ocp/CHANGELOG.md

Changelog

v3.18.0 — 2026-06-01

Hardening release from a multi-agent code audit (1 P0 + 14 P2 + 2 P3 findings, each adversarially verified and independently reviewed) plus three follow-ups (#123–#125). Every change shipped as its own PR with a fresh-context reviewer (Iron Rule 10). The single-user default path (AUTH_MODE=none, no TUI) is behavior-identical except the /health change in #109.

Security

• #109 (P0) — /health no longer advertises PROXY_ANONYMOUS_KEY to remote callers by default. The anonymousKey field is gated behind a new PROXY_ADVERTISE_ANON_KEY=1 opt-in env var; localhost callers are always exempt. Prevents any LAN-reachable device from harvesting a working, quota-spending bearer credential from the unauthenticated /health endpoint. Behavior change: ocp-connect zero-config Path A now requires the server to set PROXY_ADVERTISE_ANON_KEY=1; otherwise pass --key or use anonymous access.
• #114 — Dashboard escapes all DB-sourced strings (key names, usage rows) before innerHTML; the revoke button uses a data- attribute + listener instead of an inline onclick a quote could break out of; POST /api/keys validates key names server-side ([A-Za-z0-9 ._-]{1,64}).
• #124 — Dashboard status/plan summary cards escaped too (uniform defense-in-depth over all innerHTML sinks).
• #111 — Streaming error paths strip filesystem paths from claude error text / stderr before sending them to clients (sanitizeError), matching the non-streaming path.

Reliability / correctness

• #110 — Non-array messages is rejected with a 400 (was silently hanging the connection until socket timeout); OpenAI array content is flattened into the prompt instead of dumped as raw JSON; a streamed upstream error now emits an SSE error frame instead of a success-looking finish_reason:"stop".
• #111 — res.on("close") escalates SIGTERM→SIGKILL on client disconnect (closes a narrow re-occurrence of the #37 concurrency-slot leak on the hottest exit path); overallTimer is cleared on semantic completion so a slow-exiting child can't record a spurious post-success timeout; per-key quota is documented as best-effort (bounded overshoot ≤ MAX_CONCURRENT, cache hits uncounted).
• #113 — CLI/installer hardening: ocp-plugin restart uses the live uid + dev.ocp.proxy/ocp-proxy labels and drops the unsafe pkill fallback; ocp-connect quotes + chmod 600s the persisted key; setup.mjs XML-escapes and newline-validates injected service-unit secrets.

Alignment / governance

• #112 — OAuth token-refresh host (platform.claude.com/v1/oauth/token) re-verified against the compiled cli.js v2.1.154 (strings, no live probe) and recorded in ALIGNMENT.md; usage-probe and default request model now derive from models.json (ADR 0003 SPOT) instead of hardcoded IDs.
• #123 — The legacy console.anthropic.com/v1/oauth/token host is pinned in the alignment.yml blacklist so a future OAuth-host drift hard-fails CI; the blacklist now documents its dual purpose (known hallucinations + pinned wrong-host variants of a verified Class A endpoint).

TUI

• #115 — The TUI LAN gate refuses any non-loopback bind (not just literal 0.0.0.0); the achieved cc_entrypoint is asserted each turn and a tui_entrypoint_mismatch warning is logged on a silent degrade to the metered sdk-cli pool.

Refactor

• #125 — isLoopbackBind extracted to lib/net.mjs, shared by server.mjs and the test suite (was duplicated via a copy-paste mirror).

New environment variables

• PROXY_ADVERTISE_ANON_KEY — opt-in (default off); advertise PROXY_ANONYMOUS_KEY on the public /health body for remote zero-config discovery (#109).

v3.17.1 — 2026-05-31

Fix — code-audit P1/P2 hardening

Fixes from a multi-agent code audit (3 P1 + 5 P2, adversarially verified). The single-user default path (AUTH_MODE=none, no TUI) is behavior-identical.

