mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-12 22:56:58 +01:00
2b461b2f5801dddb8b0a5bb4d194bc6f136b2c71
81
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 DottaandClaude Opus 5.5
|
465da4227a |
fix(runner): drop a tool target path that breaks a line so the controller can acknowledge its event (#20238)
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The Paperclip Runner turns provider tool calls into durable PRP
events. The controller acknowledges each event only after it validates
and commits it.
> - The controller's event schema forbids line terminators in a safe
path such as `tool.execution` `target`.
> - The ACPX sidecar and the Rust runner accepted a location path that
contained a newline. Claude sometimes emits a malformed Write call that
puts the file content into the path.
> - The controller refused that event without an acknowledgement. The
runner redelivered the same bytes, and the run stopped making progress
for 14 minutes (2,848 reconnects).
> - This pull request makes both producers drop such a path, so the
event carries a null target and the controller accepts it.
> - The benefit is that a malformed provider path can no longer wedge a
run's event delivery.
## Linked Issues or Issue Description
**What happened?**
In restart-chaos wave seed 9807 (claude, R1, local), the run stopped
receiving events after runner source seq 33. The runner reconnected
2,848 times in 14 minutes. Offline replay of the saved runner outbox
through the controller's `validatePrpEvent` showed that seq 34 fails
`/payload/target` (the safePath pattern), because the target is
`packages/shared/src/chaos/slug-2c5c3c8f.ts\n<parameter
name="content">export function chaosSlug…`. Seq 35, 39 and 40 (the same
tool call) fail the same way.
**Expected behavior**
The runner never emits an event that the controller's schema refuses. A
malformed tool path becomes a null target, and the tool event still
arrives.
**Steps to reproduce**
1. Have an ACPX provider send a tool call whose location path contains a
newline (for example, a Write call with the content in the path).
2. See that the runner emits `tool.execution.progressed` with that
target.
3. See that the controller closes the connection without an
acknowledgement on every redelivery.
**Paperclip version or commit**
master at
|
||
|
DottaandClaude Opus 5.5
|
9c18cf61da |
fix(runner): keep discarded OpenCode token deltas from delaying tool calls (#20209)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Native OpenCode runs use a TypeScript app-server proxy between OpenCode and runnerd > - runnerd reads the proxy's frames in order, only after the controller acknowledges earlier events > - For each frame, runnerd rewrites its whole durable provider state with fsync, including every tool result that the turn retains > - The proxy sent one `item/delta` frame for each reasoning or tool-output token, and runnerd discards `item/delta` > - A Paperclip tool call request therefore waited behind hundreds of discarded frames, and the wait grew with each tool result in the turn > - This pull request stops the proxy from sending the token deltas that runnerd does not consume > - The benefit is that tool calls reach runnerd without that queue, so agent turns finish faster ## Linked Issues or Issue Description **What happened** In the chat eval `plugins.configure-plugin` (runner-opencode, deepseek-v4.1-flash, GitHub Actions run 42574640038), `paperclip_search_api` calls in one turn slowed from about 1.4 s to 9-15 s each. The server handled every call in 50-250 ms (`tool.execution` spans). For one `call_api` call, 6.3 s passed between the server's 403 and the next agent activity. Time to first token was about 4.4 s. The run events show the cause. Events that OpenCode streams reach runnerd in bursts. In one burst, the usage events for three different model requests arrived within 0.5 s, which no model can do. Each burst ends with the next tool call request. 143 of 203 recorded runner-opencode runs that we checked show such bursts, and 108 show a gap of 8 s or more. Many chat eval cases that time out use this runner. The mechanism: 1. OpenCode streams reasoning one token at a time. The proxy forwarded each token as its own `item/delta` frame. 2. runnerd reads proxy frames in order and only after the controller acknowledges earlier events. For each frame it calls `save_state`. That serializes the whole provider state, with the tool results retained in the turn, and fsyncs it. 3. runnerd's Codex facade has no mapping for `item/delta`, so it discards the frame after the save. 4. A tool call request is one more frame in the same ordered stream. It waits until runnerd works through every earlier delta frame. The wait is about (reasoning tokens) x (save cost), and the save cost grows with each retained tool result. **Expected behavior** A Paperclip tool call reaches runnerd soon after OpenCode makes it. Its delay does not grow with the reasoning length or with the number of earlier tool calls in the turn. **Steps to reproduce** 1. Run a native OpenCode chat turn with a reasoning model that makes many sequential Paperclip tool calls, for example `search_api`. 2. Compare each tool's `item.completed` tool_result time with the `tool.execution.completed` time and with the next `item.started` tool_use time in the run events. 3. See that the gap grows during the turn, and that events for several model requests arrive within less than one second. 4. For a local model of the mechanism: run the pinned OpenCode binary with a controlled OpenAI-compatible provider that streams 300 reasoning tokens before each tool call. Pass the driver events through the proxy's mapping and batching into a reader that consumes one frame at a time with a save cost that grows by 4 ms per completed tool result. Before this change, 8 sequential calls waited 1.7, 3.1, 4.2, 5.4, 6.7, 7.9, 9.2 and 10.5 s behind 142-261 queued frames. After this change, they waited 64-93 ms behind 0 frames. ## What Changed - `shouldForwardOpenCodeProxyItem` now takes the event type and payload. For `item.delta`, it forwards only assistant text (`agentMessage` or `text`), which runnerd maps to `item/agentMessage/delta`. - The proxy keeps reasoning and tool-output token deltas. Completed reasoning and tool items still go to runnerd as `item/completed`. Tool progress still goes as `item/updated`. - New regression test: a step with 1,000 streamed reasoning and tool-output tokens puts the same number of frames before the tool call request as a step with 1 token, and no `item/delta` frame is written. - New test: assistant text deltas are still forwarded. Completed reasoning items are still forwarded. ## Verification - `pnpm exec vitest run src/cli/opencode-proxy-events.test.ts src/cli/opencode-proxy-output.test.ts` in `packages/paperclip-runner`: 15 passed. - Red/green: with the predicate change reverted, the two new tests fail. With the change, they pass. - `tsc --noEmit -p tsconfig.test.json` in `packages/paperclip-runner` has no errors in the changed files. Local errors exist only in `src/eval/workflow-harness.ts`, which needs a built `@paperclipai/paperclip-eval-kernel`. - Local before/after measurement with the real pinned OpenCode binary (`opencode-ai@1.18.34`), described in Steps to reproduce, step 4. - Not run locally: the suites that need the `paperclip-runnerd` debug binary or the bundled provider entrypoints (`runnerd-opencode-streaming-tools`, `runnerd-codex-transport`, `opencode-proxy-thread-read`). They fail the same way on the unchanged base in this worktree because those build outputs are missing. CI covers them. ## Risks - Low risk. The changed frames were discarded by runnerd. No persisted state shape changes, so no previous-release story is needed. - If runnerd later maps a reasoning delta method, the proxy must forward it with batching, as it does for assistant text. The test names this boundary. - This change does not change the per-frame durable save in runnerd. Mapped frames (assistant text, tool items) still pay it. A runnerd change that skips the save when a notification changes no state would protect other proxies too. That is a separate change. > 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 — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - Anthropic Claude Opus 5.5 (`claude-opus-5-5`), used through Claude Code with tool use (shell, file edits, local benchmarks). ## 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 - [x] 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 - [ ] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
Nicky LeachandClaude Opus 5.5
|
2d93413085 |
perf(runner): prepare the next Claude provider generation at park (#20145)
## Thinking Path
> - Paperclip runs agents through Paperclip Runner, and a host can park
an idle Runner between runs and resume it for the next run on the same
task.
> - For Claude (ACPX), a follow-up run on a parked Runner pays about
1.5–2.3 s at `run.attach` before the provider can start the turn. The
attachment closes the Claude sidecar and spawns a new one: initialize,
`session.open` with `session/load`, `run.attach`, then a dormant verify.
> - The respawn is required. The tool-bridge MCP endpoint lasts for the
whole session and can't tell which turn a late callback came from, so a
new turn must not run in a process that ran an earlier one.
> - Nothing requires the respawn to happen at the *start* of the next
run. A turn that ends 2 s later is a better experience than one that
starts 2 s later.
> - This pull request does the respawn while parking. The next run's
`run.attach` then only rebinds the run id on a fresh, never-used
generation.
> - Follow-up Claude runs on a parked Runner reach the provider about
1.5–2 s sooner, and the late-callback guarantees are unchanged.
## Linked Issues or Issue Description
No public issue exists. The issue is described inline.
### What happened?
On a hosted deployment with parked Runners, Claude follow-up runs
reached the provider about 1.8 s later than Codex follow-ups.
`runner.session.resume` medians were 5.2 s for Claude and 3.4 s for
Codex. The extra time is the ACPX respawn inside `run.attach`. Codex
keeps its process in place.
### Expected behavior
The respawn happens while the Runner parks, so the next run starts on a
prepared generation.
### Steps to reproduce
1. Run a Claude (ACPX) task on a host that parks Runners between runs.
2. Let the run finish and the Runner park.
3. Send a follow-up. `run.attach` closes the provider and starts,
initializes, opens and attaches a new sidecar before `turn.start`. The
Claude CLI itself starts at the first prompt on either path.
### Paperclip version or commit
`master` at
|
||
|
DottaandClaude Opus 5.5
|
946c098bf3 |
fix(opencode): bind the attached run's contract after a restored launch (#20001)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Native OpenCode agents run through runnerd and a small OpenCode proxy. The proxy checks each `paperclip_finish` claim against the run's completion contract. > - Each follow-up run has its own contract revision. #19874 lets runnerd keep the OpenCode process across a contract change, and sends the new contract on `turn/start`. > - When runnerd starts again for a follow-up, it restores the saved session first. The restored proxy launches with the saved run's contract, but its environment already names the new run. > - The proxy applied the `turn/start` contract only when the run id changed. Here the run id did not change, so the proxy kept the saved contract and refused every correct finish claim. > - This pull request makes the proxy rebind whenever the turn's contract differs from the one its session holds. The stale-revision error also names the expected revision. > - The benefit: a queued-comment follow-up finishes on its first try, and an agent that sends a stale revision can repair it. ## Linked Issues or Issue Description Refs #19874 (warm runs carry their own completion contract). **What happened** A user sent a follow-up comment while an OpenCode agent was working. After the first run finished, Paperclip started a continuation run for the queued comment. The agent updated the plan and called `paperclip_finish` with the current revision `2`. The tool refused it twice with "Semantic result completion contract revision does not match". The error did not name the expected revision. The agent searched for it for 3 minutes, and cleanup cancelled the run. Root cause: runnerd restores a saved `session_open` session before it applies `run.attach` (`provider_backend.rs`: "execute() restores the durable provider before dispatching run.attach"). The restore launches the OpenCode proxy with the saved contract (revision `1`). Runnerd's environment already names the new run, so the proxy's `PAPERCLIP_RUN_ID` is the new run. `attach_run_in_place` keeps this provider for a changed contract (#19874) and sends `paperclipCompletionContract` revision `2` on `turn/start`. The proxy compared only the run id. The run id matched, so the proxy skipped `attachRun` and kept revision `1`. **Expected behavior** The continuation's first `paperclip_finish` with the current revision is accepted. If a claim has a stale revision, the error names the expected revision. **Steps to reproduce** 1. Use a native OpenCode agent with warm follow-ups (the default). 2. Start a task. While the agent works, post a follow-up comment, so that it queues. 3. Let the first run finish. Paperclip starts a continuation run with completion revision `2` and restores the saved OpenCode session. 4. The agent calls `paperclip_finish` with `contractRevision: "2"`. 5. Before this fix, the tool refuses it with "Semantic result completion contract revision does not match". The chat eval `steering.discard-queued-message` (runner-opencode) shows this in run events: `session.resumed` carries revision `2`, and both `paperclip_finish` results fail with the mismatch. ## What Changed - `opencode-app-server-proxy.ts`: record the contract that the session opened with. On `turn/start`, call `attachRun` when the run id changes or when the supplied `paperclipCompletionContract` differs from the session's contract. - `opencode-proxy-task-envelope.ts`: add `sameOpenCodeProxyCompletionContract`. - `opencode-server-driver.ts`: the stale-revision error now ends with `Use contractRevision "<expected>".`, like the criteria error. - Tests: a real-proxy regression for the restored launch, a driver test for the new error text, and a `repair-revision` mode in the fake OpenCode fixture. ## Verification - `pnpm exec vitest run src/cli/opencode-proxy-input.test.ts src/drivers/opencode/opencode-server-driver.test.ts src/cli/opencode-app-server-proxy.test.ts src/cli/opencode-proxy-thread-read.test.ts` in `packages/paperclip-runner`: 88 passed. - Red/green: without the source changes, both new tests fail. `binds the current contract when a restored launch already names the attached run` never sees the finish call reach the controller. `names the expected revision in a repairable stale-revision tool error` does not find the expected revision in the error. - `npx tsc --noEmit -p packages/paperclip-runner`: no errors in the changed files. (My worktree is missing a link for `@paperclipai/paperclip-eval-kernel`, which causes unrelated errors in `src/eval/workflow-harness.ts`.) - End-to-end: the chat eval `steering.discard-queued-message` (runner-opencode) with this fix cherry-picked. The run link goes in a comment below. ## Risks - Previous-release story (`rules/upgrade-safe-run-state.mdc`): this change does not change a persisted shape. The regression test uses the saved-state shape: launch parameters from the saved run, environment and `turn/start` from the new run. A runnerd that does not send `paperclipCompletionContract` behaves as before, so the proxy keeps its launch contract. The proxy and runnerd ship in the same runner artifact. - The proxy can now call `attachRun` for the same run id when the contract changes. `attachRun` resets the per-run result state. This occurs only at `turn/start`, when no turn is active, and only when the contract is different. A result for the earlier contract is not valid for the new contract. - The error text changed. No code parses it. > 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 — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - Anthropic Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use (shell, file edit, test execution). ## 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 - [x] 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 - [ ] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
dcaada5f59 |
fix(native): carry each warm run's own completion contract (#19874)
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - A warm runner (`lifecycleMode: warm`) keeps runnerd and the provider
process alive between runs, so a follow-up message can start fast.
> - Each run has its own completion contract. The revision changes with
each follow-up, and the agent must name that revision when it finishes.
> - On a warm attachment the transport rebuilt the `run.attach` payload
from its constructor options. Those options belong to the first run.
Every later run kept the first run's contract.
> - The OpenCode proxy checks the finish claim locally against that
stale contract. Every warm OpenCode follow-up was refused ("Semantic
result completion contract revision does not match"), and the agent
looped until the run timed out.
> - This pull request carries each run's own contract into the warm
attachment, and lets runnerd adopt it without a cold provider resume.
> - The benefit: warm follow-ups finish correctly, and they keep the
live provider process, which is the reason to be warm.
## Linked Issues or Issue Description
Refs #19852 (startup sub-spans), #19846 (TTFT baseline).
**What existing behavior does this improve?**
Warm cross-run attachment for native Codex and OpenCode agents.
**Current behavior**
In a local measurement wave with `lifecycleMode: warm`, 4 of 4 OpenCode
follow-ups looped for 8+ minutes. Each finish call was refused with
"Semantic result completion contract revision does not match". The saved
`runAttachTemplate` after the attachment still had revision `1`, while
the follow-up turn named revision `2`. Codex hid the defect because its
finish claim goes through the controller's tool path, which uses the
current input.
**Proposed behavior**
The attachment carries the attaching run's contract. Runnerd updates the
contract in place for Codex and OpenCode and keeps the provider process.
The OpenCode proxy receives the current contract with the run identity
on `turn/start`.
**Reason and benefit**
Warm follow-ups are the largest TTFT lever in the baseline. A
correctness-only fix (cold-resume the provider when the contract
changes) would make every warm follow-up relaunch Codex or OpenCode,
because the revision changes on every follow-up.
## What Changed
- `attachRun` carries `completionContract` through `NativeSession`, the
harness backend, the Codex harness session and the runnerd transport.
`executeNativeSession` passes the current input's contract. The
transport uses it instead of its first-run `resumeCompletionContract`.
- Runnerd (`codex_provider.rs`, `attach_run_in_place`): a changed
contract no longer forces a cold resume for `codex` and `opencode`.
Codex app-server never receives the contract, and the OpenCode proxy now
receives it per turn. Other providers keep the cold-resume boundary. A
changed tool set still forces it.
- Runnerd sends `paperclipCompletionContract` with each OpenCode
`turn/start`, next to the existing `paperclipRunId`.
- The OpenCode proxy passes that contract to `attachRun` when the run
changes. `OpenCodeHarnessSession.attachRun` replaces its envelope's
contract and validates it.
## Verification
- `src/live/runnerd-codex-transport-warm-attachment.test.ts` (new case):
real runnerd and fake Codex. After a warm attachment with a new
contract, the saved `runAttachTemplate` has the new revision and the
Codex pid is unchanged.
- `src/cli/opencode-proxy-input.test.ts`: the real proxy bundle serves a
warm second run with revision `proxy-v2`. The second
`paperclip/runResult` is produced and names `proxy-v2`. Without the fix
the finish call is refused.
- Each test fails without its part of the fix: the proxy test without
the proxy change; the transport test without the transport change (stale
saved revision); and, with `PAPERCLIP_ATTACH_TRANSITION_RUNNER` pointed
at a runnerd built without the `codex_provider.rs` change, the Codex pid
changes.
- `cargo test -p paperclip-runner-core --lib warm` (11 tests),
`native-session-runtime.test.ts` (232), the OpenCode driver, backend and
warm-attachment suites, and `tsc --noEmit` for the runner package pass.
## Risks
- Previous-release story (`rules/upgrade-safe-run-state.mdc`): no
persisted shape changes. Saved `runAttachTemplate` values carry forward,
and the next attachment writes the current contract. A new runnerd with
an old OpenCode proxy behaves as today: the proxy ignores the new
parameter and keeps the stale contract. An old runnerd sends no
parameter, so a new proxy keeps its launch contract.
- In-place adoption widens the warm-retention path for Codex and
OpenCode to changed contracts. The idle, accounting and pending-work
checks still apply first.
> 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 — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- Anthropic Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with
tool use (shell, file edit, test execution).
## 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
- [x] 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
- [ ] 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
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
||
|
DottaandClaude Opus 5.5
|
fd58378ee6 |
fix(runner): never dispatch an OpenCode tool call its MCP client abandoned (#19546)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The Paperclip runner runs native OpenCode agents. OpenCode calls Paperclip tools through an MCP bridge inside the OpenCode proxy. The proxy sends each call to runnerd as an `item/tool/call` frame on stdout. > - runnerd reads the proxy stdout only after the controller acknowledges earlier events. A backlog of event frames can build in the proxy. A tool call waits behind that backlog. > - The OpenCode MCP client can time out while the call waits. The agent then gets `MCP error -32001: Request timed out`. But the queued frame still reaches runnerd later, and runnerd still runs the call. > - This is a safety bug. A mutating call (for example, create a gateway token) can succeed after the agent was told that it failed. The agent can then repeat it. > - This pull request makes sure that a call whose MCP client abandoned it is never sent to runnerd while it is still queued in the proxy. > - The benefit: "timed out" now means "did not run" for every call that had not left the proxy. ## Linked Issues or Issue Description **What happened?** In chat-feature evals with native OpenCode, the agent got `MCP error -32001: Request timed out` for a POST tool call. The server still ran the POST and returned 201 about one second later. Other Paperclip tools that took 0.03–0.5 s on the server reached OpenCode 10–22 s later. The delay grew over the run, and then the calls failed with -32001. Sometimes they failed at once. **Expected behavior** If the MCP client abandons a tool call before Paperclip dispatches it, Paperclip must not run it. **Steps to reproduce** 1. Run a native OpenCode agent (`paperclip_runner` adapter, runnerd path) for a long chat turn with many tool calls. 2. Make the controller acknowledge runnerd events slowly, so a backlog builds in the proxy. 3. Let the OpenCode MCP client time out on a mutating call that waits in the backlog. 4. See that the agent gets -32001, but the call still runs on the server. **Where the per-call lag comes from (finding)** - runnerd (`provider_backend.rs`, `poll_current_provider_with_control`) does not read proxy stdout while any event is not acknowledged. It reads at most 128 events per poll. - Each poll that admits events, and each acknowledgement, calls `persist_state`. That function writes the full provider state JSON again (up to 16 MiB, and it grows during the run) and does two fsyncs. So each round trip gets slower during the run. - Pipe writes from Node are asynchronous on POSIX. OpenCode event frames and `item/tool/call` requests therefore wait in one FIFO buffer in the proxy. A tool call waits behind all earlier event frames, and the results come back through the same gated path. - OpenCode starts its MCP timeout when it calls the tool, not when runnerd reads the frame. The -32001 event frame can itself wait in the backlog, so it can look "instant" when it arrives. - Evidence: the delay from runner emit to server receipt stays below 0.5 s. But runnerd's `item.completed` for a call comes 10–22 s before OpenCode's `tool.execution.completed`, and the gap grows during the run. - The fix for the lag is not small. It needs a change to runnerd persistence: do not gate stdout reads on a full acknowledgement, or use an append-only event log instead of a full state rewrite with two fsyncs for each batch. This pull request does not change runnerd. ## What Changed - `mcp-bridge.ts`: abort the call signal when the MCP client drops its HTTP connection before a response. The `notifications/cancelled` path already aborted it. - `opencode-server-driver.ts`: send the bridge abort signal to `dynamicToolHandler` (new optional `signal` field). - `opencode-proxy-output.ts`: add `createBackpressuredFrameWriter`. It gives the stream only what its buffer accepts and keeps the backlog in its own queue. Frames keep their order. If a queued frame's signal aborts, the writer removes the frame and calls `onAbandoned`. - `opencode-app-server-proxy.ts`: write stdout through the new writer. Tool-call requests carry the call signal. An abandoned request fails with "abandoned by the MCP client before it was dispatched; it did not run". Shutdown drains all live frames. - Tests: a new regression test uses the real bridge and the writer with a stalled stdout. It covers a cancel after timeout, a dropped connection, and a live call. There are also unit tests for the writer. ## Verification - `npx vitest run src/drivers/opencode src/cli/opencode` in `packages/paperclip-runner`: 23 files, 226 tests pass. - Red check: I removed the disconnect abort and the queue gating. Then 2 of the 3 tests in `opencode-proxy-abandoned-tool-call.test.ts` failed: the abandoned `item/tool/call` reached stdout. After I restored the code, they pass. - `pnpm verify` exits 2 because the changed proxy files are outside its resolved test graph. The required CI jobs supply broad coverage. - `tsc --noEmit` for the runner package shows no errors in the changed files. One error remains in `src/eval/workflow-harness.ts`. It comes from a workspace package that is not built and is not related to this change. ## Risks - A call that already left the proxy (it is in the kernel pipe buffer or in runnerd's reader) still runs after a client timeout. The window is about 64 KiB of pipe buffer plus Node's 16 KiB high-water mark. To close it fully, runnerd must get a deadline or a cancellation for each call. That is a follow-up. - Frames now wait in a proxy queue instead of the Node stream buffer. Delivery order does not change. The new code drains this queue on shutdown before the last stdout flush. - When a client disconnects, a durable call is now cancelled. Before this change it stayed pending. The client cannot get the result in either case. - No schema, contract, or ACPX profile changes. ## Model Used - Anthropic Claude Opus 5.5 (`claude-opus-5-5`), used in Claude Code with tool use (shell, file edit, test runs). ## 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 - [x] 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 - [ ] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
30a0b5982e |
fix(runner): let Codex agents generate images with their existing provider key (#19516)
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The Paperclip runner launches Codex agents in an isolated app-server
with a sandboxed shell
> - On the Codex API path, the agent's OpenAI API key reaches only the
trusted app-server process, never the shell
> - The runner launched Codex with `--disable image_generation`, so
Codex's built-in image tool was not available
> - Codex then falls back to its `image_gen.py` script, which needs
`OPENAI_API_KEY` in the shell, so the agent asked the user for a second
key
> - This pull request keeps Codex's built-in image tool on, so it uses
the agent's existing provider auth, and lets the sandbox read only the
folder where Codex saves the images
> - The benefit is that a Codex agent can make images without a second
key, and the provider key still does not reach the shell
## Linked Issues or Issue Description
**What happened?**
Manual onboarding test on Paperclip Cloud staging (Codex API path):
"Open AI requests another api key for image model even though it has an
active api key powering the agent."
**Steps to reproduce**
1. Create a company with a Codex agent that uses an OpenAI API key.
2. Ask the agent to generate an image.
3. The agent asks for another OpenAI API key.
**Expected behavior**
The agent uses the OpenAI API key that already powers it.
**Root cause**
`createIsolatedCodexAppServerArgs` passed `--disable image_generation`
and the thread config set `features.image_generation: false`. The pinned
Codex 0.160.0 binary has two image paths. Its own instructions say the
built-in `image_gen` tool "Does not require `OPENAI_API_KEY`". The
fallback CLI path "Requires `OPENAI_API_KEY`". The runner removes
`OPENAI_API_KEY` from the shell on purpose
(`codex-shell-environment.ts`), so the fallback can never work and the
agent asks the user.
## What Changed
- `codex-security-config.ts`: remove `--disable image_generation` and
`features.image_generation: false`. Codex's built-in tool runs in the
trusted app-server with the agent's existing auth.
- `codex-security-config.ts`: in the workspace and plan permission
profiles, grant **read** on `CODEX_HOME/generated_images` only. Codex
saves images there and tells the agent to copy them into the workspace.
The rest of `CODEX_HOME` (for example `auth.json`) stays denied.
Preconfigured-home mode is unchanged (it does not deny `CODEX_HOME`).
- `eval-gateway-runtime.ts`: set `image_generation = false` in the
controller-gateway Codex config. That gateway admits no hosted tools
(`unqualified_hosted_tool`), so qualified evals keep the earlier
behavior.
- Tests: two new N-12 tests, and updates to the tests that asserted the
old disable flag.
