agentel 0.2.4 → 0.2.6

package/README.md

@@ -9,8 +9,8 @@ Core capabilities:
 - markdown-primary, redacted local archive under `~/.agentlog/data/agentlog/`
 - 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, ChatGPT export, Claude Code CLI, Claude Code
-  Desktop, Claude Workspace, Claude.ai export, Gemini CLI, Antigravity,
+- 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
 - `agentlog-recall` MCP stdio server exposing `search_past_sessions`
@@ -41,7 +41,7 @@ ref for repeatable installs:
 ```sh
 npm install -g brianlzhou/agentlog
 # or
-npm install -g brianlzhou/agentlog#v0.2.4
+npm install -g brianlzhou/agentlog#v0.2.6
 agentlog init
 ```
 
@@ -77,6 +77,8 @@ npm test
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js init --yes --skip-import --no-autostart --no-claude --no-recall --no-telemetry
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source codex-cli --since 30d
 AGENTLOG_HOME=/tmp/agentlog-demo node ./bin/agentlog.js import --source codex-desktop --since all
+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 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
@@ -219,7 +221,7 @@ 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`,
-`chatgpt`), Anthropic (`claude`, `claude-code-desktop`, `claude-workspace`,
+`codex-sdk`, `chatgpt`), Anthropic (`claude`, `claude-code-desktop`, `claude-workspace`,
 `claude-web`, `claude-sdk`), Google (`gemini-cli`, `antigravity`), Cognition
 (`devin-cli`), then other local tools (`cursor`, `cline`, `opencode`,
 `aider`).
@@ -234,7 +236,7 @@ still run `agentlog import --source all` for a one-time catch-up,
 `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, and Aider. New configs still support
+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
@@ -363,22 +365,28 @@ 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.v1` canonical event shape:
+`events.jsonl` uses the local `agentlog.events.v2` canonical event shape:
 `session.started`, `prompt.submitted`, `response.generated`, `tool.called`, and
-`tool.completed`. 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
+`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.
 
 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. Cursor sessions
+each session, and the web stats view reads those fields directly. 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
@@ -388,10 +396,12 @@ parts. During pre-v1 development, if those stats fields or parser semantics
 change, rebuild the local archive with
 `agentlog update --yes --since all`.
 
-ChatGPT and Claude.ai web exports are imported manually from an official `.zip`,
-an unzipped export folder, or a direct JSON file. These imports are stored as
-local scoped web-chat archives and displayed through virtual conversation roots
-such as `[chatgpt]conversations/<account-id>` and
+ChatGPT and Claude.ai are manual export providers. Run `agentlog import chatgpt`
+or `agentlog import claude-web` for current export instructions; after the
+provider emails a download link, pass the official `.zip`, unzipped export
+folder, or direct JSON file back to agentlog. These imports are stored as local
+scoped web-chat archives and displayed through virtual conversation roots such
+as `[chatgpt]conversations/<account-id>` and
 `[claude]conversations/<account-id>/<project>`. The importer records account
 metadata in `~/.agentlog/state/web-accounts.json`; use
 `agentlog import accounts list` to inspect mappings and
@@ -471,15 +481,15 @@ local stores.
 After discovery, init offers a checkbox-style source picker. Rows marked `[x]`
 are selected; type one or more row numbers, such as `1 3 8`, to toggle sources
 on or off, then press Enter with no input to accept the current selection.
-Claude SDK jobs are shown as a separate opt-in source because batch SDK traffic
-can exceed interactive sessions. The selected sources are saved in config and
-used by later `agentlog import --source all` runs unless `--sources` is provided
-explicitly.
+Codex SDK jobs and Claude SDK jobs are shown as separate opt-in sources because
+batch SDK traffic can exceed interactive sessions. The selected sources are
+saved in config and used by later `agentlog import --source all` runs unless
+`--sources` is provided explicitly.
 
