## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The `codex_local` adapter isolates local Codex runs by assigning
managed `CODEX_HOME` state per company and per agent
> - PR #8272 tightened that isolation, but it left a gap: once
`CODEX_HOME` became explicit, the adapter treated it like a user-managed
override and skipped auth seeding
> - That meant newly isolated agents could launch with no usable
`auth.json`, hit OpenAI unauthenticated, and fail with `401 Missing
bearer`
> - Users who had already persisted one of those broken managed homes
could remain stranded even after config changes unless Paperclip
repaired the home itself
> - This pull request teaches Paperclip to seed managed homes correctly,
backfill already-stranded managed homes on startup, and reject
credential-less managed homes before they reach the provider
> - The benefit is that affected managed `codex_local` agents recover
automatically after upgrade and restart, without manual `CODEX_HOME`
surgery
## Linked Issues or Issue Description
- Fixes#497
- Refs #5028
- Related PR: #8272
- Related PR: #8399
## What Changed
- Distinguished Paperclip-managed `CODEX_HOME` paths from genuine
external overrides and always seeded auth into managed homes, even when
`CODEX_HOME` is explicit in config.
- Wrote API-key-backed `auth.json` files for managed homes when
`OPENAI_API_KEY` is configured, otherwise symlinked the shared Codex
auth for subscription/OAuth flows.
- Added a startup reconciliation pass that backfills already-isolated
managed homes created by the broken release so upgrade plus restart
repairs stranded agents automatically.
- Preserved previously resolved API-key auth when the stored
`OPENAI_API_KEY` binding is secret-backed and startup cannot resolve the
secret value directly.
- Hardened the managed-home preflight to require a credential-bearing
`auth.json`, not just file presence, and documented the recovery
behavior.
- Added regression tests covering managed-home seeding, fail-fast
behavior, and server-side startup reconciliation.
## Verification
```bash
pnpm exec vitest run packages/adapters/codex-local/src/server/codex-home.test.ts packages/adapters/codex-local/src/server/execute.auth.test.ts server/src/__tests__/codex-auth-reconciliation.test.ts server/src/__tests__/codex-local-execute.test.ts server/src/__tests__/server-startup-feedback-export.test.ts
pnpm --filter @paperclipai/adapter-codex-local typecheck
pnpm --filter @paperclipai/server typecheck
pnpm check:tokens
pnpm exec vitest run server/src/__tests__/server-startup-feedback-export.test.ts
```
GitHub Actions `PR` workflow is green on latest head `e5b1e08d4`,
including policy, typecheck, test shards, build, e2e, serialized server
suites, and canary dry run. Greptile Review is green on latest head with
0 comments added. No UI changes.
## Risks
- Startup reconciliation now mutates persisted managed Codex homes at
boot. Risk is low because it only touches Paperclip-managed
company/agent home paths and no-ops when a home already has usable auth.
- Genuine external `CODEX_HOME` overrides remain intentionally
self-managed, so those users still own repair steps inside their custom
home.
- Hosts with neither shared Codex auth nor an explicit per-agent API key
now fail earlier with a clearer adapter error instead of surfacing a
downstream `401`, which changes timing but not capability.
