mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-23 09:07:46 +02:00
572bef4ba7679451ac1543db25cb8ebd533bf919
4
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Nicky LeachandPaperclip
|
da9af67415 |
Persist agent-owned instance secrets through lifecycle results (#16191)
## Thinking Path > - Paperclip coordinates agents and controls when they can run. > - Lifecycle plugins prepare and remove resources for each agent. > - Those resources can require private connection credentials. > - The current SDK can resolve configured secrets but cannot save these credentials securely. > - Ordinary company secrets can be bound to agents and do not provide the required server-only boundary. > - This change saves agent-owned instance secrets through the existing local lifecycle result and native secret service. > - The tenant can retain runtime credentials through restarts without a separate encryption system or remote API. ## Linked Issues or Issue Description **Subsystem affected** Agent lifecycle, plugin contract, and native secret storage. **Problem or motivation** Lifecycle plugins need to save private runtime connection details for the owning agent. Worker memory loses these details on restart. Plugin state and company secrets do not provide a private runtime-only boundary. **Proposed solution** Add optional instance-secret changes to lifecycle results. Save them through the existing secret service and local encrypted provider before accepting the result. Require company, agent, plugin, phase, operation, revision, and current unexpired attempt ownership. Supply saved values through the existing local preparation/resume request. **Alternatives considered** A separate encrypted store duplicates the native secret system. Generic plugin company-secret writes proposed by #5007 do not supply agent ownership or a server-only secret scope. This change does not add that general write API. **Roadmap alignment** Extends the existing lifecycle contract from #15631. It does not add a resource provider or select an execution backend. ## What Changed - Add an instance scope to native secrets with mandatory agent/plugin ownership, a company-qualified agent foreign key, and key uniqueness per owner. Existing company and user scopes retain their constraints. - Reuse native creation, rotation, deletion, secret versions, access audit, and the local encrypted provider. Keep values out of company catalogs, normal bindings, agent access, and public agent records. - Accept local secret patches only after locking and checking the current lifecycle operation and required plugin selection. Storage failure or a stale reply cannot complete setup. Expired or replaced attempt owners cannot overwrite a successor's credentials. - Keep vault-import conflicts company-scoped. Protect instance-owned account-home paths during failed device-login cleanup with a private, fail-closed scan. - Skip decryption on stop and cleanup so a lost key cannot block removal. Cascade secret records when their agent or plugin is deleted. - Log fixed provider diagnostics without raw errors that can contain credentials. Document the local contract, runtime resolver, and access-map exclusions. Retain the five latest migration snapshots through the normal generator pruning. ## Verification - 239 focused tests passed across agent-instance-secrets, lifecycle, secrets-service, secrets-routes, plugin-secrets-handler, and agent-device-login-routes. Used disposable PostgreSQL 18 clusters through the existing test constructor seam because the bundled binary cannot start on this macOS host. The temporary harness is outside git. - Regression tests reproduced the vault-import conflict and missed cleanup claimant before the fixes; both pass after the fixes. - New coverage includes encrypted native versions, rotation, restart recovery, company/agent/plugin isolation, ordinary-read and binding denial, stale replies, storage failure, safe logging, cleanup without the master key, and same-name secret isolation, native account-home mutation guards, lease takeover/expiry, and live agent/plugin deletion cascades. - Direct server TypeScript check, DB/shared typechecks, migration numbering/safety checks, module boundaries, and git diff check passed. - Full workspace typecheck and build were attempted; both stop at the missing local cargo toolchain. The full test command was started and stopped after failures in unchanged native-runtime/workspace suites plus bundled-PostgreSQL skips; it did not complete. CI must verify the full toolchain paths. - Current head `c0f8bfd12477ad509252ecd40e168a6c84dbeb36`: all 55 CI checks passed, including the previously canceled e2e shard. Greptile Apex reviewed this exact head at 5/5 with no unresolved threads. GitHub reports the branch mergeable and clean. - No live provider probe, production data access, or deployment. Reviewed the diff for credentials, private references, and run artifacts. ## Risks Apply migration 0339_luxuriant_iron_monger.sql before deploying tenant code. It adds nullable ownership columns, a partial unique index, foreign keys, and a stricter scope constraint. Existing rows remain valid. Keep the schema on application rollback. Preserve the existing secrets master key through deployments and backup restoration. The lifecycle request/result now has a sensitive, server-only field. Plugins must never log it or return it to an agent or browser. Values stay in the tenant database through the existing encryption provider. Trusted runtime consumers must apply normal execution admission before resolving them. Older hosts omit instanceSecrets; plugins that require durable storage must reject those hosts. ## Model Used OpenAI GPT-6 via Codex, with reasoning, repository inspection, code editing, and local test execution. The exact serving model identifier and context window 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
|