## Verification
Red on `master` (
|
||
|
DottaandClaude Opus 5.5
|
a0cba70f18 |
fix(runner): continue restart-interrupted ACPX and OpenCode turns (#19501)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Native runs keep their provider conversation when the control plane restarts > - A local Codex turn lost in a restart already continues once in the same conversation (#15297) > - ACPX (Claude and the other ACPX profiles) and OpenCode took a different path: the runner closed the lost turn as a provider failure > - The task then blocked with "Provider turn failed", and the user's queued follow-up stayed unread > - A restart must not need a user action when continuing is safe > - This pull request gives ACPX and OpenCode the same recoverable restart-loss cause and the same single continuation as Codex > - The benefit is that work interrupted by a controller restart finishes on its own ## Linked Issues or Issue Description Refs #15297 (Codex continuation), #19399 (restart-interrupted turn hook), #19471 (harness fix used for the live reruns). **What happened?** After a control-plane restart during an active native ACPX Claude turn, the task ended `blocked` with `native_provider_terminal_failed: Provider turn failed`. The queued follow-up comment was not consumed. No continuation started. The next run then failed with `native_session_cleanup_quarantined`. A native OpenCode run killed mid-turn ended the same way (`turn.failed` with `error: null`). **Expected behavior** When the old provider process is gone and the conversation can be restored, continue the task once in the same conversation. When that is not safe, record an honest restart cause instead of a generic provider failure. **Steps to reproduce** 1. Start a native ACPX Claude task on a local runner. 2. Submit a follow-up comment while the turn is active. 3. Restart the control plane while the turn is still running. 4. Run `pnpm test:e2e:runner -- --max-automatic-retries 0 --id everyday-workflows.runner-acpx-claude.local.recover-controller`. **Root cause** - `runner-core/src/acpx_provider_backend.rs` `restore_session_if_needed`: a saved `turn_active` state always closed the session. It recorded `turn.failed` with only a top-level `code: acpx_active_turn_recovery_closed` and no `error` object. It also emitted `run.terminal`. - The runnerd transport forwards only `error`, so the controller saw `error: null` and reported generic `provider_turn_failed`. - `runner-core/src/provider_backend.rs` gave the recoverable `provider_turn_lost_on_restore` cause only to `provider_label == "codex"`. OpenCode shares that backend. - `nativeRestartInterruptedTurnId` accepted only `codex_app_server`. The runtime continuation gate accepted only `provider.kind === "codex"`. - Two follow-on defects appeared once the continuation ran live: - The restored ACPX provider rejected the controller's result for the lost turn's open semantic call. That call never settled. - The restored provider's MCP request ids restart. The controller keys semantic calls by `hash(runId, callId)`. The continuation's first Paperclip tool call reused an earlier id, was treated as already answered, and hung. After the result was accepted, `runner_settlement_incomplete` failed the run. ## What Changed - ACPX runner: for an active turn lost to a runner restart, prove that the original provider lifetime lost its fence quorum. Then restore the same conversation and record `turn.failed` with `error: { code: "provider_turn_lost_on_restore", recoverable: true }`. Keep the run open for the controller's continuation. An accepted result, an unanswered runtime request, or an active goal keeps the old close behavior. So do an unproven lifetime fence and a failed restore. - ACPX runner fallback close: add a structured `error` (`acpx_active_turn_recovery_closed`, not recoverable, with an honest restart message), so the cause survives the transport. - ACPX runner: track open semantic calls durably. On restore, retire the lost turn's open calls. Acknowledge their controller results as `retired` and do not send them to the new provider. - ACPX sidecar: when the sidecar restores an existing session, prefix forwarded semantic `callId`s with a per-process namespace (`r<hex>:<id>`). Fresh sessions keep raw ids. - OpenCode runner: give OpenCode the same recoverable cause and open run as Codex (`restart_lost_turn_is_continuable`). Cursor Cloud stays excluded because its agent runs remotely. - Runner TS: `nativeRestartInterruptedTurnId` accepts `acpx_runtime` and `opencode_server`. The runtime continuation gate accepts `acpx` and `opencode`. All other Codex safety rules are unchanged: one continuation, admitted dead-runner restart only, no compaction, goal, semantic result, or pending runtime request. - Docs: `doc/execution-semantics.md` and `doc/run-log-events.md`. ## Verification Red, then green, at each layer: - Rust `tests/acpx_warm_attachment.rs` `restores_the_conversation_after_losing_an_active_turn_to_a_runner_restart`. Red: status `closed`. Then red on the lost call's result: "tool result does not match a pending provider call". Green after the fix. - Rust `tests/native_provider_backend.rs` `restart_lost_opencode_turn_records_a_recoverable_cause`, with the qualified OpenCode launch fixture. Red: `error` was `null`. Green after the fix. - Rust unit test `restart_lost_turns_continue_only_for_locally_restored_providers` (Codex, OpenCode yes; Cursor Cloud no). - TS `native-session-runtime.test.ts` "continues a restart-lost acpx_runtime / opencode_server turn once". Red: `NativeProviderTerminalFailure provider_turn_lost_on_restore`. Green: exactly one continuation, which does not resend the task. - TS `acpx-runtime-sidecar.test.ts`: a restored provider's call ids are namespaced and resolve. - Server `native-runner-restart-recovery.integration.test.ts`: a checkpointed `acpx_runtime` or `opencode_server` restart interruption is claimed as `resume_dead_runner`. Red without the driver gate. Green with it. - Two `native_provider_backend.rs` tests asserted the old close-on-restore result. They now assert the new contract. Their real invariant still holds: the delivered response is never replayed. Suites run locally on the final revision: - runner-core: `cargo test --no-fail-fast acpx`, `--test native_provider_backend` (38), `--test acpx_warm_attachment`, `--test codex_provider restart_lost` - runner TS: `native-session-runtime`, `runnerd-restart-continuation`, Codex driver recovery, contracts, and `acpx-runtime-sidecar` (all pass) - server: `native-runner-restart-recovery.integration.test.ts` (80 passed) - `pnpm --filter "@paperclipai/paperclip-runner..." build` (all generated-contract checks pass) Live runner E2E (local, real Claude via ACPX, macOS arm64): - `everyday-workflows.runner-acpx-claude.local.recover-controller`: PASS twice in a row on the final runner code. The restart crossed an active turn. The task finished `done`, the queued follow-up was consumed, the ZIP download was verified, and there were no failure codes. - `stock-harness.runner-acpx-claude.local.continuity-restart` regression: PASS. - Earlier failing reruns are kept as evidence of the follow-on defects: one harness `kill EPERM` while stopping the server (unrelated to this change), one hang on the colliding call id, and one `runner_settlement_incomplete`. ## Risks - A continuation can run more work in the restored conversation. Its prompt requires inspecting state before repeating an uncertain action, as for Codex. - The ACPX restore waits up to 5 s for the original provider lifetime fence before it falls back to the old close. - The ACPX provider state file gains two fields with defaults. Older saved states still load. A downgraded runner cannot read state that a newer runner wrote with these fields. - Restored ACPX sessions now forward prefixed call ids. Only fresh sessions keep raw ids. Live proof covers Claude. Codex-ACP, Pi, Cursor, Copilot, Grok, Kimi, and Antigravity share this path, but this PR proves them only by unit tests and code review. - OpenCode is covered by the runner fixture and gate tests. The live OpenCode restart-chaos cell was not rerun here. - `runner-core` `unconfirmed_suspension_state_becomes_recoverable_only_after_cleanup_and_suspend` is flaky when run in parallel. It also fails with the new path disabled, so it predates this change. ## Model Used - Anthropic Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use, code execution, and extended reasoning. ## 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 - [x] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
Nicky LeachandClaude Opus 5.5
|
83c6832ccb |
fix(build): typecheck package, Playwright, and e2e test files in CI (#18839)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Runner, plugin, and Playwright tests verify how those agents run, connect, and appear in the board > - Most package tsconfigs exclude tests, and Vitest strips types, so a type error in those tests fails nothing > - The tests drifted to 803 real type errors, and some of those errors hid assertions that checked nothing > - paperclipai/paperclip#18739 and paperclipai/paperclip#18738 check the server test tree and four test projects, but not these files > - This pull request adds a required check for these test files, fixes every error, and fails CI if a test file is in no program > - The benefit is that a type error in any test file outside `server/src` now fails CI ## Linked Issues or Issue Description Refs #18739 Refs #18738 **What happened?** 517 test files were in no program that required CI checks. A type error in those files did not fail CI. **Expected behavior** CI fails on a type error in any test file. **Steps to reproduce** Add `export const value: number = "text";` to a test file under `packages/paperclip-runner/src` on master. CI stays green, because `tsconfig.json` excludes test files and Vitest strips types. **Measured gap** Each row is a program with its tests included, on one thread. File and error counts are for head `7d4b5e907a`. Memory peaks were measured before the two latest merges of master. | Group | Test files | Real errors | Peak | | --- | ---: | ---: | ---: | | `paperclip-runner` Node source | 290 | 644 | 1.09 GiB | | `paperclip-runner` surfaces | 9 | 12 | 0.42 GiB | | `paperclip-runner` devtools and examples | 14 | 0 | 0.68 GiB | | `sandbox-providers/kubernetes` | 21 | 65 | 0.44 GiB | | 8 other sandbox providers and `bridge-template` | 32 | 4 | 0.34 GiB | | `plugins/sdk` | 22 | 15 | 0.41 GiB | | `plugin-workspace-diff` | 5 | 0 | 0.37 GiB | | `plugin-orchestration-smoke-example` | 1 | 1 | 0.15 GiB | | `kv-demo-mcp-server` | 3 | 0 | 0.13 GiB | | `packages/db` scripts | 1 | 0 | 1.01 GiB | | 8 Playwright suites under `tests/` | 52 | 25 | 1.72 GiB | | `tests/runner-acceptance` | 3 | 0 | 0.58 GiB | | `tests/e2e`, through layer declarations | 63 | 37 | at most 1.59 GiB | | `ui` `AttentionInteractionResolver.test.tsx` | 1 | 0 | n/a | | **Total** | **517** | **803** | | 27 of the 803 errors came from master while this pull request was open. Each merge of master brought new test code that no check had read. Errors that were config errors, not real errors: - One TS2688 for each provider, because the root install does not install provider dependencies. - 9 in the Runner Node program (TS7016 and TS6059). - 2 in `tsconfig.browser.json`. TypeScript 7 removed `baseUrl`, so that config was invalid. - 213 in the Playwright suites (`@/*` aliases and Vite types). - About 60 in `tests/e2e` (import extensions and aliases). `packages/plugins/create-paperclip-plugin` has no gap. Its tsconfig excludes its test, but `cli/tsconfig.json` reaches that test through an import. `server/test-baselines` also has no gap, because `tests/lifecycle-baseline` reads it. ## What Changed - Added `scripts/typecheck-test-programs.mjs` and its tests. The `Typecheck + Release Registry` job runs it. It checks each program in `PROGRAMS` on one thread. - The script fails if a tracked `*.test.ts(x)` or `*.spec.ts(x)` file outside `server/src` is in no program. The compiler file list decides this, because `include` drops `foo.test.tsx` when `foo.test.ts` exists. - Added a `tsconfig.test.json` to each uncovered package, and `tests/tsconfig.playwright.json`. - Added `tests/e2e` to `PROJECTS` in `scripts/typecheck-test-projects.mjs`, with a `tsconfig.json` and a `tsconfig.layers.json`. - Added `scripts/typecheck-sandbox-providers`. It is a small workspace that installs provider SDKs from one lockfile. I did not add a lockfile inside each provider, because `scripts/build-standalone-public-packages.mjs` uses a frozen install when one exists, and that changes what a release resolves. - Corrected `packages/paperclip-runner/tsconfig.browser.json` for TypeScript 7. - Set `rootDir` to `..` in `packages/paperclip-runner/tsconfig.test.json`, because one Runner test imports from `packages/adapter-utils/src`. The program does not emit files, so this changes no build output. - Moved the Kubernetes provider from `vitest ^3.2.4` to `^4.1.8`, the version the other providers use. Vitest 3 requires `tinypool ^1.1.1`, which has two critical advisories (GHSA-85c8-ppgw-ccpr and GHSA-5gmw-xhrv-c9v3). The first patched version is 2.1.2. Its tests have the same result on both versions: 189 passed, and the same 12 `file-sync` tests failed. - Moved the Kubernetes provider from `zod ^3.24.2` to `^4.6.6`, and gave its two `z.record` calls a key schema. This is the only production change, and it stays in this pull request. See "Production change for review". - Renamed `AttentionInteractionResolver.test.ts` to `AttentionInteractionResolver.replace.test.ts`, so TypeScript reads the `.test.tsx` beside it. - Fixed all 803 errors, with changes to test files and test support only. The fix for `contracts/native-execution.test.ts` is the same as the fix in paperclipai/paperclip#18739, so those two changes merge cleanly. - Updated `doc/DEVELOPING.md`. This pull request does not edit `server/scripts/typecheck-layers.mjs`. paperclipai/paperclip#18739 and paperclipai/paperclip#18738 have both merged, and this branch includes them. ### Production change for review The new lockfile made dependency review flag `zod@3.25.76` as a high-severity advisory (GHSA-mrhx-c7xc-m3w5). The first patched version is 4.6.6, so 3.x has no fix. The published Kubernetes plugin uses zod to validate operator config. The zod 3 source does not compile against zod 4, so a typecheck-only override cannot fix this. The existing tests do not prove this change, because they also passed with the invalid one-argument `z.record`. So I parsed 45 inputs with the same schema on zod 3.25.76 and zod 4.6.7: | Result | Inputs | Detail | | --- | ---: | --- | | Identical | 23 | Includes defaults, valid config, and a `__proto__` key | | Same outcome, new error wording | 21 | For example, `Invalid url` is now `Invalid URL`. `validateConfig` shows this text to operators. | | Different outcome | 1 | `jobTtlSecondsAfterFinished: 2 ** 60` was valid and is now rejected. The new limit is `Number.MAX_SAFE_INTEGER`. | I did not test this against a real cluster. The decision is to keep this change in this pull request. Since then, paperclipai/paperclip#17364 has moved the rest of the repository to zod 4.6.x, so the Kubernetes plugin now matches it. ### Behavior change for review `reducedMotion` under `use` is not a Playwright option. It had no effect in 11 configs and 2 `test.use` calls, so those suites ran with `no-preference`. The options are now under `contextOptions`, so reduced motion now takes effect. `app-shell-design.spec.ts` asserts a real transition, so it now asks for `no-preference` itself. The baseline manifest has `snapshotCount: 0`, so this invalidates no published baseline. A frozen trial reference PNG can differ. ### Findings These are product questions. I did not change them, and I did not hide them with casts: 1. **`PrpEvent` and its schema disagree.** The TypeScript type in `src/protocol/replay-contract.ts` requires `normalizedSessionId`. The `required` list in `protocol/schemas/event.schema.json` does not include it. `validatePrpEvent` accepts events that the type forbids. 2. **`requestCheckboxConfirmation` is stricter than its runtime.** It uses the output type, so plugin authors must pass `continuationPolicy` and `allowDeclineReason`, although the schema gives them defaults. `z.input` would fix this. 3. **`RetainedRunnerdMaintenanceInput.backend.kind` is a free string.** The quarantine domain comes from `descriptor.kind`, but the release uses `proof.backend.kind`. If they differ, `completeRetainedNativeSessionCleanup` returns 0 and the quarantine stays. The production caller passes `"runner"` today, so this is not a live bug. 4. **`CodexHarnessSession.close(input?)` is optional, but the contract requires `{ reason }`.** These are tests that verified nothing. I corrected them, and they pass: - `backends/native-instruction-measurement.test.ts` filtered on `placement === "core"`, which is not a valid placement. It measured an empty tool list. It now measures 14 tools. - `drivers/acpx/codex-acpx-driver.test.ts` checked for `usage.updated`, which is not an event type. - The `hostFixture()` helper in `drivers/acpx/runtime-host.test.ts` ignored two overrides, so `expect(prepareSandbox).not.toHaveBeenCalled()` could not fail. - `live/live-session.test.ts` set `agent: "pi"` before a spread that overwrote it. - `native-distribution-integrity.test.ts` passed an AbortSignal where `openCommand` expects `{ signal }`. These are gaps that this pull request does not close: - **The root lockfile still has some old zod versions.** paperclipai/paperclip#17364 moved the direct zod dependencies to 4.6.x. `pnpm-lock.yaml` still resolves `zod@3.25.76`, `4.1.11`, and `4.4.3`, which are below the patched 4.6.6. `packages/paperclip-runner/scripts/pi-distribution/package.json` pins `zod` to `3.25.76`, and some agent SDKs resolve `4.4.3`. Dependency review does not flag them, because this pull request does not add them. - **Dead GitHub coverage.** `chat-adapters-ui-providers.spec.ts` returned early for GitHub, so four later `provider === "github"` branches never ran. I removed them. They included the private key file and paste match, and the reconnect flow. Nothing asserts those behaviors in that spec now. - **Provider tests do not run in CI.** The root `vitest.config.ts` lists only Daytona. The other 8 providers, `bridge-template` included, are typechecked now, but CI does not run their tests. - **One `packages/db` test never runs.** `scripts/clean-poisoned-claude-sessions.test.ts` is outside the `include` of `packages/db/vitest.config.ts`. - **`plugin-orchestration-smoke-example` does not collect.** `@paperclipai/shared` is not linked in its `node_modules`. It passes 3 of 3 with an alias. ## Verification Run these commands: ```sh node scripts/typecheck-test-programs.mjs --low-memory pnpm --filter @paperclipai/server typecheck node scripts/typecheck-test-projects.mjs --low-memory --reuse-declarations node --test scripts/typecheck-test-programs.test.mjs ``` Results on macOS (arm64), Node 26.12. CI uses Node 24, and its `Typecheck + Release Registry` job also passes. At head `7d4b5e907a`, the test programs, `tests/e2e`, and the script tests pass again with 0 errors. The times and peaks below come from the run before the two latest merges of master: | Check | Result | | --- | --- | | Test programs, `--low-memory` | Exit 0, 0 errors, 42 seconds, peak 1.78 GiB | | Server layers, low memory | Exit 0, 0 errors, 38 seconds, peak 3.41 GiB | | Test projects, including `tests/e2e` | Exit 0, 0 errors, 13 seconds, peak 1.59 GiB | | Script tests | 12 passed | | Injected type error in each of 23 places | Each one failed its program with TS2322 | | Coverage check | 0 unchecked files, 10 seconds | I did not run this in a 4 GiB container. The peaks above are `maximum resident set size` for the largest single process. **Runtime check of the fixes.** Types do not prove that a test still works, so I ran the suites before the two latest merges of master: | Suite | Result | | --- | --- | | Runner, full suite | 4,885 passed, 3 failed, 13 skipped | | Sandbox providers, 10 packages | 939 passed, 12 failed, 36 skipped | | Plugin SDK | 200 passed | | `kv-demo-mcp-server` | 12 passed | | Renamed UI test and its sibling | 4 passed | All 15 failures exist without these fixes or come from the local machine: - **3 Cursor Cloud timeouts.** `artifact-delivery.test.ts` has 1 and `cursor-cloud-driver.test.ts` has 2. They time out in a full local run, and all 133 tests in those files with `codex-security-config.test.ts` pass when run alone. They fail in the same way with those two files at their unedited versions. - **12 Kubernetes `file-sync.test.ts` failures.** They fail in the same way before and after the fixes. The first failure is that `/proc/self/fd` does not exist on macOS. After each of the two latest merges of master, I ran only the Runner test files that I changed: | Merge | Result | | --- | --- | | `885c249cb9`, 8 files | 534 passed | | `7d4b5e907a`, 7 files | 672 passed, 16 failed | The 16 failures are in the two `source-reconciliation` test files. They fail in the same way with master's unedited versions of those files. 15 of them fail with `ACPX sidecar exited at initialize`, so I think my local build of the Rust and sidecar binaries is out of date. I did not rebuild them to check. CI builds them from scratch, and all Runner jobs pass in CI at `7d4b5e907a`. **Not run:** - `tests/e2e` and the 8 Playwright suites need a server, so most of them have only compile checks. `playwright test --list` loads 308 tests from the main e2e config. - `packages/plugins/sandbox-providers/kubernetes/test/integration` needs a cluster, so it has only compile checks. - I did not run the full `pnpm test:run` or root `pnpm build`. Required CI runs them. **Reduced motion.** I ran 6 motion-sensitive Storybook specs in system Chrome with a temporary config, once with `reduce` and once with `no-preference`. Both runs had 45 passed and the same 5 failed. So reduced motion did not change those results. The 5 failures do not depend on motion. At least one comes from the browser, because system Chrome prints `oklch(55.6% 0 0)` where the test expects `oklch(0.556 0 0)`. I did not run the other Storybook specs. The `storybook-visual` label runs that workflow. ## Risks - **A new lockfile to maintain.** A change to a provider `package.json` now fails the typecheck job until someone refreshes `scripts/typecheck-sandbox-providers/pnpm-lock.yaml`. The failure message gives the command. - **The job has a new install.** The step downloads provider SDKs, so it depends on the npm registry. It uses `--frozen-lockfile` and `--ignore-scripts`. - **The local install replaces provider `node_modules`.** A contributor with a standalone provider install must reinstall that provider after running the script. - **Reduced motion can change Storybook results.** See "Behavior change for review". That workflow is not part of required CI. - **Kubernetes plugin validation changed.** A release of this plugin ships zod 4. Error wording changes, and very large integers are now rejected. See "Production change for review". - **Master moves fast.** Each merge of master brought new test code with type errors, 27 so far. After this merges, the check reports those errors in the pull request that adds them. ## Model Used - Provider: Anthropic Claude, through Claude Code - Model: Claude Opus 5.5 (`claude-opus-5-5`) - Capabilities: tool use, code execution, and subagents for the type fixes in separate files ## 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) - [ ] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details. The app generated the branch name. - [ ] I have run tests locally and they pass. See the failures explained in Verification. - [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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
Nicky Leach
|
96516a8622 | Keep ACPX output while Core reconnects (#19365) | ||
|
DottaandClaude Opus 5.5
|
22281d4b3a |
feat(task-chat): approve harness-proposed plans (Codex plan mode, Claude ExitPlanMode) (#19291)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Agents run through the native runner. Codex and Claude Code each have their own plan mode, and each produces a proposed-plan document. > - Paperclip already has a planning work mode, an issue `plan` document, and a `request_confirmation` approval gate for plans. > - These parts were not connected. The Codex proposed-plan item was transcript text only. The server path never put Codex into plan mode. Claude was never put into plan mode, and its ExitPlanMode plan was dropped. A planning run could close its task as done with no approval. > - This pull request turns a harness's own proposed plan into the issue's Plan document and the existing approval gate, for Codex and Claude. > - The benefit is that users approve or send back the agent's real plan from the task chat. Approve resumes the agent. Request changes sends the reason back to the agent. ## Linked Issues or Issue Description Refs #19252 **Subsystem affected** Native runner provider events (Codex and ACPX Claude), the runner Codex provider (Rust), server native plan synchronization, and the task chat UI. **Problem or motivation** Codex and Claude both produce a proposed-plan document in their native plan mode. Paperclip did not use it. In live tests on the server path, a Codex planning run was not in Codex plan mode, saved its own `implementation-plan` document, and marked the task done without approval. Claude planning runs were not in Claude plan mode, and the ExitPlanMode plan text never reached Paperclip. **Proposed solution** Add a canonical `plan.proposed` event for a harness's proposed plan. Put Codex and Claude into their native plan mode for planning runs. Save a completed proposal as the issue `plan` document with the existing `request_confirmation` gate. Agents can also propose a plan on a standard task; the work mode stays standard. **Alternatives considered** Reuse `plan.updated`. Its schema is the within-turn checklist and is not the durable Plan document, so a separate event keeps the two clear. Stronger prompt text without native plan mode. Live tests showed that the model kept its own document workflow. **Roadmap alignment** This reuses the issue plan document, planning work mode and approval gate that already exist. It adds one canonical provider event. ## What Changed - `packages/paperclip-runner/protocol/schemas/*`: add the `plan.proposed` event (`paperclip.plan.proposed.v1`: `proposalId`, `status`, `markdown` up to 60k characters, `source`). Regenerate the schema bundle, validators and manifest. - `packages/paperclip-runner/src/provider-events.ts`: map the Codex `plan` item and a `<proposed_plan>` block in a completed Codex message to `plan.proposed`. Add `claudePlanProposalEvent`. - `packages/paperclip-runner/runner/crates/runner-core/src/codex_provider.rs`: send Codex's native `collaborationMode: plan` on `turn/start` for a read-only (planning) Codex run. Before this change the server path never sent it. - `runner-core/src/acpx_event_payload.rs`: admit `plan.proposed` as ACPX rich display activity. - `drivers/acpx/codex-runtime-adapter.ts`: set Claude Code to native plan mode for a read-only run. Capture Claude's ExitPlanMode plan from its permission request, record it, and decline the native "Ready to code?" prompt. - `drivers/acpx/codex-acpx-driver.ts`, `cli/acpx-runtime-sidecar.ts`: emit the captured proposal as a rich event. Complete that turn instead of reporting it as cancelled. - `backends/codex-native-backend.ts`: per-harness plan-mode instructions, and a short opt-in hint for Claude on standard tasks. - `server/src/services/native-runtime/native-session-executor.ts`: synchronize a completed `plan.proposed` into the `plan` document and a `request_confirmation` in planning and standard mode. Do not change the issue status during the run (that revoked the run's lease). The run finalizer turns the pending confirmation into the review wait. - `server/src/services/heartbeat-run-summary.ts`: keep a `<proposed_plan>` block out of the posted reply. - UI: new `plan_proposal` provider family. The task chat shows a live "Writing plan" card while a proposal streams and a one-line record when it completes. Resolved plan reviews keep a receipt ("Approved Plan v1", "Requested changes to Plan v1: reason"). Plan previews skip section headings. - Storybook: `Tasks and conversations/.../Task chat/Proposed plan approval` shows the journey. - `doc/SPEC-implementation.md`: describe harness-proposed plan approval. ## Verification - `cargo test -p paperclip-runner-core --lib` (new: `read_only_codex_turns_use_native_plan_collaboration_mode`) - `cd packages/paperclip-runner && npx vitest run src/provider-events.test.ts src/drivers/acpx/codex-runtime-adapter.test.ts` - `cd server && npx vitest run src/__tests__/native-plan-proposal-sync.test.ts src/__tests__/heartbeat-run-summary.test.ts` - `cd ui && npx vitest run src/components/transcript/native-run-events.test.ts src/components/task-chat` - Live test on a local worktree instance with real harnesses: - Codex (`gpt-5.6-sol`), planning task: Codex asked one question, then produced a native plan item. The task showed Plan v1 with Approve plan / Request changes and moved to in review. Approve changed the work mode to standard. Codex then implemented the plan and its tests passed. - Codex, Request changes with a reason: Codex woke in planning mode and produced Plan v2 that includes the change. - Claude (`claude-opus-5-5`), planning task: Claude was in plan mode. ExitPlanMode became Plan v1 and the turn completed. Approve resumed Claude in standard mode, and Claude implemented the plan. - Claude, standard task that asks for a plan first: Claude stopped before code changes and asked for plan approval. The work mode stayed standard. - Storybook: open `Proposed plan approval` and check each stage. ## Risks - Codex planning runs now really use Codex plan mode on the server path. Codex can ask a clarifying question before it proposes. This matches Codex plan mode. - Claude planning runs now use Claude plan mode. A declined ExitPlanMode ends the Claude turn; the runner reports it as completed. Claude's tool row for that request records a rejection from Claude's side. - Codex does not stream the proposed plan on the server path yet, so the live card shows a placeholder until the plan completes. - A `<proposed_plan>` block in any completed Codex message on a standard task now asks for approval. This is the documented opt-in path. > 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 — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - Anthropic Claude Opus 5.5 (`claude-opus-5-5`), via Claude Code with tool use (shell, file edits, browser). Long context. No extended thinking mode was used. ## 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 - [x] 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 - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [ ] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
2575b941d0 |
