agentel 0.2.6 → 0.3.0

package/README.md

@@ -10,11 +10,11 @@ Core capabilities:
 - canonical event JSONL alongside each transcript for provider-independent search
 - canonical repo keying from git remotes, first commits, or path hashes
 - Codex CLI, Codex Desktop, Codex SDK jobs, ChatGPT export, Claude Code CLI,
-  Claude Code Desktop, Claude Workspace, Claude.ai export, Gemini CLI, Antigravity,
-  Devin CLI, and Cursor imports
-- event-first `agentlog history` search with markdown/transcript fallback
+  Claude Code Desktop, Claude Cowork, Claude.ai export, Gemini CLI, Antigravity,
+  Devin CLI, Devin Desktop, Windsurf, and Cursor imports
+- canonical-event `agentlog history` search with explicit markdown recovery
 - `agentlog-recall` MCP stdio server exposing `search_past_sessions`
-- installable recall commands, workflows, skills, and MCP hooks for common
+- installable recall and continue-from commands, workflows, skills, and MCP hooks for common
   coding agents
 - local web viewer for full conversation history inspection
 - device-scoped S3-compatible upload sync for backup and future multi-device recall
@@ -27,7 +27,7 @@ services.
 
 ## Install
 
-Install the CLI globally so agent-facing recall commands can call `agentlog`
+Install the CLI globally so agent-facing recall and continue-from commands can call `agentlog`
 from PATH:
 
 ```sh
@@ -35,13 +35,19 @@ npm install -g agentel
 agentlog init
 ```
 
+On direct installs, agentlog includes a small postinstall helper. When npm runs
+that helper in an interactive terminal, it offers `agentlog update` if an
+existing config is present and `agentlog init` otherwise. It skips CI, `npx`,
+and indirect dependency installs, and you can suppress it with
+`AGENTLOG_SKIP_POSTINSTALL=1`.
+
 You can also install directly from the GitHub repository. Use a tag or commit
 ref for repeatable installs:
 
 ```sh
 npm install -g brianlzhou/agentlog
 # or
-npm install -g brianlzhou/agentlog#v0.2.6
+npm install -g brianlzhou/agentlog#v0.3.0
 agentlog init
 ```
 
@@ -61,6 +67,7 @@ npx agentel init
 Requirements:
 
 - Node.js 20 or newer
+- npm 11.10 or newer when developing from source or publishing releases
 - `sqlite3` for Codex, Cursor, and Devin local database imports
 - `rg`/ripgrep for faster history search
 - `unzip` for ZIP web exports
@@ -69,6 +76,23 @@ Requirements:
 Run `agentlog doctor` after install to check optional tools and configured
 sources.
 
+## Single-file binary (optional)
+
+An optional standalone executable can be built via Bun's `--compile`:
+
+```sh
+npm install
+npm run build:binary             # dist/agentlog for the current platform
+npm run build:binary -- --target=bun-linux-x64 --outfile=dist/agentlog-linux-x64
+```
+
+The binary (~62MB) bundles the Bun runtime and the `better-sqlite3` native
+module, so it runs standalone without `node_modules`. Useful for distributing
+`agentlog` to environments that can't `npm install`, and shaves ~30ms off
+the `agentlog show` cold-start that agents hit on each `/recall` invocation.
+Supported Bun targets: `bun-darwin-arm64`, `bun-darwin-x64`, `bun-linux-x64`,
+`bun-linux-arm64`, `bun-windows-x64`.
+
 ## Try From Source
 
 ```sh
@@ -80,10 +104,11 @@ AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source codex-de
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import chatgpt
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import claude-web
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import chatgpt ~/Downloads/chatgpt-export.zip --username you@example.com
+AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import chatgpt "~/Downloads/OpenAI-export/User Online Activity" --username you@example.com
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import claude-web ~/Downloads/claude-export --username you --display-name "Personal Claude"
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source claude --since 30d
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source claude-code-desktop --since all
-AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source claude-workspace --since all
+AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source claude-cowork --since all
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source gemini-cli --since all
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source antigravity --since all
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source devin-cli --since all
@@ -118,6 +143,7 @@ Before publishing a release, run:
 
