opencode-codex-memory 0.1.2

package/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1.  Definitions.
+
+    "License" shall mean the terms and conditions for use, reproduction,
+    and distribution as defined by Sections 1 through 9 of this document.
+
+    "Licensor" shall mean the copyright owner or entity authorized by
+    the copyright owner that is granting the License.
+
+    "Legal Entity" shall mean the union of the acting entity and all
+    other entities that control, are controlled by, or are under common
+    control with that entity. For the purposes of this definition,
+    "control" means (i) the power, direct or indirect, to cause the
+    direction or management of such entity, whether by contract or
+    otherwise, or (ii) ownership of fifty percent (50%) or more of the
+    outstanding shares, or (iii) beneficial ownership of such entity.
+
+    "You" (or "Your") shall mean an individual or Legal Entity
+    exercising permissions granted by this License.
+
+    "Source" form shall mean the preferred form for making modifications,
+    including but not limited to software source code, documentation
+    source, and configuration files.
+
+    "Object" form shall mean any form resulting from mechanical
+    transformation or translation of a Source form, including but
+    not limited to compiled object code, generated documentation,
+    and conversions to other media types.
+
+    "Work" shall mean the work of authorship, whether in Source or
+    Object form, made available under the License, as indicated by a
+    copyright notice that is included in or attached to the work
+    (an example is provided in the Appendix below).
+
+    "Derivative Works" shall mean any work, whether in Source or Object
+    form, that is based on (or derived from) the Work and for which the
+    editorial revisions, annotations, elaborations, or other modifications
+    represent, as a whole, an original work of authorship. For the purposes
+    of this License, Derivative Works shall not include works that remain
+    separable from, or merely link (or bind by name) to the interfaces of,
+    the Work and Derivative Works thereof.
+
+    "Contribution" shall mean any work of authorship, including
+    the original version of the Work and any modifications or additions
+    to that Work or Derivative Works thereof, that is intentionally
+    submitted to Licensor for inclusion in the Work by the copyright owner
+    or by an individual or Legal Entity authorized to submit on behalf of
+    the copyright owner. For the purposes of this definition, "submitted"
+    means any form of electronic, verbal, or written communication sent
+    to the Licensor or its representatives, including but not limited to
+    communication on electronic mailing lists, source code control systems,
+    and issue tracking systems that are managed by, or on behalf of, the
+    Licensor for the purpose of discussing and improving the Work, but
+    excluding communication that is conspicuously marked or otherwise
+    designated in writing by the copyright owner as "Not a Contribution."
+
+    "Contributor" shall mean Licensor and any individual or Legal Entity
+    on behalf of whom a Contribution has been received by Licensor and
+    subsequently incorporated within the Work.
+
+2.  Grant of Copyright License. Subject to the terms and conditions of
+    this License, each Contributor hereby grants to You a perpetual,
+    worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+    copyright license to reproduce, prepare Derivative Works of,
+    publicly display, publicly perform, sublicense, and distribute the
+    Work and such Derivative Works in Source or Object form.
+
+3.  Grant of Patent License. Subject to the terms and conditions of
+    this License, each Contributor hereby grants to You a perpetual,
+    worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+    (except as stated in this section) patent license to make, have made,
+    use, offer to sell, sell, import, and otherwise transfer the Work,
+    where such license applies only to those patent claims licensable
+    by such Contributor that are necessarily infringed by their
+    Contribution(s) alone or by combination of their Contribution(s)
+    with the Work to which such Contribution(s) was submitted. If You
+    institute patent litigation against any entity (including a
+    cross-claim or counterclaim in a lawsuit) alleging that the Work
+    or a Contribution incorporated within the Work constitutes direct
+    or contributory patent infringement, then any patent licenses
+    granted to You under this License for that Work shall terminate
+    as of the date such litigation is filed.
+
+4.  Redistribution. You may reproduce and distribute copies of the
+    Work or Derivative Works thereof in any medium, with or without
+    modifications, and in Source or Object form, provided that You
+    meet the following conditions:
+
+    (a) You must give any other recipients of the Work or
+    Derivative Works a copy of this License; and
+