feat(task-chat): show hook and auto-review decisions as governance rows (#19266)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Agents run on harnesses such as Codex and Claude, and the task chat shows what each run did > - Harnesses make automatic decisions: hooks block or allow tool calls, and Codex auto-review approves or denies actions > - Today Paperclip drops these decisions or shows them as generic rows. Codex `safety.review.*` always says `decision: "unknown"`, the native Rust runner drops `hook/*` and `item/autoApprovalReview/*`, and claude-agent-acp drops Claude hook messages > - An operator cannot see why an agent changed course or which action ran without a person's approval. This conflicts with Paperclip's approval-gate model > - This pull request records each hook and review decision with its reason and shows it as a small governance row in the task chat > - The benefit is that automatic decisions become auditable, and a blocked action explains itself without opening run logs ## Linked Issues or Issue Description Refs #19252 (precedent: canonical `plan.updated` events rendered as a task-chat card). Builds on #19259 (ACP `_meta` passthrough from ACPX), now merged. **Subsystem affected** Runner provider events (Rust native Codex normalizer, TS drivers, ACPX sidecar), the claude-agent-acp patch, the PRP provider-event schema, and the task chat activity UI. **Problem or motivation** Hook and auto-review outcomes reach Paperclip but are lost or flattened. Codex reviews always record an unknown decision. Native Codex runs drop hook and review notifications in the Rust normalizer. Claude hook messages never leave the adapter. Codex reuses one `run.id` for every call of a hook, and the id contains a host path. **Proposed solution** Map the real outcome, decision, action, risk and reason into additive optional fields on `paperclip.hook.v1` and `paperclip.safety.review.v1`. Forward Claude SDK hook messages. Render small grey rows: a stopped action is tinted and shows its reason, an approved review folds into the command it approved as an "auto-approved" mark, and routine hook passes stay out of activity summaries. **Alternatives considered** Separate rows for every approval. This duplicated each approved command, so approvals fold into the command row instead. ## What Changed - Runner (Rust): new `governance_events.rs`. `normalize_codex_notification` now maps `hook/started|completed` and `item/autoApprovalReview/started|completed`. Each hook call gets its own id (a digest of the run id and start time), so no host path is stored. - Runner (TS): new `governance-events.ts` with the same mapping for the TS Codex driver, and the Claude hook mapping. The ACPX sidecar publishes Claude hook updates as schema-validated `hook.*` rich events. - claude-agent-acp patch: turns on `includeHookEvents` and forwards `hook_started` / `hook_response` on `session_info_update._meta.claudeCode.hook`, with bounded output. - Protocol: additive optional fields. Hook records get `outcome`, `message`, `source` and `toolName`, and the `blocked` and `stopped` statuses. Review records get `actionKind`, `action`, `riskLevel`, `userConsent` (the reviewer's user-authorization level; keys that end in "authorization" are redacted as secrets), `rationale` and `decidedBy`, and the `timed_out` and `aborted` decisions. Regenerated the manifest and validators. - Fixed: the hook `blocking` flag read `executionMode === "blocking"`, but Codex sends `sync` / `async`. - UI: `native-run-events` keeps the full hook and review payloads. `governance-presentation.ts` writes the row labels. `fold-auto-reviews.ts` attaches an approved review to its command row. The rows show the tint, the reason line and the "auto-approved" mark. Activity summaries lead with a block or denial. - Storybook: "Task chat / Governance rows" shows every outcome, a Codex run, a Claude run and the live line. - Docs: added a governance activity section to `packages/paperclip-runner/docs/protocol-compatibility.md`. ## Verification - `pnpm --filter @paperclipai/paperclip-runner exec vitest run src/governance-events.test.ts src/provider-events.test.ts src/drivers/codex src/drivers/acpx src/cli`. 2305 tests pass. This includes a replay of real Codex 0.160 notifications from a session with hooks and auto-review (`test-fixtures/governance/codex-0.160-hooks-auto-review.json`, sanitized). - `cargo test --release -p paperclip-runner-core`. The full suite passes, and `governance_events::tests` replays the same fixture. - `cd ui && npx vitest run`. 11,047 tests pass. - `node scripts/typecheck-low-memory.mjs`, `pnpm check:token-gates`, and the runner contract checks (`check:protocol-manifest`, `check:protocol-types`, `check:capability-contract`, `check:protocol-coverage`, replay goldens, contract fingerprints) pass. - Live test on a local isolated instance. A Codex agent and a Claude agent each used a preconfigured home with a PreToolUse hook that blocks edits to `0001_init.sql`, plus UserPromptSubmit and PostToolUse hooks. Both runs showed "PreToolUse hook blocked a tool call" (Codex) or "PreToolUse hook blocked Bash" (Claude), with the hook's message. They also showed "UserPromptSubmit hook added context", and the group summary started with the block. - Auto-review cannot run in Paperclip today, because the native Codex runner only allows `approvalPolicy: never`. The review mapping and the approval fold are proven against real Codex 0.160 app-server output (fixture above) and in Storybook. ## Risks - Low risk to execution. These records are display-only and carry no authority. All new schema fields are optional, so older records stay valid and older UIs ignore the new fields. - The `auto-approved` fold depends on `targetItemId` matching the command's execution id. Real Codex 0.160 data confirms that it matches. When there is no match, the review stays as its own row. - In Paperclip's isolated homes, hooks do not run, because the runner never copies hooks into an isolated home. Rows appear only for agents with a preconfigured home, or with future managed hooks. - The claude-agent-acp patch changes. The ACPX profile check still passes, because the patch is Paperclip's ACPX layer and not the upstream release. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use (shell, browser and file editing) and extended reasoning. ## 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 - [x] 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 - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [ ] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
dd889e6a0b |
feat: show the assignee's provider usage limit in task properties (#19270)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Agents run on the native Runner through the Codex app-server and the Claude ACP harness > - Both harnesses report the provider account's rate-limit windows: Codex sends `account/rateLimits/updated`, and Claude sends its SDK `rate_limit_event` as `usage_update._meta["_claude/rateLimit"]` > - Paperclip dropped both signals, so an operator could not see that an agent was near or past its provider limit > - This pull request normalizes both signals into one account-scoped snapshot, keeps the latest snapshot per agent, and shows it as one "Usage limit" line in the task properties pane > - The benefit is that an operator sees "5h 78% · resets 15:40" (amber above 80%, "Limited until …" when the provider refuses work, "using credits" when a used-up window falls back to credits) next to the assignee, and can click it for every window ## Linked Issues or Issue Description Refs #19246 Refs #19259 **Is your feature request related to a problem?** Codex and Claude report provider rate-limit windows during a run. Paperclip dropped them: the Codex notification fell through the Rust normalizer with no branch, and ACPX dropped Claude's `_meta`. Operators could not see how close an agent was to its provider limit. **Describe the solution you'd like** Store the latest reported windows per agent and show one compact line in the task properties pane, with a popover that lists every window. **Describe alternatives you've considered** A full gauge in the agent list and the run header. A design review chose one property line with a details popover instead. ## What Changed - Runner (Rust, the runnerd path): new `provider_rate_limits.rs`. Codex `account/rateLimits/updated` becomes a `provider.notice.recorded` event (category `provider.rate_limits`, scope `account`). `CodexProviderState` merges sparse updates and emits a notice only when the windows change. ACPX `usage_update` with a sanitized `rateLimit` field also emits the notice. - Runner (sidecar): `acpx-runtime-sidecar.ts` forwards only `status`, `rateLimitType`, `utilization` and `resetsAt` from `_meta["_claude/rateLimit"]`. This needs the ACPX `_meta` passthrough from #19259. Until that merges, Claude emits nothing. - Runner (TypeScript in-process drivers): the same mapping in `codex-session-notifications.ts` and `codex-acpx-driver.ts` through `drivers/provider-rate-limits.ts`. - Shared: `provider-rate-limits.ts` holds the snapshot type, the parser, the merge, and `summarizeProviderRateLimits` (fullest current window, expiry by reset time, limited versus using credits). - Server: `agent-provider-rate-limits.ts` merges each notice into `agent_runtime_state.state_json.providerRateLimits`, scoped by company and agent. A session reset keeps the snapshot. No migration. - UI: `AgentRateLimitPropertyValue` adds a "Usage limit" row under the assignee in `IssueProperties`. Transcripts treat the notice as run-log only. A run status event refreshes the assignee's runtime state. - Storybook: `Tasks and conversations/Task creation and lifecycle/Usage limit property`. - Docs: `doc/run-log-events.md` describes the notice and its storage. ## Verification - `cd packages/paperclip-runner/runner && cargo test -p paperclip-runner-core --lib rate_limit` and `--test acpx_provider_events`: sparse Codex merge, dedupe, reached window, checkpoint round trip, Claude utilization and rejection, notice shape. - `cd packages/paperclip-runner && npx vitest run src/drivers/provider-rate-limits.test.ts src/drivers/codex` - `cd packages/shared && npx vitest run src/provider-rate-limits.test.ts`: summary, expiry, limited, using credits, parse and merge. - `cd server && npx vitest run src/__tests__/agent-provider-rate-limits.test.ts`: create and merge, out-of-order snapshot, company isolation, unrelated notices, session reset keeps the snapshot. - `cd ui && npx vitest run src/components/transcript src/components/issue-properties src/context/LiveUpdatesProvider` - `pnpm -r typecheck` and `pnpm check:token-gates` pass. - Live test on a local worktree instance: a native Codex agent on a ChatGPT subscription login ran a real task. The runner recorded one `provider.rate_limits` notice. The server stored it. The task properties pane showed "7d 100% · using credits" (this account's weekly window was used up and had credits, and the run succeeded). The transcript showed no extra row. - Not verified live: Claude. The local Claude CLI was not signed in, and the Claude path also needs #19259. The Rust and sidecar paths have tests. - Not run locally: the full `pnpm test:run` and `pnpm build`. CI runs them. ## Risks - Low risk. The snapshot is display data. It does not hold or start work. The existing provider-limit wait (#19246) still reads typed run failures. - Codex can send a rate-limit update often. The runner emits a notice only when the windows change, so run-log growth stays small. - With API-key auth, the harnesses report no windows, so no row appears. This is the intended result. - `CodexProviderState` gains two optional serde fields with defaults, so older checkpoints still load. > 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 — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, through Claude Code with tool use (shell, file edits, browser) and extended reasoning. ## 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 - [x] 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 - [ ] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
86a9d3ec6c |
feat(task-chat): tool rows that say what ran and how it went (#19265)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The task chat shows each tool call an agent makes as a short activity row. > - Real Claude runs showed Bash rows named "Terminal" with no command and Write rows stuck at "Preparing file…". No row showed an exit code or a duration, and a tool refused by policy looked like any other failure. > - Codex already reported exit codes, durations and parsed command actions, but the UI dropped them, and every Codex read looked like a shell command. > - This pull request gives both harnesses one row grammar: a verb icon, the real subject, an exit chip and a duration. > - The benefit is that a reviewer can see what ran and how it went without opening each row. ## Linked Issues or Issue Description Refs #19259 (this branch includes its `_meta` passthrough commit; merge #19259 first or together). **Problem or motivation** Claude tool rows hide what ran: the runner keeps the first ACP title ("Terminal", "Preparing file…") and drops the refined one. `exitCode` and `durationMs` are null on every Claude tool event. The UI ignores `tool.execution.progressed`, `exitCode` and `durationMs` for every harness. **Proposed solution** Read real tool facts in the runner (Claude `_meta.claudeCode`, raw input and result text; Codex `commandActions`), carry them in the canonical tool event, and render one row grammar in the task chat. **Alternatives considered** Enable Claude's `terminal_output` client capability to get `terminal_exit`. That changes how command output arrives, and Claude's own exit code is derived from the error flag anyway, so this PR reads the error flag and the "Exit code N" text instead. ## What Changed - **Runner (TS):** `createAcpxToolEventNormalizer` keeps the latest concrete title instead of the first placeholder. It merges tool facts across the lifecycle and measures the duration. New `acpxToolDetailFromRuntimeEvent` reads the native tool name, the command or pattern, the description, the exit code and a "Permission denied" reason. Exit 0 is inferred only for Claude `Bash`, where a non-zero exit is always a failed result. - **ACPX sidecar:** reads the facts before `rawInput` is dropped and sends a bounded `toolDetail`. A file path argument becomes an attested workspace-relative location. - **runner-core (Rust):** validates `toolDetail`. `normalize_acpx_tool_call` uses the native name, exit code, duration, subject, description and blocked reason. Codex `commandExecution` gets its operation, a single-file target and a subject from `commandActions`. The shell wrapper is removed, and a single search reads as `"TODO" in src`. - **Protocol:** `toolExecution` gains the optional fields `subject`, `description` and `blockedReason`. Generated validators and the manifest are regenerated. - **UI:** - `nativeRunEventsToTranscript` handles `tool.execution.progressed` and passes a canonical `detail` on `tool_call` entries. - The task-chat row shows `$ command`, a path or a pattern, a red `exit N` chip (exit 0 only for commands) and a duration (0 is hidden). - Three or more consecutive reads fold into "Read N files a, b, c +1". - A refused tool shows "Blocked" with its reason. - **Storybook:** `Tasks/Tool rows` compares the data recorded today with the new runner data for Claude and Codex. ## Verification - `cd packages/paperclip-runner && npx vitest run src/provider-events.test.ts src/cli src/drivers/acpx` (1,957 pass) - `cd packages/paperclip-runner/runner && cargo test -p paperclip-runner-core --lib provider_events` - `cd ui && npx vitest run src/components/transcript src/components/task-chat` (973 pass) - `pnpm check:token-gates`, `pnpm --filter paperclip-runner build` (includes the protocol coverage and replay-golden checks) - Live runs on a local instance with real harnesses: - Codex (gpt-5.6-sol): the rows read `$ node --test` with `exit 1` and then `exit 0`, plus real durations. A three-file `sed` shows as one command and does not claim a single file. - Claude (claude-sonnet-5-5 through ACPX): the rows show `Bash` and `Edit` instead of "Terminal" and "Preparing file…". Commands show their real text, `exit 0` and durations, and edits show `Edited temp.js`. - Not seen live: a real Claude `Write`, a folded read run and a Claude policy denial. Unit and Rust tests cover them. ## Risks - The tool-execution schema gains only optional fields, so older events stay valid. Older runs keep rendering with what they recorded. - Commands now cross the sidecar boundary as `subject` (bounded to 4,000 characters). Codex already recorded commands as the tool name, and server redaction still applies. - The tool lifecycle now keeps the latest concrete title. A provider that retitles a call to something less useful would show the newer title. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use, code execution and browser automation. ## 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 - [x] 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 - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [ ] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
1eff07f29e |
feat(task-chat): show Claude subagents as a collapsible tree in the runner turn (#19264)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The task chat shows what an agent does in a run. The Paperclip Runner sends this activity as canonical provider events. > - Claude runs subagents through its Agent (Task) tool. A run that delegates showed a confusing burst of unrelated tool calls. > - The subagent data was already sent, but it was lost: ACPX dropped `_meta`, the hardened sidecar dropped `rawInput`, and async subagents report "launched" as the tool result. > - This pull request maps each Agent call to a canonical `delegation` event, links each child tool to its subagent, and shows subagents as a collapsible card or tree. > - The benefit is that operators can see what each subagent was asked, what it is doing now, which tools it used, and what it returned. ## Linked Issues or Issue Description Refs #19252 (the docked plan card used the same canonical-event pattern) Refs #19259 (ACPX `_meta` passthrough, merged). This PR builds on it. **What happened?** When a Claude agent used its Agent tool, the task chat showed one generic "Task" row and then the subagents' tool calls as flat rows in the parent turn. The subagent type, prompt, progress and result were not visible. **Expected behavior** Each subagent shows as its own card with its type, description, prompt, live progress summary, nested tool rows and result. Subagents that start together show as one tree with status dots. **Steps to reproduce** 1. Assign a Claude (Paperclip Runner, ACPX) agent a task that asks it to launch three Explore subagents in parallel. 2. Open the task while the run is live. 3. Before this change, the subagents' tool calls appear flat in the parent turn. ## What Changed - **claude-agent-acp patch:** Under the isolated runner context, the patch turns on the SDK option `agentProgressSummaries`. It forwards each subagent's `task_progress` summary and its terminal state and summary onto the spawning tool call as `_meta.claudeCode.subagentProgress` and `subagentState`. Native subagent sessions stay off, because ACPX cannot follow child ACP sessions. - **Runner:** The new file `claude-subagent-lineage.ts` tracks each Agent/Task call across ACP update deltas. It maps the call to `delegation.started|updated|completed` events and stamps child tools with `parentItemId`. An async subagent stays running after its "Async agent launched" result until its own state settles. - **Sidecar path:** `acpx-runtime-sidecar.ts` reads the lineage before it drops `_meta` and `rawInput`. Delegations go out as schema-checked rich events. Child tools carry `parentToolCallId`, which Rust (`acpx_event_payload.rs`, `provider_events.rs`) maps to `parentItemId`. - **Contracts:** The provider-event schema adds optional `prompt` and `result` to delegation children and optional `parentItemId` to tool executions. The protocol modules are regenerated. ACPX Claude now advertises the `delegation` event family. - **UI:** `native-run-events.ts` keeps delegation payloads and the tool parent link. `buildTurnTimelineRows` groups adjacent delegations into a new `subagent_group` row, nests child tool rows (plain and provider-activity shapes), and hides the spawning call's own tool row. The new `TaskChatSubagentCard.tsx` renders the card and tree. A new size token caps the result height. - **Storybook:** The new story `Tasks and conversations/…/Task chat/Subagents` has 7 states. ## Verification - `pnpm --filter @paperclipai/paperclip-runner exec vitest run src/cli src/drivers/acpx src/provider-events.test.ts src/claude-subagent-lineage.test.ts src/protocol` (2069 passed) - `cargo test --release --locked -p paperclip-runner-core --lib` in `packages/paperclip-runner/runner` (488 passed, including the new parent-link test) - `node --test test/protocol-contract.test.mjs test/acpx-sidecar-contract.test.mjs test/acpx-codex-package-contract.test.mjs test/acpx-rich-extensions-package-contract.test.mjs` (48 passed) - `pnpm --filter @paperclipai/ui exec vitest run src/components/task-chat src/components/transcript`, including the new `subagent-timeline.test.ts` - `check:protocol-types`, `check:protocol-manifest`, `check:acpx-profiles` and `pnpm check:token-gates` pass. - **Live test:** A local test-drive instance ran a Claude Opus 5.5 agent on the Paperclip Runner (hardened sidecar path). The agent ran real tasks that launched three parallel Explore subagents. The live view showed "Running 3 subagents · 2 done" with a progress summary. The settled view showed "Ran 3 subagents", each with its prompt, nested tools and its own result text. ## Risks - `agentProgressSummaries` makes Claude Code generate a short progress summary for each running subagent about every 30 seconds. This adds a small model cost to runs that delegate. - The adapter patch reads `task_notification` and terminal `task_updated` messages. A future claude-agent-acp version can change these. The patch hunks then fail to apply, and the dependency bump must update them. - If a delegation event is lost, child tools stay at the top level as before. Nothing is hidden without a matching delegation. - Codex is not changed. Codex subagents need `multi_agent`, which Paperclip keeps off on purpose. Changing that is a separate policy decision. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use (shell, file edits, browser automation). It did the investigation, implementation, tests and live test. ## 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 - [x] 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 - [ ] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
d361f92071 |
feat(task-chat): show harness status notices as chips, out of the answer (#19267)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Agents run through the native runner. The runner turns harness events from Codex and Claude into canonical provider events, and the task chat shows them. > - Harnesses report their own lifecycle: context compaction, retries, model fallback, and warnings. Paperclip lost or mangled these reports. > - Claude (claude-agent-acp 0.73) sends compaction, model-fallback and warning banners as ordinary message text, so "Compacting..." ended up inside the agent's answer and the issue comment. > - Codex sends `error` with the text in `error.message` and a `willRetry` flag. Paperclip read `params.message`, so every Codex error said "Provider notice", and every retry looked fatal. > - This pull request keeps these reports out of the answer and shows them as small status chips between the turn's activity. > - The benefit is that users can see why an agent paused, retried or forgot earlier context, and the answer text stays clean. ## Linked Issues or Issue Description **Subsystem affected** Native runner provider-event mapping (TypeScript driver, ACPX sidecar and Rust runner-core) and the task chat transcript. **Problem or motivation** Claude status banners are mixed into assistant answer text. Codex error notices lose their message and their retry state. The task chat hid all of these notices, and settled turns stripped every provider notice. **Proposed solution** Classify Claude banners as provider notices at the ACPX boundary. Map Codex `TurnError` fields and `willRetry` correctly. Render status notices as inline chips. A retry chip fades after later provider work. A final error shows the real provider message. **Alternatives considered** Patch claude-agent-acp to tag banners in `_meta`. ACPX keeps only `origin`, `kind` and `source` from `_meta`, and other sessions own the ACPX `_meta` passthrough work. Banner chunks already have no `messageId`, and model output always has one, so the classification needs no adapter patch. **Roadmap alignment** This makes existing harness signals visible. It adds no new protocol schema. It uses the existing `paperclip.provider.notice.v1` `category` and `details` fields. ## What Changed - Codex `error` notifications (TypeScript `provider-events.ts` and Rust `runner-core/src/provider_events.rs`): read `error.message`, map `willRetry: true` to a recoverable `provider_retry` notice, keep category `error` for a final error, and add the `CodexErrorInfo` kind, HTTP status, and the "Reconnecting... n/m" attempt count as notice details. Retries in one turn share one notice id. - New `claude-status-banners.ts`: classifies the claude-agent-acp compaction, model-fallback and SDK informational banners. A chunk must have no `messageId` and match a known banner exactly. - ACPX sidecar and the TypeScript ACPX driver emit these banners as `provider_notice` events instead of answer text. Compaction start and end share one notice key and carry a `Phase` detail. - Rust runner-core accepts an optional `noticeKey` and bounded `details` on ACPX `provider_notice` events. - UI: new `TaskChatStatusNotice` chip and `status-notice-presentation.ts`. Status notices become top-level timeline rows, render as chips wherever protocol cards render, and stay visible in settled (historical) turns. Generic warnings stay hidden as before. - New tokens `--tc-status-notice-warning-*` in `ui/src/index.css`. - Storybook story `Tasks and conversations/.../Task chat/Status notices` with eight states. - `doc/run-log-events.md`: describes the status notice categories. ## Verification - `pnpm --filter @paperclipai/ui exec vitest run src/components/task-chat src/components/transcript` - `pnpm --filter @paperclipai/paperclip-runner exec vitest run src/provider-events.test.ts src/drivers/acpx/claude-status-banners.test.ts src/drivers/acpx/codex-acpx-driver.test.ts src/cli/acpx-runtime-sidecar.test.ts` - `cargo test -p paperclip-runner-core --lib provider_events` and `--test acpx_provider_events` - `pnpm check:token-gates` - Storybook: open `product-task-chat-status-notices--all-states-gallery`. - Live test-drive on an isolated worktree instance: - Codex (gpt-5.6-sol, app-server 0.160): a local pass-through proxy in front of the real OpenAI API cut the first two response streams. Codex ran its own retries. The chat showed an amber "Reconnecting" chip live, then "Recovered after retry" once work continued. With every stream cut, Codex made five retries and then sent a final error with the real message. - Claude (claude-haiku-5-5 through claude-agent-acp 0.73): a long reading task triggered Claude's own auto-compaction twice. The chat showed "Compacting context…" live and "Context compacted" afterwards. The final answer and the issue comment contained no compaction text. - Not verified live: model fallback and Claude informational banners. They need a model refusal or a blocking hook. Unit tests cover them. ## Risks - Low to medium. A Claude model message that is exactly a banner text and has no `messageId` would become a notice. Model output from claude-agent-acp always carries a `messageId`. - Older stored Codex `error` notices (category `error`, not recoverable) now render as a red row instead of being hidden. - Claude retries (`api_retry`) are still not visible. claude-agent-acp reports them only to clients that negotiate session-failure records, and ACPX drops `_meta`. This is a follow-up that depends on the ACPX `_meta` passthrough work. - On a failed Codex turn the thread collapses to a summary, so the red row does not show there. The existing task banner already shows the real provider message. - Some local suites failed on this machine. They do not touch the changed code: Cursor Cloud staging-custody tests, the ACPX Claude dependency-graph pin test (a timeout), and the Rust `task_memory` monitor tests. CI is the reference for these. > 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 — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use, code execution and browser automation. Default context window. Extended reasoning was not enabled. ## 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 - [x] 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 - [ ] 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 Refs paperclipai/paperclip#19252 (plan card precedent). 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
c6996799c4 |
feat(task-chat): show an inline diff for every file edit (#19269)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - The task chat shows what an agent did during a run, including each tool call > - Codex and Claude both report the patch for every file edit, but Paperclip dropped it. Claude's ACP `diff` content was never read. The Codex `fileChange` item became a generic item with no patch. Codex `turn/diff/updated` had no native-runner mapping > - A reviewer could not see what an agent changed without opening the workspace > - This pull request carries a bounded patch on each edit call and shows it in the edit row. Each turn that changed files ends with a "Changed in this turn" card > - The benefit is that a reviewer can check every change in the conversation, with the same view for Codex and Claude ## Linked Issues or Issue Description Refs #19252 (precedent: canonical `plan.updated` events as a docked plan card). **Subsystem affected** Paperclip runner (Rust and TypeScript canonical event mapping), PRP provider-event schema, and the task-chat UI. **Problem or motivation** Edit rows say "Edited a file" with no content. Claude Edit/Write `diff` content is lost after the ACPX sidecar. The Codex native runner drops `fileChange.changes` and `turn/diff/updated`. The existing workspace-changes card showed a raw text patch in a dialog, and only on the in-process Codex path. **Proposed solution** Add an optional, bounded `fileChanges` list to `paperclip.tool.execution.v1`. Fill it from Codex `fileChange` items and Claude ACP `diff` content. Map Codex `turn/diff/updated` to `workspace.change.updated` on the native runner. In the UI, show `+N −M` on each edit row, open a compact colored diff, and end the turn with the change set. **Alternatives considered** A runner-side git diff at turn end. It needs workspace access and extra cost on every turn. The harness patches are already available. For Claude, the UI builds the turn card from the edit rows instead of new per-turn runner state. ## What Changed - Protocol: optional `fileChanges[]` on `toolExecution` in `provider-event.schema.json`, with the regenerated schema bundle, validators and manifest. Paths are workspace-relative. A patch is at most 32 KiB, and a call has at most 32 files. - Runner (Rust): new `tool_file_changes.rs`. A Codex `fileChange` item now also emits `tool.execution.*` with `fileChanges`; the native item event stays for the recovery and progress projections. `turn/diff/updated` becomes `workspace.change.updated`. `normalize_acpx_tool_call` re-validates the sidecar's `fileChanges`. `normalize_codex_notification_in` resolves absolute paths against the session cwd. - Runner (Rust): `has_bounded_rich_display_shape` accepts schema-valid workspace diffs. Without this change, durable storage cut each patch string to a 4 KiB preview. Patches use the uncapped secret redactor. - Runner (TS): new `tool-file-changes.ts`. The ACPX sidecar computes `fileChanges` from ACP `diff` content with the working directory. The in-process Codex and ACPX mappers do the same, with an optional `context` argument. - UI: new `TaskChatDiffView` (colored rows, hunk labels, a height cap, "Show N more lines"). Edit rows show counts and the diff. Collapsed activity groups show edit totals. The workspace card is now "Changed in this turn", with in-place per-file diffs, and it sits at the end of the turn. When a harness sends no whole-turn diff (Claude), the card is built from the edit rows. A change set is marked complete when its run ends. - UI: `native-run-events.ts` maps `workspace.change.updated` and attaches each edit's latest patch to its row (the `diff` transcript entries now carry `toolUseId`). - Design tokens: `--diff-add-*`, `--diff-remove-*` and `--sz-edit-diff-max-h` come from the status icon hues. - Storybook: `Tasks/Edit diffs` story. Docs: `doc/run-log-events.md`. ## Verification - Real runs on a local instance (`test-drive`, native runner): - Codex (`gpt-5.6-sol`): the "Applied a patch" rows show `+9` and `+35 −2` with their diffs. The turn ends with "Changed in this turn", 2 files, `+42`, from `turn/diff/updated`. - Claude (`claude-opus-5-5` via ACPX): the Write and Edit rows show `+5`, `+14 −1` and `+9` with correct hunks. The turn card is built from the edit rows. - Codex model note: with `gpt-5.4`, pinned Codex 0.160 reports "model metadata not found". The model then wrote files through the shell, so no `fileChange` items occurred. - `pnpm check:token-gates`: all gates clean. - `pnpm --filter @paperclipai/ui exec vitest run src/components/task-chat src/components/transcript src/adapters`: 1073 passed. - `packages/paperclip-runner`: `vitest run src/provider-events.test.ts src/tool-file-changes.test.ts src/cli/acpx-runtime-sidecar.test.ts` passed. `check:protocol-types` and `check:protocol-manifest` match. - `cargo test -p paperclip-runner-core --lib provider_events tool_file_changes`: passed. `cargo fmt --check`: clean. - Storybook: open `Tasks and conversations/…/Tasks/Edit diffs`. ## Risks - Larger payloads: an edit call can carry up to 96 KiB of patch in Rust, and the sidecar keeps 48 KiB under its 128 KiB frame. Above the budget, a file keeps its counts and drops its patch (`diffTruncated`). - Redaction: each patch goes through the shared secret redactor. Before this change, a 4 KiB preview cap also applied. - Claude turn card: it joins each edit's patch in order. It is not a net diff. For a file the turn created, the counts are net and exact. For an existing file, the counts are summed over its edits. - The workspace card moves to the end of the turn. One adapter test changed to match. - Local only: four Linux cgroup `task_memory` Rust tests fail on macOS. They do not touch these modules. ## Model Used Claude Opus 5.5 (`claude-opus-5-5`), via Claude Code with tool use (shell, browser and file editing) and a long context window. ## 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 - [x] 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 - [ ] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandClaude Opus 5.5
|
e37ab23dbc |