 ```sh
 npm run check
+npm run security
 npm test
 npm run pack:dry
 npm run smoke:pack
@@ -137,22 +163,22 @@ agentlog integrations add-to opencode
 agentlog integrations add-to aider
 ```
 
-`integrations add-to codex` installs the MCP server plus a Codex recall skill.
-`integrations add-to claude` installs the MCP server plus a Claude `/recall`
-command plus a Claude skill under `~/.claude/skills/agentlog-recall/SKILL.md`.
-`integrations add-to gemini` installs the MCP server plus a Gemini `/recall` command
-under `~/.gemini/commands/recall.toml`.
+`integrations add-to codex` installs the MCP server plus Codex recall and
+continue-from skills. `integrations add-to claude` installs the MCP server plus
+Claude `/recall` and `/continue-from` commands plus matching Claude skills.
+`integrations add-to gemini` installs the MCP server plus Gemini `/recall` and
+`/continue-from` commands under `~/.gemini/commands/`.
 
 Additional native surfaces are installed where the client exposes one:
 
 | Agent | Recall surface |
 | --- | --- |
-| Antigravity | MCP config in `~/.gemini/antigravity/mcp_config.json` plus an Agent Skill at `~/.gemini/antigravity/skills/recall/SKILL.md` |
-| Devin | MCP config in `~/.config/devin/config.json` plus `/recall` skill at `~/.config/devin/skills/recall/SKILL.md` |
-| Cursor | MCP config in `~/.cursor/mcp.json` plus project files `.cursor/commands/recall.md` and `.cursor/rules/agentlog-recall.mdc` |
-| Cline | MCP config in `~/.cline/data/settings/cline_mcp_settings.json` plus `/recall.md` workflow at `~/Documents/Cline/Workflows/recall.md` |
-| OpenCode | MCP config in `~/.config/opencode/opencode.json` plus `/recall` command at `~/.config/opencode/commands/recall.md` |
-| Aider | Loadable recall instructions under `~/.agentlog/aider/`; Aider does not expose a documented custom slash-command registry, so load them with `/load ~/.agentlog/aider/load-recall.aider` or configure the generated markdown as `read:` in `.aider.conf.yml` |
+| Antigravity | MCP config in `~/.gemini/antigravity/mcp_config.json` plus Agent Skills at `~/.gemini/antigravity/skills/{recall,continue-from}/SKILL.md` |
+| Devin | MCP config in `~/.config/devin/config.json` plus `/recall` and `/continue-from` skills under `~/.config/devin/skills/` |
+| Cursor | MCP config in `~/.cursor/mcp.json` plus project files `.cursor/commands/{recall,continue-from}.md` and matching `.cursor/rules/agentlog-*.mdc` rules |
+| Cline | MCP config in `~/.cline/data/settings/cline_mcp_settings.json` plus `/recall.md` and `/continue-from.md` workflows under `~/Documents/Cline/Workflows/` |
+| OpenCode | MCP config in `~/.config/opencode/opencode.json` plus `/recall` and `/continue-from` commands under `~/.config/opencode/commands/` |
+| Aider | Loadable recall and continue-from instructions under `~/.agentlog/aider/`; Aider does not expose a documented custom slash-command registry, so load them with `/load ~/.agentlog/aider/load-recall.aider` or configure the generated markdown as `read:` in `.aider.conf.yml` |
 
 The generated recall files use a skill-style layout with command tables,
 workflow steps, query-selection guidance, archive layout notes, and
@@ -161,6 +187,14 @@ troubleshooting. They ask the agent to infer a focused search query, then call
 access to `~/.agentlog`. Users can ask for context naturally, such as `/recall
 the migration bug and update the test`.
 
+The generated continue-from files are stricter: after selecting a session they
+instruct the agent to read both the first window
+(`agentlog show <session_id> --json --msg-offset 0 --msg-limit 8`) and latest
+window (`agentlog show <session_id> --json --msg-limit 12`). The first window
+recovers the original goal and constraints; the latest window recovers the
+current state, files touched, test status, blockers, and next action before the
+agent resumes work.
+
 Skill/command files can also be installed directly:
 