## Model Used
- OpenAI Codex, GPT-5-based coding agent in a local Codex session; exact
served model ID/context window were not exposed to the session. Tool use
and code execution were 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 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] If this change affects the UI, I have included before/after
screenshots
- [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>
## Thinking Path
> - Paperclip's `claude_local` adapter persists Claude Code session
jsonls under `~/.claude/projects/…/{sessionId}.jsonl` and resumes them
on the next heartbeat
> - When Claude Code injects `<synthetic>` placeholder assistant
messages (after rate-limit, max-turn exhaustion, or transient-upstream
failures) those placeholders get UUID-format `message.id`s rather than
`msg_…`-format ids
> - On the next `--resume`, Claude Code passes that UUID as
`previous_message_id` and Anthropic's API rejects it with a 400:
``diagnostics.previous_message_id: must be the `id` from a prior
/v1/messages response (starts with `msg_`)``
> - The adapter had a session-rotation fallback only for "unknown
session" errors, so the poisoned session was `--resume`-d indefinitely
and the agent flipped between `idle` and `error` every heartbeat
> - Even worse, the *result* event of the failing run still carried a
`session_id`, and the adapter was persisting that id into the
issue-scoped session store (`agentTaskSessions`). So even after we
detected the 400, every subsequent continuation re-loaded the same
poisoned id and hit the same 400 again — the issue was permanently
stranded
> - We observed this on multiple agents in our deployment; the only
manual fix was to rename the `.jsonl`, which is not a viable long-term
workaround
> - This PR detects the 400, runs the same session-rotation fallback the
unknown-session path uses **and** stops persisting the poisoned id, so
the next attempt starts genuinely fresh
## Linked Issues or Issue Description
No external GitHub issue is linked. Describing the problem inline
following the bug-report template:
**What happened:** `claude_local` agents flipped between `idle` and
`error` on every heartbeat because the persisted session jsonl carried a
synthetic UUID `previous_message_id` (from `<synthetic>` assistant
placeholders injected after rate-limit/max-turn/upstream errors).
Anthropic's API rejected every `--resume` with a 400:
``diagnostics.previous_message_id: must be the `id` from a prior
/v1/messages response (starts with `msg_`)``.
**Expected behavior:** When the persisted session is poisoned and
unrecoverable, the adapter should rotate to a fresh session — the same
fallback path already used for unknown-session errors — and stop
re-persisting the poisoned `session_id`.
**Actual behavior:** The session-rotation fallback only matched the
"unknown session" pattern, so the poisoned session was `--resume`-d
forever. The result event of the failing run still carried `session_id`,
which was being persisted into `agentTaskSessions`, so every subsequent
continuation reloaded the same poisoned id and hit the same 400.
**Reproduction:** Inject any flow that causes Claude Code to emit a
`<synthetic>` placeholder (rate-limit, max-turn exhaustion, transient
upstream failure). The next `--resume` will fail with the 400 and the
agent will not self-recover.
**Scope of fix:** Add a `previous_message_id` 400 detector; route it
through the existing unknown-session fallback; drop the poisoned
`sessionId` and emit `clearSession: true` so the heartbeat service wipes
the persisted row; best-effort delete the local poisoned `.jsonl`.
## What Changed
Two commits:
1. **`adapter-claude-local: auto-rotate session on previous_message_id
400 (synthetic-msg poisoning)`** — detector + execute-time rotation
2. **`adapter-claude-local: guard against persisting poisoned
sessionId`** — validate-before-persist + `clearSession`
Combined diff:
- `parse.ts`: new `isClaudePoisonedPreviousMessageIdError(parsed)`
matching ``/diagnostics\.previous_message_id.*starts with `msg_`/i``
against `parsed.result` and `extractClaudeErrorMessages(parsed)`
- `parse.ts`: `isClaudeTransientUpstreamError()` excludes the new error
from transient classification so it isn't masked as retryable upstream
noise
- `execute.ts`: expand the resume-fallback branch so it triggers on both
`isClaudeUnknownSessionError` and the new
`isClaudePoisonedPreviousMessageIdError`, with a distinct log line
(`"returned a poisoned message-id"` vs `"is unavailable"`)
- `execute.ts`: for local (non-remote) execution targets, best-effort
delete the poisoned `~/.claude/projects/.../{sessionId}.jsonl` before
retrying so the file can't be accidentally resumed by an out-of-band
caller. The `fs.unlink` and follow-up log call are in separate try/catch
blocks so a closed log stream cannot mask a successful unlink (and vice
versa)
- `execute.ts` / `toAdapterResult`: when a result carries the poisoned
400, **drop** `sessionId`/`sessionParams`/`sessionDisplayId` (return
`null`) and emit `clearSession: true` so the heartbeat service's
`resolveNextSessionState` wipes the persisted row. The result also
surfaces `errorCode: "claude_poisoned_previous_message_id"` for
observability
- `docs/adapters/claude-local.md`: runbook entry — symptom,
auto-recovery flow, on-call checklist
- Tests:
- 4 new `parse.test.ts` cases covering positive detection in `result`
and `errors[]`, negative cases, and non-transient classification
- 3 new `claude-local-execute.test.ts` cases: (a) fresh run reports the
poisoned error → sessionId dropped + `clearSession: true`; (b) recovery
retry also reports the poisoned error → same guards apply; (c)
session-rotation success on retry
## Verification
```bash
pnpm --filter @paperclipai/adapter-claude-local exec vitest run src/server/parse.test.ts
pnpm --filter @paperclipai/server exec vitest run src/__tests__/claude-local-execute.test.ts
```
Both suites green locally. This patch is also currently running as a
hot-patch over the published `2026.513.0` adapter on the reporting
deployment — sessions that previously looped indefinitely now
self-recover on the first heartbeat after the 400 surfaces.
