The core loop is identical — both platforms inject context, capture exchanges, and score outcomes. The delivery mechanism differs:

Claude Code prompts the main LLM to score each exchange via the score_memories tool. OpenCode never self-scores — an independent sidecar (a separate API call) reviews each exchange as a third party, removing self-assessment bias. The score_memories tool is not registered on OpenCode. Scoring is disabled by default until you explicitly configure it via roampal sidecar setup. During setup, Roampal detects local models (Ollama, LM Studio, etc.) and lets you choose a scoring model. Zen free models are available as an explicit opt-in choice for users without a local model or API key — they route through OpenCode's proxy which may log data. A cheap or local model works great — scoring doesn't need a powerful model.

v0.5.9: Memory footprint fix + embedder/reranker upgrade + crash observability — triggered by a MemoryError crash traced to ONNX Runtime's CPU memory arena never releasing per-shape scratch buffers, compounded by FP16 model files up-converting to FP32 at load. Disables the arena and mem-pattern cache on both models, switches the embedder to its own measured INT8 export (same mpnet model — the planned e5-base upgrade was held back to v0.6.0 after an accuracy gate caught a near-duplicate-guard regression) and the cross-encoder to its own INT8 export, and shares one cross-encoder session across all profiles instead of one per profile. Measured process footprint drops from ~2,355MB to ~484MB in isolation (~5x), and search gets faster on both the embed and rerank paths rather than trading memory for latency. A background, per-collection re-embed migrates existing vectors to the new embedder automatically on first start — never blocking the MCP client, never mixing model families within a collection. Also adds file-based logging, MemoryError/ExceptionGroup handling, an RSS heartbeat, and a /api/status endpoint so the next incident like this one leaves a trace, and degraded states (embedder down, reranker down, migration in progress) are surfaced to the user instead of silently returning an empty result.

v0.5.8: Crash-resilience release — enables SQLite WAL + FULL durability on the ChromaDB catalog so hard terminations (Windows port conflicts, external process kills, power loss) no longer corrupt or empty the database. Rewrites SessionManager.mark_scored() to perform an atomic temp-file replace, guaranteeing the JSONL transcript survives a crash mid-write. Also ships 16 new automated tests covering both fixes, fixes pre-existing test debt that left the full suite red on Windows, and adds dev tooling (pytest-timeout, pytest-forked, build, twine). No data migration required; WAL is applied on the next server start.

v0.5.7: Startup garbage collection for the MCP hook's _completion_state.json. The file accumulated one entry per conversation_id ever seen with no cleanup, driving I/O amplification on every write and leaving stuck scored_this_turn=True flags that could poison the cross-session scoring fallback. New _cleanup_completion_state pass drops entries older than 30 days or with no matching transcript, enforces a 500-entry hard ceiling, and writes atomically. JSONL transcript TTL bumped 7 → 30 days to stay in lockstep with the state-file TTL. Ships paired with Roampal Desktop v0.3.3.

v0.5.6: Hardening release — closes remaining coverage gaps from the v0.5.5.x verification audit. Phantom sweep after archived cleanup, auto-cleanup under capacity pressure, dedup observability, hardened delete permissions, archive-then-add cycle tests, sidecar prompt alignment with benchmark, async scoring queue (per-session deferred retry), MCP tool definition quality rewrite (TDQS), OpenCode Go auto-detect in sidecar setup wizard, and user name extraction fix.

v0.5.5.2: Hotfix — Windows plugin install now verifies copy succeeded (post-copy size check + manual read/write fallback for OneDrive/antivirus interference). Also installs to %APPDATA%\opencode\plugins as fallback since some Electron apps resolve config paths differently on Windows. Fixes remaining cases of issue #11 where roampal init --force reported success but the plugin was empty or in the wrong directory.

v0.5.5.1: Hotfix — OpenCode Desktop now correctly switches profiles when you switch projects in the UI (issue #10). Plugin reads the active session's directory via client.session.get() instead of caching the profile at module load, so a singleton plugin across a multi-project workspace still hits the right profile per message. Also: roampal init --force actually overwrites the OpenCode plugin file now (issue #11), with clearer errors when Desktop holds a file lock.

v0.5.5: Soft-delete for memory_bank — ChromaDB hard delete doesn't actually remove vectors from HNSW, causing phantom dedup matches that block new memories after GUI deletion. Replaced with status=archived metadata update plus status filter on all query/dedup paths. Also: scoring mutex → async queue (eliminates dropped requests), sidecar summary contamination fix (delimiter fencing).

v0.5.4: Profile binding is now per-request, not per-process. Every client (MCP server, OpenCode plugin, Python hooks for Claude Code / Cursor) sends an X-Roampal-Profile header so a single FastAPI server can cleanly serve multiple profiles simultaneously. Fixes issue #7 where OpenCode Desktop's per-project ROAMPAL_PROFILE in opencode.json was ignored because the singleton FastAPI bound the profile once at startup.

v0.5.3: Sidecar scoring now requires explicit configuration (no automatic fallback to Zen or localhost). Small local models (qwen2.5:3b, etc.) that return bare JSON arrays instead of OpenAI-shaped responses are handled transparently via server-side shape tolerance.

┌─────────────────────────────────────────────────────────┐
│  pip install roampal && roampal init                    │
│    Claude Code: hooks + MCP → ~/.claude/                │
│    OpenCode:    plugin + MCP → ~/.config/opencode/      │
└─────────────────────────────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────────┐
│  HTTP Hook Server (port 27182)                          │
│    Auto-started on first use, self-heals on failure     │
│    Manual control: roampal start / roampal stop         │
└─────────────────────────────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────────┐
│  User types message                                     │
│    → Hook/plugin calls HTTP server for context          │
│    → AI sees relevant memories, responds                │
│    → Exchange stored, scored (hooks or sidecar)         │
└─────────────────────────────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────────┐
│  Single-Writer Backend                                  │
│    FastAPI → UnifiedMemorySystem → ChromaDB             │
│    All clients share one server, isolated by session    │
└─────────────────────────────────────────────────────────┘

See dev/docs/ for full technical details.

• Restart Claude Code (hooks load on startup)
• Check HTTP server: curl http://127.0.0.1:27182/api/health

• Verify ~/.claude.json has the roampal-core MCP entry with correct Python path
• Check Claude Code output panel for MCP errors

• Make sure you ran roampal init --opencode
• Check that the server auto-started: curl http://127.0.0.1:27182/api/health
• If not, start it manually: roampal start

This is expected. Roampal has self-healing -- if the HTTP server stops responding, it is automatically restarted and retried.