# Import coverage by company and product > Compare exact import routes, product boundaries, verification gaps, and unsupported harnesses. Reviewed 2026-09-29. This inventory accounts for **79 registered source selectors**, **127 source formats**, **5 browser providers**, and **223 product or surface entries** across **74 company or project groups**. Implemented means that an import route exists in the code. It does not mean every client version, field, account plan, or operating system has passed a native trial. The verification column records this catalog's evidence level; older validation elsewhere is not promoted without a reviewed evidence record. ## Product boundaries ChatGPT and Codex cloud are different products. Claude.ai chat, Claude Code cloud, and Cowork cloud have distinct import sources. Anthropic is rolling out a unified chat/task experience; that branding change does not establish shared export coverage or execution identity. Gemini chat, Gemini Notebook (formerly NotebookLM), and Gemini Spark need separate coverage. Grok chat, Grok Build, and Grok Bot are different products. Muse Code support does not imply support for Meta's consumer assistant. Microsoft Copilot and GitHub Copilot have separate histories. GitHub-hosted Claude and Codex agents are distinct from their vendor-owned cloud products. Copilot SDK Remote Control shares local execution; Copilot SDK cloud sessions execute on GitHub. Qwen Chat is separate from Qwen Code; its desktop, daemon, editor, SDK, channel and batch surfaces require independent acquisition evidence. Cowork cloud currently has partial coverage through tagged Claude Desktop cache records under `claude-cowork`; this is not an account-wide cloud enumeration route. Remote Control describes transport to a local Claude Code runtime and is not evidence of a hosted Claude Code run. ## Choosing an import route Local-store routes read retained files and can be watched. Cloud routes are explicit network imports. Manual exports remain useful alongside browser or cloud capture. A desktop cache only covers data the application retained. A product opened in a desktop wrapper does not become a different product, and a model provider does not identify the harness that ran it. Use the linked guide for exact commands, authentication, paths, and limitations. The route names on unsupported rows describe investigation targets, not working commands. Missing metadata, unknown models, and unmeasured usage must remain explicit; a source's replay support is a separate property from its importer. ## Implemented and partial routes ### Agentic AI Foundation | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | [Goose](https://www.hansard.dev/imports/goose/) | `goose` | local-store | Goose shared SQLite sessions and legacy JSONL transcripts, including tools, reasoning, usage, and child sessions. Shared local CLI, desktop, and API storage does not reliably identify the producing interface. Historical inference and ledger models remain separate from current configuration. Missing counters remain unknown; explicit zero stays in metadata. Direct raw parser replay passed, but full SQLite raw rebuild remains unsupported. | fixture-tested; 7 open gates. 2026-09-29 native trial (partial): Official CLI 1.52.0 with a local synthetic endpoint: initial/resumed conversation retained sixteen messages, two human prompts, seven ledger rows, five tool calls, controlled edit/shell errors and a byte-verified image. Initial transcript prefix, repeat import, source bytes and direct raw parser replay passed. All 127 observed field paths audited. Full raw rebuild, hosted usage and viewer acceptance remain open. | ### Aider | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------- | ------------------------- | ----------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Aider](https://www.hansard.dev/imports/aider/) | `aider` | local-store | Aider repo-local .aider.chat.history.md transcripts with optional LLM/input history raw backup. Chat transcript is captured; model and usage metadata require the optional LLM history sidecar. | fixture-tested; 4 open gates. | ### Alibaba | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Qwen Code](https://www.hansard.dev/imports/qwen-code/) | `qwen-code` | local-store | Qwen Code historical chats, checkpoints, archives, and subagents from the runtime tmp/projects stores. Active JSONL branches, tools, native failures, actual patches, embedded images and token splits are preserved. Assistant-record requested models remain distinct from response-model ledger totals. External attachment references stay unavailable. Offline raw rebuild requires the parser 0.5.6.1 ledger binding. Other producing interfaces remain unverified. | fixture-tested; 7 open gates. 