fix: hold an agent's new work while its provider usage limit is active (#19246)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Routine-driven agents run on the native Runner through ACP harnesses such as Claude > - When the agent's provider account runs out of allowance, every new wake for that agent fails the same way > - The ACP harness reported the exhausted allowance as a generic "terminal limit failure" with an `unknown` category, so Paperclip could not tell it from a context or turn limit > - Paperclip recorded a reset time only for the failing run's own startup retry; other wakes of the same agent kept dispatching, each spent about two minutes on workspace setup, and then failed > - This pull request classifies the limit, keeps its reset time, and holds the agent's new work until that reset > - The benefit is that a limited agent stops burning runs, shows a clear "waiting for usage limit reset" state with a time, and resumes its queued work after the reset ## Linked Issues or Issue Description Refs #13148 Refs #13379 **What happened?** A routine-driven Claude agent on the native Runner failed 29 times in about 15 hours. 20 runs failed with `native_provider_terminal_failed` and "ACP agent reported a terminal limit failure." The recorded provider failure had category `unknown`. 6 runs failed with `provider_session_open_rejected`. Their `session.open` result is `command_execution_failed` with classification `provider_rate_limit`, and the provider failure is HTTP 429 `rate_limit` ("would exceed your account's rate limit"). The startup retry of one such run recorded a cooldown until one hour later. A new wake for a different task of the same agent dispatched 16 minutes later, spent two minutes on workspace setup, and failed with the same 429. Separately, 4 runs failed with "Project authentication conflicts with this agent's managed AI connection". That message did not say which file or setting conflicted. The same message was also shown when the check could not finish. **What did you expect?** A provider usage limit is classified distinctly. Paperclip records the reset time when the provider reports one. New work for that agent waits for the reset with a visible reason. Queued work resumes after the reset, and no doomed run starts. A configuration conflict is reported only when one is found, and the message names the file to fix. **Steps to reproduce** 1. Use a native Runner agent with a Claude ACP harness whose account is rate limited or out of usage. 2. Let a routine or assignment wake the agent on several tasks. 3. See each run fail with a generic terminal limit failure or a `session.open` rejection, and see new runs keep starting. ## What Changed - Runner: The ACPX turn now receives the typed AIR session failure (`onTerminalSessionFailure`) through the runtime host and the ACPX port. The sidecar adds the provider's title to the provider failure message. Only a rate-limit or quota title becomes `rate_limit` or `quota_exhausted`. Context, turn and configured budget limits stay `unknown`. The failure details stay private. - Server: A native `turn.failed` with a `rate_limit` or `quota_exhausted` provider failure is now `native_provider_usage_limit`, the same code as the Codex usage-limit terminal. - Server: `agentProviderLimitCooldown` (extracted from the startup retry) also reads a reset clock in the provider's wording, such as "resets 2am (UTC)". The clock parser moved from the recovery service to `provider-quota-reset.ts` without changes. - Server: New `heartbeat/provider-limit-wait.ts`. Before any workspace or provider work, a queued run for an agent with an active provider limit is cancelled as `provider_limit_wait`. The run records the reset time, whether the provider reported it, the category and the run that reported the limit. Paperclip schedules one retry of the same wake at the reset through the existing AI connection wait lane. That lane does not consume the failure retry budget. Manual runs, recovering runs, conversation turns and pool-routed connections are not held. - Server: The execution projection shows "Waiting for usage limit reset" with the reset time and the next step. - Server: Only a found project authentication conflict is a configuration failure. Its message names the project file and the settings to remove. A check that cannot finish (timeout or another exit code) is now an ordinary failure, not a configuration conflict. - Docs: `doc/execution-semantics.md` describes the agent-level limit wait. ## Verification Red before the fix, green after: - `server/src/__tests__/heartbeat-provider-limit-wait.test.ts`: An automation wake after a 429 `session.open` rejection dispatched the adapter before the fix. Now the run is cancelled as `provider_limit_wait` and a scheduled retry exists at the reset. After the reset passes, the retry is promoted and the work succeeds. A manual run, a later success, expired evidence and an unclassified terminal still dispatch. - `native-startup-retry.integration.test.ts`: "reads the reset clock from an ACP terminal limit failure's provider wording" (it fell back to one hour before). - `native-session-executor.test.ts`: An ACP `turn.failed` with a typed `quota_exhausted` or `rate_limit` failure is a usage-limit terminal; `unknown` is not. - `packages/paperclip-runner/src/drivers/provider-failure.test.ts`: A typed AIR limit title is kept and classified; context, turn and budget limits are not; details do not leak. - `execution-projection.test.ts`, `ai-connections.test.ts`: The wait label, and conflict versus unfinished check. - Safety cases: `runtime-host.test.ts` and `codex-runtime-adapter.test.ts` forward the callback. The existing startup retry, provider capacity, recovery classification, legacy reconciliation, retry scheduling and execution configuration suites pass. Commands: - `cd server && npx vitest run src/__tests__/heartbeat-provider-limit-wait.test.ts src/__tests__/ai-connections.test.ts src/services/native-runtime/ src/services/recovery/ src/services/execution-projection.test.ts src/services/legacy-execution-recovery.test.ts src/__tests__/heartbeat-retry-scheduling.test.ts src/__tests__/heartbeat-execution-configuration.test.ts` - `cd packages/paperclip-runner && npx vitest run src/drivers/provider-failure.test.ts src/drivers/acpx/runtime-host.test.ts src/drivers/acpx/codex-runtime-adapter.test.ts src/cli/acpx-runtime-sidecar.test.ts` - `tsc --noEmit` for server and paperclip-runner; the ACPX sidecar and provider-failure contract checks pass. I did not run a live provider limit on staging. The live evidence is the staging run records for the affected agent, which I read only. ## Risks - The limit evidence is per agent, not per account. If the board changes the agent's AI connection, automatic wakes can still wait until the old reset (at most one hour when no reset was reported, and at most one day). A manual run is not held, and one successful run clears the evidence. - A new wake that arrives during a limit is now cancelled and retried at the reset, instead of failing. The task stays in its status, and the run shows the reset time. - The Runner change takes effect when the provider pack is rebuilt and deployed. Until then, the server still holds new work using the existing `rate_limit` evidence from `session.open` rejections. - A turn terminal with a typed rate limit or quota is now `native_provider_usage_limit` instead of `native_provider_terminal_failed`. Both are terminal and board-owned. The recovery text now asks the board to restore provider usage capacity. > 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 — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, used through Claude Code with tool use (shell, file edits, browser reads of staging run records) and extended reasoning. ## 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 - [x] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandPaperclip
|
039e0dad2c |
Connect TestOps protocol plans to verified GitHub attempts (#18985)
## Thinking Path > - Paperclip lets people coordinate agent work through a governed control plane. > - Runner protocol evals test real provider sessions against a seeded mock control plane. > - The saved TestOps protocol plan has no GitHub executor. Its dashboard shows historical results. > - A current one-case attempt also failed before any tool call or provider output. Its retained public-safe snapshot withheld the error cause. > - This pull request connects selected cases to the existing trusted workflow and retains closed operator failure facts. > - Each selected case receives a current result. Missing evidence remains broken. Existing assertions and machine grades remain unchanged. ## Linked Issues or Issue Description **Current behavior** The saved protocol plan cannot start a GitHub qualification attempt. Historical dashboard results can be mistaken for current execution. A failed provider turn can also lose its failure category when the live snapshot applies public evidence redaction. **Proposed behavior** The existing workflow accepts TestOps service inputs, validates exact case identities before provider work, runs the selected cases, and verifies their published statuses. Eval artifacts retain only validated failure phase, category, HTTP status, and retryability. **Reason and benefit** Operators can run the standing plan from TestOps and inspect current, source-bound results. A targeted pass cannot stand in for full-plan coverage. A failed startup can be diagnosed without publishing provider messages or request identifiers. ## What Changed - Add optional TestOps selection and protected reporting jobs to the existing Runner protocol workflow. - Keep the current actor, source, provider credential, and controlled accounting gates. TestOps retains the explicitly selected controlled or legacy mode and a separate 41-case Claude roster. Controlled mode preserves its existing reviewed policy, immutable bindings, tracing and zero-retry admission. Its paid workers explicitly use GitHub-hosted runners, matching the current manifest admission contract even when the legacy AWS fleet is enabled. - Bind the exact standing plan, workflow, job run, source revisions, selected cases, and saved statuses. Accept only verified workflow URL aliases. - Create a closed Allure projection inside the report job. Transfer only fixed case identities, check verdicts, numeric usage and statuses to the reporting environment. Controlled raw/chat/controller evidence remains private. - Publish one result for every selected case. Retain missing execution/report evidence as broken. Reject unsupported passes, model mismatch and source drift. Preserve the evidence schema literal, stop publication on cancellation, and retain closed API error codes/statuses. - Tag full selections separately from targeted attempts. Add bounded ingestion observation. Apply the exact TestOps filter before the unchanged controlled provider/cell-capacity check, so a one-cell registration fits a one-cell reviewed policy. - Retain up to eight eval-only closed provider failure records before board evidence redaction. Forward the original notifications unchanged. - Add selection, reporting, privacy, and admission regression controls. Document scope and remaining acceptance. ## Verification - Direct Node protocol publication, projection, metrics, and security tests: 56 passed. Focused controls exercise both mode admissions, missing controlled policy/retries/source rejection, closed result transfer, exact metadata, and missing-result handling. - `actionlint .github/workflows/runner-protocol-live-evals.yml` and `git diff --check` passed. - A proposed one-cell controlled policy passed the actual hosted validator with a synthetic prepared request and zero provider calls. The actual 41-case catalog filter selected case194/get-task-context and the real hosted admission accepted it under maxCells1. Negative controls rejected the unfiltered41, unsupported provider, source, selection, origin, expiry and lock drift. This does not verify provider auth, a runtime build or TestOps publication; final merged source/lock binding is still required. - The actual diagnostic TypeScript module passed positive, negative, secret-exclusion, and unchanged-notification controls through the existing tsx runtime. A local actual-CLI startup serializer probe passed with closed facts, secret exclusion, exit status and read-only fixture cleanup. This used an isolated resolver into the existing dependency cache; canonical exact-dependency CI remains required. - Prior-head CI passed typecheck, Runner static/Rust/native-server checks and 4946 Runner package tests. One new serializer fixture failed during Linux read-only directory cleanup; this head applies the existing neighboring cleanup pattern. Unrelated chat E2E and CLI import timeouts remain retained. Latest-head required gates are pending. - Original current-source one-case attempt: https://github.com/paperclipai/paperclip/actions/runs/41860234840 . It failed with no tool calls or output. That failure remains retained and is not a passing qualification claim. - Diagnostic candidate attempt: https://github.com/paperclipai/paperclip/actions/runs/41863410602 . It retained the new closed field but still failed before output with category unknown. This disproves the claim that typed retention alone identifies the cause. - The earlier passing run https://github.com/paperclipai/paperclip/actions/runs/40627274706 used controlled Braintrust routing. Both current failures used direct legacy credentials, a different auth path. Next acceptance is one explicitly controlled case with a reviewed current policy, followed by TestOps registration and a fresh full plan. None is claimed complete by this PR body. ## Risks The TestOps contract currently binds the existing 41 cases and one recorded Claude Sonnet 5 profile. Catalog changes fail closed until reviewed. This does not qualify other providers. Admission and execution qualify only the selected accounting mode; a controlled pass does not prove direct credential health. Model-request readiness retains pending operating reconciliation. TestOps ingestion can fail independently; persisted results are checked, and missing evidence is never accepted as a pass. The new failure field contains closed facts only; raw messages, identities, credentials, and tool payloads are excluded. ## Model Used OpenAI Codex, GPT-6. The exact hosted model ID and context window are not exposed in this session. Used reasoning, repository inspection, code editing, and tool execution. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used and the available capability details - [x] I have checked ROADMAP.md and confirmed this does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs - [x] I have described the issue with the enhancement template field labels - [x] I have not referenced internal or instance-local Paperclip issues - [x] My branch name describes the change and contains no internal ticket ID - [x] I have run the available targeted local checks and reported the remaining checks - [x] I have added relevant positive and negative regression controls - [x] I have updated the authoritative protocol documentation - [x] I have considered and documented the risks - [ ] All required Paperclip CI gates are green on the latest head - [ ] Greptile is 5/5 with no open actionable feedback on the latest head - [x] I have addressed all current review feedback --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
612d9931a6 |
Support per-turn Runner sessions on ephemeral web servers (#18932)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The web server controls native Runner sessions in remote sandboxes. > - An ephemeral web server must recover without its previous local filesystem. > - The existing admission rule accepts warm sessions. Managed Claude, Grok, and OpenCode sessions resolve to per-turn execution. > - Per-turn execution also needs durable provider-session bytes after the sandbox is retired. > - This pull request adds encrypted backup publication and removes the warm-only admission rule. > - Both lifecycle modes can use the existing native ownership and checkpoint contracts during a web deployment. ## Linked Issues or Issue Description Refs: #18518, #18529, #18826, #18835, #18841, #18864, #18887. **What existing behavior does this improve?** Native Runner execution on web servers with `PAPERCLIP_EPHEMERAL_SERVER=true`. **Current behavior** The admission rule requires a warm Runner lifecycle. Managed provider credentials can resolve an agent to per-turn execution, so enabling the ephemeral deployment profile blocks those turns. A database controller checkpoint does not preserve provider files after the old web home and per-turn sandbox are removed. **Proposed behavior** Admit native execution in either resolved lifecycle. Keep provider and credential choices unchanged. Publish encrypted provider state to shared storage before sandbox cleanup. Restore it from a fresh web home for the next turn. Use the existing controller lease and generation checks for active takeover. **Reason and benefit** Operators can remove the web server volume without excluding per-turn providers or forcing managed accounts into warm sessions. New native Daytona profiles automatically enter both rolling-deployment qualification lanes. **Breaking changes** The additive migration creates a backup publication ledger. Existing volume-backed local-disk installations retain their local backup path. S3 installations publish encrypted backups and require a stable secrets master key. Existing-volume enrollment must import surviving session data before detaching the volume. ## What Changed - Admit native Runner execution independently of its warm or per-turn lifecycle. Keep host-owned legacy execution excluded from ephemeral deployments. - Store private provider state as encrypted objects. Journal uploads before I/O, read them back, and fence publication against the current native owner. Keep the previous published backup when storage or ownership checks fail. - Restore exact provider bytes into a private cache. Require an exact durable backup before sandbox cleanup. Extend the existing bounded retention pass to retire stored objects without adding idle polling. - Import selected legacy controller and provider state in the existing offline maintenance process. Preserve queued work, task pointers, pending recovery, and original files. Prefer canonical database checkpoints. - Preserve already-failed legacy controllers with missing original artifact proof as encrypted archives. These archives do not become execution authority. Successful retained sessions still require proof. Report archival and executable imports separately. - Verify unmanaged Grok API keys through the existing xAI account validator. The live test exposed a readiness gap that kept remote Grok agents paused after platform checks. Preserve failed credentials and the separate runtime warning. - Ingest Grok whole-prompt usage at the owning ACP boundary. Bind the receipt to the exact outbound request/session; reject replay, conflicts, and incomplete authority. Separate turn cost from cumulative session cost in the sidecar schema and Rust normalization. Preserve managed billing identity and identify direct xAI API credentials. - Preserve published workspace directory names across cold allocations, including destroyed-allocation cleanup. Keep unpublished epoch/lease directories isolated and refuse to overwrite an occupied preparation. This fixes the cold-session identity regression exposed by #18922. - Increase bounded checkpoint-header inspection to 1 MiB. Retain the aggregate inspection limit. - Register all nine native Daytona profiles in per-turn and warm rolling-deployment suites. Delete the entire departing server home, exercise ordinary reads and writes, require active ownership transfer, then check a later turn on another fresh server. Permit only exact notification replay after reconnect. Ownership stays with the existing modules: Runner validates its protocol state; Core validates run scope and controller ownership; storage owns object I/O; the maintenance process owns offline conversion; the E2E wrapper owns process replacement and probes. No provider protocol is added to the shared admission rule. Grok receipt parsing stays in its provider module. The shared sidecar gains an explicit cost basis because its existing price field means session-cumulative spend, while Grok reports prompt totals. Existing consumers retain cumulative behavior when the new field is absent. ## Verification - Focused native admission, archive validation, publication fencing, cleanup, readiness, legacy import, and E2E observer tests pass. Real PostgreSQL cases verify that queued intent and historical recovery rows stay unchanged. - Full typecheck and build pass on the rebased branch. The review follow-up passes server typecheck, 29 focused PostgreSQL/archive/readiness tests, and module-boundary checks. Revision fb8d39a7a1 reached 55 successful CI checks and Greptile 5/5 with no unresolved threads. The Grok follow-up passes Runner/server typechecks, 238 ACP runtime/projection/usage tests, 16 sidecar-schema tests, the Rust cost regression, and Core billing regression. The |
||
|
DottaandPaperclip
|
3910352c92 |
feat(runner): add experimental Cursor Cloud provider (#18068)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Runner gives each provider durable execution, tool, and completion contracts. > - Cursor Cloud currently has a direct adapter outside that native contract. > - Cloud work needs exact ownership across HTTP, SSE, Stop, and recovery. > - This PR adds a qualified Cloud API driver and verified proxy to Runner. > - Product setup and hosted placement remain separate dependent changes. ## Linked Issues or Issue Description Refs #5664, #11803, #17299, and #17471. Product integration is #18069. Managed-only API placement is #18310. The related direct-adapter model/transcript work is not replaced. No duplicate native Cursor Cloud integration was found. ## What Changed - Add native `cursor_cloud` / `cursor_cloud_api` with explicit model/repository validation, bounded HTTP/SSE, durable per-turn checkpoints and a qualified Node proxy launched through the Rust facade. - Commit terminal custody before publication/release; coalesce consumers, preserve ambiguous create/Stop/recovery fences, reject late tools, and distinguish definitely-unsent oversized requests from ambiguous responses. - Support scoped cold attachment, current authority, reconnect and verified artifact staging. Keep unsupported warm/external and Windows paths closed. - Preserve early source cursors and verify immutable legacy prefixes before suffix replay, including supported compaction/masking. Optional proof publication failure falls back to complete cold verification. - Preserve canonical records at the durable native producer with JSON-safe privacy and the existing 8MiB bound; drain admitted successor flushes. Reconcile upstream semantic/pack/schema/lifecycle changes and retain S3 and legacy CLI checks. ## Verification Core head `37c442ec8dd4`: all 66 check contexts are terminal successful/neutral/skipped, including required `ci / verify` and `ci / e2e`; fresh exact-head Greptile is 5/5 with zero unresolved threads. Dependent Product `81e828d20a77` and Top `dd2959689627` include the later client handoff correction and are running their own fresh gates. Core: 47/47 Rust, 4/4 compiled-native retirement, 19/19 settlement and normal Runner build passed. Runtime Top `9af1a5de42a2`: build and recursive typecheck passed. Earlier source-scoped evidence includes 398 focused tests, five relay tests and token/type gates. The 251-assertion, 7/8-suite run failed physical PostgreSQL teardown; the unchanged stable WSP suite passed 128 through the documented wrapper. The downstream fixture corrections passed 7/7 browser and 121/121 startup tests without timeout/oracle relaxation; a broken-unsubscribe control fails. Hosted runtime `9af1a5de42a2` has a passing normal build and recursive typecheck. Latest dependent heads additionally contain a pure client fix for stale live/history overlap, with 48 focused tests, UI typecheck and token gates passing. Its new client is not deployed in the frozen hosted image; server/native/API/provider source is unchanged by these four downstream files. Fresh hosted Linux admission on `9af1a5de42a2` retired its owned runner/proxy/socket with zero prompts. The saved configuration survived reopening, and Test authenticated the bound key/catalog/selected model without a prompt. Artifact with `claude-sonnet-4-5` completed, downloaded the exact 27 bytes, matched 121 canonical identities against complete logs and independently reached FINISHED. The active Stop retry was clicked within its immutable boundary, produced one canonical interrupted turn and acknowledged run-only cancellation, retained a valid 35.076s quiet window (maximum gap 4.584s), and independently remained CANCELLED/artifact-absent beyond the original 180-second command deadline. All provider-observer credential callbacks, DB clients and loaders closed; accounting is settled and explicitly unpriced. The first fresh Stop retains its failed 10.373s sampling gap and every sample. On the upgraded9af server, the historical F226 artifact was reopened and downloaded with its exact original hash after its provider agent had been deleted/GET404 earlier today. Historical F226 full Artifact/Stop cleanup, Question, corrected Plan and reconnect retain their original identities. Deleting the three newly created disposable provider agents and the new-case post-delete grade remain blocked on explicit user approval after automatic review rejected expanding the two original approved IDs. No new-case cleanup or complete fresh matrix pass is claimed; this is separate from the directly observed task/Stop behavior and retained exact cleanup proof. Retained failures: stale fixture 132/133; E8 48/135 with 87 reset-hook failures; Mac 17 SQL failures/skips; earlier startup-title, title-save, custody/Stop and deletion failures with unknown causes and bounded recoveries. `dea023` Artifact passed 17 checks but Stop failed its false warning and 50 duplicate log identities. Pre-repair ACK failure and original Core CI failure remain recorded; retry alone establishes no cause or full local-suite pass. Provider dollar cost stays UNKNOWN. ## Risks Experimental: Cursor independently acknowledges neither the effective model nor instruction digest before the first prompt. The caller’s explicit values are submitted and behavior checked live. Unpriced provider dollar cost stays UNKNOWN. Only qualified per-turn controllers are admitted. Uncertain work and incomplete cleanup stay fenced. Existing damaged/duplicate archives remain failed evidence. Prefix proof adds bounded object-store I/O; the 8MiB producer bound does not guarantee future providers’ output fits. ## Model Used OpenAI Codex, GPT-6 family, assisted with reasoning, repository tools, code execution, browser verification, and delegated code review. The serving model’s exact API ID and context window are not exposed. No value is inferred from the model catalog. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used and the limits of available model metadata - [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 linked public issues or described the issue in this PR - [x] I have not referenced internal or instance-local Paperclip issues or links - [x] My branch describes the change and contains no internal ticket ID - [x] I have run the scoped local tests reported above; pending gates are stated separately - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation - [x] I have considered and documented the risks - [x] All required CI gates pass on the current head - [x] Fresh Greptile is 5/5 with no unresolved findings on the current head - [x] I will address all reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
b22ef22d56 |
fix(runner): show provider failure details on tasks and runs (#18622)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Native Runner starts providers and records their run outcomes. > - Provider failures can contain useful details below a generic protocol error. > - Those details were lost at the sidecar, command receipt, and run projection boundaries. > - A blocked task therefore showed a generic failure even when the provider gave a clear reason. > - This pull request carries a bounded, sanitized provider failure through those boundaries. > - Operators can read the actual cause on the task and run pages. Existing recovery policy still controls retries. ## Linked Issues or Issue Description Refs #17543 for the related closed JSON-RPC classification work. Refs #17272 for provider recovery in the legacy OpenCode adapter. This change adds display evidence for native Runner providers and keeps recovery policy separate. **What happened?** A native Claude session returned an HTTP 429 message below an ACP `Internal error`. The task and run showed only a generic startup failure. Operators had to inspect the provider response to learn that the account was rate limited. **Expected behavior** The task and run show the sanitized provider message, provider name, startup or turn phase, and available HTTP status. Unknown categories keep the message. Display evidence does not grant a retry or replace a recovery decision. **Steps to reproduce** 1. Start a native Claude run whose account is rate limited during model selection, or return a structured provider failure from a Codex or OpenCode turn. 2. Let the run fail and open its task page. 3. Before this change, the page shows a generic failure. With this change, the page shows the provider explanation. The run page shows the same explanation after reload. **Paperclip version or commit** Source checkout based on `f8a888a072`. ## What Changed - Add one JSON Schema for `ProviderFailure` and generate matching Runner and shared TypeScript readers. Keep the Runner package independent of the app workspace at runtime. - Normalize known ACPX, Codex, and OpenCode error fields. Preserve unknown messages. Redact known credential values and credential patterns before applying the 4,000-character limit. Do not copy response bodies, headers, stacks, or prompts. - Carry startup failures through the sidecar, Rust Runner, durable command receipts, and private transport error details. Keep provider text out of generic transport error strings and Sentry failure messages. - Keep turn failures in authenticated run events. Recover the same evidence from persisted events during server finalization. Store the cause in the company-scoped run result. - Show one shared notice on failed tasks and run details. Keep existing retry permissions, scheduled retry state, and resolved-task behavior. - Reapply registered run-secret and current-user redaction to task display data. Batch secret lookups for only the visible provider causes. - Document the contract and update the capability maps. Add regressions for nested Claude 429 errors, OpenAI quota and rate limits, OpenCode errors, redaction, durable receipt replay, restart finalization, and UI rendering. ## Verification - `pnpm -r typecheck` passed. `pnpm build` passed. All GitHub Actions build, test, package, and validation jobs passed on `d49c79ab4a`. The security checks passed. Greptile gave this head 5/5 with no open review threads. Paperclip Review remains pending. Its review worker exhausted six workspace recovery attempts with export_interrupted. A fresh review request was accepted and is waiting for that saved workspace. The ordinary Retry action rejected reuse of the stopped request. This is an external review-worker blocker; no check was overridden. The duplicate local `pnpm test:run` was stopped after the CI test shards passed. - Focused server settlement, provider evidence, and restart tests: 93 passed. Runner admission and normalization tests: 103 passed. Focused Runner wire and terminal tests: 29 passed. The real Rust/sidecar command receipt replay test passed. - The new projection test failed before implementation because the task had no provider cause. The startup producer regression also failed before extraction moved ahead of the generic error-code replacement. Both pass with this change. - Live check: a rebuilt local sidecar received an actual Claude HTTP 429 during startup. The new cause kept the full provider message. A synthetic task in an isolated local app then reached the same provider error through the native Runner path. The dedicated run result, task API, task banner, and run detail all showed the same message after reload. The later reporting fix keeps run.error generic; a regression proves the display cause still survives restart and stays out of Sentry capture. - The first isolated app attempt failed earlier in `admission_credential`. An ordinary manual Retry reached the provider and produced the 429 above. This PR does not claim to fix that separate admission failure. An initial parallel local database test setup also failed; the serial restart suite passed. - Security review found that copying display text into run.error could forward it to Sentry. A regression failed with that behavior. The fix keeps the cause in its display field. All 38 settlement/restart tests and the server typecheck pass. - All 29 protocol contract tests pass, including bounds and extra-field rejection. An earlier full Rust core run passed. The later full run hit one 5-second receipt-limit timing assertion; its isolated rerun passed. The full Linux and Windows Rust CI jobs passed on this head. - Review regressions pass for explicit Codex driver identity, native Rust startup and resume receipt propagation, oversized OpenCode/ACPX errors, task read-time registered-secret redaction, and the standalone source closure. The focused Runner run passed 103 tests; projection/restart tests passed 16. - Read-time redaction edge cases passed: a missing decryption key omits only the unsafe optional explanation; expanded redacted messages remain visible within the Unicode character limit. All 14 task projection tests and server typecheck pass. - The package Build check found an old Pi assertion against Error.message. The probe now checks the exact closed classification in the authenticated receipt and requires the new provider cause. Both polling transport cases pass. A local credential-free Pi probe stopped at admission_installation because this checkout lacks the Pi distribution; the installed Linux package probe passed in CI on this head. - UI coverage includes startup and turn text, unknown categories, literal rendering of provider text, read-only retry behavior, and resolved-task suppression. Token gates and map checks passed. - The live check covers Claude startup on macOS. Codex, OpenCode, terminal failures, and restart paths have deterministic regression coverage. The change is not deployed. ## Risks - Provider messages are untrusted text. The boundary selects specific fields, redacts credential patterns and known environment secret values, bounds the message, and renders plain text. New provider-specific secret formats may need added redaction patterns. - Optional fields preserve compatibility with older producers and stored runs. Old runs without the field keep their current fallback text. No database migration is required. - The cause stays in company-scoped run data. This change does not send provider text to first-party Telemetry or add it to OpenTelemetry span attributes. - Normalized categories and retryability are display evidence. Existing recovery classifiers, retry limits, ownership checks, and approval gates keep their authority. ## Model Used - OpenAI GPT-6 through Codex, with reasoning, repository tools, code execution, and browser verification. The host does not expose the exact serving variant or context window size. ## 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 and contains no internal Paperclip ticket id or instance-derived details - [x] 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 - [ ] 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> |