 Default init sources:
 
 - Codex CLI sessions and Codex Desktop sessions from Codex state, shown as
-  separate toggles
+  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
   the Claude app data, shown as separate toggles
@@ -493,7 +503,7 @@ Default init sources:
   to same-project workspace sessions, duplicate prefix pruning, and newer
   `~/.cursor/projects/<project>/agent-transcripts` files
 - Cline task folders from VS Code/JetBrains globalStorage, including checkpoint diffs when present
-- OpenCode JSON session/message/part storage under `~/.local/share/opencode`
+- 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`
   model/usage enrichment, `.aider.input.history` backups, and matching auto-commit diffs
 
@@ -528,9 +538,12 @@ 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,aider --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 --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 claude-web ~/Downloads/claude-export --username you --display-name "Personal Claude"
 agentlog import --source claude --since 30d

package/docs/code-reference.md

@@ -99,11 +99,12 @@ low-signal filtering.
 Exports:
 
 - `CANONICAL_EVENT_SCHEMA_VERSION`: current event schema id,
-  `agentlog.events.v1`.
+  `agentlog.events.v2`.
 - `EVENT_KINDS`: constants for `session.started`, `prompt.submitted`,
   `response.generated`, `tool.called`, and `tool.completed`.
 - `normalizeSessionEvents(session, messages, options)`: maps transcript
-  messages into canonical events.
+  messages into canonical events and links `tool.completed` events to matching
+  `tool.called` parents.
 - `messageToCanonicalEvents(message, session, options)`: maps one message into
   zero or more canonical events.
 - `stableEventId(sessionId, messageIndex, kind, ordinal, content)`: creates a
@@ -219,7 +220,9 @@ Command handlers:
 - `integrationsCommand(args, env)`: canonical integration command group for
   recall surfaces.
 - `mcpCommand(args, flags, env)`: canonical MCP server command group.
-- `importCommand(args, flags, env)`: imports local sources or web export files.
+- `importCommand(args, flags, env)`: imports local sources and downloaded web
+  export files, or prints manual ChatGPT/Claude.ai export instructions when no
+  web export path is supplied.
 - `recallCommand(args, env)`: handles recall server/install/show/reindex flows.
 - `showRecallSession(sessionId, env)`: prints a session through the recall path.
 - `showCommand(sessionId, flags, env)`: prints, opens, or JSON-serializes a
@@ -555,9 +558,9 @@ Import dispatch and generic providers:
   Desktop/Workspace metadata and audit sessions.
 - `matchesImportedSessionRepo(session, repo, wantedRepos)`: checks repo filters
   for sessions with repo or scope attribution.
-- `importCodexProvider(provider, since, options, env)`: imports Codex CLI or
-  Desktop threads from state DB, rollout files, and Codex supplementary
-  summaries when available.
+- `importCodexProvider(provider, since, options, env)`: imports Codex CLI,
+  Desktop, or opt-in exec/SDK threads from state DB, rollout files, and Codex
+  supplementary summaries when available.
 - `importCursorProvider(provider, since, options, env)`: imports Cursor SQLite
   and Cursor project transcript sessions; supervisor calls set
   `cursorRecovery=false` to skip raw SQLite salvage/backfill.
@@ -581,7 +584,10 @@ Generic parsing helpers:
   shapes.
 - `extractClaudeMessagesFromEvent(event, provider, context)`: Claude Code/SDK
   JSONL parser for text, thinking, tool calls/results, model, request id, and
-  usage metadata, including `apply_patch` shell calls promoted to edit diffs.
+  usage metadata, including lineage fields, agent/slug/tool-use ids, MCP
+  structured content, API error metadata, richer Claude usage extras, Remote
+  Control lifecycle context messages, tool result name repair from prior
+  `tool_use` ids, and `apply_patch` shell calls promoted to edit diffs.
 - `updateClaudeParseContext(event, provider, context)`: keeps Claude model,
   session, and cwd context while parsing JSONL records.
 - `extractCodexSummaryMessage(event, provider)`: extracts readable Codex
@@ -599,6 +605,8 @@ Generic parsing helpers:
   summary for tool-call metadata.
 - `normalizeWebConversations(provider, data)`: normalizes web export
   conversations.
+- `webExportInstructions(source)`: returns the provider-specific manual export
+  instruction payload used by ChatGPT and Claude.ai import commands.
 - `chatgptMessages(conversation)`: parses ChatGPT export conversation nodes
   and attaches provider or estimated message usage.
 - `claudeMessages(conversation)`: parses Claude.ai export messages, separating
@@ -610,8 +618,8 @@ Discovery and summary helpers:
 