 ```sh
@@ -215,30 +249,43 @@ opened. Search runs as you type with a short debounce. The web endpoint uses a
 warm compatible index when available, but it will not synchronously parse or
 rebuild an obsolete index during an interactive query or scan every rendered
 conversation as a fallback; rebuilds are left to `agentlog index rebuild` or
-the supervisor. The static viewer uses shadcn/ui-style design tokens
+the supervisor. Session lists and stats are backed by derived indexes under
+`agentlog/indexes/`, so repeat page loads avoid walking every metadata file.
+The static viewer uses shadcn/ui-style design tokens
 and compact button/input/select/sidebar patterns without requiring a frontend
 build step. Archives still keep stable `path:<hash>` keys for folders without
 git identity, but the UI displays the local path.
 
 Provider filters use one stable order: OpenAI (`codex-cli`, `codex-desktop`,
-`codex-sdk`, `chatgpt`), Anthropic (`claude`, `claude-code-desktop`, `claude-workspace`,
+`codex-sdk`, `chatgpt`), Anthropic (`claude`, `claude-code-desktop`, `claude-cowork`,
 `claude-web`, `claude-sdk`), Google (`gemini-cli`, `antigravity`), Cognition
-(`devin-cli`), then other local tools (`cursor`, `cline`, `opencode`,
+(`devin-cli`, `devin-desktop`), then other local tools (`cursor`, `cline`, `opencode`,
 `aider`).
 
 The supervisor is agentlog's local background watcher. When it is running, it
-polls the watcher source list chosen during init every 30 seconds using the
-configured import window, defaulting to the last 30 days. If you opt out of
+watches each source's on-disk history roots with filesystem events (FSEvents
+on macOS): writes mark the source dirty and an import runs a few seconds
+later, so new conversation turns usually land in the archive within seconds.
+SQLite-backed stores such as Cursor's `state.vscdb` use a wider ~20-second
+coalesce window because their databases churn while the app is open. Events
+are a latency optimization, never the source of truth — watched sources are
+still re-polled on a 15-minute heartbeat to catch dropped events, sources
+whose roots can't be watched (Aider project folders, JetBrains Cline) keep
+the original 30-second poll with a 5-minute idle cadence, and failing sources
+retry with exponential backoff, so an idle machine isn't spawning import
+workers all day. Imports use the configured import window, defaulting to the
+last 30 days. If you opt out of
 starting it at login, agentlog does not install a login item. During setup,
 uncheck `Start watcher at login` or run `agentlog init --no-autostart`; you can
 still run `agentlog import --source all` for a one-time catch-up,
 `agentlog watcher start` to watch for the current session, or
 `agentlog watcher login enable` later. The default
 watcher choices are Codex CLI, Codex Desktop, Claude Code CLI, Claude Code
-Desktop, Claude Workspace, Gemini CLI, Antigravity, Devin CLI, Cursor, Cline,
-OpenCode CLI, OpenCode Desktop, OpenCode Web, and Aider. New configs still support
-`imports.autoDiscoverSources=true`, but init records the chosen watcher list
-exactly by setting `imports.autoDiscoverSources=false`.
+Desktop, Claude Cowork, Gemini CLI, Antigravity CLI, Antigravity 2.0, Antigravity IDE, Devin CLI, Devin Desktop, Windsurf,
+GitHub Copilot CLI, Factory Droid, Grok Build, pi, Cursor,
+Cline, OpenCode CLI, OpenCode Desktop, OpenCode Web, and Aider. New configs
+still support `imports.autoDiscoverSources=true`, but init records the chosen
+watcher list exactly by setting `imports.autoDiscoverSources=false`.
 Cursor raw SQLite recovery is intentionally left to explicit imports such as
 `agentlog import --source cursor --since all`; the supervisor handles
 incremental Cursor logs going forward and prunes duplicate transcript snapshots.
@@ -283,6 +330,13 @@ after the initial backfill. If the watcher is allowed to start at login, init
 also asks for a cloud autosync cadence; the supervisor then uploads new archive
 changes on that interval whenever it is running.
 