||
|
DottaandPaperclip
|
1bc3ed6dd5 |
fix(opencode): keep native tool calls pending until Runner settlement (#18711)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Native OpenCode sends semantic tool calls through the durable Runner protocol. > - The Runner retains a call until its result is known. > - OpenCode and its HTTP bridge each stopped waiting after 30 seconds. > - A slow response could leave a call pending after the provider had moved on. > - A later run then failed the pending-call guard during attachment. > - This pull request keeps native calls under their Runner owner until settlement or cancellation. > - The benefit is one delivered result and a safe next run. ## Linked Issues or Issue Description Related: #18343 applies the durable wait policy to native ACPX calls. This change applies that policy to native OpenCode. **What happened?** An assigned tool call took more than 30 seconds. OpenCode reported an MCP timeout while the Runner still retained the request. The source turn could finish, but suspension failed. A later `run.attach` failed because provider tool calls were still pending. **Expected behavior** The native proxy must wait for the authoritative result under the Runner owner. Stop, bridge close, and lease expiry must still end the wait. Unknown effects must still block attachment. **Steps to reproduce** 1. Start a native OpenCode run with an assigned semantic tool. 2. Hold the controller's result for 31 seconds. 3. Observe the provider's MCP result and attach a later run to the session. **Paperclip version or commit** Reproduced against `6d72243d8af0362d73fbcb5331fd42a384800d4e`. The branch is based on `36df8933f0`. ## What Changed - The native OpenCode proxy enables a driver capability for durable tool requests. - That capability removes the bridge's separate request timer and sets OpenCode's fixed MCP client ceiling to one hour, consistent with the native ACPX sidecar. - Ordinary driver calls keep their 30-second deadline. Assigned external MCP connections keep their existing budget. - Cancellation, result replay, tool authorization, and the pending-call attachment guard keep their existing contracts. - The native regression holds a result for 31 seconds, then completes a second run with the same Runner process and no pending provider calls. - The deterministic provider fixture honors the emitted MCP budget and retains the initial completion contract across ordinary follow-ups. - Execution semantics and the session verification maps describe the wait and its safety checks. ## Verification - Red before production edits: the bridge aborted a durable request at the ordinary 30-second boundary. The driver emitted `30000` instead of the expected `3600000` client budget. - The final combined bridge, driver, proxy, and native protocol run passed: 95 tests in five files (71.17 seconds). - The native delayed-result probe passed with the current Rust Runner and current bundled proxy. It completed the later run with the same Runner PID and an empty pending-call ledger. - Actual provider check passed on macOS arm64 with `opencode-ai@1.18.34`, the changed source, and a local deterministic OpenAI-compatible model. One assigned write waited 31 seconds and saved one file. Both turns completed. The second turn retained the saved tool receipt. The write ran once across five model requests. - Bridge safety cases cover result replay without another action, ordinary timeout behavior, MCP cancellation, and teardown of an unanswered durable request. - Both runner TypeScript projects passed typecheck. The first attempt lacked the eval-kernel build; it passed after building that declared dependency. - Map alignment, module boundaries, and `git diff --check` passed. - The first native follow-up probe failed because its synthetic provider forgot the initial completion-contract revision. This caused a repair turn and another discovery call. The fixture now retains the contract, and the same probe passed. The failure is retained here. - Runtime acceptance used the implementation at `583d316ad4`. The later clarification commit changes comments, documentation, and a test name only. It does not change runtime behavior. - Full current-head CI passes, including typecheck, build, general and serialized tests, Rust/Runner checks, all eight E2E shards, and the `ci / e2e` and `ci / verify` aggregate gates. Greptile is 5/5 on this commit, with no unresolved review threads. No deployment or retry of the affected historical task was performed. The actual provider check used a local model; it does not qualify a deployed Linux sandbox or a live model service. ## Risks - A native call can wait longer while its Runner owner remains valid. Stop, teardown, and lease expiry still end the wait. The MCP client has a separate fixed one-hour ceiling. Runner ownership can renew beyond that ceiling. If the client deadline expires first, the operation outcome remains unknown and the existing hold must still block replay and run attachment. - This prevents new premature timeouts. It does not classify or replay an old request whose effect remains unknown. - No schema, migration, credential, or permission change is required. ## Model Used - OpenAI Codex, GPT-6 family. The harness does not expose the exact model ID or context window. Capabilities used: code generation, tool-assisted diagnosis, local execution, and test analysis. ## 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 - [x] 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> |
||
|
DottaandPaperclip
|
66e8fab944 |
fix: complete native chat responses and improve API discovery (#18364)
## Thinking Path > - Paperclip must perform work and report its outcome accurately. > - A chat response and its delegated or operator-owned work are separate stages. > - Native chat contracts instead required literal completion of the user's whole request. > - Agents kept searching or waiting even when a truthful handoff should finish the response. > - OpenCode also has separate acknowledgement backlog and empty-response failure paths. > - This PR aligns chat completion with its current stage and makes OpenCode completion truthful. ## Linked Issues or Issue Description Refs #18098 for retained OpenCode evidence and #18377 for separate eval setup, oracle and reporting repairs. **What happened?** Real pinned OpenCode 1.18.34 reproduced an MCP timeout behind 800 text fragments. Pilot [41222196525](https://github.com/paperclipai/paperclip/actions/runs/41222196525) separately exposed a fabricated successful reply after a reasoning-only response. Later restart attempts timed out without an answer. Their native criterion literally required restarting the instance, although the chat instructions and authority required an operator handoff. General authority guidance alone did not resolve it. **Expected behavior:** A standing chat completes its current authorized response. It performs and verifies permitted actions, verifies delegated handoffs, or explains the specific unavailable action and operator path. The worker's task remains separate. Ordinary execution tasks must still complete their requested work. Empty provider responses must not become invented success. **Version and reproduction:** Actual pinned OpenCode and native Rust Runner, with retained full-stack AWS attempts. Product baseline master `51ea624344`. This PR adds no historical catalog to master. ## What Changed - Build standing-chat completion contracts from the server-owned conversation identity. Scope each current request to the response stage; preserve request text, criterion IDs, order, human-response scope and source revisions. Require verified authorized actions and truthful handoffs. Ordinary task contracts stay strict. Existing admitted inputs retain their saved contract during recovery; new contract content uses the existing revision/hash mechanism. - Guide prospective defaults to their owning resource and preserve existing work unless backfill is requested. Guide unavailable board/operator operations to the supported handoff. These are general chat instructions with no eval identities or expected answers. - Batch adjacent assistant text for at most 50 ms and 4,000 UTF-8 bytes. Preserve text, metadata and order; flush before non-text frames and shutdown. - Give an empty OpenCode response one correction within its existing turn, model, reasoning, context and deadline. Accept actual completed answer parts with incomplete headers. Preserve actual active tool work, bound idle evidence grace and fail truthfully if correction stays empty. - Reject empty OpenCode terminals in Rust without actual prose or an accepted semantic result. Never invent successful replies or evidence. Refresh generated project-discovery contracts. - Preserve accurate public API-discovery descriptions for existing project defaults and managed instance restart operations, including their field scope and authority limits. ## Verification **Qualified: [pilot 41256592937](https://github.com/paperclipai/paperclip/actions/runs/41256592937) passes 3/3, with all 35 independent checks passing.** | Case | Checks | Full case duration | Evidence and cleanup | | --- | --- | --- | --- | | Instance restart | 9/9 | 140.1 s | complete | | Project defaults | 11/11 | 204.2 s | complete | | Project work | 15/15 | 204.0 s | complete | All three are original-attempt results from source `c51e079f7f2364305b131ffd549e263ff78c5335`, containing the exact product files from `13c2b61f31d873a475ea0c3c026b19926ff42301`. Actual saved conversation contracts were inspected, as were ordinary native worker contracts where present. Each protected archive includes the actual API state and final PNG; cleanup completes. Original queries, `openrouter/deepseek/deepseek-v4.1-flash-1017`, finite case clocks, concurrency one and zero eval retries are preserved. Earlier passes do not transfer into this qualification. Both current heads pass all checks: product **62** (56 success, one neutral, five skipped), catalog **56** (54 success, one neutral, one skipped). Both have exact-head Greptile **5/5**, zero unresolved review threads and clean mergeability. The three trusted private-evidence protocol files remain byte-identical to the dispatch workflow. Raw evidence stays protected. - **2,044 API discovery tests pass.** Red controls showed that “restart instance” selected unrelated drain/settings operations and “save project defaults” selected repository replacement. Accurate public summaries now rank the existing operations correctly; route registration preserves descriptions. No endpoint, permission or field behavior changes. - **112 real-database, authenticated HTTP, native Runner and OpenAPI consumer tests pass locally**, using disposable task-owned Docker PostgreSQL. It was removed afterward; shared IPC was untouched. These cover persisted contract selection, admitted native input and the model envelope together. The isolated CI suites also pass. - **77 focused contract/input/context tests pass.** Red controls catch the wrong conversation predicate; canonical identity requires both agent and user IDs, including the actual heartbeat projection. Ordinary tasks, agent-only issues and planner tasks remain strict. Coalesced requests preserve criterion identities, source hashes and human-response scope. - **144 OpenCode driver tests pass**; native core **441 pass, one ignored**; packaging **56 pass, six skipped**. Server typecheck and build pass. - Real pinned OpenCode/native Runner: a delayed 25-second acknowledgement completes within the original 30-second MCP deadline. The text-fragment control changes 817 notifications / 54.1 seconds / timeout to 45 / 19.0 seconds / accepted finish. Separate fast, six-minute and real authenticated API probes complete 32 tool calls plus finish. These do not reproduce every remaining historical MCP timeout, and no common cause is claimed for all such failures. Retained failures remain attributed to their original source. Earlier runs exposed fabricated empty-response success, prospective-default backfill, a literal whole-task chat criterion, fixture readiness and oracle/reporting defects. The immediately preceding [41250502608](https://github.com/paperclipai/paperclip/actions/runs/41250502608), product `c0bf249807` / source `7b1de24ce1`, is **1/3**: work 15/15; restart 4/9 with the repaired contract actually admitted but no answer; defaults timed out before settlement, then exceeded the unchanged 256 MiB original-evidence allowance. Defaults domain behavior on that attempt remains inconclusive. #18377 retains the full attempt ledger, including missing archives and pre-paid cancellations. The fresh 3/3 establishes these selected outcomes; it does not establish full-catalog reliability. ## Risks The shared contract change applies to standing native chats across providers. It changes model instructions and completion scope, while permission, approval and review gates remain enforced by their existing owners. Incorrect model claims remain possible; the product evals independently require actual mutations, native work and delivery. The correction adds at most one provider request within the existing deadline; text batching can delay adjacent text by 50 ms. Three qualified attempts do not establish full-catalog reliability. ## Model Used OpenAI GPT-6 through Codex, with repository inspection, tool use, code execution and live eval tooling. Exact hosted model revision and context-window size are not exposed. ## 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 #` 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 - [x] 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 - [x] Final same-source three-cell pilot passes 3/3 with required evidence and cleanup --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
59da15066a |
feat(runner): deliver native Kimi Code (#18391)
Deliver native Kimi Code setup, exact models, scoped credentials, verified packages and runtime packs. Preserve current upstream release attestations and restore verified same-run remote retry dispatch without weakening process ownership. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
b866fa4bdc |
feat(runner): add pinned Kimi Code native runtime (#18028)
Add the pinned Kimi Code runtime, native instruction and model admission, scoped credentials, and pending-candidate recovery contracts. Retain current master release attestations and provider-pack compatibility. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
Nicky LeachandClaude Opus 5.5
|
fa760dbce4 |
fix(runner): reuse image packs only with matching contract digest (#18237)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Remote native runs use a provider pack. The controller reuses a protected pack from the sandbox image when the pack is compatible. > - #17749 gates this reuse on a hand-maintained interface revision in `provider-pack-contract.json`. > - Later changes altered the runner/pack boundary (#17922, #18188), but nobody bumped the revision. A stale Claude or Codex image pack can still be reused across a sidecar contract change. This is the failure class of #17972. > - A manual revision has a "forgot to bump" failure mode. Source-byte hashes change on every refactor, so they are too brittle. > - This pull request declares the sidecar `session.open` contract in its JSON schema and computes a contract digest from the JSON contracts and Rust shapes. > - Image-pack reuse now requires an equal digest. > - The benefit is that an incidental change keeps image packs reusable, and a real contract change retires them automatically. ## Linked Issues or Issue Description Refs #17749, #17972, #17922, #18188. **What happened?** The controller reused an image provider pack when `compatibility.acpx` and the selected agent's profile digest matched. For Claude and Codex, that profile digest binds only the upstream executable. The ACPX interface revision stayed at 1 after later sidecar contract changes. A pack built before those changes passed the reuse check. **Expected behavior** The controller reuses an image pack only when the pack uses the same runner/pack contracts as the controller's bundled pack. Comments, formatting and refactors do not change that result. **Steps to reproduce** 1. Build an image pack from a commit before a sidecar input change, such as a new `session.open` field. 2. Run a controller from a later commit that sends the new field, with the same interface revision and Claude version. 3. Before this fix, `verifyRemoteProviderPack` accepts the old image pack. ## What Changed - Declare the sidecar `session.open` parameter set as a closed `sessionOpenParams` definition in `acpx-sidecar.schema.json`. - `generate-acpx-sidecar-contract.mjs` now generates `GENERATED_ACPX_SIDECAR_OPEN_PARAMS` from it. - `parseOpenParams` uses the generated list instead of an inline `Set`. The accepted set is unchanged. - This is the surface of #17972. The schema is now its source of truth. - Declare the nested `session.open` contracts that the sidecar parses strictly: - `protocol/provider-schemas/runtime-context.schema.json` closes every runtime context object. `parseNativeRuntimeContext` uses the field lists that `scripts/generate-runtime-context-contract.mjs` generates from it. - The sidecar schema declares the closed `providerPolicy` object, and `parseProviderPolicy` uses its generated field list. - The accepted fields do not change. - Add `packages/paperclip-runner/scripts/contracts/contract-fingerprints.mjs`. It fingerprints these contracts: - the PRP and sidecar JSON schemas, with annotation text removed - the generated catalogs in `generated/` - the Rust serde shapes, `json!` payload keys, match literals and env keys in `runner-core/src`, without test-only modules - the reserved env key lists in `configured_environment.rs` - Read only the trees that every pack build context contains. Fail when a registered source is missing, so two build contexts cannot silently produce different digests. - Use only Node built-ins. The registry adds no dependency. - Write `contractDigest` as a top-level payload field in `build-provider-pack.mjs`. The manifest digest algorithm and the existing field layout do not change. - Require an equal `contractDigest` for image-pack reuse in `remote-provider-pack-verification.ts`. A pack without a digest is not reused. The controller uploads its bundled pack, as it does today for any incompatible pack. - Re-attest the source-hashed profiles, because this PR changes their bound sidecar sources: - Grok becomes profile 15 and now also binds the generated allowlist, so a Grok field change in the schema still invalidates the Grok identity. - Copilot becomes profile 88, and also binds the generated runtime context fields. - Earlier profiles stay decodable. - Add the registry script and `generated/` to the Daytona image content inputs. - Document the digest and the schema-first rule in `docker/daytona-runner/README.md` and `doc/DEVELOPING.md`. ## Verification - `node --test scripts/contracts/contract-fingerprints.test.mjs` (in `packages/paperclip-runner`): 4 tests pass. - These changes keep the digest: - schema description text - schema reformatting - renaming `parseOpenParams` - Rust comments, `#[serde(skip)]` fields and `#[cfg(test)]` modules - edits to the `#[path]` test module `tests/provider_api_validation.rs` - These changes alter the digest: - a new `session.open` schema field - a changed constraint on the `remainingWork[].description` property - a new reserved env key - a new sidecar env key - a new checkpoint field - A build context without a registered source fails. - `node --test test/acpx-sidecar-contract.test.mjs`: 13 tests pass. A new case rejects an unknown `session.open` parameter and accepts each declared parameter. - `node --test scripts/grok-profile-identity.test.mjs`: 4 tests pass. A change to the Grok field in the generated allowlist invalidates the Grok identity. - `generate-acpx-profiles.mjs --check`, `generate-acpx-sidecar-contract.mjs --check` and `generate-protocol-manifest.mjs --check` pass. - Runner vitest suites pass: 470 passed, 1 skipped. They cover the sidecar, sidecar input and protocol, Copilot and Pi installation, profile compatibility, native execution, recovery identity, the backend factory and the environment. - Server tests: pack verification, executor and artifact preparation pass (1,004 tests). - `tsc --noEmit` passes for `packages/paperclip-runner` and `server`. - `tests/runner-e2e/daytona-image.test.ts`: 10 of 11 tests pass. The failing test also fails on `master`. It expects a literal `profile-v19-identity.json` line in `.dockerignore`, which uses a `profile-v*` glob. - Not run locally: - A complete `build-provider-pack.mjs` run. The builder rejects the local Homebrew Node because it is not portable after relocation. - Rust tests and `acpx-controller-recovery.test.ts`, because `cargo` is not installed. - The full `pnpm -r typecheck`, `pnpm test:run` and `pnpm build`. ## Risks - Only JSON contracts and Rust shapes are part of the digest. The remaining TypeScript-only definitions are the `paperclip_finish` and `paperclip_block` tool schemas in `completion-result.ts` and the TypeScript env key lists. They are not covered until they move into a schema. The nested `expectedIdentity` and `tools` values ignore unknown fields, so a change there cannot cause a startup rejection. - A change there can let a stale image pack be reused. The sidecar then rejects the input with its strict parser error. - Today, Claude and Codex image packs have no contract check at all. - The digest covers all registered contracts for the whole pack. A contract change for one provider kind also retires image packs for the other. Each replacement costs about 16 s per remote start until the image is refreshed. - Existing image packs have no digest. After deploy, the controller uploads its bundled pack until the image is rebuilt. - The Grok and Copilot re-attestations start fresh sessions for those agents once after deploy, as each profile bump does today. - The Daytona image content ID formula changes, so the next image build does not reuse a cached image. > 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 — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used Anthropic Claude Opus 5.5 (`claude-opus-5-5`) through Claude Code in the desktop app, with repository tools, shell execution and research subagents. The session does not expose the context window size. ## 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 - [ ] 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 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
Nicky LeachandPaperclip
|
1d571de5f9 |
Add shared native turn attribution boundaries (#18213)
## Thinking Path > - Paperclip manages work performed by AI agents. > - Native execution crosses the plugin worker, Runner, sidecar, and durable event boundaries. > - Existing outer spans leave repeated preparation and admission work unattributed. > - Optimizations need a common baseline with accurate ownership and event meanings. > - This change extends the existing opt-in tracing contract with bounded timing receipts. > - It preserves execution policy and keeps provider internals opaque where the API provides no timing proof. ## Linked Issues or Issue Description **What existing behavior does this improve?** Attribution of native task preparation, retained/cold Runner handoff, and completion-to-text work. **Current behavior** Worker spans use a flat provider contract. Workspace calls lack a consistent dispatch envelope. Submitted-to-started timing is named as a provider queue even though it includes other work. The transport does not expose a shared breakdown of its waits. **Proposed improvement** Add invocation-scoped nesting, bounded numeric remote receipts, current-run transport timing, durable receipt intervals, and distinct completion/text milestones. Reuse the existing exporter. No latency optimization is included. Related public work: #17842 consolidates existing startup tracing tests; it does not add this runtime coverage. ## What Changed - Extend the optional SDK tracer with nested async scopes and completed timing receipts. Keep the host responsible for parent identity, capability checks, attributes, clocks, depth, and count limits. - Add dispatch and bounded host-read timings for environment and workspace providers. - Resolve transport parents on each call so retained sessions do not retain an earlier run's trace. - Split cold/resume/attach/prepare/registration/command/started-event waits. Add opt-in numeric ACPX Runner/sidecar status and prompt-start receipts. - Distinguish first completion request, validated tool receipt, final result commit, first nonempty text, and event persistence. Rename the submitted-to-started interval to match its meaning. - Link completed earlier remote lifecycles to their host-owned observer rather than placing them under a later polling request. Preserve sampling, timestamp limits and budgets. - Document the versioned coverage map, causal clock limits, and baseline acceptance requirements. ## Verification - Current head: GitHub CI is fully green. Standard Greptile and Apex are both 5/5, with no unresolved review threads. Full-suite validation was performed in CI; follow-up local validation was limited to affected packages and tests. - Review follow-up: early rejection, missing provider capability and startup-parent regressions were reproduced and fixed. The affected worker/SDK/timing set passes 128 tests; 28 timing/context tests, SDK typecheck and direct server TypeScript checking pass. The server typecheck wrapper reached an unrelated Runner rebuild and stopped because Cargo was absent from PATH; full Runner/image validation remains in CI. - CI failure accounting: the earlier Turbo cache/force conflict and Linux OpenCode shell assertion were reproduced and diagnosed. A direct proc probe ruled out permissions; a portable shell comparison identified Bash skipping BASH_ENV with stripped SHLVL and socket stdin. Upstream #18230 now supplies the CI and ignored-stdin fixture fixes; this PR adopts them without duplicate CI changes. The strict Linux OOM assertion passed before this source-equivalent merge. - Retry follow-up: the three insertion/replay/failure timing cases and server typecheck pass. The existing database regression now asserts a single marker across identical result replay; the current-head CI integration gate passes. - Upstream CI alignment: all three real-Turbo 2.11.10 integration cases pass. The repository policy gate rejected committing a generated lockfile; the final PR contains no lockfile edit and uses the maintained inline stale-lockfile recovery. - Linked-lifecycle follow-up: 44 focused host/export tests pass (three optional SDK-dependent cases skip); SDK and server typechecks pass. The API contract test verifies an explicit root context, host-owned observer link and unsampled suppression. - SDK typecheck and focused worker/invocation tests: 30 passed, including clock changes, bounded legacy IPC, and manual-span creation-scope parentage. - Focused reviewed host/native/transaction-boundary checks: 44 passed. The 86-test worker-manager suite passes after updating its exact assertions for the host-owned timing budget found by CI. Earlier preparation/first-text checks also passed. - Affected server and Runner TypeScript checks pass after building local workspace declarations. - Merge follow-up: the profile/candidate startup subset passes 94 tests, the four Grok source-identity checks pass, and Runner TypeScript checking passes. A subsequent execution-factory merge passes 21 focused timing/trace tests and server TypeScript checking. - Pinned Rust build and the ACPX Rust subset pass. The hostile receipt projection test passes. Source profile compatibility checks: 127 passed, one existing skip. Grok identity checks: four passed. - Broad transport/ACPX suite: 410 passed after building all fake provider binaries. Earlier attempts failed on missing Runner/fake-provider outputs; building the required fixtures resolved those failures. - The first CI run correctly rejected stale source attestations. After integrating current master, Grok advances 13→14 and Copilot 84→85; master’s historical fixtures and Pi 35 stay byte-identical. Provider dependencies, models and permission defaults are unchanged. Identity generation/checks now pass. - The added real-Postgres result lock regression could not initialize its local embedded cluster. The insertion/replay/failure unit regressions pass. The current-head CI integration gate passes. - Comprehensive repository checks and image builds are delegated to CI, as requested for this instrumentation pass. No deployment, model run, collector-ingestion proof, or latency improvement is claimed. ## Risks The new SDK methods are optional. Legacy span calls and endpoint-off behavior remain supported. The host accepts only closed timing names and bounded attributes. Remote durations are anchored at local receipt; transport/scheduling uncertainty remains explicit. Trace trees have count/depth limits. The first rollout must inspect actual collector exports before treating the baseline as accepted. Fresh live qualification for the new source identities remains a rollout requirement. Revert these commits to remove the new measurements; no schema migration is required. ## Model Used OpenAI Codex, GPT-6 family, with reasoning and local code/tool execution. The exact runtime model ID and context-window size are not exposed in this session. ## 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 following the enhancement template - [x] I have not referenced internal/instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal issue details - [x] 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] Standard Greptile and Apex are both 5/5, with no unresolved findings - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
Devin FoleyandClaude Opus 5.5
|
16816d45e6 |
fix(runner): keep OpenCode thread/read within runnerd's frame limit (#18218)
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner runs OpenCode agents through runnerd and the
OpenCode app-server proxy
(`packages/paperclip-runner/src/cli/opencode-app-server-proxy.ts`).
> - When runnerd restores an OpenCode session, it sends `thread/resume`
and then `thread/read`. It uses `thread/read` only to find an active
provider turn.
> - The proxy answered `thread/read` with the full retained OpenCode
message history (`GET /session/{id}/message`) in one JSON-RPC line.
> - runnerd rejects a provider stdout line that is larger than 4 MiB
(`CODEX_APP_SERVER_MAX_FRAME_BYTES`). A long OpenCode session therefore
can never resume. Each restore fails with `harness stdout frame exceeded
4194304 bytes`, and the run stops with `provider_frame_too_large`.
> - This pull request makes the proxy return turn metadata only, the
same as the Codex metadata-only read.
> - The benefit is that long OpenCode sessions resume again, and resume
no longer reads the full message history.
## Linked Issues or Issue Description
**What happened?**
A Paperclip Runner OpenCode task on staging tried to resume its session
in a new sandbox. The restored OpenCode state was approximately 41.5 MB.
The `run.attach` command failed with `failed to resume OpenCode
provider: failed to start opencode provider: harness stdout frame
exceeded 4194304 bytes`. The server recorded
`native_session_recovery_failed` with error code
`provider_frame_too_large`, and it stopped automatic replay. Each new
attempt has the same failure, because the message history only grows.
**Steps to reproduce**
1. Run an OpenCode task until its session holds more than 4 MiB of
message parts.
2. Let the run continue in a new runner process, so that runnerd must
send `thread/resume` and then `thread/read`.
3. The proxy writes the full message history in the `thread/read`
response. runnerd rejects the frame and the resume fails.
**Expected behavior**
The resume succeeds. The size of the session history does not change the
size of the `thread/read` response.
**Root cause**
`thread/read` in the OpenCode proxy added `transcript: await
session.read?.()`. No consumer reads this field. The Rust provider reads
only `thread.turns` (`latest_active_turn_id`). The Codex path already
avoids message hydration for the same check ("Never hydrate message
contents just to decide whether this thread has an active turn").
## What Changed
- `opencode-app-server-proxy.ts`: `thread/read` now returns `thread.id`,
`thread.cwd` and `thread.turns` only. It does not call `session.read()`.
- `test/fixtures/fake-opencode-server.mjs`: the fake OpenCode server can
now return a large retained message history. The test enables this with
a `fake-message-history-bytes` file in `XDG_DATA_HOME`. This follows the
existing file-switch pattern of the fixture. Without the file, the
response is `[]`, as before.
- `src/cli/opencode-proxy-thread-read.test.ts`: a new regression test.
It builds the real bundled proxy entrypoint, starts a session, stops the
proxy, gives the persisted session a 5 MiB history, then starts a new
proxy and sends `thread/resume` and `thread/read` (the runnerd restore
sequence). It asserts that all stdout frames stay below 4 MiB and that
`thread/read` still reports the thread id and turns.
## Verification
- Red before the fix: `npx vitest run
src/cli/opencode-proxy-thread-read.test.ts` failed with `expected
5243183 to be less than 4194304`. The 5,243,183-byte frame was the
`thread/read` response.
- Green after the fix: the same command passes.
- `npx vitest run src/cli/opencode-app-server-proxy.test.ts
src/cli/opencode-proxy-thread-read.test.ts`: 6 passed.