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
|
||
|
Nicky LeachandPaperclip
|
5badea4798 |
Use the agent lifecycle contract for plugin setup and status (#15391)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Some plugins must prepare resources before an agent can work. > - Those resources must stop or be removed when the agent pauses or terminates. > - The agent lifecycle module now owns these steps and their durable completion. > - Plugins use its required callback contract instead of a separate readiness query. > - This PR documents that contract and shows its progress and retry action on the agent page. ## Linked Issues or Issue Description Refs: #15631 **Subsystem affected** Required plugin lifecycle work and the agent detail page. **Problem or motivation** The lifecycle module exposes `onAgentLifecycle` and `agents.lifecycle.manage`, but the plugin authoring guide does not explain their use. The agent page displays legacy status. Setup therefore looks paused and offers Resume. Termination leaves the page before resource cleanup completes. **Proposed solution** Use the callback, admission guards, persisted state, and retry route supplied by the lifecycle module. Show pending phases and fixed host errors. Keep the detail page open during incomplete termination. Use lifecycle state for pause and resume controls. **Alternatives considered** A separate plugin readiness query would duplicate the module's state and admission rules. The final diff contains no readiness API, database commit hooks, or second admission check. ## What Changed - Document the manifest declaration, callback results, phase ordering, capability scope, retry behavior, and provider revision requirements. - Correct SDK comments for lifecycle, routing, and external object callbacks. - Show preparation, verification, pause, resume, termination, and cleanup progress from the existing agent fields. - Refresh pending steps every two seconds and other states every thirty seconds. Keep these reads separate from the agent record used by editable forms. Use the existing authorized retry route for failed steps. - Offer Pause during setup. Disable pause and resume while stop or cleanup is incomplete. Keep cleanup failures reachable on the detail page. Disable new work after termination starts. - Test required resource work across setup, pause, resume, and confirmed deletion. Test every worker callback phase, missing handlers, retry authorization, and UI behavior. ## Verification - Focused UI tests: 139 passed across lifecycle status, action buttons, API tests, and the configuration form. A regression preserves unsaved edits during an in-flight lifecycle refresh and a failed refresh. - Focused host and shared tests: 113 passed across lifecycle integration, retry authorization, plugin RPC, and manifest validation. The database suite used isolated local PostgreSQL 18 through a temporary loader outside the repository. - Module boundary tests: 11 passed. Module import/write checks and UI token gates passed. - Plugin SDK build, server direct TypeScript check, and UI TypeScript check passed. - `git diff --check` and an added-line secrets/private-reference scan passed. Fixtures use synthetic identities. - Full `pnpm -r typecheck` and `pnpm build` passed using the existing local Rust toolchain. - Visually checked all six progress phases with the application components and styles. Captured preparation and cleanup failure screenshots from the production UI build with synthetic API data; artifacts are kept outside git. - Full local `pnpm test:run` was attempted and stopped after a native-runner failure reproduced in isolation: `native-session-resume.test.ts` / `archives a damaged prior epoch before completing guarded same-task replacement with real runnerd` returns a failed Codex fixture result instead of success. The native-runtime and runner trees are unchanged from the base. No full local test pass is claimed. - All latest-head CI checks passed, including test shards, verification, E2E, and the canary packaging check. Greptile reviewed commit `96473e03a` at 5/5 with no unresolved comments. ## Risks - Selected required plugins remain a dependency for lifecycle completion. The lifecycle module retains their requirements when a plugin is disabled or removed. - Plugins must make repeated provider operations safe and fence older revisions. Host revision checks do not cancel external requests. - Polling adds one agent-detail read every two seconds during pending work and every thirty seconds otherwise. - No schema change, private VM provider implementation, resource backfill, or deployment is included. No live provider test was run. ## Model Used OpenAI GPT-6 through Codex, with reasoning, repository inspection, code editing, and command execution. The exact model revision and context window were not reported by the runtime. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either linked existing issues or described the issue in-PR - [x] I have not referenced internal or instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal ticket id - [x] I have run focused 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 risks - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no unresolved comments - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