+Init always records a device name in the main agentlog config. New session
+metadata includes that device identity, and remote sync uses the same slug so
+multiple machines stay distinguishable in one archive bucket.
+Existing archived sessions are not rewritten by init; run
+`agentlog import --source all --since all` if you want to reimport old local
+history with the current device metadata.
+
 Remote objects are namespaced by device so multiple machines can upload into
 one bucket without overwriting each other's archive roots:
 
@@ -292,13 +346,20 @@ s3://<bucket>/agentlog/
     work-laptop/
       sessions/...
       raw-sources/...
-      indexes/...
+      memory/...
+      telemetry/...
   snapshots/
     20260504T173000Z/
       work-laptop/
         sessions/...
 ```
 
+Sync uploads every object under the local archive root, so memory items and
+their snapshot history (the Memories tab data) ride along automatically next to
+sessions. The one exception is derived local indexes under `agentlog/indexes/`,
+which are intentionally excluded; each device rebuilds those caches from the
+canonical archive objects.
+
 In a terminal, `agentlog sync` asks you to choose the remote target, previews
 the upload-only plan, and requires a confirmation phrase before writing. This is
 intentional even when only one remote is configured, because multiple remotes
@@ -364,32 +425,87 @@ alongside it:
 For large multi-session stores such as Cursor SQLite, the per-session raw
 manifest may reference one shared copy under `raw-sources/` instead of copying
 the same database into every session folder.
-
-`events.jsonl` uses the local `agentlog.events.v2` canonical event shape:
-`session.started`, `prompt.submitted`, `response.generated`, `tool.called`, and
-`tool.completed`; completed tool events link back to the matching call when the
-source exposes stable ids or matching names. Parser versions are stamped by
-source type so importer output changes can trigger reimport with a new
-fingerprint. Recall/search builds a keyword index over event text first and
-falls back to transcript/markdown for legacy archives without events. The local
-search index stores compact term postings for CLI compatibility plus a SQLite
-FTS5 sidecar for fast web queries; when either index format changes,
-`agentlog history` and `agentlog index` rebuild it from archived
-transcripts/events without a full source
-reimport. The web viewer avoids doing that rebuild on a keystroke so a large
-old index, or a full-archive Markdown fallback, cannot block interactive
-search.
+Web chat imports may also reference a shared raw export archive; ChatGPT
+attachments remain preserved there and fresh imports render image/file cards in
+the readable transcript when the export includes the file bytes.
+
+`events.jsonl` uses the local `agentlog.events.v5` canonical event shape:
+`session.started`, `prompt.submitted`, `response.generated`, `tool.called`,
+`tool.completed`, `memory.read`, `memory.write`, and `memory.loaded`;
+completed tool events link back to the matching call when the source exposes
+stable ids or matching names. Tool calls and results may include provider diff
+hunk metadata such as `structuredPatch` for numbered viewer diffs. Parser
+versions are stamped by source type so importer output changes can trigger
+reimport with a new fingerprint. Recall/search builds the interactive index
+from canonical event text; legacy transcript/markdown scanning is an explicit
+recovery path rather than a hidden fallback during normal queries. The normal
+local search rebuild
+writes a small JSON summary plus a SQLite FTS5 sidecar for fast web, terminal,
+and MCP queries. The older full BM25 JSON index remains available only to
+explicit compatibility callers, avoiding huge JSON serializations during
+`agentlog update` on large web-chat archives. Both index paths are keyed by the
+session-list fingerprint so stale checks avoid statting every archived file.
+When the index contract changes, run
+`agentlog index rebuild` to rederive search and common stats payloads from the
+archive without a full source reimport.
+When canonical diff metadata changes, run
+`agentlog update --yes --since all --sources codex` or
+`agentlog import --source codex --since all` for older Codex archives that need
+fresh `patch_apply_end` structured hunks from raw source events; the bumped
+view schema rederives `.view.json` on read.
+Memory read/write/load events are also rendered as memory activity in the web
+and Markdown views, so memory-file edits do not appear as ordinary source-code
+diffs after the view payload is regenerated.
 
 Stats are import-time metadata, not viewer-time transcript repair. Archive
 metadata stores message counts, user-message counts, token usage, and models for
-each session, and the web stats view reads those fields directly. Codex SDK and
+each session, and the web stats view reads those fields directly. Token totals
+include cache-read/cache-write tokens when providers report them, while the
+stats payload and UI also keep input, output, cache, and reasoning sub-counts
+separately when available. New archive metadata also stores compact tool-usage
+summaries and provider/export cost fields when present; the stats view uses
+those fields for most-used tools, session-time summaries, and estimated spend
+charts. Archive schema v6 also stores compact output-token work metadata
+(`text`, `toolUse`, `reasoning`, `unknown`) and lightweight outcome counts
+(`editToolCalls`, `filesTouched`, `knowledgeCaptures`, `memoryReads`,
+`memoryWrites`, `memoryLoads`) at import time. Canonical events v5 include
+`memory.read`, `memory.write`, and `memory.loaded` events for provider memory
+files and instruction files such as `AGENTS.md` and `CLAUDE.md`. The web stats