- `npx vitest run src/cli/opencode-proxy
src/backends/native-instruction-measurement.test.ts
src/drivers/opencode`: 158 passed, 1 failed. The failure
(`opencode-server-driver.test.ts` > "uses provider structure rather than
prose length to select a post-tool answer") also fails on the unchanged
base commit in this environment. This change does not touch that path.
- `tsc -p tsconfig.json --noEmit` for `packages/paperclip-runner`:
passed.
- Safety checks:
- Consumers: only the runnerd Rust provider (`read_thread`) calls
`thread/read` on this proxy. It reads `thread.turns`. No TypeScript or
Rust code reads `transcript`.
- Active-turn detection does not change. The `turns` logic is the same
code.
- Resume now does less work: one `GET /session/{id}/message` request
less.
- Not run locally: the Rust tests and a full runnerd plus real OpenCode
resume. This environment has no Rust toolchain. The Rust code does not
change. CI runs the Rust suites.
## Risks
- Low risk. The change removes one unused response field.
- If an external tool read `transcript` from the proxy's `thread/read`,
it does not get it now. I found no such consumer in this repository.
- Tasks that already failed with `provider_frame_too_large` continue
only after this proxy reaches the runner provider pack and the task runs
again.
## Model Used
- Provider: Anthropic. Model: Claude Opus 5.5 (`claude-opus-5-5`). Used
through Claude Code with tool use (shell, file edit, GitHub connector)
and standard reasoning.
## 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 (related: #16401 kept OpenCode turns alive through oversized
SSE events. It does not change `thread/read`.)
- [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
- [x] 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 (none
required: no documented contract includes `transcript`)
- [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
- [ ] I will address all Greptile and reviewer comments before
requesting merge
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
||
|
DottaandPaperclip
|
54cc522e86 |
feat(runner): add gated native Antigravity ACP execution (#18188)
## Thinking Path > - Paperclip manages agents and their work. > - Native Runner must bind each provider turn to the selected task, account, model, and instructions. > - Antigravity needs native ACP admission and physical process ownership across continuation. > - A saved conversation must not reuse an old process owner or silently switch its effective model. > - This pull request adds the native candidate behind exact operator admission. > - The default release gate remains closed while qualification is pending. ## Linked Issues or Issue Description Builds on merged #18187. Product account setup and the candidate producer are in dependent #18189. The repeatable browser journey is in #18190. Refs: #12503, #14938; those proposals use legacy CLI adapters. **Agent or provider** Google Antigravity ACP 1.4.3. **Why this adapter is useful** Users need to set up an Antigravity agent and run real work through their managed Google subscription. **How the agent is invoked** Native Paperclip Runner uses the pinned Antigravity ACP runtime. Exact operator admission is required while qualification remains pending. ## What Changed - Add native Antigravity ACP model and instruction admission, selected-account homes, and fenced refresh ownership. - Carry exact candidate authority from the control plane through Runner, Rust, the sidecar, and each current run. Clamp daemon lifetime to the absolute permission expiry, including replacement owners. - Preserve a rotated OAuth refresh token before later identity verification can fail, including failed or cancelled startup admission. Make private lease-close retries safe. - Bound native probe retirement and retry the exact original owner; do not delete credential homes before physical proof. - Preserve Gemini API-key recovery when shared Google subscription capability is added. - Resume the same tagged native conversation with fresh per-turn process ownership and physical native retirement. - Include native manifests in isolated Rust image stages, release cache keys, and dev rebuild detection. The workflow changes only extend existing cache input lists. - Keep current master provider behavior and append Grok 13, Pi 35, and Copilot 84 input identities. Preserve prior identities, including saved Copilot 82 and 83 runs. ## Verification - Runner TypeScript main checks, profile generators, Rust formatting, and offline workspace checks pass. The native backend integration target passes 28 tests. - The complete transport and cleanup group passes 387 tests without unhandled rejections. These checks use local scripted children and actual process and port ownership. - Saved-profile decoding, native-execution parsing, installation, and selected-credential controls pass 208 focused tests. All 109 pre-existing profile identity files remain byte-for-byte unchanged. Copilot, Grok, and shared TypeScript/Rust generation checks pass. - The final recovery fixture passes all seven cases. After the master rebase, the combined recovery and owned-Node-runtime group passes all 10 cases. Each expiry case sets one 45-second absolute grant before startup. It includes the deliberate six-second cold delay, four existing eight-second command budgets, and active-turn headroom. The test proves an active turn before expiry and then checks the daemon, owned process group, child processes, and all three native port fences. The 60-second test deadline does not renew provider authority. - The consolidated model-discovery and pending-release group passes 22 tests. Google credential compatibility and auth recovery pass 25 tests, including existing Gemini API-key recovery. The full product settings test group remains intact in #18189. - Earlier failures remain in their original CI runs and local records. They exposed the Copilot 82 decoder gap, an expired five-second fixture bootstrap ticket, and a fixture grant consumed before activation on loaded CI. Each repair has a separate result. Production ticket limits and admission behavior are unchanged by the final test commits. - An unrelated decision-expiry check failed in [the earlier CI run](https://github.com/paperclipai/paperclip/actions/runs/40941986698/job/123688668997). Its owning code is unchanged from the base. The unchanged suite passes 20 tests on isolated PostgreSQL. A controlled database rollback reproduces the earlier wake: clean startup schedules the 120-second decision expiry, while rollback reconciliation leaves a 30-second continuation-coalescing wake. The decision stays open, with no wake delivery or error. The fresh final-head server shard passes; the failed result is preserved. - Final native commit `ec6bc7e4d77f5ae0cc4946dbba6c662e95a87f5b` passed `ci / verify` and `ci / e2e`. Fresh Greptile and Paperclip reviews both score 5/5, with no open findings. Antigravity retains the recorded native `.5` closure and exact low-model profile. This PR does not claim global or cross-platform qualification. ## Risks - The new transport carries private managed credentials. Exact ownership, account generation, model, instructions, and native retirement are fail-closed. - Only local macOS ARM64 has a verified complete Antigravity runtime. Default Antigravity task execution remains disabled without current trusted operator admission. The Google server sign-in lane and production candidate producer ship in #18189; this native slice does not expose the subscription catalog choice. - Shared launch inputs change provider identities. New identities are append-only; existing recorded identities remain available. ## Model Used OpenAI Codex (GPT-6). The host did not expose the exact model revision or context limit. The model used tools for code edits, tests, and 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 (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 - [x] 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> |
||
|
DottaandPaperclip
|
b81b870732 |
Add QA smoke journeys and OpenCode run traces (#18098)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Product E2E journeys verify saved application behavior across deployments. > - Task creation and questions need reusable smoke selections and exact run attribution. > - Operators also need to inspect the OpenCode execution behind a measured question. > - Company observability does not currently support native OpenCode. > - This change adds the journeys and a bounded projection of normalized OpenCode run events. > - The projection follows the configured capture policy and retains the current run identity across warm reuse. ## Linked Issues or Issue Description Related foundation: #17262. Related alternative: #17989 exports metadata from OpenCode's native OTLP stream. This change uses normalized run events to support the existing content switches and per-run linkage. It does not forward the native stream. The two PRs overlap in launch registration and must be reconciled before both land. **What existing behavior does this improve?** Reusable Product E2E smoke selections and company observability for native OpenCode. **Current behavior** The journey catalog lacks reusable task creation and attached-agent question checks. Native OpenCode is marked unsupported for company observability, so a successful destination connection test does not prove that agent traces will appear. **Proposed behavior** Add explicit task-create and ask-question selections. Verify saved state and exact company, issue, agent, model, environment and successful run attribution. Export normalized OpenCode turns, tools and usage to the configured OTLP destination. Honor each capture switch and redact known secrets. **Reason and benefit** CI can run a small measured smoke selection, retain its screenshots and checks, and link results to traces belonging to the same run. **Breaking changes** Existing selectors remain unchanged. OpenCode export is opt-in through existing company settings. Legacy OpenCode stays unsupported. ## What Changed - Add reusable task creation and question journeys, configured-agent capability, owned-fixture checkpoints and strict evidence validation. - Add an OpenCode-owned projection of normalized run events. No provider SDK or raw payload schema enters heartbeat coordination. - Extend the private launch union and reserved environment allowlist for native OpenCode. With export disabled, no receiver request runs. - Keep destination headers in the parent wrapper and out of the actual provider child environment and configuration. - Bound each turn to 64 tool and 64 usage entries, 8 KiB per text field and a 1 MiB request. Use a three-second request deadline, four concurrent exports, and no retries or idle worker. - Pass the rotated runner authority to each proxy turn. A retained process no longer attributes later turns to its original launch run. - Update settings copy, observability documentation and capability maps. ## Verification - `pnpm -r typecheck` and `pnpm build` passed after the implementation changes. - Adapter launch/redaction: 9 tests passed. Projection and actual proxy: 12 tests passed before the review fix; the expanded projection suite passed all 12 cases after the fix. The proxy test exercises two runs in one process against a real local HTTP receiver and a fake provider. - Full OpenCode driver/projection suite: 72 passed, one existing response_wake test timed out at five seconds. A focused check then passed both existing omitted-continuation cases and the new trace export case. The timeout cause remains unconfirmed. - Runner package TypeScript and Rust `cargo check` passed. Map and UI token checks passed. - Prior journey validation: 273 tests across 12 files and the journey TypeScript check passed. - Broad local `pnpm test:run` encountered native-runtime integration failures with repeated embedded PostgreSQL initialization failures and was stopped. All 16 failing cases passed in an isolated run outside the filesystem sandbox (961 unrelated cases unselected). The broad local run is not a clean acceptance result. A later focused database-backed chat/heartbeat run passed all six selected observability cases, including native OpenCode launch and successful allocation (1,809 unrelated cases were unselected). - All CI gates passed for `21085f880d8babc9efeb22d0623db99613d33093`, including packaged-runner, clean-install, browser and build checks: https://github.com/paperclipai/paperclip/actions/runs/40884658995 . Greptile reviewed the same commit at 5/5 with no unresolved findings. - Verified OTLP JSON acceptance and indexing with an explicitly synthetic transport marker. No live OpenCode model trace or deployed smoke acceptance is claimed yet. ## Risks Export is best effort. Abrupt termination, recovered in-flight turns without a new submitted event, limits or receiver failure can lose traces. Export failure does not change task success. The projection represents observed normalized events, not raw native model spans or hidden reasoning. Known-secret redaction is not an OS isolation boundary. UI changes can break journey locators. Deployment adapters retain credential, ownership and cleanup responsibility. Both the controller and native runner bundle must be updated before live qualification. ## Model Used OpenAI Codex, GPT-6, with reasoning, code execution and browser tools. The exact serving model ID and context size are not exposed to this session. ## 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 - [x] I have run tests locally and they pass (targeted suites; broad local limitation documented above) - [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> |
||
|
DottaandPaperclip
|
356c7de9b7 |
fix(runner): bind Grok packs to current admission source (#17972)
## Thinking Path > - Paperclip manages agents and their work. > - Native agents use verified Runner and provider-pack artifacts. > - A protected installed pack can be reused when its selected provider profile matches. > - Grok kept profile 1 when its sidecar gained effort, search, and startup diagnostics. > - An older Grok sidecar can therefore pass compatibility and reject the new session fields before provider startup. > - This PR binds the current Grok profile to its admission source so a fresh run selects the current verified pack. ## Linked Issues or Issue Description Refs: #17922, #17942, #17962. Related installation contract: #14024. No duplicate repair was found. **What happened?** The selected Grok profile digest stayed unchanged across native session contract changes. The installed-pack verifier correctly compared that digest, but the unchanged value let a pre-effort sidecar satisfy a current controller. That old parser rejects `grokEffort` and `grokDisableWebSearch` before the new startup diagnostics run. **Expected behavior** A fresh Grok run must use a pack that supports its current session contract. Source-only app changes must still permit warm reuse when the selected Grok profile matches. Reattachment must keep its exact admitted artifact authority. **Steps to reproduce** 1. Retain a protected pack with published Grok profile 1 and ACPX interface 1. 2. Upgrade the controller to the native effort and search contract. 3. Start Grok 4.7 with High effort and disabled web search. 4. The old profile passes installed-pack compatibility, but its sidecar rejects the new fields. **Paperclip version or commit** Reproduced from master at `09ad9adce2cf4742944353a3707a2f908e9bb35e`. ## What Changed - Advance Grok to profile 7. Keep historical versions 1–6 decodable and keep the Grok 1.0.13 runtime pin. - Stamp the Grok admission source identity into a generated launcher comment. Keep the existing physical command-byte digest check unchanged. Bind effort/search/credential handling, sidecar admission, and Rust backend/session/diagnostic source. - Check the source attestation in the existing TypeScript/Rust profile build gate. Keep its required fixture in the Docker context. Refuse to overwrite a versioned identity after source changes. - Add regression coverage for rejecting the old pack, current-profile warm reuse, exact historical recovery authority, and actual sidecar dispatch of Grok 4.7 High with both search policies. - Re-attest Copilot as profile 71 because its bound shared recovery decoder now retains Grok 6. Preserve Copilot 70 and all earlier identities. Keep the compatibility algorithm, other provider identities, dependencies, lockfile, and workflows unchanged. ## Verification - The production installed-pack regression failed before the profile update: the old Grok pack was accepted. It now passes. - 105 server manifest, artifact, archive, and authority tests passed. - 246 Runner profile, physical launcher integrity, Grok effort/search/credential, and actual sidecar process tests passed; six existing platform cases were skipped. - 31 Node packaging and identity tests passed, including an actual generator CLI regression that preserves all authority files when a versioned identity would change. - 55 Rust ACPX unit tests and 17 real sidecar pipe tests passed. After the final profile declaration, all 55 unit checks passed again. - Final `pnpm -r typecheck` and `pnpm build` passed at the final source. - CI on the preceding head caught Copilot’s stale attestation for the shared recovery decoder. The same current-source test failed locally, then passed after profile 71 was generated with version 70 retained. All 106 affected Copilot/profile checks pass. Final head `78e6d76fc52f492371e15574482b3641735a6d89` passed the full CI workflow; the failed prior job log is retained. - Review follow-up: mutating the Rust backend’s actual Grok descriptor field left the prior identity unchanged. This regression failed before binding `acpx_provider_backend.rs` and passes afterward. Profile 7 retains the prior versioned fixture and recovery decoder. All 179 affected Runner checks and 75 focused server pack/manifest checks passed after this change. - `pnpm test:run` hit the recorded embedded PostgreSQL bootstrap failure after five attempts. The full run also exposed a current-release fixture with the historical Grok digest; it now reads the current profile. Its 11 focused manifest tests now pass. The failed local run log is retained; final exact-head CI passed. - The same filtered-context Docker build that failed CI now passes locally after adding its required source fixture. - A separate probe used the built sidecar in a private HOME with no credentials. It admitted the current profile and the new Grok fields, then returned the closed working-directory rejection before provider launch or inference. - A historical parser probe reproduced the pre-effort sidecar rejection. These probes establish the contract boundary; they do not establish native subscription task acceptance. - Initial restricted local ownership tests failed because loopback listeners were denied. The same tests passed with loopback access. One new dispatcher fixture first lacked required instructions; the completed request passed. These setup failures are retained in local evidence. - Live native task acceptance remains pending deployment. Earlier deployed attempts failed before tool output. No successful native shell proof is claimed. - Final exact-head merge gate: all 62 contexts are clean (57 success, four intentional skips, one informational neutral formal review). Greptile and Paperclip reviews are both 5/5, with no unresolved actionable threads. The formal review uses the existing report-only neutral policy. ## Risks - The first fresh Grok run after upgrade may need to stage the current provider pack. Matching current profiles keep their existing reuse path. - Fresh admission rejects older Grok profile identities. Historical decoding and exact reattachment authority remain separate; this change does not reinterpret an old identity or replace an active session's pack. - Future changes to bound source require a new Grok profile attestation. The build gate fails if the checked-in identity is stale. - Model, effort, search, credential, approval, and retry policy are unchanged. ## Model Used - OpenAI Codex, based on GPT-6, with reasoning, tool use, and code execution. The exact deployment model ID and context-window size are not exposed in this session. ## 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 - [x] I have run tests locally and they pass (focused checks; full-suite database failure is retained above) - [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> |
||
|
DottaandPaperclip
|
6b9e5f3a80 |
fix(evals): enforce qualified ACPX profile admission before paid turns (#17964)
## Thinking Path
> - Paperclip coordinates agent work through Runner.
> - Controlled evals route model calls through a budget gateway.
> - The definitions pin each ACPX runtime identity.
> - A stale qualified profile currently reaches a paid turn before
scoring rejects it.
> - The Runner CLI already checks an exact expected profile before it
creates a provider.
> - This change forwards that existing admission argument through the
controller.
> - Profile drift can then stop before model spending.
## Linked Issues or Issue Description
Refs #17943 and #17929.
**What happened?**
The worker in run 40618022700 passed all four behavior checks and
retained three final request receipts. Its grader then rejected the old
Claude SDK pin. The controlled wrapper could not pass the existing
`--expected-acpx-profile` argument to the built CLI.
**What did you expect to happen?**
The built CLI must reject a stale expected profile before provider
creation.
**Steps to reproduce**
Run a controlled ACPX cell with a definition that pins a different SDK
from the built Runner. The old wrapper accepts only request and output
arguments. It cannot enforce the profile admission supplied by updated
definitions.
**Paperclip version**
The observed run used
|
||
|
DottaandPaperclip
|
0d22e27dc4 |
fix(runner): preserve closed native startup diagnostics (#17962)
## Thinking Path
> - Paperclip runs agents through a controlled execution boundary.
> - Native Runner starts ACPX providers through a TypeScript sidecar and
a Rust transport.
> - That transport hides arbitrary provider messages because they can
contain credentials.
> - Grok admission failures currently have no stable code. Other startup
failures can also lose their owning stage.
> - A real native startup failure therefore reports only
`classification=unclassified`, even when the ordinary subscription hello
test succeeds.
> - This pull request preserves fixed failure categories without
forwarding provider text or changing admission policy.
> - The benefit is a useful next diagnostic result before another
functional repair or retry.
## Linked Issues or Issue Description
Refs #17922 and #17942.
**What happened?**
A native Grok session failed before its first tool. Runner assets passed
verification. The Rust rejection discarded the cause because only closed
error codes may cross that boundary. The existing admission guard used
plain errors. Startup errors outside that guard could also lose their
stage.
**Expected behavior**
Report a fixed Grok admission reason, or a fixed startup stage when no
known error code exists. Keep credentials, provider messages, session
IDs, and paths out of the classification. Keep the failure and cleanup
effective.
**Steps to reproduce**
1. Have a Grok ACP fixture return a session without its native effort
acknowledgement.
2. Start it through the real ACPX client and pass the failure through
the sidecar classifier.
3. Before this change, the result is `acpx_sidecar_command_failed`. Rust
reduces that to `unclassified`.
4. The same loss occurs for injected sandbox, credential, and runtime
admission failures.
## What Changed
- Give Grok effort admission errors fixed codes for missing
acknowledgement, model or effort mismatch, session mismatch, conflicting
configuration, drift, and invalid protocol use.
- Record closed host startup stages in a private weak map. Preserve the
original error object, cancellation, and resource cleanup.
- Prefer existing known error codes over a fallback stage. Ignore
arbitrary provider-supplied stage properties and messages.
- Map only exact new codes to Rust diagnostic categories. Add real
ACPX-client and sidecar-pipe regressions with secret canaries and
unknown-code controls.
- Bind the changed shared source and new diagnostic modules in Copilot
profile 70. Preserve profile 69 and earlier history.
- Document the diagnostic contract. There are no dependency, lockfile,
workflow, auth, model, permission, or retry-policy changes.
## Verification
- Red before the production change: four TypeScript cases lost the
native reason or host stage. A Rust case returned `unclassified` for the
new closed categories.
- Final focused checks: 320 tests passed: 241 across sidecar
classification, Grok admission, the real ACPX client, recovery, runtime
adapter, and Copilot installation; all 79 host integration tests also
passed in isolation. These include nine startup-stage cases, translated
errors, actual missing Pi skill materialization, missing Copilot/Cursor
credentials, and a missing workspace binding.
- Review follow-up: a translated Copilot rejection lost its stage, and a
real Pi skill-loading failure reported configuration. Both regressions
failed before the two-line repair and pass afterward. Stage recording
now follows provider translation and starts before Pi skill acquisition.
The current unpublished Copilot 70 identity was regenerated.
- Formal review follow-up: missing Copilot and Cursor credentials
reported configuration. Both cases failed before the two-line stage
repair and pass afterward. A missing-workspace case also verifies the
separate binding catch.
- Seven Rust unit checks and 17 sidecar transport integration checks
passed. The pipe checks preserve known categories and reject unknown
suffixes without disclosing the provider message.
- `pnpm -r typecheck` and `pnpm build` passed. Rust formatting and the
generated profile/source identity checks passed.
- Host integration history is retained: one complete 73-case host run
passed. Other batches hit credential-port ownership errors in different
existing cases; the four new stage regressions passed. The final 79-case
host run passed after the last review fix. The prior intermittent lease
failures remain recorded and are not claimed fixed here.
- `pnpm test:run` was attempted and stopped after repeated embedded
Postgres bootstrap failures. The same local database failure predates
this change. Full CI must pass before merge.
- A metadata-only probe with pinned Grok 1.0.13, private HOME, synthetic
credentials, a local catalog, and no inference passed fresh Grok
4.7/High admission and cold restore. This is supporting ABI evidence. It
does not prove live subscription execution.
- Initial CI history is retained: server shard 1 failed its unchanged
final rate-limit slot test (two requests allowed instead of one). No
server policy code changed here. The review follow-up requires fresh
full CI; this is not claimed fixed.
- Second CI history is retained: chat shard 2 failed the unchanged Slack
session-sync quiet-queue test (three selects during the quiet window).