Availability / correctness (P1):

• Guard proc.stdin against EPIPE — a fast-failing spawned claude (auth error, bad model, large prompt) no longer crashes the single-process daemon.
• Add unhandledRejection/uncaughtException/clientError safety nets + wrap all request-body read loops — a client aborting mid-upload no longer crashes the daemon.
• TUI transcript reader: only turn_duration is terminal (was also tool_use), which silently truncated any TUI turn that used a built-in tool.

Security gates / cache integrity (P2):

• AUTH_MODE=multi: the default spawn now passes --disallowedTools (Bash/Read/Write/Edit/…) so a guest prompt cannot drive operator-filesystem tools. Single-user path unchanged.
• /sessions (DELETE), /settings (PATCH), /logs, /usage, /status are now admin-gated (were dispatched before the admin check).
• Streaming path no longer caches an is_error response as success (cache-poisoning fix).
• TUI fail-loud guard extended to none+0.0.0.0 (unless OCP_TUI_ALLOW_LAN=1) and + PROXY_ANONYMOUS_KEY.
• TUI send-keys paste uses -l (literal) so a prompt equal to a tmux key token (e.g. C-c) is typed, not interpreted.

---

v3.17.0 — 2026-05-31

Provider — default claude invocation ported to stream-json + --system-prompt (Phase 6c)

OCP's default (non-TUI) claude spawn moves from claude -p --output-format text to claude --output-format stream-json --verbose --no-session-persistence --system-prompt <wrapper> (no -p). The NDJSON event stream is parsed into the assembled response. Benefits: ~64% per-request cost reduction and anti-hallucination via --system-prompt tool-use suppression. Clients see no API change — the OpenAI-compatible request/response shapes are identical. Faithful port of OLP's production-verified implementation; covered by 17 new stream-json parser tests.

⚠️ Billing note: from 2026-06-15 this default path carries cc_entrypoint=sdk-cli and bills against the Agent SDK credit pool. Use the new opt-in CLAUDE_TUI_MODE (below) to keep traffic on the Pro/Max subscription pool.

---

feat(tui): opt-in CLAUDE_TUI_MODE — serve via interactive claude (cc_entrypoint=cli / subscription pool), single-user only; default stream-json path unchanged

From 2026-06-15 Anthropic routes claude -p / --output-format invocations to the Agent SDK credit pool (cc_entrypoint=sdk-cli). This feature adds an opt-in bridge: when CLAUDE_TUI_MODE=true, OCP serves each request via a real interactive claude session (no -p, no --output-format) so it carries cc_entrypoint=cli and bills against the Pro/Max subscription.

The complete string response is read from claude's native JSONL session transcript and replayed to callers as a normal OpenAI completion or chunked SSE. Clients see no API change. The default stream-json path is byte-for-byte unchanged when CLAUDE_TUI_MODE is unset.

Security: single-user / single-operator only. Never enable on a multi-user OCP. See ADR 0007 and README § "Subscription-pool (TUI) mode".

New env vars: CLAUDE_TUI_MODE, CLAUDE_TUI_WALLCLOCK_MS, OCP_TUI_CWD, OCP_TUI_HOME. New ADR: docs/adr/0007-tui-interactive-mode.md. New modules: lib/tui/transcript.mjs, lib/tui/session.mjs (shipped in preceding commits on this branch).

---

Model — add claude-opus-4-8

Add claude-opus-4-8 as the newest Opus to models.json (index 0, newest first). Repoint aliases.opus from claude-opus-4-7 to claude-opus-4-8. claude-opus-4-7 remains in the list callable by literal id. legacyAliases.claude-opus-4 left pointing at claude-opus-4-7 (no change — legacy alias tracks the prior generation). README Available Models table and model-count references updated accordingly.