+view uses only those metadata fields for output job-mix charts and
+tokens-per-meaningful-event ratios; it does not reread transcripts or events in
+the request path. Existing archives need `agentlog update --yes --since all` or
+a clean reimport before these new charts have full coverage. Subagent child
+sessions stay direct-addressable, but aggregate stats exclude them by default so
+parent-thread provider counters are not counted again;
+the web stats view can include them with the Subagents toggle. Spend is labeled
+as an estimate unless a provider supplied an actual
+cost field, and unpriced tokens stay visible instead of being folded into a
+blended-rate guess. The model-pricing table lives in `src/pricing.js` with an
+explicit `pricing_version`, and the stats payload exposes a 30-day usage capsule
+with latest-day spend, 7-day spend, 30-day spend, tokens, prompts, sessions, and
+top model. The web stats endpoint keeps the first payload light by shipping the
+current chart window and rolling activity heatmap first; all-time daily series
+are fetched only when the viewer asks for the all-time range or an older
+activity year. Codex imports preserve `threads.tokens_used` as the
+provider total and split rollout `token_count` events into fresh input, cache
+read, output, and reasoning metadata. Codex SDK and
 Claude SDK batch jobs are kept out of primary activity totals, streaks, folder
 rankings, and provider/model charts; the stats payload and web view expose them
 as a separate SDK jobs section so high-volume automation does not drown out
 interactive work. Cursor sessions
 without provider-reported token usage can also carry separately labeled
 `estimatedUsage`, which the stats view includes while reporting estimated token
-coverage. ChatGPT and Claude.ai exports without provider usage get estimated
+coverage. Cursor `agent-transcripts` imports also preserve Composer model
+configuration in session metadata, including the canonical model and reasoning
+effort parameters. They infer working directories from explicit transcript
+paths before falling back to Cursor's project-folder slug, which avoids stale
+slug attribution when Cursor writes an agent transcript under the wrong project
+directory; existing Cursor transcript archives need `agentlog update --yes
+--since all` or a clean Cursor reimport to gain that metadata and attribution.
+Cursor transcript imports are the preferred v1 source when both
+modern transcript files and legacy Cursor SQLite rows describe the same
+Composer conversation, and a full Cursor reimport prunes those older duplicate
+copies. ChatGPT and Claude.ai exports without provider usage get estimated
 `metadata.usage` on their native chat messages, split into non-assistant input,
 assistant output, and Claude thinking output where the export provides separate
 parts. During pre-v1 development, if those stats fields or parser semantics
@@ -406,13 +522,24 @@ as `[chatgpt]conversations/<account-id>` and
 metadata in `~/.agentlog/state/web-accounts.json`; use
 `agentlog import accounts list` to inspect mappings and
 `agentlog import accounts rename <provider> <account-id-or-username> --display-name <name>`
-to change the viewer display name. Claude.ai exports preserve conversation
-summaries and split structured thinking parts from visible assistant answers
-when the export includes that detail. Repeated manual uploads are incremental:
-unchanged conversations are skipped, and updated conversations replace the
-stable session for that provider/account/conversation id. Existing malformed
-pre-v1 web-chat archives are not migrated automatically; reimport from the
-original export after a reset or cleanup.
+to change the viewer display name.
+
+For newer OpenAI privacy exports named `OpenAI-export`, unzip the download and
+import the `User Online Activity` folder. Running `agentlog import chatgpt`
+without a path starts a walkthrough that asks for export paths one at a time,
+then account username/email and display name. ChatGPT
+conversations may be split across multiple
+`Conversations__...chatgpt...part-000N` ZIPs or folders; passing the parent
+folder is best, but the walkthrough can also collect the split part folders
+individually and preserve `chat.html`, manifests, ZIPs, and attached files in
+the shared raw export archive. Claude.ai exports preserve conversation summaries
+and split structured
+thinking parts from visible assistant answers when the export includes that
+detail. Repeated manual uploads are incremental: unchanged conversations are
+skipped, and updated conversations replace the stable session for that
+provider/account/conversation id. Existing malformed pre-v1 web-chat archives
+are not migrated automatically; reimport from the original export after a reset
+or cleanup.
 
 Tool calls and tool results are normalized before archive write where provider
 data is available. For example, Devin tool calls live in
@@ -421,6 +548,9 @@ being appended to assistant prose as synthetic `Grep(...)` text. Canonical
 tool events also carry viewer-facing `category`, `categoryLabel`, `icon`,
 `inputPreview`, and `target` fields so the web viewer can render Bash, edit,
 read, search, web, task, skill, and MCP calls consistently across providers.
+Devin CLI imports also read `tool_call_state` and same-session subagent roots
+from `sessions.db`; existing Devin CLI archives created before parser v2 should
+be rebuilt with `agentlog import --source devin-cli --since all`.
 
 Use `agentlog reset` to stop agentlog, disable autostart, and remove agentlog's
 local home, config, state, cache, logs, and archive objects. Source application
@@ -432,16 +562,34 @@ importer/parser logic to rebuild the local archive without redoing setup:
 