+    (b) You must cause any modified files to carry prominent notices
+    stating that You changed the files; and
+
+    (c) You must retain, in the Source form of any Derivative Works
+    that You distribute, all copyright, patent, trademark, and
+    attribution notices from the Source form of the Work,
+    excluding those notices that do not pertain to any part of
+    the Derivative Works; and
+
+    (d) If the Work includes a "NOTICE" text file as part of its
+    distribution, then any Derivative Works that You distribute must
+    include a readable copy of the attribution notices contained
+    within such NOTICE file, excluding those notices that do not
+    pertain to any part of the Derivative Works, in at least one
+    of the following places: within a NOTICE text file distributed
+    as part of the Derivative Works; within the Source form or
+    documentation, if provided along with the Derivative Works; or,
+    within a display generated by the Derivative Works, if and
+    wherever such third-party notices normally appear. The contents
+    of the NOTICE file are for informational purposes only and
+    do not modify the License. You may add Your own attribution
+    notices within Derivative Works that You distribute, alongside
+    or as an addendum to the NOTICE text from the Work, provided
+    that such additional attribution notices cannot be construed
+    as modifying the License.
+
+    You may add Your own copyright statement to Your modifications and
+    may provide additional or different license terms and conditions
+    for use, reproduction, or distribution of Your modifications, or
+    for any such Derivative Works as a whole, provided Your use,
+    reproduction, and distribution of the Work otherwise complies with
+    the conditions stated in this License.
+
+5.  Submission of Contributions. Unless You explicitly state otherwise,
+    any Contribution intentionally submitted for inclusion in the Work
+    by You to the Licensor shall be under the terms and conditions of
+    this License, without any additional terms or conditions.
+    Notwithstanding the above, nothing herein shall supersede or modify
+    the terms of any separate license agreement you may have executed
+    with Licensor regarding such Contributions.
+
+6.  Trademarks. This License does not grant permission to use the trade
+    names, trademarks, service marks, or product names of the Licensor,
+    except as required for reasonable and customary use in describing the
+    origin of the Work and reproducing the content of the NOTICE file.
+
+7.  Disclaimer of Warranty. Unless required by applicable law or
+    agreed to in writing, Licensor provides the Work (and each
+    Contributor provides its Contributions) on an "AS IS" BASIS,
+    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+    implied, including, without limitation, any warranties or conditions
+    of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+    PARTICULAR PURPOSE. You are solely responsible for determining the
+    appropriateness of using or redistributing the Work and assume any
+    risks associated with Your exercise of permissions under this License.
+
+8.  Limitation of Liability. In no event and under no legal theory,
+    whether in tort (including negligence), contract, or otherwise,
+    unless required by applicable law (such as deliberate and grossly
+    negligent acts) or agreed to in writing, shall any Contributor be
+    liable to You for damages, including any direct, indirect, special,
+    incidental, or consequential damages of any character arising as a
+    result of this License or out of the use or inability to use the
+    Work (including but not limited to damages for loss of goodwill,
+    work stoppage, computer failure or malfunction, or any and all
+    other commercial damages or losses), even if such Contributor
+    has been advised of the possibility of such damages.
+
+9.  Accepting Warranty or Additional Liability. While redistributing
+    the Work or Derivative Works thereof, You may choose to offer,
+    and charge a fee for, acceptance of support, warranty, indemnity,
+    or other liability obligations and/or rights consistent with this
+    License. However, in accepting such obligations, You may act only
+    on Your own behalf and on Your sole responsibility, not on behalf
+    of any other Contributor, and only if You agree to indemnify,
+    defend, and hold each Contributor harmless for any liability
+    incurred by, or claims asserted against, such Contributor by reason
+    of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+Copyright 2026 Moritz Flöter
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

package/NOTICE

@@ -0,0 +1,9 @@
+opencode-codex-memory
+Copyright 2026 Moritz Flöter
+
+This project is a TypeScript port of the memory system from
+OpenAI Codex (https://github.com/openai/codex), licensed under the
+Apache License 2.0. Copyright 2025 OpenAI.
+
+The prompt templates under src/templates/ are adapted from Codex's
+memory templates. Per-file provenance is tracked in codex-map.yaml.