## Risks
- Low risk. The detector is conservative (regex over `result` +
`errors[]` only) and the rotation reuses the existing unknown-session
fallback path
- The local-only `fs.unlink` of the poisoned `.jsonl` is wrapped in
`try/catch` and ignored on failure — strictly an optimization; the
server-side session clear is the authoritative reset
- Remote execution targets (`executionTargetIsRemote`) skip the disk
cleanup because the file lives on a remote host that we can't safely
reach from the adapter
- The `clearSession: true` + nulled session fields path is a no-op on
healthy runs; it only fires when the new detector matches, so existing
successful continuations are unaffected
- No DB schema changes, no public API changes, no new dependencies
## Model Used
- Provider: Anthropic Claude
- Model: `claude-opus-4-7` (Opus 4.7)
- Context window: 1M
- Capabilities: extended reasoning, tool use, code execution
- Role: implemented the detector, expanded the fallback branch, added
the persist-guard + `clearSession`, wrote the unit + integration tests,
validated locally, and applied the equivalent hot-patch to the deployed
`2026.513.0` install while this PR is in 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 similar or duplicate PRs and linked
them — closed#2295, #2361, #3572, #5438 as duplicates of this canonical
fix; complementary fixes#4838 (heartbeat_timer reset) and #4932 (gemini
context-overflow rotation) target different code paths
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots — N/A, adapter-only change
- [x] I have updated relevant documentation
(`docs/adapters/claude-local.md` runbook entry)
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Danial Jawaid <danial.jawaid@gmail.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Devin Foley <devin@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents across isolated execution
workspaces; the local cwd is the only persistence boundary between runs.
> - Workspace lifecycle (worktree_prepare → execute →
workspace_finalize) and the wake/accept flow are what guarantee that
dependent issues see a consistent worktree.
> - PAPA-380 / PAPA-431 / PAPA-432 / PAPA-440 surfaced three holes in
that contract: silent env reuse across assignees, dependent wakes firing
before finalize, and `issue.interaction.accept` advancing before
finalize landed.
> - PAPA-441 / PAPA-442 then needed to document the "no remote git"
contract and prevent future adapter/runtime code from quietly
reintroducing `git push` as a backdoor sync.
> - This pull request lands those server fixes, the static
`check-no-git-push` enforcement, the AUTHORING.md cross-link, and the
Cody-review follow-ups on the PAPA-430 thread.
> - The benefit is that finalize is a real barrier — board accepts,
dependent wakes, and operator-set env all respect it — and adapter code
can't bypass it via raw `git push`.
## What Changed
- **server (PAPA-380, PAPA-431):** `execution-workspace-policy` refuses
silent env reuse when the assignee's resolved env disagrees with the
workspace it would inherit. The inheritance protection is now scoped to
the actual inheritance signal — explicit issue-level `environmentId` is
honored even when the agent's default env is `null`.
- **server (PAPA-432):** `heartbeat.ts` gates dependent wakes on
`listUnfinalizedExecutionWorkspaceIds`, and writes a
`workspace_finalize` row on the succeeded path. Write failures now
surface instead of being swallowed so dependents aren't silently
stranded behind a missing row.
- **server (PAPA-440):** `issue-thread-interactions.acceptInteraction`
adds a workspace_finalize precondition for `request_confirmation` (not
`suggest_tasks`). Accept returns 409 if finalize hasn't succeeded for
the latest workspace operation.