---

v3.16.4 — 2026-05-13

Refactor — port-literal SPOT + CI guardrail

Closes the structural side of the port-drift cascade addressed by v3.16.2 and v3.16.3. Those two releases reverted plist / plugin / scripts back to 3456 line-by-line, but the underlying invitation to drift — a hardcoded port literal scattered across six source files — was still intact.

Changes:

• New lib/constants.mjs — single source of truth for shared literals. Exports DEFAULT_PORT = 3456, LOCAL_HOST = "127.0.0.1", OPENAI_API_BASE = "/v1", LOCAL_PROXY_URL.
• server.mjs:127, setup.mjs:36, scripts/upgrade.mjs:137, scripts/doctor.mjs:84 + :205, scripts/sync-openclaw.mjs:73 — all replaced with imports from lib/constants.mjs. Behavior is identical; the literal 3456 now exists in exactly one place per language (lib/constants.mjs for .mjs, ocp + ocp-connect for bash, test-features.mjs for pinned historical-port tests).
• .github/workflows/alignment.yml — extended the path filter to setup.mjs, scripts/**, lib/**, ocp, ocp-connect. Added a new port-spot hard-fail job that greps for any hardcoded 3478 or 3456 literal in .mjs/.js/.ts/.json outside the EXEMPT_REGEX (which lists lib/constants.mjs, test-features.mjs, the bash CLIs, docs, and the workflow itself). Any future PR re-introducing a hardcoded port literal will be blocked at CI before it can cascade.
• Doc comments in server.mjs env-var summary and setup.mjs usage banner reworded so the literal 3456 no longer appears as documentation text (CI grep is intentionally aggressive — it does not parse comments — so doc strings reference DEFAULT_PORT from lib/constants.mjs instead).

No behavior change for any user. CLAUDE_PROXY_PORT env var remains the runtime override; the only difference is the unset-env fallback now flows through one shared constant.

ALIGNMENT.md hard-requirements: this PR modifies server.mjs (one-line import + one literal swap, mechanical). No cli.js operation changed; the citation requirement does not apply. SPOT principle (Rule 2 spirit) is the entire motivation.

v3.16.3 — 2026-05-13

Fixes — completes v3.16.2 port-drift revert

v3.16.2 reverted the plugin / openclaw.plugin.json / README / Mac mini plist back to 3456 (the historical source default since 593d0dc), but missed three places in scripts/ that still defaulted to 3478. Those three lines were the residual cascade source: every time ocp doctor or ocp upgrade ran without CLAUDE_PROXY_PORT in the env, they probed 3478, reported "OCP not responding" against a healthy 3456 instance, and (in the case of OpenClaw sync follow-ups on the maintainer's host) re-introduced 3478 into downstream config.

Changes:

• scripts/upgrade.mjs:137 — default port 3478 → 3456.
• scripts/doctor.mjs:84 — default port 3478 → 3456.
• scripts/doctor.mjs:205 — default port 3478 → 3456.

No behavior change for users who set CLAUDE_PROXY_PORT explicitly; env still takes precedence. The fix only affects the unset-env fallback, which now matches server.mjs:126 and the rest of the codebase.

Test plan: existing test-features.mjs cases that pin CLAUDE_PROXY_PORT=3478 continue to pass — they use the env path, not the default.

v3.16.2 — 2026-05-12

Fixes — corrects v3.16.1

The v3.16.1 fix was directionally correct (plugin now reads env first, falls back to a hardcoded default) but the narrative and the hardcoded default were both wrong.

What v3.16.1 said: "OCP server moved to 3478 default in v3.14+; plugin lagged at 3456." What is actually true:

• OCP server source default has been 3456 since 593d0dc (initial release) and has never changed. Every line in server.mjs, setup.mjs, and the ocp CLI still uses 3456 as the documented and code-level default.
• The single OCP installation observed on 3478 is the maintainer's Mac mini, whose plist was rewritten with --port 3478 during a PR #71 dogfood smoke-test accident on 2026-05-08 (see ~/.cc-rules/memory/learnings/subagent_setup_mjs_prod_host_collision.md). The plist drift was never reconciled back to source default, and v3.16.1 incorrectly canonised the post-accident value as if it had been a release decision.