package/README.md

@@ -0,0 +1,173 @@
+# opencode-codex-memory
+
+Persistent memory for [opencode](https://opencode.ai). Your agent remembers what
+it learned in past sessions — your conventions, your projects, the decisions you
+made — and brings that context into new conversations automatically.
+
+It's a single plugin. No core changes, no MCP server, no separate process, no
+cloud service. Everything stays on your machine under
+`~/.local/share/opencode/`.
+
+## Why
+
+By default every opencode session starts from zero. You re-explain your build
+commands, your code style, and the quirks of each repo over and over.
+
+opencode-codex-memory closes that loop:
+
+- **It learns in the background.** After a session goes idle, the plugin reviews
+  the transcript and extracts durable facts — preferences, project structure,
+  what worked and what didn't.
+- **It consolidates.** Periodically it merges those notes into a compact,
+  searchable memory, pruning what's stale.
+- **It remembers at the right time.** A short summary is injected into the system
+  prompt, and the agent can search the full memory on demand when a task looks
+  related to past work.
+- **It self-corrects.** When the agent actually uses a memory it cites the source,
+  so useful memories rank higher over time and unused ones fade.
+
+The result: opencode gets more useful the more you use it, without you managing
+anything.
+
+## Install
+
+1. Add the plugin to your `~/.config/opencode/opencode.json`:
+
+   ```json
+   {
+     "plugin": ["opencode-codex-memory"]
+   }
+   ```
+
+   (While developing locally, point it at an absolute path to your checkout
+   instead of the package name.)
+
+2. That's it. The memory workspace is created on first use. Installing the
+   plugin is the opt-in: background learning and summary injection are active
+   immediately (codex ships the same system behind an experimental flag with a
+   consent prompt; a standalone memory plugin *is* the consent).
+
+Requires only opencode (official release). Git is bundled (`isomorphic-git`) —
+no `git` binary or any other external tool needed.
+
+The two restricted sub-agents that do the background learning (`memorize`,
+`memorize-extract`) register themselves automatically. To customize one — e.g.
+pin a cheaper model for extraction — define an agent with the same name in your
+own config; your definition wins and the plugin leaves it alone.
+
+## Try it
+
+Just use opencode normally. After a session goes idle, the plugin reviews it in
+the background and starts building memory — you don't have to do anything. Come
+back for a later session and ask something like *"what do you know about how I
+work?"* or *"what was I doing in this repo?"* and the agent draws on what it
+learned. The more you use it, the more it knows.
+
+You can also steer it in plain language, mid-conversation:
+
+- *"remember that I deploy this project with `make release`"* → saved as a note.
+- *"what was I working on in this repo last week?"* → time-scoped recall.
+- *"reset my memory"* → wipes it and starts over.
+
+Want to prime it before the first session has a chance to be learned? You can
+drop a starter summary in yourself — it's just a file:
+
+```bash
+mkdir -p ~/.local/share/opencode/memories
+echo 'I prefer TypeScript strict mode and 2-space indentation.' \
+  > ~/.local/share/opencode/memories/memory_summary.md
+```
+
+## Where your data lives
+
+```
+~/.local/share/opencode/
+├── memory.db                       # the plugin's own database (never touches opencode's)
+└── memories/
+    ├── memory_summary.md           # compact summary injected into the system prompt
+    ├── MEMORY.md                   # searchable index of everything learned
+    ├── rollout_summaries/          # one recap per past session
+    ├── skills/                     # reusable procedures discovered over time
+    └── extensions/ad_hoc/notes/    # things you explicitly asked it to remember
+```
+
+It's all plain files and a local SQLite database. Read them, edit them, delete