- **ci (PAPA-442):** new `scripts/check-no-git-push.mjs` static check
scans `packages/adapters/`, `packages/adapter-utils/`, `server/src/`,
and `cli/src/` for any `git push` invocation (string or args-array).
Wired into the `policy` PR job and `test:release-registry`. Operators
can opt in per-call with `// paperclip:allow-git-push: <reason>`.
Release scripts are out of scope by design.
- **docs (PAPA-441):** `AUTHORING.md` documents the no-remote-git
contract and cross-links the static check so adapter authors learn the
rule and the enforcement together.
- **review follow-up (PAPA-430, Cody):** three fixes — env resolver bug,
accept-gate scope (request_confirmation only), and finalize record write
on the succeeded path.
## Verification
- `pnpm exec vitest run
server/src/__tests__/execution-workspace-policy.test.ts
server/src/__tests__/issue-thread-interactions-service.test.ts` → 33/33
pass
- `node scripts/check-no-git-push.test.mjs` → check covers string form,
args-array form, comment exclusions, and per-line allow-comment.
- Manual: server compiles; the policy job runs the check in <1s before
heavier jobs.
## Risks
- **Behavioral shift in accept:** boards accepting
`request_confirmation` while finalize is in-flight now get 409s. This is
intentional — they can retry — but it changes timing on a hot path.
`suggest_tasks` is unaffected.
- **Workspace policy:** the env-reuse refusal is a new error path.
Issues that previously silently reused an env from a different-assignee
workspace will now fail-loud; the resolver still honors explicit
issue-level `executionWorkspaceSettings.environmentId`.
- **CI rule:** any future legitimate `git push` in scoped dirs must be
marked with the allow-comment, which is the intended ergonomic.
## Model Used
- Claude Opus 4.7 (`claude-opus-4-7`, extended thinking), via Claude
Code in the Paperclip executor adapter.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots (N/A — server/CI/docs only)
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
Closes related issues: PAPA-430, PAPA-380, PAPA-431, PAPA-432, PAPA-440,
PAPA-441, PAPA-442
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents via adapters (`claude_local`,
`codex_local`, etc.)
> - Each adapter type has different capabilities — instructions bundles,
skill materialization, local JWT — but these were gated by 5 hardcoded
type lists scattered across server routes and UI components
> - External adapter plugins (e.g. a future `opencode_k8s`) cannot add
themselves to those hardcoded lists without patching Paperclip source
> - The existing `supportsLocalAgentJwt` field on `ServerAdapterModule`
proves the right pattern already exists; it just wasn't applied to the
other capability gates
> - This pull request replaces the 4 remaining hardcoded lists with
declarative capability flags on `ServerAdapterModule`, exposed through
the adapter listing API
> - The benefit is that external adapter plugins can now declare their
own capabilities without any changes to Paperclip source code
## What Changed
- **`packages/adapter-utils/src/types.ts`** — added optional capability
fields to `ServerAdapterModule`: `supportsInstructionsBundle`,
`instructionsPathKey`, `requiresMaterializedRuntimeSkills`
- **`server/src/routes/agents.ts`** — replaced
`DEFAULT_MANAGED_INSTRUCTIONS_ADAPTER_TYPES` and
`ADAPTERS_REQUIRING_MATERIALIZED_RUNTIME_SKILLS` hardcoded sets with
capability-aware helper functions that fall back to the legacy sets for
adapters that don't set flags
- **`server/src/routes/adapters.ts`** — `GET /api/adapters` now includes
a `capabilities` object per adapter (all four flags + derived
`supportsSkills`)
- **`server/src/adapters/registry.ts`** — all built-in adapters
(`claude_local`, `codex_local`, `process`, `cursor`) now declare flags
explicitly
- **`ui/src/adapters/use-adapter-capabilities.ts`** — new hook that
fetches adapter capabilities from the API
- **`ui/src/pages/AgentDetail.tsx`** — replaced hardcoded `isLocal`
allowlist with `capabilities.supportsInstructionsBundle` from the API
- **`ui/src/components/AgentConfigForm.tsx`** /
**`OnboardingWizard.tsx`** — replaced `NONLOCAL_TYPES` denylist with
capability-based checks
- **`server/src/__tests__/adapter-registry.test.ts`** /
**`adapter-routes.test.ts`** — tests covering flag exposure,
undefined-when-unset, and per-adapter values
