.
## What Changed
- Added the qualified OpenCode app-server proxy and input queue.
- Added collaboration-mode and provider-event normalization.
- Added the OpenCode MCP bridge and native session backend.
- Added strict fixtures and focused unit coverage.
- Added only the package exports and adapter configuration required by
this runtime.
- Kept deferred SDK, lab, eval, and public package surfaces out of this
change.
## Verification
- GitHub Actions is the authoritative verification environment for this
PR.
- Run the package type checks and focused OpenCode tests in CI.
- Run repository typecheck, test, build, security, and policy gates
through the stack-aware workflow.
- Local tests were not run because this checkout is resource
constrained.
## Risks
- OpenCode protocol changes could affect event normalization or
recovery.
- The driver fails closed on malformed input and unsupported runtime
behavior.
- Existing Codex selection remains unchanged unless the stored provider
is OpenCode.
> For core feature work, check [ROADMAP.md](ROADMAP.md) first and
discuss it in #dev before opening the PR. Feature PRs that overlap with
planned core work may need to be redirected.
## Model Used
OpenAI Codex, GPT-5.6, with repository tools, code execution, and
parallel agent review.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either linked existing issues or described the issue in-PR
following the relevant issue template
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
Paperclip ticket id
- [ ] I have run tests locally and they pass — GitHub Actions is
authoritative for this resource-constrained checkout
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Stack
- Position: 1 of 4
- Base: master
- Next: additional qualified provider runtimes