This release:

• Restores the plugin fallback to http://127.0.0.1:3456 to match server source default.
• Updates openclaw.plugin.json configSchema.proxyUrl.default back to 3456.
• Restores README §"Environment Variables" CLAUDE_PROXY_PORT default to 3456.
• Plugin reads OCP_PROXY_URL env (full URL) first, then CLAUDE_PROXY_PORT env (port only), then falls back to 3456. Hosts whose OCP plist injects a non-default port must also inject the same CLAUDE_PROXY_PORT into the OpenClaw plist for the plugin to follow.
• Maintainer's Mac mini plist was reverted from 3478 to 3456 as part of this release deploy (no source change reflects this; it was a one-host correction).

Governance

• No cli.js citation needed (no server.mjs change). ALIGNMENT.md Rule 2 not engaged.

v3.16.1 — 2026-05-12 (superseded — narrative incorrect; see v3.16.2 erratum)

Fixes (as shipped — note erratum above)

• OCP plugin port lag — ocp-plugin/index.js hard-coded http://127.0.0.1:3456. While OCP server moved to 3478 in v3.14+, (corrected v3.16.2: no such move ever happened.) The Mac mini's plist was on 3478 only as residue from a dogfood accident. Result: /ocp slash commands from the home Telegram bot returned "OCP error: fetch failed". v3.16.1 changed the plugin default to 3478 (wrong direction; v3.16.2 reverts to 3456).

Governance

• No cli.js citation needed (no server.mjs change). ALIGNMENT.md Rule 2 not engaged.

v3.16.0 — 2026-05-10

Features

• ocp doctor --check oauth (PR #93) — fast path that runs only the OAuth check, skipping version detection / from-version / git operations / models endpoint. ~50ms vs. full doctor's ~200-500ms. Use cases: AI agent repair loops, post-claude auth login verify, quick health gates. Help text in cmd_doctor_help now reflects working behaviour.
• ocp update --rollback --gc — manually garbage-collect old upgrade snapshots. Retention policy: keep last 5 snapshots OR snapshots newer than 30 days OR the single most recent (always-keep safety net). --dry-run previews. Successful ocp update runs auto-GC at the end of the full path; light path does not (no snapshot created there).

Behavior changes

• After a successful cross-minor ocp update, the auto-GC emits [gc] removed N old snapshots to stderr if any were collected. Safe to ignore; manual gc is ocp update --rollback --gc.

Governance

• No cli.js citation needed (no server.mjs change). ALIGNMENT.md Rule 2 not engaged.
• PR #93 (--check oauth) merged separately; this release bundles it with the GC feature.

v3.15.1 — 2026-05-10

Fixes

• doctor: dynamic latest_version from origin/main:package.json — v3.15.0 doctor used a hard-coded latest = "v3.14.0" fallback, which made any v3.15.0+ install report kind = upgrade (against a stale value). ocp update would then attempt git checkout v3.14.0 — a downgrade. Doctor now fetches git -C ~/ocp show origin/main:package.json to determine the actual latest version; on failure (offline, fresh clone with no remote), falls back to currentVersion so kind = noop instead of recommending a downgrade.

v3.15.0 — 2026-05-10

Features

• ocp doctor — health & upgrade-readiness check; primary entry for AI-driven debugging. --json mode emits a next_action with ai_executable[] for agents to run verbatim and human_required[] for steps requiring the user (typically only OAuth).
• ocp update cross-version path — for cross-minor jumps (e.g. v3.10 → v3.14), ocp update now runs doctor → snapshot → setup.mjs (with the plist env-merge from PR #90) → service restart → post-flight /health + /v1/models verification. Same-patch updates retain the existing light path; users see no change for routine patch bumps.
• ocp update --rollback — restore the most recent (or specified) upgrade snapshot. Snapshots are saved to ~/.ocp/upgrade-snapshot-<ISO-ts>/ and never auto-deleted.
• Fresh-install routing — ocp update on installations < v3.4.0 routes to a fresh-install flow (with --yes to skip confirmation; AI agents pass this). OAuth survives via Claude Code's credential store; users do not re-OAuth unless their token was independently broken.
• AI prompt blocks in README — §Installation, §Upgrading, and §Troubleshooting each start with a copy-paste prompt for Claude Code / Cursor / Copilot, so users can drive install / setup / upgrade through their existing AI assistant.