- **`docs/adapters/creating-an-adapter.md`** — new "Capability Flags"
section documenting all flags and an example for external plugin authors
## Verification
- Run `pnpm test --filter=@paperclip/server -- adapter-registry
adapter-routes` — all new tests pass
- Run `pnpm test --filter=@paperclip/adapter-utils` — existing tests
still pass
- Spin up dev server, open an agent with `claude_local` type —
instructions bundle tab still visible
- Create/open an agent with a non-local type — instructions bundle tab
still hidden
- Call `GET /api/adapters` and verify each adapter includes a
`capabilities` object with the correct flags
## Risks
- **Low risk overall** — all new flags are optional with
backwards-compatible fallbacks to the existing hardcoded sets; no
adapter behaviour changes unless a flag is explicitly set
- Adapters that do not declare flags continue to use the legacy lists,
so there is no regression risk for built-in adapters
- The UI capability hook adds one API call to AgentDetail mount; this is
a pre-existing endpoint, so no new latency path is introduced
## Model Used
- Provider: Anthropic
- Model: Claude Sonnet 4.6 (`claude-sonnet-4-6`)
- Context: 200k token context window
- Mode: Agentic tool use (code editing, bash, grep, file reads)
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Pawla Abdul (Bot) <pawla@groombook.dev>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Re-align phase1 with upstream: hermes_local ships via hermes-paperclip-adapter on the server and UI (hermes-local module). Fixes ERR_PNPM_OUTDATED_LOCKFILE from server/package.json missing a dep still present in the lockfile.
Add shared BUILTIN_ADAPTER_TYPES and skip external plugin registration when it would override a built-in type. Docs list Hermes as built-in; Droid remains the primary external example.
Made-with: Cursor
- Plugin loader: install/reload/remove/reinstall external adapters
from npm packages or local directories
- Plugin store persisted at ~/.paperclip/adapter-plugins.json
- Self-healing UI parser resolution with version caching
- UI: Adapter Manager page, dynamic loader, display registry
with humanized names for unknown adapter types
- Dev watch: exclude adapter-plugins dir from tsx watcher
to prevent mid-request server restarts during reinstall
- All consumer fallbacks use getAdapterLabel() for consistent display
- AdapterTypeDropdown uses controlled open state for proper close behavior
- Remove hermes-local from built-in UI (externalized to plugin)
- Add docs for external adapters and UI parser contract
- Fix openclaw → openclaw_gateway type key in adapters overview and managing-agents guide
- Add missing adapters to overview table: hermes_local, cursor, pi_local
- Mark gemini_local as experimental (adapter package exists but not in stable type enum)
- Update "Choosing an Adapter" recommendations to match stable adapter set
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New subcommand to install Paperclip skills for Claude/Codex agents and
print the required PAPERCLIP_* environment variables for local CLI
usage outside heartbeat runs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove Docker option from quickstart, make `npx paperclipai onboard --yes` the recommended path
- Add tip about `create-agent-adapter` skill in the creating-an-adapter guide
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Restored docs/ directory that was accidentally deleted by `git add -A`
in the v0.2.3 release script
- Replaced generic "P" favicon with actual paperclip icon using brand
primary color (#2563EB)
- Added light/dark logo SVGs for Mintlify navbar (paperclip icon + wordmark)
- Updated docs.json with logo configuration for dark/light mode
- Fixed release.sh to stage only release-related files instead of `git add -A`
to prevent sweeping unrelated changes into release commits
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Rename all workspace packages from @paperclip/* to @paperclipai/* and
the CLI binary from `paperclip` to `paperclipai` in preparation for
npm publishing. Bump CLI version to 0.1.0 and add package metadata
(description, keywords, license, repository, files). Update all
imports, documentation, user-facing messages, and tests accordingly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Devin Foley