 - `summarizeFiles(files)`: counts files, projects, and oldest mtime.
 - `summarizeCodex(env, source)`: summary wrapper for Codex threads.
-- `summarizeCodexThreads(allThreads, source)`: summarizes Codex CLI/Desktop
-  counts.
+- `summarizeCodexThreads(allThreads, source)`: summarizes Codex CLI/Desktop or
+  opt-in exec/SDK counts.
 - `summarizeClaude()`: summarizes Claude Code CLI files.
 - `summarizeClaudeScan(scan)`: formats Claude scan results.
 - `summarizeClaudeSdk()`: summarizes Claude SDK job files.
@@ -643,7 +651,8 @@ Source location and file helpers:
 - `scanClaudeProjectFiles(options)`: scans and classifies Claude project JSONL.
 - `isClaudeConversationFile(file)`: tests whether a Claude file is interactive.
 - `classifyClaudeFile(file)`: classifies Claude JSONL as conversation, SDK job,
-  or other.
+  or other; Remote Control `sdk-cli` transcripts with Remote Control deferred
+  tool names are kept with interactive Claude Code conversations.
 - `readInitialLines(file, maxLines, maxBytes)`: reads a bounded prefix of a
   large JSONL file.
 - `readCodexThreads(env)`: queries Codex state DB for top-level threads and
@@ -790,13 +799,13 @@ Cline helpers:
 
 OpenCode helpers:
 
-- `openCodeDatabaseFiles(env)`: resolves normalized OpenCode `opencode.db`
+- `openCodeDatabaseFiles(env, options)`: resolves normalized OpenCode `opencode.db`
   files from data-root defaults and database override env vars.
-- `openCodeStorageRoots(env)`: resolves global and project-scoped OpenCode
+- `openCodeStorageRoots(env, options)`: resolves global and project-scoped OpenCode
   `storage` directories, plus override env vars.
 - `readOpenCodeSqliteSessionsFromDb(dbPath)`: reads the `session`, `message`,
   `part`, and `project` tables from `opencode.db` and emits
-  `opencode-sqlite-history` sessions.
+  desktop or explicitly configured SQLite sessions.
 - `openCodeSessionFiles(root)`: finds session JSON files.
 - `openCodeMessageSessionIds(root)`: finds message-only OpenCode session
   directories when session metadata is missing.

package/docs/history-source-handling.md

@@ -77,6 +77,13 @@ without a specific archived model group as `claude-unknown`, because the model
 family is still known. Favorite-model stats still use known archived model
 metadata.
 
+SDK source types (`codex-sdk-history` and `claude-sdk-history`) are excluded from
+the primary stats totals, daily activity, streaks, folder rankings, and
+provider/model/company charts by default. The stats payload still exposes their
+own SDK aggregate fields plus `split_stats.sdk`, and the web view renders an SDK
+jobs card and heatmap. This keeps high-volume batch automation searchable and
+auditable without letting it swamp interactive usage stats.
+
 Cursor sessions that still lack provider-reported usage get a separate
 `estimatedUsage` metadata field instead of synthetic `usage`. The estimate uses
 empirical per-assistant-turn Cursor rates by model family, with visible
@@ -130,7 +137,7 @@ agentlog does not blindly copy entire source directories.
 ## Canonical Events
 
 `events.jsonl` is the provider-independent archive/search substrate. It uses
-schema version `agentlog.events.v1` and these event kinds:
+schema version `agentlog.events.v2` and these event kinds:
 
 - `session.started`
 - `prompt.submitted`
@@ -150,9 +157,14 @@ events add viewer-facing display metadata:
 - `metadata.toolCalls[]`: `id`, `name`, `displayName`, `category`, `title`,
   `status`, `argument`, `rawInputSummary`, `inputPreview`, `target`, `icon`,
   `categoryLabel`, and `provider`.
-- `metadata.toolResult`: `provider`, `kind`, `title`, `summary`, `output`,
-  `lineCount`, `collapsed`, `category`, `categoryLabel`, `icon`, and optional
-  `status`.
+- `metadata.toolResult`: `id`, `name`, `provider`, `kind`, `title`, `summary`,
+  `output`, `lineCount`, `collapsed`, `category`, `categoryLabel`, `icon`, and
+  optional `status`.
+
+`tool.completed.parentEventId` links to the matching `tool.called` event when a
+provider exposes stable ids or matching tool names. When those are absent,
+canonical event derivation falls back to the next unmatched tool call so streams
+such as Devin CLI still preserve the call/result relationship.
 