The first rate-limit failure did not recur there. No chat or server
policy code changed in this PR. Final head
|
||
|
DottaandPaperclip
|
f60ac29cf1 |
fix(runner): migrate Grok Build with native reasoning effort (#17922)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Harness selection maps supported agents to Paperclip Runner. > - The native Runner already supports Grok Build, but its migration mapping excludes Grok. > - Grok agents also have a thinking-effort setting that the native execution contract does not carry. > - This pull request adds the migration path and preserves explicit Grok effort through startup and resume. > - Operators can upgrade an existing Grok agent without silently losing its model, account, or effort. ## Linked Issues or Issue Description **What happened?** Existing Grok Build agents have no Runner selector or upgrade action. Adding only the mapping would route conversion through the Codex fallback and lose Grok execution semantics. Native execution also ignores the legacy reasoning-effort field. **Expected behavior** A qualified Grok agent can explicitly upgrade. The saved model, account, instructions, history, and supported effort remain intact. Unsupported legacy settings fail before saving. The provider must acknowledge the selected effort before inference. **Steps to reproduce** 1. Open the runtime page of an existing Grok Build agent on a qualified Linux x64 or macOS ARM64 computer. 2. Observe that the Runner selector and upgrade action are absent. 3. Compare the native execution input with the saved legacy reasoning-effort setting. Related work: #13882 introduced native Grok Build. #15422 covers the earlier default-runner work. This change extends the current shared selection contract. ## What Changed - Add the Grok harness mapping, qualified platform limits, upgrade action, and company-scoped computer qualification. - Translate Grok settings to ACPX without changing the selected account or explicit model. Resolve the legacy default model to the native default. Preserve the effective legacy search policy. Reject incompatible command, argument, permission, and turn-limit settings. - Add native execution input v10 for explicit Grok effort and search policy. Preserve historical schemas. Enforce disabled search through Grok requirements and bind it across startup and recovery. - Apply and verify ACP `reasoning_effort` before prompting. Bind the value to provider descriptors, checkpoints, runtime identity, and resume checks. - Use the Grok catalog and effort choices in the task composer. Apply task model and effort overrides while retaining the agent account and search policy. Update runtime controls, portability/default handling, documentation, and capability maps. - Advance Pi and Copilot source attestations for changed shared transport and recovery code. Keep historical identities intact and update all Rust integration fixtures. ## Verification - Migration and review regressions were reproduced before the fixes. Coverage includes the Grok mapping, default model, explicit effort, implicit search policy, task overrides, and incompatible legacy settings. The broad migration, route, immutable-input, and composer check passed 478 tests. The final catalog and task-input check passed 135 tests. - Runner startup, recovery, search policy, and profile checks passed 361 tests, with one platform skip. The final source-identity, search-admission, and transport event-pump check passed 89 tests. - All 757 Rust workspace tests passed for the broad implementation. After the final source attestation update, all 55 ACPX profile/session tests passed. - `pnpm -r typecheck` and `pnpm build` passed for the implementation. Server and Runner typecheck passed after the final production change. Server `tsc --noEmit` passed after the final test-fixture change. Docker context integrity, token gates, maps, generated protocol data, and replay goldens passed. - The v10 startup fixture initially used an ambient local Grok login and failed on CI. An explicitly empty credential home reproduced all four failures. The fixture now supplies a synthetic key and a private empty home. A separate case checks that missing credentials fail closed. All seven selected Grok v10 and Claude v9 startup cases pass without host credentials. - The full local suite could not complete because embedded PostgreSQL failed before database-backed fixture setup. The broad executor-suite attempt hit the same limit and was stopped. Neither attempt is counted as passing. Current-head CI must verify those paths before merge. - Earlier CI found missing Rust input fields, stale source attestations and exact fixture pins, a missing Docker context entry, and an outdated import expectation. Those failures were fixed and checked locally. The CI logs retain the original failures. - Different earlier CI runs also failed unchanged cleanup pagination, device-login timeout, and chat lost-response recovery cases. Later attempts passed the cleanup and login cases without changes to those implementations. Their causes remain unproven. The original evidence remains in [the first run](https://github.com/paperclipai/paperclip/actions/runs/40563402840), [the login run](https://github.com/paperclipai/paperclip/actions/runs/40571128328), and [the chat run](https://github.com/paperclipai/paperclip/actions/runs/40573072163). A passing retry does not establish a root-cause fix. - Both reviews rate current head `16fba9b4cdf12bc7945e6628912e79da42959f35` 5/5. All current-head CI gates pass in [run 40576580699](https://github.com/paperclipai/paperclip/actions/runs/40576580699). All 60 check runs completed cleanly, including the four intentional skips and the neutral 5/5 Paperclip review. The legacy security status is successful. No review threads remain unresolved. - Staging migration and a real shell task are pending deployment. This PR does not claim full Grok provider qualification. Reviewers can verify the operator path by upgrading a qualified Grok agent, checking its saved model and effort, and running a shell task through native execution. ## Risks - Explicit effort and search policy require the matching Runner and sidecar build. Older immutable execution inputs keep their existing schemas. - Providers that omit or reject the selected effort fail before a prompt. Unsupported effort does not fall back silently. - Existing agents retain their saved runner until an explicit change. New Grok agents use native execution only on qualified platforms. - Grok token and cost reporting remain unverified, as before. ## Model Used OpenAI Codex, GPT-6 family. The exact serving model ID and context-window capacity are not exposed in this session. Used reasoning, source editing, shell execution, and browser inspection. ## 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 and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and the focused suites pass; the full local suite has the environment limitation recorded above - [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> |
||
|
|
3cd3af5d75 |
Trace native preparation and OpenCode execution phases (#17918)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Each native run prepares its workspace and skills, then starts its provider. > - A long preparation span does not show whether inventory refresh, a cache lock, repository reads, or file checks caused the delay. > - One hosted run spent 81 seconds in this phase. The same deployed service and pinned files took 2.55 seconds in a separate diagnostic process. > - Another hosted turn spent 69 seconds before its first output. A matched public-workspace local model replay took 7.64 seconds. > - We need skill preparation and provider-internal measurements before choosing another fix. > - This pull request adds skill spans, a real-service benchmark, and opt-in filtered provider timing. > - The benefit is a faster and more precise diagnosis loop. ## Linked Issues or Issue Description Refs #17620. That PR owns the batched read optimization. This PR adds diagnostics and does not change its read policy. Refs #17907. That PR protects long cache lock transactions from the database idle timeout. **What happened?** Native skill configuration can take much longer than matched standalone resolution. Provider execution also has long gaps with no internal timings. Existing spans cannot separate inventory refresh, cache acquisition, repository reads, context loading, Git snapshots, or model streaming. **Expected behavior** An operator-configured trace shows these phases under the existing run context. Without an OTLP endpoint, the new spans stay off. A local benchmark can reproduce the service path with real PostgreSQL, files, an agent actor, and a responsible user. **Steps to reproduce** 1. Run `pnpm --filter @paperclipai/server exec tsx scripts/benchmark-native-skill-preparation.ts --actor=agent --staging-shape=true`. 2. Inspect cold and warm phase timings, SQL counts, and file verification results. 3. Set the existing operator OTLP configuration and add `--export-otlp=true` to inspect the same hierarchy in the collector. ## What Changed - Add bounded skill inventory, refresh wait, cache acquisition, row, version, repository, file check, and consumer spans. - Keep the existing endpoint gate, attribute allowlist, cache locks, authorization, file validation, and durable pin boundary. - Add a standalone benchmark with a full repository fixture, immutable snapshot input, calibrated local transport delay, and optional OTLP export. - Verify every delivered file and executable bit outside the timed section. Create its fixture agent through the lifecycle API. - Add an opt-in authenticated loopback sink for OpenCode. Discard raw attributes, logs and content. Retain only closed phase names and timestamps. - Carry one bounded diagnostic batch through the real proxy, Rust normalization, durable journal and server trace projection. Group provider phases under their execution parent. - Freeze the Date clock in an existing delegated Slack rate-limit test. This fixes a CI failure when consecutive requests cross a rate-window boundary. It does not change rate-limit behavior. - Document phase boundaries and the difference between SDK startup and confirmed ingestion. ## Verification - Skill service, runtime selection, concurrency, cache and timing suites: 122 tests passed with real PostgreSQL and migrations. Enabled-span integration tests also passed. They verify parent relationships and a real advisory-lock timeout. - A captured 208-file repository produced 209 verified runtime files. The benchmark uses real agent and responsible-user authorization. The lifecycle fixture correction passed with the staging-shaped inventory. - Affected OpenCode driver, collector and transport tests: 72 passed. The tests cover authentication, content removal, size/count bounds, disabled behavior and the rebuilt native Runner boundary. One Rust projection test and 18 server trace tests also passed. A held run-log sink proves that a full 128-span diagnostic batch adds no duplicate database writes before terminal consumption. - The two CI-failing delegated Slack rate-limit cases passed against real PostgreSQL with only the Date clock frozen. - Runner TypeScript and server TypeScript checks passed. Rust formatting and module-boundary checks passed. - Real Honeycomb readback confirmed the 14-span skill waterfall and a 40-span provider waterfall. Provider phases have the correct execution parent. The provider export uses synthetic model replies and is instrumentation proof only. - Earlier full local checks failed on missing package-local executables, then on the default Node heap and a missing generated service worker. The dependency links were repaired. The server check passed with a larger heap. The full local test attempt could not start embedded PostgreSQL on this host and was stopped after retaining its failures; real database coverage uses an isolated database on an existing local server. These attempts do not count as a full local pass. - CI on the prior revision passed typecheck, build, Runner and all E2E shards. It failed the benchmark lifecycle boundary and one existing rate-window test. Those fixes passed CI. A later Runner assertion exposed the Copilot source identity pin on the shared transport file. The diagnostic flag now uses the existing configured-environment projection, preserving that file byte-for-byte. All 66 selected installation and native transport tests passed. New-head CI and review remain required. - The under-15-second hosted response target remains unmet. This PR adds diagnostics and does not claim a hosted latency fix. ## Risks - Skill spans and Honeycomb export retain the operator endpoint gate. OpenCode phase collection requires a separate explicit diagnostic flag. Without an endpoint, its closed measurements stay in the instance run log. - Raw OpenCode OTLP can contain prompts and authorization attributes. The new sink rejects unauthenticated requests and discards all attributes before any measurement reaches PRP or the operator collector. Request, event and per-phase limits bound memory and journal growth. - Collection does not wait for a provider flush. Late or oversized exports can be absent; these measurements are not a complete profiling guarantee. - The benchmark's inventory contents and transport delay are explicit fixtures. They do not reproduce server contention or prove hosted response time. - The one durable diagnostic batch remains the local evidence. Its child span export does not add per-phase run-log rows. - No database migration, authorization policy, model selection or inference transport changes. The Rust Runner and OpenCode proxy must be shipped together for the new opt-in diagnostic. ## Model Used OpenAI GPT-6 through Codex, with repository inspection, shell execution, browser tools, and Honeycomb queries. The session does not expose a verifiable backend deployment ID or context-window size. ## 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 - [x] 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 - [ ] 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing> Co-authored-by: Paperclip <paperclip@paperclip.ing> |
||
|
DottaandPaperclip
|
41c42895fa |
feat(evals): enforce fixed Runner request allocations (#17452)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Runner evals execute real provider harnesses against maintained fixtures. > - Turn-level usage arrives after requests have already spent money. > - Parallel cells need distinct allowances before requests start. > - Missing output must preserve the remaining allowance and any known charges. > - This pull request adds a controller that reuses the existing request ledger and gateway. > - It makes a bounded local Runner attempt reviewable before hosted scheduling is enabled. ## Linked Issues or Issue Description Refs #17440. That PR added the explicit Runner gateway route. This PR owns request admission and retained campaign accounting for that route. The existing hosted matrix is not enabled or changed here. Its global allocation, rerun rejection, and private evidence archive remain separate integration work. ## What Changed - Validate a trusted manifest with exact request, CLI, package, daemon, model, and source identities. Assign each selected cell a distinct allowance. Count operating overhead once. Reject allocations above the campaign limit before launch. - Run native Codex or ACPX Claude through the shared request proxy and append-only ledger. Pass only the proxy credential to the child. Refuse local attempt reuse and preserve existing output files. - Close gateway admission on cancellation. Retain the ledger, receipts, route descriptor, child result, and cleanup evidence outside the disposable workspace. - Recompute campaign accounting from retained ledgers. Missing or invalid final evidence holds the full cell allowance while preserving known charges. Reports distinguish provisional and incomplete costs. - Accept namespaces containing only local function/custom tools. Disable web search in the controlled Codex profile. Continue to reject hosted tools, including tools hidden inside a namespace. - Add controller tests to the existing Runner static test path and document this source-checkout entry point. ## Verification - 20 controller tests pass. They use real child processes, local HTTP, and the actual ledger. Cases cover reservations before dispatch, concurrent cell isolation, caps, cancellation, replay rejection, lost artifacts, changed receipts, and Braintrust Claude routing. Upstream responses are synthetic. - 52 shared gateway tests and 55 Runner CLI tests pass. The namespace acceptance and web-search configuration regressions failed before the repair and pass afterward. - Runner TypeScript/Rust checks, Runner build, shared E2E typecheck, and `git diff --check` pass. - The first actual-harness probe found that Codex advertised both a local tool namespace and web search. It reached no upstream transport. That failure is retained; the compatibility repair does not allow paid hosted tools. - An earlier test failure showed that separate dynamic imports created different admission-error classes. The shared runtime bridge now loads one module graph. Another regression showed that a missing final report hid known ledger charges; the collector now preserves those charges. - The repaired actual-harness probe passed its control checks for native Codex and ACPX Claude: each reached exactly one synthetic upstream request after the ledger reservation; both retained the unresolved hold and route evidence; both recorded clean process exit. A scan of 41 retained files found no synthetic upstream credential. Deliberate provider rejection preserved the failed Codex turn and Claude timeout; these are not semantic passes. Prices, operating bounds, and the package archive identity in this probe were synthetic. - Review regressions reproduced lost request/receipt evidence, lost admission metadata, executable replacement after verification, and a SIGTERM-resistant descendant surviving the CLI. The repairs now pass. Executable bytes are staged before launch; a trusted Node resolution hook preserves relative imports. A symlink-path regression also failed before its repair and now passes. The final staged native probe repeated both one-request checks successfully. - Full current-head [CI](https://github.com/paperclipai/paperclip/actions/runs/40115932485) passed on `4781487215116afd10a415d4db53b1ec8e004dd5`: all 58 check runs and the legacy status are successful, neutral, or skipped. Greptile and Paperclip both reviewed this commit at 5/5. All five finding threads are fixed and resolved. No paid provider request ran during this change. ## Risks - This is a trusted source-checkout controller, not a published package command. It needs the repository's installed shared cost dependencies. - The manifest declares reviewed prices and full-lifecycle bounds. Synthetic tests do not qualify real prices, invoices, storage, or Braintrust metering. - The attempt-directory guard is local. Hosted fanout still needs unique global allocations, rerun rejection, and durable private retention. Do not enable the existing matrix on this change alone. - Forced child termination can leave cleanup unverified. That attempt remains incomplete and holds its full allocation. These checks do not claim a host security boundary against an adversarial target. - The current private publisher does not archive the separate controller directory. Native trace relay, private report integration, and live qualification remain open. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, tool use, and code execution. This runtime does not expose the exact model ID or context-window size. ## 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 - [x] 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> |
||
|
DottaandPaperclip
|
aec86c794b |
fix(runner): preserve native work through controller outages (#17594)
Keep remote native work under its authenticated connection lease through controller outages. Hold durable ACPX tools through reconnection, align the native Claude HTTP MCP client budget, and wait for the recovered handler before dispatch. Preserve Stop, cancellation, exact identity and artifact checks. Verified with real-process regressions and a real Claude Opus 5.5 Daytona workflow: 125 seconds offline during useful work, original process and lease retained, no failed native tool calls, queued follow-up completed, independently verified ZIP and committed workspace receipts. All current-head CI gates pass and Greptile is 5/5 with all findings resolved. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
044628f59e |
Add explicit native tracing to the Runner eval CLI (#17483)
## Thinking Path > - Paperclip manages AI agents and their work. > - Runner Evals exercise real providers against a mock control plane. > - The controlled gateway route creates a disposable provider home. > - That route had no explicit native trace configuration. > - Codex skips normal home preparation for a preconfigured home. > - This change validates and applies the existing observability launch contract before provider creation. > - Operators can collect native evidence without passing vendor keys to the child. ## Linked Issues or Issue Description Refs #17440. Related: #17452 and #17469. This PR is based directly on master and does not include those pending controller changes. **Current behavior** The eval-session CLI cannot pass an explicit native observability launch. Passing environment alone cannot configure Codex in the disposable gateway home. **Proposed behavior** Accept an opt-in descriptor bound to the gateway attempt. Validate the existing provider launch contract, add a scoped relay token in memory, and apply it only to the owned provider home and environment. **Reason and benefit** A controller can route native evidence through its bounded local relay while the CLI keeps configuration distinct from verified ingestion. This is the CLI contract; hosted controller integration remains separate work. ## What Changed - Add a strict, bounded descriptor reader for native Codex and ACPX Claude. Bind campaign, execution, attempt, project, trace, span, and mock authority identifiers. - Reuse Runner observability materialization and redaction. Preserve the model gateway route. Reject upstream destinations, extra environment fields, credentials in headers, and unknown exporter settings. - Add `--observability-config`, requiring an explicit gateway. Keep direct and unconfigured paths unchanged. - Retain secret-free configured/unverified metadata in success and failure artifacts. - Document the contract and controller responsibilities. No workflow, runtime dependency, paid schedule, or public report changes. ## Verification - Eval CLI regression selection: 81 passed before the test-only relocation. The 17 new cross-package observability tests now pass from `tests/runner-e2e/runner-eval-observability.test.ts`; their integration-suite typecheck also passes. They use the actual shared launch generator, real disposable homes, CLI success/failure paths, and credential redaction. The first run exposed two test setup references introduced by a broad edit; both were corrected and its failure log remains retained. - Runner TypeScript build and release daemon build passed. Full `pnpm -r typecheck` passed. - Actual native Codex and ACPX Claude reached a local receiver with authenticated OTLP protobuf and the expected Braintrust parent. Codex sent four log and two trace batches; Claude sent three log and one trace batch. All recorded processes exited, disposable homes were removed, and 29 retained files contained neither synthetic credential. - The local model endpoint deliberately returned 401. Codex retained a failed terminal turn; Claude retained a provider timeout. These are route/export proofs, not semantic eval passes. Native retries reached only the fake endpoint. No paid provider or Braintrust request was made. - The first local probe failed before provider launch because its TypeScript loader path was wrong. It was corrected to the installed loader; both attempts remain retained. - Full repository build passed at initial head |
||
|
DottaandPaperclip
|
d1fdfced9d |
feat(evals): route Runner sessions through a controller gateway (#17440)
## Thinking Path > - Paperclip manages AI agents and their work. > - Runner Evals test provider behavior against a mock control plane. > - A campaign budget needs to observe and admit each provider request. > - The existing eval CLI does not select the provider-home mode needed for a controller-assigned route. > - A proxy URL alone therefore cannot establish controlled Codex routing. > - This change adds an explicit route with an isolated home and retained identity. > - The controller can use that route as the basis for request accounting and admission. ## Linked Issues or Issue Description **What happened?** The direct Runner eval CLI passes the ambient environment to the native transport. The transport deliberately removes an environment-only preconfigured-home marker unless its explicit option is also set. This prevents a controller from assigning a Codex gateway through that marker alone. **Expected behavior** A controller can explicitly route a supported eval attempt through its local proxy. The provider receives the proxy token and isolated configuration. The artifact identifies the assigned route on success and failure. Ordinary direct runs keep their current path. **Steps to reproduce** Run the new CLI tests for `--gateway-config`. They validate the descriptor, inspect the actual transport inputs and provider sanitizers, and check retained artifacts and owned-home cleanup. The local probe also ran built native Codex and ACPX Claude against a fake loopback API using only synthetic credentials. Related request-accounting work: https://github.com/paperclipai/paperclip/pull/17432. ## What Changed - Add an explicit gateway descriptor bound to the requested provider, exact model, campaign, execution, and attempt. - Accept only the controller's IPv4 loopback URL and a separate proxy token. - Create a fresh provider home for native Codex and ACPX Claude. Exclude ambient provider credentials, subscription logins, proxies, and startup hooks. - Retain route identity and descriptor hash in successful and failed artifacts. Remove the owned home in finalization. - Document the CLI contract and its limits. The Runner eval CLI owns this behavior. It uses the existing native preconfigured-home contract. Production routing, permissions, and provider protocols are unchanged. ## Verification - Initial verification passed 56 focused gateway/CLI tests and 246 CLI and adjacent provider-isolation tests. After the admission repair, all 247 CLI and adjacent provider-isolation tests passed, with TypeScript checks and build passing again. - Runner TypeScript checks and build passed. - The native daemon rebuilt from the candidate base with locked, offline dependencies. - Local fake-API probe: six authenticated Responses requests from native Codex and six authenticated Messages requests from ACPX Claude reached the assigned endpoint. Claude also made an unauthenticated hello check. The final commit retained both route artifacts. All 27 retained files were scanned for the synthetic proxy token and contained none. Both temporary homes were removed, and all four recorded provider/daemon PIDs were absent after exit. - The fake API intentionally rejected inference. Codex retained a failed turn; Claude retained a timeout. These are route observations, not passing semantic evals or live provider qualification. No paid provider calls ran. - The first focused command used the wrong directory and discovered no tests. It was corrected before the successful runs above. - Full Runner validation: 3,967 tests passed, 13 skipped, and five failed in three unchanged installation and native-settlement files. The failures were two installation timeouts and three retained-cleanup settlement failures. One isolated run passed all 109 applicable tests with six skips. This shows recovery, not a proven cause for the original five failures; those remain retained. Hosted [CI 40111220754](https://github.com/paperclipai/paperclip/actions/runs/40111220754) passed on final commit `a5c47b64e56c1228fca718b72a81ddc3b1d185a4`, including repository typecheck, build, tests and Runner checks. All 57 checks passed or were neutral/skipped, and the legacy status passed. Greptile and Paperclip reviews both scored 5/5 on that commit; no findings remain unresolved. - Rebased onto current master `71c04c0bfb205cc9e7f7bc20c29fd76051b44cc4`. Its added change concerns server cleanup; Runner source is unchanged. - An actual ACPX Codex probe failed before reaching the fake API. Review and source inspection confirmed that Runner deliberately rejects its preconfigured home to protect Runner state. This route is now rejected before service creation. Both explicit and default ACPX Codex admission regressions failed before the repair. The unsupported lane is not presented as qualified. ## Risks This is an explicit new CLI route. Unsupported providers fail before service creation. Upstream route is a controller declaration, not independent billing evidence. The local probe saw six Codex requests where legacy usage counted one, so the controller's request ledger must remain the budget source. Campaign allocation, proxy lifecycle, hosted workflow wiring, dedicated OTLP relay routing, and paid qualification are separate remaining integration steps. This PR enables none of those schedules. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, tool use, and code execution. The exact serving model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used, including the information available in this session - [x] I checked ROADMAP.md; this is eval infrastructure, not a competing core feature - [x] I searched for duplicate PRs for this exact route change - [x] I described the issue in-PR using the bug template labels - [x] I have not referenced internal or instance-local issues - [x] My branch describes the change and contains no internal issue ID - [x] Relevant focused tests pass - [x] I added tests for the new contract and lifecycle - [x] I updated the relevant documentation - [x] I described the risks and unqualified behavior - [x] All current-head Paperclip CI gates are green - [x] Current-head Greptile is 5/5 with no unresolved findings - [x] I will address review findings before merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
a3e1d915a7 |
fix(evals): preserve unknown Codex provider cost (#17158)
## Thinking Path > - Paperclip manages AI agents and their work. > - Direct Runner evals report usage and costs for each attempt. > - Codex App Server supplies token counts without a provider USD receipt. > - The legacy Runner ledger fills an absent cost with zero. > - The eval result exposed that ledger value as provider-reported cost. > - This fix keeps provider cost unknown and preserves the estimate and budget stop. ## Linked Issues or Issue Description Refs #17009 and #17154. This is a separate direct Runner accounting fix based on master. ## What Changed - Codex direct eval usage now reports null provider USD cost with unavailable provenance. Token counts and the pinned price estimate remain available. - Preserve the original ledger amount as optional `legacyLedgerCostNanodollars`. Keep the original snapshot receipts unchanged. - Apply the existing budget ceiling to the retained ledger amount as well as the token estimate. Correcting a label does not relax admission or settlement checks. - Use the unique operator UUID for Muse test company prefixes, eliminating collisions from the previous 24-bit random suffix. - Document the cost distinction in the Runner/Evals integration contract. Other provider behavior and historical artifacts remain unchanged. ## Verification - Reproduced both zero and nonzero legacy amounts being labelled as provider USD cost before the fix. - The current eval-session contract and entrypoint tests pass (39 tests). The new regression uses the bounded usage consumer and actual campaign cost projection. It checks unknown provider cost, the separate estimate, unchanged raw evidence and the legacy ledger budget stop. - All 15 Runner report, campaign and metrics Node tests pass. Four adjacent CLI entrypoint/runtime tests also pass. - Runner TypeScript validation passes with its standard dependency-build prerequisite; `git diff --check` passes. Both Runner TypeScript configurations also passed during the original accounting verification. - Hosted CI run [39960367674](https://github.com/paperclipai/paperclip/actions/runs/39960367674) passes on `7d84f138044bac58cdced6baa2d0ec3d63767bb8`, including typecheck, build, server tests and browser checks. Greptile and Paperclip Review both report 5/5 on that commit with no actionable findings. - The previous CI failure was a PostgreSQL unique-index collision on `companies_issue_prefix_idx` during Muse fixture setup. Local Muse verification could not reach test execution because embedded PostgreSQL timed out during macOS startup (initially reporting a missing zstd library). The corrected fixture passed in hosted Linux CI. - Verification used no model calls. Full repository checks were performed by hosted CI; local verification was scoped to the changed contracts and fixture. ## Risks Consumers that assumed Codex always had a numeric provider cost must handle null. The contract already permits null for other profiles, and the report consumer retains missing-cost coverage. The legacy amount remains available as unverified evidence and still triggers the existing budget stop. Neither the estimate nor that ledger amount proves an invoice charge. This change does not rewrite old artifacts or qualify other provider routes. ## Model Used OpenAI GPT-6 through Codex, with repository tools and code execution. The exact deployment variant and context-window size are not exposed by this session. ## 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 - [x] 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> |
||
|
Nicky LeachandPaperclip
|
0081863463 |
Fix isolated ACPX admission for assigned PRP tools (#17149)
## Thinking Path - Paperclip uses Runner to execute agent tasks under Core's selected policy. - The ACPX sidecar can receive assigned MCP tools in its PRP catalog. - Isolated admission still requires a separate native MCP endpoint for those assignments. - This check rejects a valid PRP route before the provider can start. - This PR identifies the sidecar's PRP transport at the runtime-host boundary. - The benefit is that assigned tools work with the existing isolated permission policy. ## Linked Issues or Issue Description **What happened?** An isolated Claude task with an assigned MCP binding fails with `assigned native MCP launch binding is unavailable` when Core delivers its tools through PRP. **Expected behavior** The sidecar must accept its authenticated PRP tool bridge as the assigned-tool route. Callers that use the native gateway must still supply its complete binding. **Steps to reproduce** 1. Open an isolated Claude sidecar session with `deny-all` permissions and a read-only policy. 2. Supply an assigned MCP binding in the runtime context and its tools in the PRP catalog. 3. Omit native gateway environment variables. Admission fails before provider startup. **Paperclip version or commit** Reproduced against `92cfd701c39bb1ea394a796023481a21decb2532`. **Deployment mode** Runner with an ACPX sidecar and controller-owned tool delivery. Related contract work: #16978. The search found no existing PR or issue for this failure. ## What Changed - Let runtime-host callers select PRP delivery when they supply the semantic tool bridge. - Select that route in the sidecar. Keep native gateway validation and direct callers' default behavior. - Preserve exact controller operation names in PRP mode, including the compact assigned-MCP catalog. Keep existing aliases for other bridge callers. - Preserve the selected permission and read-only policies. - Add one process-level sidecar regression and one host admission regression. The host test calls the real authenticated MCP bridge. - Document the route and refresh the generated Copilot source hashes. The provider and profile versions stay the same. ## Verification - Passed 11 focused tests after the rebase across the runtime host, sidecar, tool bridge, and Copilot identity tests. They cover both compact catalog operations, restricted and approve-all policies, legacy aliases, missing and invalid gateway bindings, and the existing direct gateway path. - The process-level test crosses the real sidecar dispatcher and stops at workspace validation before provider startup. The host test uses real ownership sockets and MCP HTTP, with a fake provider port. - The generated identity tests match the current source hashes. The historical fixture stays unchanged. - The standard review passed on the rebased commit. [Apex passed the required 5/5 threshold](https://github.com/paperclipai/paperclip/runs/119513362214) on `e63a223`, with 11 files reviewed and no findings. - Rebased onto master `734c265`. The conflicts affected generated source identities and their test expectations. All reviewed behavior files remain byte-for-byte unchanged. The user authorized retaining the Apex result for this rebase. [CI passed on `3facef5`](https://github.com/paperclipai/paperclip/actions/runs/39685163239). The final PR checks contain 56 passes and four expected skips. The branch is current with master, has no conflicts, and has no unresolved review comments. - `node packages/paperclip-runner/scripts/copilot-profile-identity.mjs --check` passed. - Initial local runs exposed missing test dependencies and sandbox denial of loopback sockets. After the scoped dependency install and socket permission, the selected tests passed. - Broad typecheck, build, and test verification runs in GitHub CI, as requested. No live provider or model request was made. ## Risks - PRP callers must supply the assigned tools in the controller-owned catalog. The existing bridge still enforces its closed catalog and authentication. - An explicit PRP selection without a semantic bridge still fails. Invalid native gateway bindings still fail. - No database, protocol-frame, provider-version, or credential-storage change is required. ## Model Used OpenAI GPT-6 through Codex, with source inspection, editing, and command execution. The exact served model ID and context-window size are not exposed in this session. ## 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 - [x] 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> |
||
|
|
eece07a747 |
fix: repair the complete projectless repository setup chain (#17088)