 ```sh
 npm install -g agentel@latest
-agentlog update --yes --since all
+agentlog update --yes
 ```
 
 `agentlog update` preserves `config.json`, redaction settings, web account
-labels, source histories, and recall integrations. It removes derived local
-archive, import, index, cache, and sync bookkeeping, then reimports configured
-local sources from the stored preferences. It does not touch remote sync objects
-by default; use `agentlog sync replace` when the remote should match the rebuilt
-local archive. It also does not rediscover manual ChatGPT/Claude.ai export
-files; reimport those web exports from the original ZIP/folder when needed.
+labels, manually imported ChatGPT/Claude.ai archives, local archives whose
+original source files are no longer present, source histories, and recall
+integrations. It removes derived local archive, import, index, cache, and sync
+bookkeeping, then reimports configured local sources from the stored
+preferences. If a source application has already aged out a transcript, such as
+Claude Code's default local cleanup, the previous agentlog archive is restored
+instead of being silently dropped, with a source/provider/sourceType breakdown.
+When Agentlog has raw backups for missing Claude Code source files, repair them
+explicitly before a clean reimport:
+
+```sh
+agentlog repair claude-code-backups --dry-run
+agentlog repair claude-code-backups --yes
+agentlog update --yes --since all --sources claude
+```
+
+`agentlog doctor` reports preserved unavailable source archives and recommends
+the same repair helper when applicable. The rebuild window comes from the initial
+backfill or an explicit all-source import such as
+`agentlog import --source all --since all`; the fallback for legacy configs is
+`all`. The watcher's rolling
+`imports.defaultSinceDays` is not used by `agentlog update`. It does not touch
+remote sync objects by default; use `agentlog sync replace` when the remote
+should match the rebuilt local archive.
 
 Use `agentlog config` to change `~/.agentlog/config.json` without rerunning the
 init wizard:
@@ -456,7 +604,7 @@ agentlog config set sync.intervalMinutes manual
 agentlog config sources edit
 agentlog config sources set codex-cli,cursor,cline
 agentlog config sources add gemini-cli
-agentlog config sources remove claude-workspace
+agentlog config sources remove claude-cowork
 ```
 
 `agentlog config setup` reopens the preferences parts of init, including what
@@ -467,14 +615,15 @@ with the current config preselected.
 