 The viewer reads canonical events or normalized metadata first. Text patterns
 such as `Grep(...)` are legacy fallback only.
@@ -183,30 +195,36 @@ package-prefixed scheme.
 
 | Source type | Version |
 | --- | --- |
-| `codex-cli-history` | `0.2.4.0` |
-| `codex-desktop-history` | `0.2.4.0` |
-| `cli-history` | `0.2.4.0` |
-| `claude-sdk-history` | `0.2.4.0` |
-| `claude-code-desktop-metadata` | `0.2.4.0` |
-| `claude-workspace-desktop` | `0.2.4.0` |
-| `cursor-workspace-sqlite` | `0.2.4.0` |
-| `cursor-global-sqlite` | `0.2.4.0` |
-| `cursor-raw-sqlite-salvage` | `0.2.4.0` |
-| `cursor-agent-transcripts` | `0.2.4.0` |
-| `devin-cli-history` | `0.2.4.0` |
-| `gemini-cli-history` | `0.2.4.0` |
-| `cline-task-history` | `0.2.4.0` |
-| `opencode-history` | `0.2.4.0` |
-| `opencode-sqlite-history` | `0.2.4.0` |
-| `aider-chat-history` | `0.2.4.0` |
-| `antigravity-history` | `0.2.4.0` |
-| `antigravity-trajectory-summary` | `0.2.4.0` |
-| `windsurf-trajectory-export` | `0.2.4.0` |
-| `web-chat-export` | `0.2.4.0` |
-| `chatgpt-export` | `0.2.4.0` |
-| `claude-web-export` | `0.2.4.0` |
-| `claude-web-memory` | `0.2.4.0` |
-| `import` | `0.2.4.0` |
+| `codex-cli-history` | `0.2.6.0` |
+| `codex-desktop-history` | `0.2.6.0` |
+| `codex-sdk-history` | `0.2.6.0` |
+| `cli-history` | `0.2.6.0` |
+| `claude-sdk-history` | `0.2.6.0` |
+| `claude-code-desktop-metadata` | `0.2.6.0` |
+| `claude-workspace-desktop` | `0.2.6.0` |
+| `cursor-workspace-sqlite` | `0.2.6.0` |
+| `cursor-global-sqlite` | `0.2.6.0` |
+| `cursor-raw-sqlite-salvage` | `0.2.6.0` |
+| `cursor-agent-transcripts` | `0.2.6.0` |
+| `devin-cli-history` | `0.2.6.0` |
+| `gemini-cli-history` | `0.2.6.0` |
+| `cline-task-history` | `0.2.6.0` |
+| `opencode-cli-history` | `0.2.6.0` |
+| `opencode-cli-sqlite-history` | `0.2.6.0` |
+| `opencode-desktop-history` | `0.2.6.0` |
+| `opencode-desktop-sqlite-history` | `0.2.6.0` |
+| `opencode-web-sqlite-history` | `0.2.6.0` |
+| `opencode-history` | `0.2.6.0` |
+| `opencode-sqlite-history` | `0.2.6.0` |
+| `aider-chat-history` | `0.2.6.0` |
+| `antigravity-history` | `0.2.6.0` |
+| `antigravity-trajectory-summary` | `0.2.6.0` |
+| `windsurf-trajectory-export` | `0.2.6.0` |
+| `web-chat-export` | `0.2.6.0` |
+| `chatgpt-export` | `0.2.6.0` |
+| `claude-web-export` | `0.2.6.0` |
+| `claude-web-memory` | `0.2.6.0` |
+| `import` | `0.2.6.0` |
 
 `cursor-sqlite-history` and `antigravity-brain` are compatibility aliases for
 older labels. Fingerprints include the parser version prefix, so changing the
@@ -244,20 +262,21 @@ real-world query should reliably find a representative archived session.
 