Nicky LeachandPaperclip
|
2dd9811e8b |
Own agent hiring and termination in a lifecycle module (#15631)
## Thinking Path > - Paperclip manages AI agents and their work. > - Agent creation, approval, pause, and termination change whether an agent can work. > - These changes currently use separate service and database paths. > - Some agents need setup after their record exists and before their harness can run. > - This PR adds one module that owns those state changes and their transactions. > - The module records progress and retries incomplete work after a server restart. ## Linked Issues or Issue Description **Problem or motivation** A hire can become active before its execution environment is ready. Direct agent state writes also bypass one common lifecycle boundary. Termination does not have a durable step for resource cleanup. **Proposed solution** Use agent lifecycle commands for hiring, approval, pause, resume, and termination. Keep proposed hires pending until approval. Prepare each approved hire, test its saved harness configuration, and then permit work. Wait for required plugin work before completing a step. **Alternatives considered** A general database commit hook would expose transaction details to callers. A timer alone would delay each new hire. This module owns each command transaction and starts its worker after commit. A periodic scan recovers work after a process stops. **Roadmap alignment** This change adds the lifecycle boundary for the existing agent and plugin systems. It does not add a user interface or a provider implementation. It replaces the lifecycle delivery approach in #15391. Related proposals include #11475 and #13099; this change does not add their external executor protocols. ## What Changed - Add durable approval, preparation, verification, pause, resume, stop, and cleanup states. - Keep agent creation, lifecycle state, configuration writes, and agent record deletion behind `modules/agent-lifecycle`. Keep validation, credential rules, reads, onboarding, invitations, general approvals, and company data deletion in their services. - Commit a hire before the remaining onboarding or invitation work. Serialize requests with the existing dedicated database connection helper. Reuse the hire after a failed attempt. - Keep accepted work in the run queue during setup. Require execution and cleanup evidence before completing pause or termination. - Retain the original credential owner when approving migrated hires. - Start lifecycle work after each command commits. Use database leases and revision checks for retries and late results. - Add a generic required plugin method and capability. Store the required plugin IDs for each agent. Track host and plugin completion separately. - Keep harness verification and credential rules in services. Supply their results to lifecycle through explicit ports. Reject failed logins and incomplete probes. - Remove reverse imports from lifecycle adapters into services. Share record queries and validation below both layers. - Use one hire decision path for agent IDs and approval IDs. Resolve the approval and agent change in one transaction. Expose policy reconciliation on the command object. - Save configuration and verification invalidation through one module operation. Ordinary commands own their transaction. Restrict the shared transaction integration to its listed callers. Reject identity, company, accounting, timestamp, and unknown fields. - Require completed termination before deleting agent records. The company deletion service calls the module through a separate deletion interface. - Save an approved secret before applying its agent binding. A failed binding leaves the secret approved. A retry reuses it. - Remove old permission and metadata export files. Move hire configuration rules out of lifecycle persistence. - Report failed worker steps and scans with operation context and known error codes. Omit provider messages, stacks, and configuration values. Document ordinary application use and extension rules. - Recover expired native owners only after execution stops. Retry cleanup of failed retained leases. Wait for setup in the live smoke script. - Keep manual, budget, and company pause reasons separate. Guard execution status writes with the ready state. - Add a migration, boundary checks, regression tests, and a lifecycle guide. Keep the current UI. - Limit periodic policy checks to 100 eligible agents per minute. Continue from the last agent ID. Exclude pending hires and agents in termination or a final state. Keep explicit company and budget updates immediate. ## Verification - Latest head `ccc3c86b0` aligns the shared status update schema with the PATCH route. All 15 shared tests, 104 server route/OpenAPI tests, 2 CLI tests, and shared/server/CLI TypeScript