## Thinking Path > - Paperclip lets people manage agents that do useful work. > - A projectless task can prepare an authorized repository in its retained workspace. > - Setup must hand work to a later run without user supervision. > - Real task attempts exposed gaps across admission, completion, and queue dispatch. > - A successful provider exit did not prove that the requested result was delivered. > - This PR repairs the existing lifecycle and checks the complete repository journey. ## Linked Issues or Issue Description Refs #17047. This PR includes the preserved repairs from #17049, #17052, and #17082. **What happened?** A projectless native task could stop after requesting a repository. It could also continue through a timer or generic recovery path and lose its saved conversation lineage. The latest real Codex and Claude attempts delivered correct files, but the native continuation had been folded into the finishing predecessor. Both attempts remain failed measurements. **Expected behavior** Prepare the authorized repository, retain the original context, and dispatch one saved continuation after its predecessor finishes. Deliver the verified result in the originating conversation. Stop, current access, approval, and real blocker rules remain authoritative. **Steps to reproduce** Run the explicit automatic-repository suite for native Codex or Claude. Inspect the downloaded result, original context artifact, both committed run records, and continuation receipts. The suite uses one attempt and does not widen the default paid selection. ## What Changed - Resolve the retained local-board identity through current company membership and workspace authority. - Prepare required source dependencies before the isolated server imports native tool authority. - Explain the saved repository continuation in production completion tools. Correct only the exact pending-checkout blocker backed by a live receipt. Reject an unfinished response wait without a real response source. - Preserve the persisted task-session workspace source and its explicit absence of root repository context. Permit Git's exact no-repository result only for a validated plain task directory. Keep other Git errors and linked metadata strict. - Revalidate server-resolved same-agent continuation values against current ownership and the saved kind, summary, and key. Carry this shape through the internal bridge schema. Keep provider-facing schemas restrictive. - Preserve terminal result authority after a correlated successful controller response. Controller rejection creates no result authority. Bind the shared guidance and transport source in Copilot v55 and preserve historical identities. - Admit native status wakes with the existing no-coalescing contract. The existing deferred queue retains a distinct future dispatch instead of retagging the finishing run. - Recover deferred conversation lineage through the actual admitted dispatch. Accept a null outbox run binding only with matching decision, effect, dispatch actor, idempotency, task, company, agent, and requester evidence. Reject a conflicting nonnull binding. - Independently grade retained random context, actual checkout bytes and HEAD, accessible output, distinct continuation receipts, and admission order. ## Verification - Real database and Git regressions fail before their repairs. Prior focused cohorts cover local-board authority, optional repository waits, plain task directories, and first/reused workspace provenance. - The new valid decision/effect-backed assembled-heartbeat regression reproduces coalescing into its active predecessor before the queue repair. With the repair, it dispatches one successor after the predecessor finishes. Duplicate sweeps create no extra run. - The deferred-outbox conversation regression fails before its repair. The repaired test also rejects a conflicting predecessor binding. - The current queue, continuation, publication, cancellation, stale-admission, and domain cohort passes 344 checks across 11 suites. Server and Product E2E typechecks pass. The strengthened automatic-repository oracle passes 34 calibration checks. - Three omitted/null/resolved forms pass through the compiled Rust runner and controlled provider. The prior shared bridge cohort passes 492 TypeScript checks and 399 Rust core checks. Runner source identity, TypeScript, Rust formatting, and locked Rust typechecks pass. - Six real local development cells passed ordinary repository, conversion, and necessary-question journeys. Independent artifacts and rendered question/result evidence agree. They do not qualify staging or Slack. - Both latest automatic-repository attempts delivered correct files but failed the strict continuation check. They remain failures. A fresh replay of this queue repair is pending. - On the combined candidate `380047f4b923807a8c4f7ef6016e4fe130ab4a3a`, `pnpm -r typecheck` and `pnpm build` pass. Product E2E support passes 3,525 checks with two existing skips, plus 128 source checks. The complete local `pnpm test:run` is running and is not yet a pass. - The first replay selection failed catalog validation due to an operator profile-ID error. A second selection used the wrong default-model suite and was cancelled before any provider job existed. Both setup attempts remain recorded. The corrected campaign selects the recorded GPT-6.1 and Opus 5.5 models plus the local Stop/resume journey. - Exact-head CI, review, and deployment acceptance remain pending. GitHub reports delayed PR updates and webhook delivery; the current head and checks have now propagated. No earlier-head green badge establishes acceptance of this commit. ## Risks This changes several boundaries of repository setup. Full product and deployment acceptance remain required. The queue uses the existing deferred admission and delivery contracts. Batch deduplication remains in place. The provenance repair requires the actual bound dispatch and does not grant publication authority. Current authorization is still checked at publication. No accepted provider result is rewritten, and completed provider work is not rerun to repair persistence or delivery. ## Model Used OpenAI Codex, GPT-6 family, with repository tools and code execution. The runtime does not expose its exact deployment ID or context-window size. Those values are not inferred. ## 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 - [x] 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 - [ ] 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing> Co-authored-by: Paperclip <paperclip@paperclip.ing> |
||
|
DottaandPaperclip
|
d855e550ad |
Finish Copilot native runtime on current master (#15701)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Paperclip Runner controls provider processes, permissions and task completion. > - Copilot needs its pinned distribution, native message identities and accepted semantic completion receipts. > - The release must preserve saved-token access and task lifecycle guarantees. > - This pull request will keep the current completion and recovery fixes while adding the Copilot runtime. > - The benefit is a reviewable part of the Copilot production release. ## Linked Issues or Issue Description Refs #14434. Supersedes the runtime work in #15560. This is the first PR in the stack; #15703, #15705 and #15706 follow. Related alternative adapter work: #15881. This change uses the shared Runner path. ## What Changed - Pin Copilot CLI 1.0.88 and bind the integrated implementation as profile45. - Keep native instruction, permission, receipt, process ownership and cancellation boundaries. - Preserve current master completion continuation and remote verification behavior. Other provider release identities stay unchanged. ## Verification Final reviewed source [`4f3f1af807d2ed21adabb04c2f27f4df9c4bc8d5`](https://github.com/paperclipai/paperclip/commit/4f3f1af807d2ed21adabb04c2f27f4df9c4bc8d5) includes master `cde944ed75648adfb569e86133adc8b118b55dd6`. The combined four-part PR tree matches it except for the CI-owned lockfile. Every prior public PR head remains an ancestor. Released master migrations remain unchanged; Copilot adds migration361. No unrelated provider is enabled. Copilot CLI1.0.88 and profile47 retain digest `sha256:55044aa235e88b3fe36ec8a556ee1e3382590870aab907e4462ef7d64af49cea`. The pending qualification marker is removed. The [qualification record](https://github.com/paperclipai/paperclip/blob/4f3f1af807d2ed21adabb04c2f27f4df9c4bc8d5/doc/plans/2026-10-20-copilot-qualification-v47.json) reports **20/20 Product cells,154 assertions;7/7 protocol cases,46 assertions** against frozen installed application `c2616370800f5f6df45246b0890ba35a7cd2faab`. Both environments use the exact authenticated model `gpt-5.6-luna`. Every passing Product case confirms cleanup. Automatic behavior retries are disabled. Original failed attempts remain recorded. The ordinary installed remote journey passed saved-token selection, authenticated model discovery, normal UI save/reopen, metadata-only Test, task completion, accepted receipt and an exact19-byte browser download. An open model catalog caused no new discovery requests during117seconds. Actual installed runtime smokes passed on macOS ARM64, macOS x64 under Rosetta and native Linux x64 on Daytona. Raw token browser entry was not exercised; the encrypted connection was created through the normal API. The original Daytona file attempt timed out during delayed semantic dispatch. Its precise stalled layer remains unresolved. Independent ordinary delivery and the other19 cells passed before one instrumented recheck passed8/8 with unchanged source,prompt,assertions and deadlines. No causal latency repair is claimed. After current-master reconciliation,129 connection tests,59 runner tests,72 shared eval tests and88 recovery/workspace tests pass. Migration generation/safety, unchanged profile identity and UI token gates pass. Prior required CI was green. Fresh exact-head required CI and E2E are green for all four updated heads. Each has a fresh Greptile5/5 review and zero unresolved review threads. The [final normal-package cloud build](https://github.com/paperclipai/paperclip/actions/runs/39414239704) is running. Recursive typecheck,full CI test shards,build and all8 browser shards pass. These checks cover the final source; no additional local full-suite pass is claimed. The [frozen image build](https://github.com/paperclipai/paperclip/actions/runs/39334401638) and [original normal package build](https://github.com/paperclipai/paperclip/actions/runs/39334407471) passed. The exact image is published and independently retrieved anonymously. No separate full-image scan is claimed. All18 original normal archives were scanned with zero selected credentials. Docker builds run in the cloud. Provider USD remains unknown and GitHub-attributed. **Qualification is complete on the recorded frozen build. Normal protected merge, automatic master canary publication and final shipped-package local/Daytona canaries remain. No production deployment is claimed.** ## Risks Shared Runner behavior can affect active tasks. Exact profile admission rejects stale runtime identities. The final campaign and installed canaries remain release gates. ## Model Used OpenAI Codex, based on GPT-6. The exact serving model ID and context window are not exposed in this task. Used for code changes, review and tool-assisted verification. ## 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> |
||
|
DottaandPaperclip
|
ac9459bae3 |
feat: configure company agent observability (#16874)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Companies use several agent harnesses and execution environments. > - Operators need one place to select where native agent logs and traces go. > - An inference proxy would add a dependency to the agent request path. > - This pull request supplies native OpenTelemetry settings to managed Codex and Claude Code processes. > - Company secrets protect destination credentials. Export failure does not change the task result. ## Linked Issues or Issue Description **Subsystem affected** Company settings, shared contracts, database, server, adapters, and runner. **Problem or motivation** An operator cannot configure a company destination for native agent logs and traces. Manual harness configuration is hard to apply across local and remote execution. **Proposed solution** Add one company destination: Braintrust or a custom OTLP HTTP/protobuf endpoint. Apply a transient snapshot when execution preparation starts. Keep credentials out of API reads, task environment manifests, recovery files, and command arguments. Replace a warm process when its export settings change and preserve its conversation. **Alternatives considered** Multiple destinations can use a user-operated collector for fan-out. This change does not add a collector, an inference proxy, or transcript scraping. **Roadmap alignment** This extends company settings, secret management, and support for multiple harnesses. The maintainer requested this implementation. Searches for observability and Braintrust found no duplicate company destination feature. Related infrastructure tracing work in #16236 has a separate content-free contract. ## What Changed - Add strict schemas, revision checks, encrypted secret storage, activity records, and board-only settings routes. - Add explicit synthetic logs and traces tests with a bounded HTTP request and sanitized results. - Supply native Codex configuration and Claude Code environment values through local and remote launch paths. - Preserve Codex login refresh through the existing managed credential link. Retain unsaved drafts across background reads. Require complete custom header re-entry when the endpoint origin changes. - Separate process export compatibility from conversation identity. Isolate generated Codex configuration and preserve resumable sessions, including remote home refresh after export changes. - Advance the immutable Pi/Copilot source attestations for shared environment and sidecar code changes. Keep their provider payloads unchanged and retain prior identities for decoding. - Redact destination credentials throughout launch diagnostics and HTTP logs. - Add the production settings form, Storybook states and journey, documentation, and feature/access map entries. ## Verification - Real managed local Codex 0.160.0 and Claude Code 2.1.286 tasks exported to Braintrust. API readback and the Braintrust UI showed the test records. A real remote Daytona Codex task exported through the legacy `exec` path. - Live tests exercised content capture off, export disabled, warm conversation reuse, and a destination that accepted connections but never replied. Agent work succeeded and export requests stopped at the configured three-second timeout. The UI connection test returned “Test payload accepted”; the saved API key stayed masked after reload. - All current-head CI test lanes, typechecks, packaging/build checks, and required aggregates passed on `71e994b2be9c8fb6d6e938a4ad7cf4c95fdafe31` ([CI run](https://github.com/paperclipai/paperclip/actions/runs/39319194318)). Greptile completed on that exact commit at 5/5, with zero unresolved review threads. The additional optional Paperclip Review check remains queued waiting for its assigned agent. - Local workspace typecheck and build passed. Focused verification included 239 combined runner tests, 789 API/native-session tests, 107 Codex home/ACP/sandbox-site tests, 204 feature/privacy tests, and the affected Rust suites. Migration, token, map, Storybook catalog, and Storybook build checks passed during acceptance. These checks ran at the relevant implementation or merge boundary; the current-head CI is the complete final gate. - Managed AI credential projections now receive enabled and disabled company export settings; genuine caller-owned Codex homes remain untouched. Two regressions reproduced the skip before the repair. All 276 engine/lifecycle tests and adapter-utils typecheck pass afterward. The launched TOML retains provider/MCP settings, credential continuity, and redaction. - Settings saves, removal, and the real company-deletion owner acquire secret mutation ownership before database locks. PostgreSQL NOWAIT probes cover all three paths; concurrent save/rotation/removal/deletion requests settle correctly. The affected suites passed 137 tests, followed by all 32 service/connection cases after expanded deletion coverage. Server and Codex adapter typechecks pass. - Codex source profiles use the effective CLI argument list. A spawned fixture CLI reproduced both ignored-argument failures; all three precedence/fallback cases now pass. - Real tar staging reproduced remote conversation loss in both API-key and subscription modes before the repair. Both now pass: changing managed settings preserves sessions, archives, native indexes, and refreshed subscription credentials. A corrupt upload preserves the prior config and conversation. - Preserved failure evidence: initial CI caught stale Pi/Copilot source attestations, a missing test-harness helper, and packaging fixture/probe mismatches; those were corrected and covered by focused checks. Superseded heads had intermittent attachment-composer timeouts despite successful uploads; [the original trace and screenshot remain available](https://github.com/paperclipai/paperclip/actions/runs/39309701089/artifacts/12215109203). The same attachment case passed on the final head: [25/25 tests in shard 3](https://github.com/paperclipai/paperclip/actions/runs/39319194318/job/118288637051). - A connection-fault fixture also exposed a stale pooled socket after its hang case; closing fixture responses isolated scenarios and the full affected suite passed. - The broad local test run was not clean: database resource failures, timeouts, an older cached module graph, and a stale optional-resource manifest assumption were recorded. Focused checks passed after the documented fixes. This does not establish a clean full local pass. - Native remote Codex, remote Claude, and the full ACPX Codex bridge remain unqualified. The direct Codex resume test does not establish full bridge acceptance. ## Risks - Native exporters perform network requests from each execution environment. A server connection test does not prove remote reachability. - Prompts, assistant responses, and tool content are enabled by default when supported. Native caps and harness-specific controls still apply. - Caller-owned Codex homes are unsupported for automatic configuration and remain untouched. - Native harnesses and their tool processes can inspect export credentials. The settings form and documentation advise using ingestion-scoped credentials. Retained headers remain bound to their saved scheme, host, and port; changing origin requires fresh values or removal. - Migration 0357 adds a company-scoped row and secret reference. It is safe to reapply. Secret removal and company deletion use the existing secret lifecycle. - Slow or unavailable destinations must not block task settlement. Export settings take effect at the next execution preparation boundary. ## Model Used OpenAI Codex, GPT-6, with reasoning, tool use, code execution, and browser verification. The exact serving model ID and context window size are not exposed in this session. ## 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 - [x] 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> |
||
|
|
d747752496 |
fix(runner): record why an OpenCode turn fails when opencode serve stops (#16863)
When `opencode serve` stops during a turn, the OpenCode driver now fails the active turn itself with a closed-vocabulary cause (server exit code or known signal, allowlisted socket error code, HTTP status, or closed stream) instead of leaving runnerd to close it with `error: null`. The proxy flushes stdout before a fatal exit so the failed turn reaches runnerd, and the server records OpenCode failed turns as `nativeTurnFailure` (live and persisted-recovery paths) so the run-failure diagnostic names the cause. Provider text is never copied. Run status, retries and recovery behaviour do not change. Co-Authored-By: Paperclip Sentry triage <Paperclip-Paperclip@users.noreply.github.com> Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
DottaandPaperclip
|
95672307f4 |
feat(runner): carry acknowledged Claude effort through native resume (#15994)
## Thinking Path > - Paperclip manages AI agents and their work. > - The native runner must carry each supported agent setting. > - Claude effort must reach its ACP session before a prompt and after resume. > - Installed Claude setup must find the owning server package without a qualification override. > - This PR adds those shared contracts and preserves historical readers. > - The Claude default change can then use the same runner path. ## Linked Issues or Issue Description Refs #15683. This prerequisite follows the actual Codex squash `adb69e8f09852c772d9901ae270e5b2d66e39c77`. Consumers: #15993 and #15997. Related scope: #15422, #13978 and #15224. ## What Changed - Add native-input v9 for Claude effort. Preserve v1–v8 readers, including v7 explicit home modes, v8 Muse, Dot and Grok Bot. - Preserve prepared task input and constraints through the newer contracts, including completion-only continuation without wrapping compact model input again. - Carry effort through daemon/sidecar admission; require provider acknowledgment before prompting and after resume. - Find installed server package authority through the verified canonical layout. Retain package-integrity, digest, architecture and no-follow checks. - Return Claude startup cancellation promptly while retaining unfinished settings writes and the lifetime lease through cleanup. Preserve merged Codex close/cleanup behavior. - Retain both independently authored historical Pi profile-24 declarations. Combined master/Claude source attestations use Pi profile 27; pending Copilot remains profile 22. This does not expand either provider's qualification boundary. - Avoid a spare verified executable snapshot when Claude effort control reuses its initialized provider. Preserve cold-control snapshot renewal and acknowledged effort. ## Verification - Reconciled with master `9179d8dcc3e908c217fde4f63c9d08ccf8132eeb`, retaining its task-loading, progress, skill-retention, permission and OpenRouter changes. - Final focused protocol/provider checks passed 155 tests (one skipped), the updated Pi attestation check passed 18 (one skipped), and 91 evaluation/catalog checks passed. Generated TypeScript/Rust profile checks and Rust formatting pass. The integrated consumer's TypeScript-only runtime build also passes. - Earlier branch checks passed 369 protocol tests (one skipped), 72 catalog checks and TypeScript checks/build; their source identities remain historical. No Rust compilation or Docker build is needed locally for this proof. - Current-head cloud CI is green. All three stack PRs have fresh Greptile 5/5 reviews and zero unresolved review threads. Required typecheck, test and build gates ran in cloud CI; Docker work stayed remote. Earlier failed checks remain in their original runs. - [Earlier four-target package qualification](https://github.com/paperclipai/paperclip/actions/runs/39267321383) passed on source `04e0202ca81387b17cbe7fd094a8338648356fe9`; it is not relabeled as proof for the final merge. Existing failures and unknown-cost holds remain preserved. - Current-head cloud CI is green. All three stack PRs have fresh Greptile 5/5 reviews and zero unresolved review threads. Required typecheck, test and build gates ran in cloud CI; Docker work stayed remote. Earlier failed checks remain in their original runs. - Latest-application manual continuation passed in 37.942 seconds on `695e5c005a85bddc8711d3fcddcaf6b7e1fb64d0`, with High effort, native Opus 5.5, Anthropic API attribution, the same resumed Claude session, an independently checked 635-byte file and persisted Done status. It uses the earlier verified Mac daemon; the preceding-source package qualification passed at `dca62c7aeb4b45f0dd91a8e18d386a16a2658ef8`. That package run predates the small TypeScript startup fix and is not relabeled as qualification for it. - Upgrade limitation: changed compiled sidecar identity rejected old durable launch state and recovery hit session-open bounds before eventually resuming. That attempt was operator-cancelled and retained; the successful manual continuation does not qualify seamless upgrades. - Local latency profile, Opus 5.5/High unchanged: three alternating real-ACP loopback samples per variant reduce median provider-ready time from 5.081s to 4.034s. The matched real API task startup improves from 5.533s to 4.348s, but total reply time changes from 17.933s to 20.221s because agent work varies. This establishes a startup saving of about one second, not a consistent total-reply speedup. A real candidate follow-up passed in 20.146s and resumed the same saved session. The loopback fixture makes no external model requests; failed initial probes remain retained. - The startup change passes 107 focused runtime/effort/lease tests, 53 profile checks (one skipped), TypeScript checking and the TypeScript-only runtime build. Native hire fixture checks pass 70 tests; their first local run retained a socket-hangup failure and stale OpenCode expectation, both accounted for before the passing rerun. Broader required checks run in cloud CI. ## Risks - Explicit Claude effort needs a daemon and sidecar that support input v9. Historical readers stay available; downstream builders and permission-pin transport checks must also use v9. - Source-bound profile changes may require reopening older Pi/Copilot sessions. Copilot remains pending and executable package closures remain unchanged. - This prerequisite changes shared runtime behavior; Claude default selection remains in #15993/#15997. No database migration or Codex default change is introduced. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, code execution and browser testing. The exact serving model ID and context-window size are not exposed in this session. ## 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 - [x] 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> |
||
|
DottaandPaperclip
|
3858d2341d |
fix(recovery): default saved-monitor waits and keep task recovery quiet (#16686)
## Thinking Path > - Paperclip manages AI agents and their work. > - A task must keep a durable path to its next action. > - A provider can save a task monitor, then fail to yield because it omits internal continuation fields. > - An interrupted provider-pack check can then be reported as permanent artifact incompatibility. > - The task asks its user to certify recovered workspace files, even though this is an operator responsibility. > - This pull request derives the saved monitor continuation, bounds verification retries, and removes that task form. > - Normal recovery stays quiet. Unresolved holds retain inspection and the existing safety checks. ## Linked Issues or Issue Description **What happened?** A yielded completion without `continuation` is rejected even after the provider saves an eligible monitor on the task. Repeated attempts cannot finish. Remote verification also treats timeouts and missing exit status as artifact incompatibility. The task recovery notice exposes raw diagnostics and asks the task user to certify infrastructure files. **Expected behavior** Use current persisted task state to fill routine continuation fields. Retry interrupted verification reads within a fixed bound. Keep normal recovery in the working state. Show a compact notice only when work cannot safely continue. **Steps to reproduce** 1. Save an eligible monitor on the active task. 2. Call `paperclip_finish` with `reportedWorkDisposition: "yielded"` and omit `continuation`. 3. Return a timed-out remote provider-pack command with empty stderr during recovery. Inspect the resulting task notice. **Paperclip version or commit** Source baseline: `aaeff418cf` (master integrated with its current task visibility and saved-source reconstruction rules). Related changes: #15824, #16104, #16451, #16493, #16690. This fix complements saved-result recovery and verified pack reuse. It does not replace their workspace ownership checks. ## What Changed - Allow omitted or null continuation at the provider input boundary. Read current authorized task context and fill a monitor continuation only for the bound run and an eligible saved monitor. Keep accepted results strict. Apply this to Codex, OpenCode, both direct and production-sidecar ACPX paths, and external drivers. Reserve the semantic call identity during the saved-context read and reject cancellation or a changed run/turn. - Bind the shared completion change and continuation helper in a new Copilot v21 source declaration. Preserve v20 history and its decoder support. Qualification stays pending. - Expose the eligible continuation in task context. Completion admission still checks persisted monitor state. No schedule is created or renewed by the default. - Retry read-only provider verification at most twice per command. Hold exhausted reads with a distinct verification-unavailable cause. Reattachment cannot renew the read budget through an unchanged provider-attempt counter. Keep completed verification failures and wrong versions incompatible. - Remove the task file-certification form. Hide the notice only for a matching durable recovery path without an unknown-action replay hold. Keep missed retries, unsafe outcomes, and unresolved file holds visible. - Add production-component stories for automatic recovery, blocked and expired holds, reader access, persisted repair decisions, source reconstruction, queued continuation, and mobile. Preserve master’s guarded saved-source reconstruction choice after confirmed source destruction. Update the execution contract and access maps. ## Verification - Completion, helper, Codex, OpenCode, ACPX, and profile regressions pass. After the sidecar review fix, 271 tests across the production sidecar and three provider suites pass, plus 72 helper/profile tests. The real sidecar MCP bridge tests cover saved-monitor acceptance, no-monitor refusal, cancellation, duplicate call identity, and raw-versus-forwarded semantic receipt hashes. The OpenCode tests also cover eligible-monitor acceptance and refusal without one. - The fresh full native executor suite passes all 743 tests. Four profile, installation-integrity, and ACPX driver suites pass all 168 tests. The earlier CI fingerprint failure required a new immutable source declaration; its follow-up Docker failure required the matching context allowlist entry. Both fixes are verified locally. Targeted server monitor, tool authority, and provider verification suites pass. The probe tests include a real timed-out subprocess, an unrelated responsive timer, transport errors, and completed integrity rejections. - All 90 tests in the merged task notice, reconstruction choice, recovery display, and lineage suites pass. They cover reader access, live/missed/mismatched recovery, unknown outcomes, saved messages, retry refusal, and removal of the file form. Both review findings have failing-baseline/passing-treatment regressions: identical polling across retry expiry, and a failed refresh after cached running activity. - Browser walkthrough passed for automatic recovery, unresolved details, a 390px mobile story, and the merged saved-source reconstruction and queued states. The reconstruction control starts disabled and normal automatic recovery shows only Working. The stories use production components and fixture API data. They do not prove live cloud recovery. - Token gates, map checks, and Storybook catalog generation pass. The exact Docker context integrity command passes locally after adding the new build declaration to its allowlist. - Workspace typecheck and build pass on the final source, including the versioned identity update. The final server and UI guards pass their focused tests, typechecks, builds, and token gates. The final standalone Storybook builds. The saved-monitor default retains master’s stricter child-task visibility filter. Re-review caught an additional production-sidecar validator before forwarding; the fix now defaults at that boundary and has passing regression controls. After preserving master’s new reconstruction capability, 68 targeted reconstruction, tool-authority, and provider-verification server tests pass. The current-master integration at `2a80050a0d` has a fresh 5/5 review with zero unresolved threads. Its complete CI matrix, including Runner tests, is the merge acceptance record. - On the final master integration, local typecheck, build, and all 90 recovery UI tests pass. A concurrent runner run hit five 5-second sidecar startup timeouts; an isolated sidecar run passed 86 tests and timed out in the unrelated unsupported-bootstrap case. Those local deadline failures remain recorded; the canonical CI Runner lanes use their normal deadlines and pass. The unsharded local full-suite attempt did not complete. It spanned source edits; the fresh native executor run above passes. An unrelated workspace fixture timed out once and then failed to reserve 32 contiguous ports on this host. Its unchanged-base control and CI server suite pass. Full-suite acceptance uses the fresh latest-head CI matrix; this PR does not claim a passing unsharded local run. ## Risks The default applies only to an eligible persisted monitor. An explicit invalid continuation still fails validation. The added read occurs only when a yielded report omits its continuation. Admission rechecks current state after that read. An interrupted verification command can add one extra 30-second probe. Completed rejections stay closed. These probes do not change the pack, launch provider work, or replay external tools. Two inconclusive reads hold the original run. They do not schedule another reattachment with an unchanged provider-attempt counter. This PR’s pending Copilot v21 declaration binds the changed shared contract, resolver, direct driver, and production sidecar sources. The previous v20 declaration is immutable and remains decodable, but launch requires the new exact identity. Qualification remains pending. Task users lose the file-certification form. Board-authorized source-only repair remains available through the resolution API with the original evidence and stop-receipt requirements. This branch does not deploy or recover historical held runs. > This is a bug fix and UI polish within existing recovery behavior. ROADMAP.md was checked. ## Model Used OpenAI Codex, `gpt-6.1-sol`, xhigh reasoning, with tool use and code execution. The host does not expose the context-window limit. ## 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 - [x] I have run tests locally and they pass (changed-area suites; the full local run limitation is recorded above) - [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> |
||
|
DottaandPaperclip
|
db2f00947b |
fix(runner): include Claude ACP in the server package (#15912)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The server ships a copy of Paperclip Runner for native agent execution. > - The Claude ACP bridge is a runner dependency, but it was absent from the server package. > - The runner resolves this bridge dynamically, so the import-based packaging check missed it. > - A Claude session then failed before startup and showed a generic connection error. > - This pull request ships the qualified bridge and reports a missing runtime with repair steps. ## Linked Issues or Issue Description **What happened?** A server install with the vendored runner could not load `@agentclientprotocol/claude-agent-acp/package.json`. The runtime test suggested checking the model or provider connection. The task reported an interrupted runner session. **Expected behavior** The server package includes its qualified Claude ACP runtime. A missing bundled runtime reports an installation error and explains how to repair it. **Steps to reproduce** 1. Use a server install with the vendored runner and no Claude ACP bridge. 2. Select the Paperclip Runner ACP harness and the Claude provider. 3. Run the runtime test or open a session. 4. Observe a missing-module failure before Claude starts. **Paperclip version or commit** Reproduced on `e733bddc45`. This branch is based on current master. **Deployment mode** Self-hosted server built from source. Related: #15224 upgrades the Claude bridge. This PR fixes its omission from the server package and keeps the current qualified version. A future bridge upgrade must update the server pin too. ## What Changed - Add Claude ACP `0.73.0` to the server dependencies and bundled dependencies. - Pin the qualified Claude SDK and bridge dependencies in the npm bundle producer graph. Publish its native packages as consumer optional dependencies instead of shipping the producer executable. - Bind source-built vendored runners to the shared pnpm dependency store while retaining the server manifest as the provider authority. Keep published npm and self-rooted deployment roots unchanged. - Include dynamically resolved Claude and Codex bridges in the vendor dependency check. - Preserve the missing-package category through the sidecar, Rust transport, and native session executor. Stop automatic retries for this installation failure. - Show **Runtime missing** in the runtime test and task thread. Explain the reinstall or rebuild, server restart, and runtime test steps. - Add regression tests and document the repair procedure. ## Verification - Red/green comparison with the production sidecar: the same missing-package setup returns a raw require-stack error on the original code and an actionable, non-retryable missing-runtime error on this branch. - The rebuilt server's vendored Claude installation probe passes using the source-server authority selected by the launcher, without starting a provider or making a model request. - Focused server verification: 830 tests passed. Runner installation and sidecar error tests: 83 passed, with 6 platform-specific skips. Packaging tests: 28 passed. Rust transport tests: 7 passed. - Source/deployment authority tests: 3 passed. Red/green packaging tests include a Linux-produced Claude SDK bundle, actual npm pack, and closed executable admission on Linux x64 and macOS ARM64/x64. - Full UI suite: 8,113 tests passed. - `pnpm -r typecheck` and `pnpm build` passed on the rebased branch. - Full current-head CI passed, including all general and serialized test lanes, Runner Rust/Vitest verification, typecheck, build, and all eight e2e shards. Greptile reviewed `d6a2741834ff922956560f2f689382827bbaf9e0` at 5/5 with no unresolved threads. - Local full-suite limitation: an earlier parallel attempt hit Postgres startup failures and timeouts; the affected server tests and a database fixture passed in isolation. The subsequent serial `pnpm test:run` was stopped while still running after complete CI passed. Focused local tests, full UI tests, typecheck, and build completed as listed above. - Token gates and `git diff --check` passed. ## Risks - Bundling the Claude bridge increases the server package size. The producer graph retains the qualified SDK version and existing isolation patch. Native platform declarations move to the published server manifest, while the runtime keeps its exact version, declared-slot, no-follow, and executable digest checks. - The new failure category is permanent. Operators must repair the server installation before they retry the task. - Existing failed runs retain their recorded error. The clearer message applies to new runtime tests and runs. - No database schema or migration changes. ## Model Used OpenAI GPT-6 through Codex. The system reports the model family; the exact deployment ID and context-window size are not exposed in this session. Used reasoning, browser inspection, tool use, and code execution. ## 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 - [x] 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> |
||
|
DottaandPaperclip
|
d6e6d1c78a |
Stream OpenCode immediately, scope reasoning to turns, and deduplicate instructions (#15708)
## 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
|