 The setup UI, import defaults, and history source filters use this grouped order:
 
-1. OpenAI: Codex CLI, Codex Desktop, ChatGPT
+1. OpenAI: Codex CLI, Codex Desktop, Codex SDK jobs, ChatGPT
 2. Anthropic: Claude Code CLI, Claude Code Desktop, Claude Workspace,
    Claude.ai, Claude SDK jobs
 3. Google: Gemini CLI, Antigravity
 4. Cognition: Devin CLI
-5. Other: Cursor, Cline, OpenCode, Aider
+5. Other: Cursor, Cline, OpenCode CLI, OpenCode Desktop, OpenCode Web, Aider
 
 `agentlog import --source all` uses the default import order from
 `src/sources.js`: `codex-cli`, `codex-desktop`, `claude`,
 `claude-code-desktop`, `claude-workspace`, `gemini-cli`, `antigravity`,
-`devin-cli`, `cursor`, `cline`, `opencode`, `aider`. Claude SDK jobs are
-intentionally opt-in. Windsurf local cache scanning is disabled for now because
-current Cascade transcripts are encrypted binary stores, but downloaded
-trajectory Markdown exports are importable with an explicit path.
+`devin-cli`, `cursor`, `cline`, `opencode-cli`, `opencode-desktop`,
+`opencode-web`, `aider`. Codex SDK jobs and Claude SDK jobs are intentionally
+opt-in. Windsurf local cache scanning is disabled for now because current
+Cascade transcripts are encrypted binary stores, but downloaded trajectory
+Markdown exports are importable with an explicit path.
 
 The background watcher polls the watcher source list selected near the end of
 `agentlog init`. New configs still support `imports.autoDiscoverSources=true`,
@@ -321,6 +340,7 @@ stable local command for the archived source.
 | --- | --- | --- |
 | Codex CLI | `codex resume <session-id>` | Uses the Codex thread id from `~/.codex/state_5.sqlite`. |
 | Codex Desktop | `codex resume <session-id>` | Uses the same Codex thread id. Codex decides whether the resumed session opens in the terminal flow. |
+| Codex SDK jobs | No interactive resume command. | These are Codex `exec`/SDK-style batch runs. |
 | Claude Code CLI | `claude -r <session-id>` | Uses the Claude Code JSONL session id. |
 | Devin CLI | `devin -r <session-id>` | agentlog archives these as `devin-<session-id>` and strips that prefix for the resume command, for example `devin -r selective-lotus`. |
 | Claude Code Desktop | No stable local resume command known. | Use Claude's own desktop/history surface or `agentlog show <session-id>`. |
@@ -383,17 +403,38 @@ rollout parser as Codex CLI. The only distinction is the `threads.source` value.
 This is why the web source dropdown can split Codex CLI and Codex Desktop even
 though both archive under the same `codex` provider.
 
+## Codex SDK Jobs
+
+- Import selector: `codex-sdk`
+- Provider: `codex`
+- Source type: `codex-sdk-history`
+- Primary store: `~/.codex/state_5.sqlite`
+- Session files: rollout paths referenced by the `threads` table
+- Source split: `threads.source = "exec"`
+- Overrides: same as Codex CLI
+
+Codex SDK jobs use the same rollout parser as Codex CLI/Desktop, but they are
+shown as a separate opt-in source because `codex exec` batch traffic can produce
+hundreds or thousands of short prompt/response sessions. They are useful for
+programmatic jobs such as Siftly bookmark enrichment and Polymarket vote
+labeling, but should not be silently mixed into the default interactive import.
+When imported, these sessions remain searchable, but the stats view keeps them
+in the separate SDK jobs aggregate instead of primary interactive totals.
+
 ## ChatGPT Export
 
-- Import command: `agentlog import chatgpt --file <path> [--scope local|team]`
+- Instructions command: `agentlog import chatgpt`
+- Import command: `agentlog import chatgpt <path> [--scope local|team]`
 - Provider: `chatgpt`
 - Source type: `chatgpt-export`
 - Source file: ChatGPT JSON export or ZIP containing a JSON export
 - Default archive scope: `chatgpt`
 
-ChatGPT is not scanned automatically from a desktop app. The user provides an
-official export file. ZIP imports prefer `conversations.json`, then another JSON
-file with `chat` in the name, then the first JSON file in the ZIP.
+ChatGPT is not scanned automatically from a desktop app. The import command
+without a path prints official export instructions for OpenAI's Privacy Portal
+and ChatGPT Data Controls. The user then provides the downloaded official export
+file. ZIP imports prefer `conversations.json`, then another JSON file with
+`chat` in the name, then the first JSON file in the ZIP.
 