 ## Import Windows
 
-`agentlog init` starts with interactive setup: choose archive destinations,
-choose the full local archive/cache path, choose whether the local watcher starts
-at login, and install recall commands or skills, then discover sources and
-optionally backfill history.
+`agentlog init` starts with interactive setup: name this device, choose archive
+destinations, choose the full local archive/cache path, choose whether the local
+watcher starts at login, and install recall commands or skills, then discover
+sources and optionally backfill history.
 After backfill, init asks which sources the background watcher should keep
 polling, then offers local OTel bridges for Claude Code, Gemini CLI, and Cline.
 Local archive storage is always enabled; R2, S3, and custom remote sync targets
-can be added as upload-only optional destinations with a device name for the
+can be added as upload-only optional destinations. The configured device name is
+stored in `config.json`, stamped into new session metadata, and used for the
 remote namespace. Discovery and import phases show progress bars while they scan
 local stores.
 
@@ -489,19 +638,42 @@ saved in config and used by later `agentlog import --source all` runs unless
 Default init sources:
 
 - Codex CLI sessions and Codex Desktop sessions from Codex state, shown as
-  separate toggles; Codex SDK jobs are available as an opt-in batch source
-- Claude Code CLI transcripts from `~/.claude/projects`
-- Claude Code Desktop metadata and Claude Workspace/local-agent sessions from
+  separate toggles, including linked Codex subagent child sessions when
+  `thread_spawn_edges` metadata is present; Codex SDK jobs are available as an
+  opt-in batch source
+- Claude Code CLI transcripts from `~/.claude/projects`, including subagent
+  definition snapshots and `subagents/*.jsonl` runs imported as child sessions
+- Claude Code Desktop metadata and Claude Cowork/local-agent sessions from
   the Claude app data, shown as separate toggles
 - Gemini CLI saved chats/checkpoints under `~/.gemini/tmp`, plus session/export JSONL stores with tool, usage, and checkpoint metadata
-- Antigravity task/plan/walkthrough artifacts under `~/.gemini/antigravity/brain`, plus partial trajectory summaries from Antigravity app state when no readable artifacts exist
-- Devin for Terminal sessions from `~/.local/share/devin/cli/sessions.db`
+- Antigravity transcript logs and task/plan/walkthrough artifacts under `~/.gemini/antigravity/brain`, including linked subagent child sessions when `INVOKE_SUBAGENT` steps point at spawned conversations, plus partial trajectory summaries from Antigravity app state when no readable artifacts exist
+- Antigravity CLI sessions (the Gemini CLI successor) from `~/.gemini/antigravity-cli/brain`
+  transcript logs and artifacts, with workspace attribution from the CLI's
+  `history.jsonl` prompt log, imported as a separate source from the 2.0 app
+- Antigravity IDE sessions from `~/.gemini/antigravity-ide/brain`, imported as
+  a third separate source; stale migration copies of 2.0 conversations are skipped
+- Devin for Terminal sessions from `~/.local/share/devin/cli/sessions.db`,
+  including tool-call state, visible thinking-duration traces, and same-session
+  subagent roots imported as linked child sessions
+- Devin Desktop ACP event logs from `~/Library/Application Support/Devin/User/acp-events`, indexed by Devin's global `state.vscdb`
 - Cursor chats from older workspace `state.vscdb` SQLite stores and global
   `cursorDiskKV` Composer/Agent rows, including `aiService` prompt/generation
   fallbacks, raw SQLite salvage from Cursor global/workspace backups and WAL
   files, conservative matching of raw assistant/tool companion fragments back
   to same-project workspace sessions, duplicate prefix pruning, and newer
-  `~/.cursor/projects/<project>/agent-transcripts` files
+  `~/.cursor/projects/<project>/agent-transcripts` files, including subagent
+  child transcripts when Cursor writes `subagents/` folders
+- GitHub Copilot CLI sessions from `~/.copilot/session-state/<id>/events.jsonl`
+  with workspace metadata, tool calls, model changes, and per-model token/premium-request
+  usage from clean-shutdown events
+- Factory Droid JSONL transcripts from `~/.factory/sessions` (legacy flat and
+  per-project layouts), joined with `.settings.json` sidecars for model, token
+  usage, Factory credits, and subagent attribution
+- Grok Build ACP update streams from `~/.grok/sessions/<encoded-cwd>/<id>/updates.jsonl`,
+  with chunked message reassembly plus `summary.json`/`signals.json` rollups
+- pi coding agent JSONL session trees from `~/.pi/agent/sessions` (v1–v3 formats),
+  including branches, compactions, per-message usage with dollar cost, and
+  `!` shell executions
 - Cline task folders from VS Code/JetBrains globalStorage, including checkpoint diffs when present
 - OpenCode CLI/core SQLite and project JSON storage under `~/.local/share/opencode`, plus OpenCode Desktop app storage and Web sessions when present
 - Aider repo-local `.aider.chat.history.md` transcripts, with `.aider.llm.history`
@@ -509,14 +681,21 @@ Default init sources:
 