+them, or check them into a private repo — it's yours.
+
+## Privacy & safety
+
+- **Local only.** Nothing is sent anywhere except through your existing opencode
+  provider, using your existing credentials. The plugin holds no keys of its own.
+- **Secrets are redacted** (API keys, tokens, private keys, passwords) before any
+  memory is written or sent to a model.
+- **The learning agents are sandboxed** — they cannot run shell commands or reach
+  the network.
+- **Reset is safe.** `memory_reset` refuses to run if the memory folder is a
+  symlink, so it can't be tricked into deleting something else.
+- **Web/MCP sessions:** by default, sessions that used web search, fetch, or MCP
+  tools are still eligible for memory (matching codex). If you'd rather exclude
+  them so scraped or external content can't enter your memory, set
+  `disable_on_external_context: true`.
+
+## Configuration
+
+Optional plugin options (all have sensible defaults). Names and defaults match
+codex's `[memories]` config so the two stay easy to compare:
+
+| Option | Default | Meaning |
+|---|---|---|
+| `generate_memories` | `true` | Turn the background learning pipeline on/off |
+| `use_memories` | `true` | Inject the memory summary into the system prompt |
+| `dedicated_tools` | `true` | Expose the `memory_read`/`memory_search`/`memory_list`/`memory_add_note` tools |
+| `disable_on_external_context` | `false` | Exclude sessions that used web/MCP tools from memory |
+| `extract_model` | opencode `small_model`, else current model | Model used for per-session extraction |
+| `consolidation_model` | opencode `model`, else current model | Model used for consolidation |
+| `max_raw_memories_for_consolidation` | `256` | How many raw memories feed each consolidation pass |
+| `max_rollout_age_days` | `10` | Ignore sessions older than this for extraction |
+| `min_rollout_idle_hours` | `6` | How long a session must be idle before it's eligible |
+| `max_rollouts_per_startup` | `2` | Max sessions extracted per pass |
+| `max_unused_days` | `30` | Prune memories unused for this long |
+
+To set options, turn the plugin entry into a `[name, options]` pair:
+
+```json
+{
+  "plugin": [
+    ["opencode-codex-memory", { "disable_on_external_context": true, "min_rollout_idle_hours": 2 }]
+  ]
+}
+```
+
+See the [opencode plugin docs](https://opencode.ai/docs/plugins/) for details.
+
+Numeric options are clamped to codex's valid ranges; unknown option keys are
+ignored with a warning. Setting `use_memories: false` also hides the memory
+tools, matching codex's extension gating.
+
+Model selection mirrors codex's cheap-extraction / capable-consolidation
+split using opencode's own concepts: when `extract_model` is unset, the
+`small_model` from your `opencode.json` is used (codex uses `gpt-5.4-mini`);
+when `consolidation_model` is unset, your main `model` is used (codex uses
+`gpt-5.4`). If neither is configured, both fall back to the session's default
+model. (opencode's *automatic* small-model pick is internal to opencode and
+not exposed to plugins — set `small_model` explicitly to get the cheap
+extraction path.)
+
+> Note: `dedicated_tools` defaults to `true` here (codex defaults it to `false`).
+> This is the one intentional default difference — the tools are a core part of a
+> standalone memory plugin. Everything else matches codex's defaults.
+
+## Under the hood
+
+opencode-codex-memory is a faithful port of the memory system from OpenAI's codex.
+If you want to understand the design, the trade-offs, or contribute, see
+[`ARCHITECTURE.md`](./ARCHITECTURE.md). Contributor guidance lives in
+[`CONTRIBUTING.md`](./CONTRIBUTING.md) and [`AGENTS.md`](./AGENTS.md) —
+in short: this repo exists to port codex's memory system to opencode, and
+PRs that break that parity will be rejected.
+
+## License
+
+Apache 2.0 — the same license as [OpenAI Codex](https://github.com/openai/codex),
+whose memory system this project ports. See [`LICENSE`](./LICENSE) and
+[`NOTICE`](./NOTICE). Not affiliated with the codex project.

package/opencode.json

@@ -0,0 +1,37 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "agent": {
+    "memorize": {
+      "mode": "subagent",
+      "prompt": "You are a memory consolidation agent. Read the workspace diff file and update MEMORY.md, memory_summary.md, and skills/ to reflect the latest memories. Keep memory_summary.md under 10000 chars (2500 tokens). Prune stale entries. Do not access the network.",
+      "permission": {
+        "bash": "deny",
+        "webfetch": "deny",
+        "websearch": "deny",
+        "task": "deny",
+        "todowrite": "deny",
+        "read": "allow",
+        "edit": "allow",
+        "write": "allow",
+        "glob": "allow",
+        "grep": "allow"
+      }
+    },
+    "memorize-extract": {
+      "mode": "subagent",
+      "prompt": "You are a memory extraction agent. Read the session transcript and extract raw_memory, rollout_summary, and rollout_slug as JSON. Exclude AGENTS.md/instruction content. Redact secrets.",
+      "permission": {
+        "bash": "deny",
+        "webfetch": "deny",
+        "websearch": "deny",
+        "task": "deny",
+        "todowrite": "deny",
+        "read": "allow",
+        "write": "deny",
+        "edit": "deny",
+        "glob": "allow",
+        "grep": "allow"
+      }
+    }
+  }
+}

package/package.json

@@ -0,0 +1,41 @@
+{
+  "name": "opencode-codex-memory",
+  "version": "0.1.2",
+  "description": "Persistent memory plugin for opencode — ports codex's two-phase memory system (extraction → consolidation → injection → citation feedback)",
+  "type": "module",
+  "main": "src/index.ts",
+  "files": [
+    "src",
+    "tools",
+    "opencode.json",
+    "NOTICE"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/moritzfl/opencode-codex-memory.git"
+  },
+  "homepage": "https://github.com/moritzfl/opencode-codex-memory#readme",
+  "bugs": {
+    "url": "https://github.com/moritzfl/opencode-codex-memory/issues"
+  },
+  "scripts": {
+    "dev": "bun --watch src/index.ts",
+    "build": "bun build src/index.ts --outdir dist --target bun",
+    "test": "bun test",
+    "typecheck": "tsc --noEmit"
+  },
+  "keywords": ["opencode", "memory", "plugin", "ai", "persistent-context", "codex"],
+  "license": "Apache-2.0",
+  "dependencies": {
+    "@opencode-ai/plugin": "^1.17.13",
+    "diff": "^9.0.0",
+    "isomorphic-git": "^1.38.6"
+  },
+  "devDependencies": {
+    "typescript": "^5.5.0",
+    "@types/bun": "^1.1.0"
+  },
+  "engines": {
+    "bun": ">=1.1.0"
+  }
+}

package/src/capture.ts

@@ -0,0 +1,137 @@
+import { Database } from "bun:sqlite"
+import { opencodeDbPath } from "./paths.js"
+import { MemoryStore, SCAN_LIMIT } from "./store.js"
+
+export interface SessionRow {
+  id: string
+  updated_at: number
+  directory: string | null
+}
+
+let opencodeDb: Database | null = null
+
+function openOpencodeDb(): Database | null {
+  if (opencodeDb) return opencodeDb
+  const p = opencodeDbPath()
+  try {
+    opencodeDb = new Database(p, { readonly: true })
+  } catch {
+    opencodeDb = null
+  }
+  return opencodeDb
+}
+
+export function listRecentSessions(limit: number = SCAN_LIMIT): SessionRow[] {
+  const db = openOpencodeDb()
+  if (!db) return []
+  try {
+    // Top-level sessions only: task-tool children are summarized into their
+    // parent, and the plugin's own sub-sessions must never be memorized.
+    return db
+      .prepare(
+        `SELECT id, time_updated AS updated_at, directory FROM session
+         WHERE parent_id IS NULL AND title NOT LIKE 'codex-memory-%'
+         ORDER BY time_updated DESC LIMIT ?`,
+      )
+      .all(limit) as SessionRow[]
+  } catch {
+    return []
+  }
+}
+
+export interface TranscriptMessage {
+  type: string
+  role?: string
+  text?: string
+  seq: number
+}
+
+export function loadTranscript(sessionId: string): TranscriptMessage[] {
+  const db = openOpencodeDb()
+  if (!db) return []
+  try {
+    const rows = db
+      .prepare(
+        `SELECT p.data, m.data AS msg_data
+         FROM part p
+         JOIN message m ON p.message_id = m.id
+         WHERE p.session_id = ?
+         ORDER BY p.time_created ASC`,
+      )
+      .all(sessionId) as { data: string; msg_data: string }[]
+    return rows.map((r, i) => {
+      let parsed: any = {}
+      try {
+        parsed = JSON.parse(r.data)
+      } catch {
+      }
+      let role: string | undefined
+      try {
+        const msg = JSON.parse(r.msg_data)
+        role = msg.role
+      } catch {
+      }
+      return {
+        seq: i,
+        type: parsed.type ?? "unknown",
+        role,
+        text: extractText(parsed),
+      }
+    })
+  } catch {
+    return []
+  }
+}
+
+function extractText(msg: any): string | undefined {
+  if (!msg) return undefined
+  if (typeof msg.text === "string") return msg.text
+  if (msg.type === "tool") {
+    // Full tool payloads: codex serializes complete FunctionCall/Output items
+    // and relies solely on the global transcript truncation. Tool outputs are
+    // the extractor's strongest evidence — do not slice them per call.
+    const tool = msg.tool ?? "unknown"
+    const input = msg.state?.input ? JSON.stringify(msg.state.input) : ""
+    const output = typeof msg.state?.output === "string" ? msg.state.output : ""
+    return `[tool: ${tool}] ${input}${output ? "\n" + output : ""}`
+  }
+  if (msg.type === "step-start" || msg.type === "step-finish") return undefined
+  if (Array.isArray(msg.parts)) {
+    return msg.parts
+      .filter((p: any) => p?.type === "text" && typeof p.text === "string")
+      .map((p: any) => p.text)
+      .join("\n")
+  }
+  if (Array.isArray(msg.content)) {
+    return msg.content
+      .filter((c: any) => typeof c === "string" || typeof c?.text === "string")
+      .map((c: any) => (typeof c === "string" ? c : c.text))
+      .join("\n")
+  }
+  return undefined
+}
+
+export interface EligibilityOptions {
+  maxAgeDays: number
+  minIdleHours: number
+  excludeSession?: string
+}
+
+export function selectEligibleSessions(
+  store: MemoryStore,
+  opts: EligibilityOptions,
+): SessionRow[] {
+  const now = Date.now()
+  const minUpdated = now - opts.maxAgeDays * 24 * 60 * 60 * 1000
+  const maxUpdated = now - opts.minIdleHours * 60 * 60 * 1000
+  const sessions = listRecentSessions()
+  return sessions.filter((s) => {
+    if (opts.excludeSession && s.id === opts.excludeSession) return false
+    if (s.updated_at < minUpdated) return false
+    if (s.updated_at > maxUpdated) return false
+    const mode = store.getMemoryMode(s.id)
+    if (mode === "disabled") return false
+    if (store.isPolluted(s.id)) return false
+    return true
+  })
+}