 For OpenAI export mappings, agentlog reads each node message, normalizes
 `author.role`, extracts `content.parts`, and uses `create_time` or `update_time`
@@ -413,17 +454,66 @@ usage as estimated.
 Claude Code CLI files are discovered under `~/.claude/projects`. Each JSONL file
 is classified before import. A file is treated as an interactive conversation
 when the initial records include `type = "user"` or `type = "assistant"` with a
-`message` object and no `entrypoint = "sdk-cli"`.
+`message` object and no `entrypoint = "sdk-cli"`. Remote Control transcripts
+also use `entrypoint = "sdk-cli"`, but include a deferred tool delta with
+Remote Control tool names such as `RemoteTrigger`, `TaskOutput`, `TaskStop`,
+`PushNotification`, `AskUserQuestion`, task tools, cron tools, or monitor tools;
+those are imported as interactive Claude Code conversations rather than SDK
+jobs.
 
 The Claude-specific JSONL parser extracts session ids, titles, cwd fields,
 message roles, text content, timestamps, assistant thinking summaries,
 `tool_use` calls, `tool_result` outputs, model, request id, stop status, and
-token usage. Tool calls and results are normalized into the shared
+token usage. It also preserves Claude JSONL lineage fields (`uuid`,
+`parentUuid`, `logicalParentUuid`, `leafUuid`, `promptId`,
+`sourceToolAssistantUUID`, `sourceToolUseID`, `parentToolUseID`, `toolUseID`,
+`agentId`, `slug`, `isSidechain`), execution metadata (`entrypoint`,
+`userType`, Claude Code version, git branch, permission mode), attribution skill,
+MCP structured-content metadata, API error metadata, Remote Control
+queue/tool-surface summaries, and richer usage extras such as service tier,
+speed, server-tool usage, and cache creation detail.
+Tool calls and results are normalized into the shared
 `metadata.toolCalls[]`, `metadata.toolResult`, and `metadata.usage` shapes.
 Bash or shell tool calls that invoke `apply_patch` are reclassified as edit
-calls and retain the patch text under `arguments.diff`. Repo attribution is
-computed from the parsed `cwd`; if no cwd is present the session is archived
-under an uncategorized provider scope.
+calls and retain the patch text under `arguments.diff`.
+Tool results are matched back to prior `tool_use` ids when possible so result
+cards inherit the tool name instead of displaying only the raw tool-use id.
+Remote Control lifecycle records are also converted into provider-generated
+system/context messages for queue operations, deferred tool catalog changes,
+MCP instruction updates, skill listings, nested memories, queued commands,
+command permissions, edited text files, date changes, max-turn notices,
+file-history snapshots, hook progress, and stop-hook summaries. These messages
+carry compact metadata and previews rather than copying large attachment bodies;
+the byte-perfect source records remain in the raw archive. Session summaries
+also include Remote Control attachment counts/details, available tool names,
+MCP server names, queue timing/content, agent ids, slugs, API error counts, and
+MCP structured-content counts.
+
+When the Claude desktop app has a matching
+`~/Library/Application Support/Claude/claude-code-sessions/**/local_*.json`
+record with `cliSessionId`, the CLI importer uses that sidecar's generated
+`title` and `originCwd` while preserving both the transcript and sidecar in raw
+archive storage. This is the source of Claude's readable auto names such as
+"Fix cursor import paths handling"; the transcript JSONL itself may only contain
+the user prompt ("Can you fix these?"). Without a sidecar title, the importer
+uses Claude JSONL `ai-title` events when present, then falls back to the first
+real user prompt. Repo attribution uses sidecar
+`originCwd` when available, otherwise the parsed `cwd`; Claude-created
+`.claude/worktrees/<name>` directories are attributed to their parent project
+when that project still exists, even if the temporary worktree has been deleted.
+The original worktree path remains stored as `cwd`. If no cwd is present the
+session is archived under an uncategorized provider scope.
+
+A sanitized subset of sidecar metadata is also copied into
+`metadata.sessionSummary.claudeCodeSidecar`: the app/CLI session ids, title
+source, cwd/origin cwd, worktree path/name, branch names, created/last-activity
+timestamps, model/effort, permission modes, completed turn count, archive state,
+enabled MCP tool count, MCP server names, and sidecar source path. The sidecar
+`model` also contributes to normalized `models[]` through `sessionSummary`
+model usage. Full MCP configuration remains available only through raw
+preservation rather than promoted metadata. After this parser behavior changes,
+run `agentlog update --yes --since all` or `agentlog import claude --since all`
+to rebuild existing local Claude Code archives.
 