checks pass. The Greptile comment is fixed. CI is running; no new Apex review was requested for this small fix. - Rebase `75708ac94` rebases onto master at `2eb5187e4`. The backup test uses the shared 90-second timeout from master; the older timeout commit was removed. The affected backup test passes. - Agent budget edits now pass the target agent ID through enforcement. All 50 affected tests, server TypeScript, and 11 boundary tests pass. Both configuration update paths have regression coverage. CI is running on the latest head. No new Apex review was requested for these small fixes. - Rebase `9b568666a` preserves the run-control extraction and delivery-work startup changes from master. All 559 affected tests, server TypeScript, and 11 boundary tests pass. CI and Apex review are running on the final head. - The policy scan fix passes 56 lifecycle and diagnostic tests, 24 policy and caller tests, and 11 boundary tests. A regression test checks the page limit, interval, excluded states, and cursor wraparound. - Rebase `fd4698750` passes all 611 tests in eight affected lifecycle, route, and heartbeat suites. Server TypeScript and all 11 module boundary tests pass. The company deletion rollback and concurrent hire tests are included. - Follow-up `00aac7646` fixes the failed decision deletion test and the public update schema. All 126 affected server tests, 8 shared tests, 2 CLI tests, and 11 boundary tests pass. Shared, server, CLI, and UI TypeScript checks pass. - Server TypeScript passes: `pnpm --filter @paperclipai/server exec tsc --noEmit`. - All 11 boundary tests pass: `node --test scripts/check-module-boundaries.test.mjs`. The repository boundary scan also passes. - All 68 lifecycle, failure diagnostic, and harness verification tests pass. Tests reject forbidden fields through the root command, combined transition command, and restricted transaction integration. They also check invalid fields returned by configuration preparation. - Failure tests cover host work, plugin work, claims, renewals, deferrals, and scans. Log tests check known error codes and exclusion of private error contents. - All 355 tests in 10 existing caller suites pass. These tests cover secret approval, pairing, pending hires, credentials, company import, built-in agents, managed agents, instructions, and skills. - The branch is rebased onto `origin/master` at `2eb5187e4`. The queue guards and cancellation lock fix use the extracted heartbeat queue. Agent cancellation uses the extracted run-control file. The source diff scan found no secrets or private URLs. - Earlier checks cover approval retries, rollback, late verification results, policy holds, deletion rollback, concurrent company deletion, and queue admission during setup. - Before the rebase, CI passed on `00aac7646` and Greptile Apex rated it 5/5 with no open comments. CI and a new Apex review are pending for the rebased commit. The branch has no merge conflicts. - The full local build and native Dot suite were not run. The host has no Cargo. No live provider test was run. ## Risks - Background policy recovery takes more than one minute when more than 100 agents are eligible. Explicit company and budget updates still reconcile immediately. - The restricted configuration integration keeps an agent reference and its dependent records in one transaction. It cannot change a budget or invoke a lifecycle transition. A periodic scan starts pending setup after that transaction commits. - Secret approval and binding use separate transactions. A failed binding can leave an approved secret with no agent binding. - New approved hires remain unavailable until setup and verification complete. Existing clients see `paused` during these steps. This PR does not change the UI. - Migration `0320_daily_onslaught.sql` maps existing statuses and pause reasons. It does not create external resources or claim that an existing harness passed verification. - Use a coordinated server update for this migration. Older server versions can write legacy status without the new lifecycle checks. - A failed onboarding or invitation request can leave a committed hire. A retry reuses that hire and completes the remaining records. - Deletion requires completed termination. Company deletion can require another request while cleanup is pending. - Required plugins must make repeated calls safe and reject older revisions. A disabled or removed required plugin blocks completion until it is restored. - A new hire can run a second harness test after the existing UI test. Some adapters can charge for this test. - No live provider test was run. Provider implementation and resource backfill remain separate work. ## Model Used OpenAI GPT-6 through Codex, with reasoning, code tools, and local 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 described the issue in this PR with the feature request field labels - [x] I have not referenced internal or instance-local issues or links - [x] My branch name describes the change - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation - [x] I have considered and documented risks - [x] Targeted local tests pass - [x] All Paperclip CI gates are green on the new commit - [x] Greptile Apex is 5/5 with no open comments on the new commit - [x] I will address review comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |