feat(sleep): add OpenCode transcript source

CHANGELOG.md

@@ -7,12 +7,14 @@ All notable changes to SkillOpt are documented here. This project adheres to
 ## [Unreleased]
 
 ### Added
+- **OpenCode transcript source** (`--source opencode`) for SkillOpt-Sleep. It
+  reads visible user/assistant text and tool names from OpenCode's local SQLite
+  history without requiring its CLI, login, or a provider connection.
 - **OpenCode CLI backend** (`--backend opencode`) for SkillOpt-Sleep model calls,
   including plain task replay, using an installed OpenCode CLI with the user's
   existing login and file-based global configuration. Calls parse OpenCode's
   JSONL output and disable project configuration, tool use, external plugins,
-  and configured MCP servers. Transcript harvesting and tool-aware replay
-  remain follow-up work.
+  and configured MCP servers. Tool-aware replay remains follow-up work.
 - **GitHub Copilot CLI backend**, in two forms: `copilot_chat` (usable as both
   optimizer and target) and `copilot_exec` (target-only execution harness).
   Because the Copilot CLI carries its own sign-in, `--backend copilot` selects

docs/reference/cli.md

@@ -4,9 +4,9 @@
 > include the generic research `openai_compatible` backend, Sleep handoff,
 > Sleep support for non-Azure OpenAI-compatible endpoints, the Sleep
 > `--preferences` flag, the research `cursor_exec` target harness, or Cursor
-> source/backend/plugin support, Pi source/backend support, the OpenCode Sleep
-> backend, or VS Code Copilot transcript harvesting; use a source install from
-> `main` for those features until the next release.
+> source/backend/plugin support, Pi source/backend support, OpenCode Sleep
+> source/backend support, or VS Code Copilot transcript harvesting; use a source
+> install from `main` for those features until the next release.
 
 ## Training
 
@@ -129,7 +129,7 @@ Actions are `run`, `dry-run`, `status`, `adopt`, `harvest`, `schedule`, and
 |---|---|
 | `--project PATH` | Project used for transcript scope, targets, state, and staging (default: current directory) |
 | `--scope invoked\|all` | Harvest this project or all projects |
-| `--source claude\|codex\|copilot\|cursor\|pi\|auto` | Transcript source; `auto` keeps Codex-then-Claude precedence and does not select Copilot, Cursor, or Pi |
+| `--source claude\|codex\|copilot\|cursor\|pi\|opencode\|auto` | Transcript source; `auto` keeps Codex-then-Claude precedence and does not select Copilot, Cursor, Pi, or OpenCode |
 | `--backend mock\|claude\|codex\|copilot\|cursor\|pi\|opencode\|handoff\|azure_openai` | Replay/optimizer backend |
 | `--model NAME` | Backend-specific model override |
 | `--cursor-home PATH` | Override `~/.cursor` for Cursor transcript harvesting |
@@ -138,6 +138,7 @@ Actions are `run`, `dry-run`, `status`, `adopt`, `harvest`, `schedule`, and
 | `--cursor-path PATH` | Path to the installed Cursor Agent CLI |
 | `--pi-path PATH` | Path to the installed Pi coding-agent CLI |
 | `--opencode-path PATH` | Path to the installed OpenCode CLI |
+| `--opencode-db PATH` | Path to the OpenCode SQLite history database |
 | `--preferences TEXT` | House rules supplied to reflection |
 | `--lookback-hours N` | Initial transcript lookback; `0` scans all history |
 | `--max-sessions N` / `--max-tasks N` | Bound the harvested workload |
@@ -214,18 +215,46 @@ The managed `schedule` command preserves the backend but not `--source`,
 `~/.skillopt-sleep/config.json`; use an absolute `pi_path` and verify
 authentication for the scheduled account.
 
-### OpenCode backend
+### OpenCode source and backend
 
-Install and configure OpenCode using its
-[official documentation](https://opencode.ai/docs/), then confirm the CLI is
-available with `opencode --version`.
+`--source opencode` reads OpenCode's local SQLite history directly in read-only
+mode. The source does not launch OpenCode, require the OpenCode CLI, use its
+login, or contact a model provider. Source selection remains explicit:
+`--source auto` keeps Codex-then-Claude precedence and does not select OpenCode.
+
+The database path is selected from `--opencode-db` or the `opencode_db` config
+key, then `OPENCODE_DB`, then
+`${XDG_DATA_HOME:-~/.local/share}/opencode/opencode.db`. A relative
+`OPENCODE_DB` value is resolved below OpenCode's data directory;
+`OPENCODE_DB=:memory:` has no persistent history to harvest.
+
+The harvester keeps visible user and assistant text, short tool names, the
+recorded project directory, Git branch, and session timestamps. It excludes
+reasoning, tool arguments and results, file contents, patches, and
+provider/model/account metadata. Only root sessions are considered, and
+sessions produced by SkillOpt's own OpenCode backend are excluded. Known
+secret-shaped strings in retained text are redacted as defense in depth;
+inspect harvested tasks before sending them to a real backend. The database is
+opened read-only, although SQLite may still update its transient `-shm` file
+while coordinating an active WAL database.
+
+The transcript source and model backend are independent. For example, export
+OpenCode-derived tasks for review before using any configured backend:
+
+```bash
+skillopt-sleep harvest --project "$(pwd)" \
+  --source opencode --output reviewed-tasks.json --progress
+```
 
 `--backend opencode` runs SkillOpt's model calls for mining, plain task replay,
 judging, and reflection through an installed OpenCode CLI. It uses the user's
 existing OpenCode login, provider environment variables, and file-based global
 configuration; SkillOpt does not manage OpenCode accounts or provider
-credentials. Transcript sources remain independent, and there is not yet a
-`--source opencode` harvester.
+credentials.
+
+Install and configure OpenCode using its
+[official documentation](https://opencode.ai/docs/), then confirm the CLI is
+available with `opencode --version`.
 
 If OpenCode is on `PATH`, no path option is needed. Otherwise use
 `--opencode-path`, the `opencode_path` config key, or
@@ -234,7 +263,7 @@ If OpenCode is on `PATH`, no path option is needed. Otherwise use
 
 ```bash
 skillopt-sleep run --project "$(pwd)" \
-  --source codex --backend opencode \
+  --source opencode --backend opencode \
   --opencode-path /absolute/path/to/opencode \
   --model provider/model --max-sessions 5 --max-tasks 3 --progress
 ```
@@ -256,11 +285,11 @@ unavailable. Calls may appear in the user's normal OpenCode session history;
 these controls are invocation settings, not complete account or process
 isolation.
 
-The managed scheduler stores the backend but not `--opencode-path`, `--model`,
-or the transcript source. Before scheduling OpenCode, put `opencode_path`,
-`model`, and `transcript_source` in `~/.skillopt-sleep/config.json` as needed.
-Prefer an absolute executable path and verify OpenCode access for the account
-that runs the scheduled job.
+The managed scheduler stores the backend but not `--source`, `--opencode-db`,
+`--opencode-path`, or `--model`. Put `transcript_source`, `opencode_db`,
+`opencode_path`, and `model` in `~/.skillopt-sleep/config.json` as needed. Use
+absolute database and executable paths, and verify OpenCode access when the
+scheduled run uses the backend.
 
 ### Cursor source and backend
 

docs/sleep/README.md

@@ -17,7 +17,7 @@ normal agent requests.
 One "night":
 
 ```
-harvest Claude Code / Codex / VS Code Copilot / Cursor / Pi transcripts → mine recurring tasks → replay via the configured backend (isolation varies by backend; mock/handoff make no network calls)
+harvest Claude Code / Codex / VS Code Copilot / Cursor / Pi / OpenCode transcripts → mine recurring tasks → replay via the configured backend (isolation varies by backend; mock/handoff make no network calls)
    → consolidate (reflect → bounded edit → GATE on real held-out tasks)
    → stage proposal → (you) adopt
 ```
@@ -90,8 +90,9 @@ skillopt-sleep schedule     # install a nightly cron entry for this project
 > **Version note.** This page tracks `main`. PyPI 0.2.0 provides the base
 > commands above. Cursor source/backend/plugin support, VS Code Copilot
 > transcript harvesting, Pi source/backend support, Sleep handoff, non-Azure
-> OpenAI-compatible endpoints, the OpenCode Sleep backend, and `--preferences`
-> landed later and require a source install from `main` until the next release.
+> OpenAI-compatible endpoints, OpenCode Sleep source/backend support, and
+> `--preferences` landed later and require a source install from `main` until
+> the next release.
 
 The per-agent integrations below still come from the repo; the CLI above is the
 standalone, pip-only way to run a cycle. Claude Code, Codex, Cursor, Copilot, and
@@ -172,7 +173,13 @@ scheduled account's Pi authentication.
 
 ### OpenCode
 
-Install and configure OpenCode using its
+Use `--source opencode` to read local OpenCode SQLite history without launching
+the CLI or requiring login or provider access. It is not selected by
+`--source auto`. See the
+[CLI reference](../reference/cli.md#opencode-source-and-backend) for database
+selection and the retained-data boundary.
+
+For model calls, install and configure OpenCode using its
 [official documentation](https://opencode.ai/docs/), then confirm the CLI is
 available with `opencode --version`.
 
@@ -184,7 +191,7 @@ not suitable:
 
 ```bash
 skillopt-sleep run --project "$(pwd)" \
-  --source codex --backend opencode \
+  --source opencode --backend opencode \
   --opencode-path /absolute/path/to/opencode --model provider/model
 ```
 
@@ -198,11 +205,11 @@ the user's existing value in that child process, so settings supplied only
 through that value are unavailable; use file-based global configuration or
 provider environment variables instead.
 
-OpenCode transcript harvesting and tool-aware replay are not implemented yet.
-For scheduling, put `opencode_path`, `model`, and the desired
-`transcript_source` in `~/.skillopt-sleep/config.json` as needed, and verify the
-scheduled account can run OpenCode. See the
-[CLI reference](../reference/cli.md#opencode-backend) for full details.
+Tool-aware replay and a native OpenCode plugin or command are not implemented
+yet. For scheduled runs, configure the source, database, executable, and model
+in `~/.skillopt-sleep/config.json` as needed; the
+[CLI reference](../reference/cli.md#opencode-source-and-backend) has the full
+scheduler details.
 
 ### Cursor
 

plugins/README.md

@@ -48,8 +48,8 @@ an importable `skillopt_sleep` module. Install with `uv tool install skillopt` o
 > **Version note.** This integration reference tracks `main`. PyPI 0.2.0
 > supports the base Sleep CLI, while Cursor source/backend/plugin support,
 > Pi source/backend support, handoff, Sleep support for non-Azure
-> OpenAI-compatible endpoints, the OpenCode Sleep backend, and `--preferences`
-> require a source checkout from `main` until the next release.
+> OpenAI-compatible endpoints, OpenCode Sleep source/backend support, and
+> `--preferences` require a source checkout from `main` until the next release.
 
 ## One sleep cycle
 
@@ -93,12 +93,15 @@ optimization.
   retained for scope filtering and may appear in miner prompts sent to a real
   backend and its provider. Known secret-shaped strings in retained message text
   are redacted only as defense in depth.
+- The core `opencode` source reads local OpenCode SQLite history without the
+  CLI, authentication, or provider access. See
+  [the CLI reference](../docs/reference/cli.md#opencode-source-and-backend) for
+  its retained-data boundary.
 - The core `opencode` backend uses the installed OpenCode CLI for plain model
   calls. It keeps the user's login and file-based global configuration
   while disabling project configuration, tool use, external plugins, and
-  configured MCP servers for those calls. OpenCode transcript harvesting,
-  tool-aware replay, and a native OpenCode plugin or command are not included
-  yet.
+  configured MCP servers for those calls. Tool-aware replay and a native
+  OpenCode plugin or command are not included yet.
 - Outbound prompts are not currently guaranteed to be free of secrets. Do not
   use a third-party provider on sensitive transcripts without reviewing the data
   source and the provider's retention policy.
@@ -136,12 +139,13 @@ Common implemented flags include:
 |---|---|---|
 | `--backend mock\|claude\|codex\|cursor\|copilot\|pi\|opencode\|handoff\|azure_openai` | `mock` | select who performs model calls |
 | `--model NAME` | backend default | select a backend-specific model |
-| `--source claude\|codex\|copilot\|cursor\|pi\|auto` | `claude` | select the transcript source; `auto` retains Codex-then-Claude precedence and does not select Copilot, Cursor, or Pi |
+| `--source claude\|codex\|copilot\|cursor\|pi\|opencode\|auto` | `claude` | select the transcript source; `auto` retains Codex-then-Claude precedence and does not select Copilot, Cursor, Pi, or OpenCode |
 | `--cursor-home PATH` | `~/.cursor` | override the Cursor transcript home |
 | `--cursor-path PATH` | auto-detect `cursor-agent` | select the Cursor Agent CLI executable |
 | `--pi-home PATH` | `~/.pi` | select the parent directory containing `agent/sessions` |
 | `--pi-path PATH` | auto-detect `pi` | select the Pi coding-agent CLI executable |
 | `--opencode-path PATH` | `SKILLOPT_SLEEP_OPENCODE_PATH`, then `opencode` on `PATH`/`PATHEXT` | select the OpenCode CLI executable |
+| `--opencode-db PATH` | `OPENCODE_DB`, then `${XDG_DATA_HOME:-~/.local/share}/opencode/opencode.db` | select the OpenCode SQLite history database |
 | `--project PATH` | current directory | select the project and invoked harvest scope |
 | `--scope invoked\|all` | `invoked` | limit transcript harvesting |
 | `--target-skill-path PATH` | managed skill | select a specific `SKILL.md` to stage/adopt |

skillopt_sleep/__main__.py

@@ -14,9 +14,10 @@
     --target-skill-path PATH explicit live SKILL.md to stage/adopt
     --tasks-file PATH   reviewed TaskRecord JSON file to replay instead of harvesting
     --backend mock|claude|codex|copilot|cursor|pi|opencode|handoff|azure_openai
-    --source claude|codex|copilot|copilot_cli|cursor|pi|auto
+    --source claude|codex|copilot|copilot_cli|cursor|pi|opencode|auto
     --vscode-workspace-storage PATH
     --copilot-cli-session-store PATH
+    --opencode-db PATH
     --model NAME
     --lookback-hours N
     --auto-adopt
@@ -85,12 +86,14 @@ def _add_common(p: argparse.ArgumentParser) -> None:
     p.add_argument("--cursor-home", default="", help="override ~/.cursor for Cursor session harvest")
     p.add_argument("--pi-home", default="", help="override ~/.pi for Pi session harvest")
     p.add_argument("--source", default="",
-                   choices=["", "claude", "codex", "copilot", "copilot_cli", "cursor", "pi", "auto"],
+                   choices=["", "claude", "codex", "copilot", "copilot_cli", "cursor", "pi", "opencode", "auto"],
                    help="session transcript source")
     p.add_argument("--vscode-workspace-storage", default="",
                    help="override VS Code User/workspaceStorage root for copilot source")
     p.add_argument("--copilot-cli-session-store", default="",
                    help="override ~/.copilot/session-store.db for copilot_cli source")
+    p.add_argument("--opencode-db", default="",
+                   help="override the local OpenCode transcript database")
     p.add_argument("--lookback-hours", type=int, default=None,
                    help="harvest window in hours; 0 = scan full history")
     p.add_argument("--edit-budget", type=int, default=0)
@@ -147,6 +150,12 @@ def _cfg_from_args(args, task_meta: Dict[str, Any] | None = None) -> Any:
         overrides["copilot_cli_session_store"] = os.path.abspath(
             os.path.expanduser(args.copilot_cli_session_store)
         )
+    if getattr(args, "opencode_db", ""):
+        overrides["opencode_db"] = (
+            ":memory:"
+            if args.opencode_db == ":memory:"
+            else os.path.abspath(os.path.expanduser(args.opencode_db))
+        )
     lh = getattr(args, "lookback_hours", None)
     if lh is not None:  # --lookback-hours was explicitly passed (0 = full history)
         overrides["lookback_hours"] = lh

skillopt_sleep/config.py

@@ -31,9 +31,9 @@
     "cursor_home": CURSOR_HOME,
     "vscode_workspace_storage": "",  # "" => auto-detect platform defaults
     "copilot_cli_session_store": "",  # "" => ~/.copilot/session-store.db
-    # Explicit sources also include copilot, copilot_cli, cursor, and pi.
-    # ``auto`` keeps
-    # the established Codex-then-Claude precedence for backward compatibility.
+    "opencode_db": "",  # "" => OPENCODE_DB or the OpenCode XDG data path
+    # Explicit sources also include copilot, copilot_cli, cursor, pi, and opencode.
+    # ``auto`` keeps the established Codex-then-Claude precedence.
     "transcript_source": "claude",
     "projects": "invoked",        # "invoked" | "all" | [list of abs paths]
     "invoked_project": "",        # filled at runtime (cwd) when projects == "invoked"
@@ -149,6 +149,15 @@ def copilot_cli_session_store(self) -> str:
             return ""
         return os.path.abspath(os.path.expanduser(str(value)))
 
+    @property
+    def opencode_db_path(self) -> str:
+        value = self.data.get("opencode_db", "") or ""
+        if not value:
+            return ""
+        if str(value) == ":memory:":
+            return ":memory:"
+        return os.path.abspath(os.path.expanduser(str(value)))
+
     @property
     def vscode_workspace_storage(self) -> str:
         value = self.data.get("vscode_workspace_storage", "") or ""