Behavior changes

• ocp update may take 10–30s longer when a cross-minor jump triggers the full path (snapshot + post-flight). Patch bumps are unchanged.
• Pre-v3.4.0 installs are routed to fresh-install rather than failing silently or half-migrating.

Governance

• No cli.js citation needed (no server.mjs change). ALIGNMENT.md Rule 2 not engaged.
• Depends on PR #90 (plist env merge bug fix; merged before this release).

v3.14.0 — 2026-05-10

Features (security hardening)

• Per-key session isolation (PR #86, S1) — the sessions Map in server.mjs is now keyed by ${keyName}|${conversationId} instead of bare conversationId. Before this fix, two clients using distinct API keys but the same session_id value (e.g. both defaulting to "default") would share the same cli.js subprocess and conversation history, creating a cross-tenant leak path. Post-fix each (key, session) pair is isolated end-to-end, extending the per-key cache isolation shipped in v3.13.0 D1 to the session layer.
• On-disk credential file modes 0700/0600 (PR #87, S2) — setup.mjs now creates ~/.ocp at mode 0700 and both admin-key and ocp.db at mode 0600. An idempotent reconcileFileModes() call in server.mjs startup tightens any existing installation to these modes automatically on every launch, so existing prod boxes fix themselves without manual chmod. Before this fix, all three files were created at the process's default umask (typically world-readable 0644 / 0755), leaving plaintext credentials readable by other local users.
• /api/usage default scope = self; admin all-keys requires ?all=true (PR #88, S3) — the usage endpoint now applies a least-privilege default: anonymous callers receive only their own rows, non-admin authenticated callers receive only their own rows, and admin callers receive only their own rows unless they explicitly pass ?all=true. When ?all=true is used, an audit log line is emitted. Before this fix, any admin-token holder could silently enumerate usage data for every key on the server.

Behavior changes

• Breaking change for admin tooling: /api/usage no longer returns all-keys data by default. Existing cron jobs, dashboards, or scripts that rely on the admin token seeing all-keys output must add ?all=true to their request URL after upgrading to v3.14.0.
• File mode reconcile at server startup logs a one-line notice per path when mode is tightened (e.g. [security] tightened ~/.ocp/ocp.db → 0600). No action is required from the operator; the reconcile is idempotent and silent when modes are already correct.
• sessions Map key is now ${keyName}|${conversationId} internally. No client-visible wire change — the session_id field in request/response is unchanged.

Verification

• Stress-test pass: 11/11 phases including S1/S2/S3 security regression checks (Phase E, I, J). 35-minute sustained run, 60 calls, 0 errors, 0 timeouts. RSS dropped 51→47 MB across the window. Per-key cache isolation, singleflight, cache_control bypass, quota enforcement, file-mode reconcile, and scope guard against escalation all verified against running code.

Governance

• All three PRs (#86, #87, #88) include the explicit cli.js-citation-not-applicable disclaimer (per PR #75 pattern) since they are OCP-internal access-control, session-state, and file-permission changes with no corresponding cli.js operation to cite.