 ## Claude SDK Jobs
 
@@ -439,7 +529,8 @@ sessions. agentlog separates them by scanning the initial JSONL records for
 batch runs can be much higher volume than interactive sessions.
 
 When imported, SDK jobs use the same Claude-specific JSONL parser as Claude Code
-CLI but archive under `claude_sdk`.
+CLI but archive under `claude_sdk`. Stats keep them in the separate SDK jobs
+aggregate instead of primary interactive totals.
 
 ## Claude Code Desktop
 
@@ -491,16 +582,18 @@ uncategorized.
 
 ## Claude.ai Export
 
-- Import command: `agentlog import claude-web --file <path> [--scope local|team]`
+- Instructions command: `agentlog import claude-web`
+- Import command: `agentlog import claude-web <path> [--scope local|team]`
 - Provider: `claude_web`
 - Source types: `claude-web-export`, `claude-web-memory`
 - Source file: Claude.ai JSON export or ZIP containing a JSON export
 - Default archive scope: `claude_web`
 
-Claude.ai is not scanned automatically from the desktop app. The user provides
-an official export file. agentlog reads `chat_messages`, `messages`, or
-`children`, normalizes sender/role fields, extracts text content, and uses
-`created_at`, `updated_at`, or `timestamp`.
+Claude.ai is not scanned automatically from the desktop app. The import command
+without a path prints official export instructions for Claude Settings >
+Privacy. The user then provides the downloaded official export file. agentlog
+reads `chat_messages`, `messages`, or `children`, normalizes sender/role fields,
+extracts text content, and uses `created_at`, `updated_at`, or `timestamp`.
 For official `conversations.json` exports, the top-level conversation `summary`
 is archived as both `sessionSummary.summary` and a supplementary transcript row.
 Assistant messages prefer structured `content[]` parts over the legacy top-level
@@ -526,7 +619,7 @@ are marked `recovered-time-unknown` in history views instead of being displayed
 as if they happened at import time. This keeps project folders from implying
 that account-level conversations were reliably tagged to Claude projects when
 the export did not preserve that relationship. Re-run
-`agentlog import claude-web --file <path>` after importing an export that
+`agentlog import claude-web <path>` after importing an export that
 contains conversation project ids or after Claude web parser semantics change.
 
 Like ChatGPT export imports, Claude.ai imports are scope-based by default because
@@ -834,18 +927,25 @@ original checkpoint files remain in raw backups.
 