 The Claude Code desktop registry mostly stores metadata pointing back to the
 standard Claude Code transcript, so agentlog imports the transcript when it exists
-and only imports Claude Workspace sessions that contain actual prompt
+and only imports Claude Cowork sessions that contain actual prompt
 content.
 
-Windsurf local cache scanning is disabled for now. Current Cascade transcripts
-are encrypted binary stores, so agentlog can detect that a session exists but
-cannot archive readable conversation text from that cache. Use Windsurf's
-"Download trajectory" Markdown export with `agentlog import windsurf <path>` to
-archive readable Cascade output. If you bulk-export multiple trajectories to a
+Windsurf local imports read Cascade plan artifacts from
+`~/.codeium/windsurf/brain` when present and preserve matching
+`~/.codeium/windsurf/cascade/*.pb` files as raw sources, but those local
+protobufs are not decoded into full transcripts. Agentlog also reads Windsurf's
+global metadata cache to identify protobuf-only conversations by title, working
+directory, and timestamp. Protobuf-only conversations are archived as
+zero-message repair stubs so they are visible in the web viewer but excluded
+from recall/search indexing. Open a stub in `agentlog web` to copy its repair
+token, then import the Windsurf "Download trajectory" Markdown export with
+`agentlog import windsurf --claim <token> <path-to-downloaded-trajectory.md>`.
+Unclaimed exports can still be imported directly with
+`agentlog import windsurf <path>`. If you bulk-export multiple trajectories to a
 folder, import the folder directly, for example
 `agentlog import windsurf ~/windsurf-cascade-export`.
 
@@ -538,20 +717,22 @@ The same choices can be run directly:
 
 ```sh
 agentlog import --source all --since all
-agentlog import --sources codex-cli,codex-desktop,claude,claude-code-desktop,claude-workspace,gemini-cli,antigravity,devin-cli,cursor,cline,opencode-cli,opencode-desktop,opencode-web,aider --since all
+agentlog import --sources codex-cli,codex-desktop,claude,claude-code-desktop,claude-cowork,gemini-cli,antigravity,devin-cli,devin-desktop,windsurf,cursor,cline,opencode-cli,opencode-desktop,opencode-web,aider --since all
 agentlog import --source codex-desktop --since 90d
 agentlog import --source codex-cli --since 30d
 agentlog import --source codex-sdk --since all
 agentlog import chatgpt
 agentlog import claude-web
 agentlog import chatgpt ~/Downloads/chatgpt-export.zip --username you@example.com
+agentlog import chatgpt "~/Downloads/OpenAI-export/User Online Activity" --username you@example.com
 agentlog import claude-web ~/Downloads/claude-export --username you --display-name "Personal Claude"
 agentlog import --source claude --since 30d
 agentlog import --source claude-code-desktop --since all
-agentlog import --source claude-workspace --since all
+agentlog import --source claude-cowork --since all
 agentlog import --source gemini-cli --since all
 agentlog import --source antigravity --since all
 agentlog import --source devin-cli --since all
+agentlog import --source devin-desktop --since all
 agentlog import --source cursor --since all
 agentlog import --source cursor --since all --explain-skips
 agentlog import --source cline --since all