No new env vars / no public API surface change beyond the documented breaking change

This release adds no new env vars or endpoints. The only externally visible change is the /api/usage scope guard (breaking for admin all-keys consumers; see Behavior changes above).

v3.13.0 — 2026-05-07

Features (cache layer hardening)

• Per-key cache isolation (D1) — the cache key now includes the API key id, so distinct keys never share cache entries. Anonymous/unauthenticated callers share one anon pool. Hash format upgraded to v2; legacy v1-format rows orphan and are reaped by the existing TTL cleanup interval (no migration script).
• cache_control bypass (D2) — when a request carries an Anthropic cache_control annotation (top-level or nested in a content array), OCP skips its own cache entirely. The caller is using Anthropic-side prompt caching deliberately, and OCP must not interfere. A cache_skipped{reason: cache_control_present} log line is emitted on bypass.
• Chunked stream replay (D3) — when a streaming request hits the cache, the cached content is now emitted as multiple SSE chunks (80 codepoints/chunk, codepoint-safe via Array.from()) instead of a single large delta. Multibyte characters (CJK / emoji) stay intact.
• Singleflight stampede protection (D4) — concurrent identical cache-miss requests now share one upstream cli.js spawn instead of spawning N processes. Followers receive byte-identical responses to what the leader returns. All-or-nothing failure semantics: if the leader errors, all followers receive the same error. Streaming-path singleflight is explicitly out of scope (TODO left for follow-up).

Behavior changes

• /cache/stats response now includes additive fields inflight and requesters (current in-flight singleflight entries and total waiting callers). Existing fields entries, totalHits, sizeBytes are preserved unchanged.

Governance

• New ADR docs/adr/0005-no-multi-provider.md: OCP stays single-provider (Anthropic via cli.js spawn). Multi-provider gateway refactor explicitly out of scope; cache improvements are explicitly in scope.
• Design spec for this release: docs/superpowers/specs/2026-05-07-cache-upgrade-design.md.

No new env vars / no public API surface change

This release adds no new env vars or endpoints. All four improvements are internal correctness/concurrency upgrades to the existing CLAUDE_CACHE_TTL-gated cache layer. No client-observable wire shape change.

v3.12.0 — 2026-04-25

Features

• Streaming heartbeat — opt-in SSE comment frame (: keepalive\n\n) emitted during silent windows on the streaming response. Controlled by CLAUDE_HEARTBEAT_INTERVAL env var (ms; 0 = disabled, default). Covers both pre-first-byte and mid-stream tool-use pauses. Addresses #47. See design doc.
• X-Accel-Buffering: no response header added to SSE responses so heartbeats survive nginx/Cloudflare default buffering.

Behavior changes

• SSE headers are now sent immediately after the claude CLI spawns successfully, not on first stdout byte. The rare "spawn succeeded but subprocess died before any byte" path now closes the SSE stream cleanly rather than returning a JSON error.

Config additions

Variable	Default	Description
CLAUDE_HEARTBEAT_INTERVAL	0 (disabled)	Interval in ms for SSE keepalive comment frames on streaming path. Resets on every real frame.

v3.11.1 — 2026-04-21

Fixes

• Concurrency slot leak on subprocess timeout (#37). The request-timeout handler called proc.kill("SIGTERM") without decrementing stats.activeRequests. A subprocess stuck in a syscall that ignored SIGTERM would hold its slot until (or beyond) the 5s SIGKILL escalation actually reaped it. Slot release is now wired to proc.once("exit", cleanup) so every termination path — normal close, error, SIGTERM, SIGKILL — releases the slot exactly once.

v3.11.0 — 2026-04-20

Features

• ocp update now automatically syncs OpenClaw's registry with the latest models (scripts/sync-openclaw.mjs)
• Server logs warn if OpenClaw registry drifts from models.json

Refactor

• models.json is now the single source of truth for model list
• server.mjs and setup.mjs derive MODEL_MAP/MODELS from models.json
• Adding a new model is now a one-file edit

Fixes

• OpenClaw's model dropdown now shows all 4 current models (opus-4-7, opus-4-6, sonnet-4-6, haiku-4.5) on existing installs after ocp update. Previously setup.mjs only wrote the registry at install time.