 ## OpenCode
 
-- Import selector: `opencode`
+- Import selectors: `opencode-cli`, `opencode-desktop`, `opencode-web`, or `opencode` for all three
 - Provider: `opencode`
 - Source types:
-  - `opencode-sqlite-history` for the normalized `opencode.db` store
-  - `opencode-history` for the JSON `storage/` layout
-- Primary data root: `~/.local/share/opencode`
-- Alternate macOS data root: `~/Library/Application Support/opencode`
-- Additional desktop roots:
+  - `opencode-cli-history` for CLI JSON `storage/` sessions
+  - `opencode-cli-sqlite-history` for the CLI/core normalized `~/.local/share/opencode/opencode.db` store
+  - `opencode-desktop-history` for desktop/app JSON `storage/` sessions
+  - `opencode-desktop-sqlite-history` for the desktop/app normalized `opencode.db` store
+  - `opencode-web-sqlite-history` for web sessions in the shared normalized SQLite store
+  - `opencode-history` and `opencode-sqlite-history` for older or explicitly configured archives
+- CLI data root: `~/.local/share/opencode`
+- Desktop/app data roots:
+  - `~/Library/Application Support/ai.opencode.desktop`
+  - `~/Library/Application Support/opencode`
   - `~/.local/share/ai.opencode.app`
   - `~/Library/Application Support/ai.opencode.app`
 - SQLite database:
-  - `opencode.db`
+  - CLI/core root: `~/.local/share/opencode/opencode.db`
+  - desktop/app roots: `opencode.db`
+  - explicit overrides only: `AGENTLOG_OPENCODE_DB`, `AGENTLOG_OPENCODE_DATABASE`, `OPENCODE_DB`, or `AGENTLOG_OPENCODE_DATA_DIR`
 - Storage roots:
   - `~/.local/share/opencode/storage`
   - `~/.local/share/opencode/project/<project-slug>/storage`
@@ -862,8 +962,17 @@ original checkpoint files remain in raw backups.
   - `AGENTLOG_OPENCODE_STORAGE_DIR` or `AGENTLOG_OPENCODE_STORAGE_ROOTS`
     points directly at one or more `storage` directories.
 
-agentlog first reads OpenCode's normalized SQLite store when `opencode.db` is
-present. The `session`, `message`, `part`, and `project` tables provide session
+agentlog reads OpenCode's normalized SQLite store from the shared core
+`~/.local/share/opencode/opencode.db` root, desktop/app roots, or when a
+database is explicitly configured. The shared core database can contain sessions
+created by Desktop, CLI, and Web clients, so agentlog classifies each SQLite
+session row individually. Desktop sessions are identified by session ids in
+OpenCode Desktop sidecar state such as `ai.opencode.desktop/*.dat`; sub-sessions
+inherit Desktop classification from a Desktop parent. CLI sessions are
+identified by session-level `agent` or `model` metadata. Remaining non-`local`
+shared core rows are labeled as Web sessions. Rows without reliable client
+evidence stay on the legacy `opencode-sqlite-history` source type. The
+`session`, `message`, `part`, and `project` tables provide session
 metadata, working directory, user/assistant messages, reasoning text, tool
 calls, tool outputs, model/provider ids, cost, and token usage. Because the
 database is a multi-session source, raw preservation stores it as a shared raw
@@ -879,7 +988,11 @@ If a session metadata file is missing but `storage/message/<session-id>/` and
 session from those message and part files.
 
 When both SQLite and JSON records exist for the same OpenCode session id,
-agentlog prefers `opencode-sqlite-history` and merges the raw source file list.
+agentlog prefers SQLite source types such as `opencode-cli-sqlite-history`
+and merges the raw source file list.
+After this source handling change, run `agentlog import --source opencode
+--since all` or `agentlog update --yes --since all` to rebuild existing local
+OpenCode archives with the corrected CLI/Desktop/Web split.
 
 When `session_diff/<session-id>.json` is present, agentlog adds a supplementary
 edit tool call with the diff payload. Unified diff text is rendered inline in

package/docs/release.md

@@ -30,7 +30,6 @@ npm run smoke:pack
 - selected docs
 - `README.md`
 - `LICENSE`
-- `agentlog-spec.md`
 - `package.json`
 
 It should not include local settings, test fixtures, `.git`, `.claude`, logs,
@@ -65,5 +64,5 @@ After tagging and pushing the release, sanity-check both public install forms:
 
 ```sh
 npm install -g agentel
-npm install -g brianlzhou/agentlog#v0.2.4
+npm install -g brianlzhou/agentlog#v0.2.6
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentel",
-  "version": "0.2.4",
+  "version": "0.2.6",
   "description": "Local-first archive and recall layer for agent coding sessions.",
   "type": "commonjs",
   "license": "MIT",

package/src/archive.js

@@ -1060,7 +1060,7 @@ function ensureConversationMarkdown(session, env = process.env) {
   return conversationPath;
 }
 
-const VIEW_SCHEMA_VERSION = 2;
+const VIEW_SCHEMA_VERSION = 3;
 
 function sessionViewPathFromMetadata(metadataPath) {
   if (!metadataPath) return "";