2026-09-29 native trial (partial): Official CLI 0.24.7 with a local synthetic endpoint: initial/two resumed turns retained twenty messages, three human prompts, seven tool calls, controlled edit/shell errors, a skipped-image notice and a byte-verified image. Prefix, repeat, source-byte and full offline raw rebuild checks passed. All 164 observed paths across 45 chat/ledger rows audited. Other interfaces and full viewer acceptance remain open. | ### Amazon | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------------- | ------------------------- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------- | | [Kiro local history](https://www.hansard.dev/imports/kiro/) | `kiro` | local-store | Unified sessions, earlier CLI and IDE stores, Crew transcripts and logs, tool arguments, checkpoints, and recorded usage. Native conversations, tools, checkpoints, and child logs. Token counters depend on the engine; credits stay separate. Cloud sessions require an explicit export. | fixture-tested; 4 open gates. | | [Kiro session exports](https://www.hansard.dev/imports/kiro/) | `kiro-export` | manual-export | Native Kiro ZIP, JSON, or unified-directory exports preserve messages, tools, reasoning, attachments, and recorded accounting. Cloud enumeration is unavailable. Export ZIPs can omit snapshots and tool-output files; missing bytes remain explicit. | fixture-tested; 4 open gates. | ### Amp | Product | Source selector or format | Route | Coverage and limitations | Verification | | --------------------------------------------------------- | ------------------------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Amp Cloud](https://www.hansard.dev/imports/amp/) | `amp-cloud` | cloud | The signed-in Amp CLI lists and exports hosted threads, including orbs, with the same identity as full JSON exports. Exported threads can omit internal subagents and compaction details. Live hosted acceptance is still pending. | fixture-tested; 4 open gates. | | [Amp exports](https://www.hansard.dev/imports/amp/) | `amp-export` | manual-export | Full Amp JSON exports from the CLI or web app overlap safely with local and cloud thread imports. Public exports can omit internal subagents and compaction details. A displayed thread is not evidence of a complete export. | fixture-tested; 4 open gates. | | [Amp local history](https://www.hansard.dev/imports/amp/) | `amp` | local-store | Earlier CLI and extension JSON threads, tool calls, usage, and file-change backups. Current server-held threads use the explicit amp-cloud import. Historical local JSON threads. Current CLI, app, and orb threads require explicit cloud export; missing message clocks and ledger cache counts remain explicit gaps. | fixture-tested; 4 open gates. | ### Anthropic | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------------------------------------------ | ------------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Claude Code CLI](https://www.hansard.dev/imports/claude/) | `claude` | local-store | Interactive Claude Code JSONL transcripts from \~/.claude/projects, including desktop-launched Claude Code sessions when stored there. Full JSONL transcript, thinking, tools, usage, Remote Control sessions, and subagents. | fixture-tested; 4 open gates. | | [Claude Code cloud](https://www.hansard.dev/imports/claude/) | `claude-cloud` | cloud | Read-only hosted Claude Code events preserve messages, tools, usage, and Git context; verified Remote Control bridges retain local Claude Code identity. This route does not enumerate Claude.ai chats or Cowork cloud history. Completeness depends on retained session events and the account organization. The configured model is a session setting, not reply attribution. Incomplete parser refreshes retain earlier messages and report pending coverage. | fixture-tested; 4 open gates. | | [Claude Code Remote Control (local runtime)](https://www.hansard.dev/imports/claude/) | `claude`, `claude-cloud` | local-store, cloud | A local Claude Code runtime controlled remotely. Local transcripts and retained bridge events share identity only when the recorded bridge ID establishes the link. Remote access does not establish hosted execution. Local JSONL and retained cloud events can have different coverage. Hosted Claude Code and Cowork remain separate surfaces. | fixture-tested; 3 open gates. 2026-09-29 native trial (partial): Six bridge sessions passed repeated import, full-event refresh, raw-hash checks, and native viewer review. This provides no hosted-execution acceptance. | | [Claude Code Desktop](https://www.hansard.dev/imports/claude/) | `claude-code-desktop` | local-store | Claude Code sessions launched from the Claude app when local metadata is available. Audit transcript when available, with local Claude app metadata used to fill gaps. Current model settings are separate from reply and usage attribution; missing reply models remain unknown. | fixture-tested; 4 open gates. | | [Claude Cowork (cloud runtime)](https://www.hansard.dev/imports/claude/) (partial) | `claude-cowork` | desktop-cache | The claude-cowork reader imports explicitly tagged remote Cowork sessions cached by Claude Desktop. Repeated cache imports retain earlier turns and raw snapshots; partial parser refreshes remain explicit. Coverage depends on retained cache bytes; metadata-only entries do not become conversations. No dedicated account-wide Cowork cloud source or separate archive provider is registered. Claude Code cloud is a distinct product. Current model settings are separate from reply and usage attribution; missing reply models remain unknown. The September 2026 unified chat/task rollout does not establish additional capture coverage; keep recorded source and execution identity. | fixture-tested; 4 open gates. | | [Claude Cowork (local audits and desktop cache)](https://www.hansard.dev/imports/claude/) | `claude-cowork` | local-store | Claude Cowork legacy local audits and tagged remote sessions cached by Claude Desktop; metadata-only entries are excluded. Repeated cache imports retain earlier turns and raw snapshots; partial parser refreshes remain explicit. Legacy audit transcripts, or cached remote transcripts after the conversation is opened or revisited in Claude Desktop. Current model settings are separate from reply and usage attribution; missing reply models remain unknown. The September 2026 unified chat/task rollout does not establish additional capture coverage; keep recorded source and execution identity. | fixture-tested; 4 open gates. | | [Claude SDK jobs](https://www.hansard.dev/imports/claude/) | `claude-sdk` | local-store | Programmatic SDK and agent batch runs under \~/.claude/projects; stats split delegated runs from one-shot batch jobs. Full JSONL transcript and usage; delegated runs count in stats while one-shot jobs stay in the SDK jobs split. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): Three retained SDK sessions passed repeat-import and raw-hash checks; full metadata and viewer acceptance remain open. | | [Claude.ai (consumer and organization chat)](https://www.hansard.dev/imports/web-exports/) | `claude-web` | manual-export, browser | Claude.ai account exports and browser capture preserve conversation trees, attachments, account identity, and provider metadata; export memories become memory records. Models and token usage remain unknown when absent. Browser captures depend on retained account data and complete conversation loading. The September 2026 unified chat/task rollout does not establish additional capture coverage; keep recorded source and execution identity. | fixture-tested; 4 open gates. | ### Augment | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Augment Cosmos cloud](https://www.hansard.dev/imports/augment/) | `augment-cloud` | cloud | Cosmos API pagination imports conversations, tools, measured tokens, credits, compaction, and child relationships. Cloud pages must agree with the reported count. Local synchronized caches can stop at 200 messages and must not replace fuller API captures. | fixture-tested; 4 open gates. | | [Augment local history](https://www.hansard.dev/imports/augment/) | `augment` | local-store | Auggie JSON sessions, IDE LevelDB exchanges, locally synced Cosmos sessions, tool arguments, edits, and recorded usage. CLI and IDE exchanges, tools, recorded models and tokens. Cosmos local sync can truncate history; credits and child cost summaries remain separate from tokens. | fixture-tested; 4 open gates. | ### ByteDance | Product | Source selector or format | Route | Coverage and limitations | Verification | | --------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------- | | [TRAE](https://www.hansard.dev/imports/trae/) | `trae` | local-store | Agent trajectories, legacy IDE stores, and desktop SQLite history. Encrypted stores require a supplied key and SQLCipher. Agent trajectories include tools and recorded usage. Desktop histories require an unlocked snapshot or SQLCipher key; model selections and context counters are not inference usage. Remote histories are limited to local caches. | fixture-tested; 4 open gates. | ### Charm | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Crush](https://www.hansard.dev/imports/crush/) | `crush` | local-store | Crush project-local .crush/crush.db sessions, including reasoning, tools, attachments, and child sessions. SQLite transcripts, reasoning, tools, embedded attachments, file history, and child sessions. Stored token counters describe the latest context, not cumulative usage. | fixture-tested; 4 open gates. | ### Cline | Product | Source selector or format | Route | Coverage and limitations | Verification | | --------------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Cline](https://www.hansard.dev/imports/cline/) | `cline` | local-store | Cline task folders from VS Code/JetBrains globalStorage, including API history, UI messages, and task metadata. API history is preferred; UI messages and task metadata fill gaps when needed. | fixture-tested; 4 open gates. | | [Cline CLI](https://www.hansard.dev/imports/cline/) | `cline-cli` | local-store | Cline SDK sessions from \~/.cline/data/sessions, including CLI, desktop, and IDE surfaces plus subagent transcripts. Versioned session manifests and message artifacts with tools, token totals, cost, and linked subagent transcripts. | fixture-tested; 4 open gates. | ### Cognition | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------- | ------------------------- | ----------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Ask Devin](https://www.hansard.dev/imports/devin/) | `devin-ask-browser` | browser | The Devin browser collector recognizes Ask query IDs separately from cloud agent session IDs. The runtime currently groups Ask under the Devin cloud harness. Verify selected repository/branch context and query-to-agent relationships. | fixture-tested; 2 open gates. | | [Devin CLI](https://www.hansard.dev/imports/devin/) | `devin-cli` | local-store | Devin for Terminal sessions from \~/.local/share/devin/cli/sessions.db. Visible branch transcript plus persisted reasoning, latency, tool timing and review state, loaded rules and skills, session costs, context configuration, and linked subagents. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): One retained session passed repeat-import and raw-hash checks; full metadata and viewer acceptance remain open. | | [Devin cloud](https://www.hansard.dev/imports/devin/) | `devin-cloud` | cloud, browser, desktop-cache | Devin API imports chat, repository and PR context, status, outcomes, ACU billing, account and organization context, and related session links. Chat APIs do not expose the full internal tool trajectory. ACUs are billing units, not model tokens; model and token attribution remain unavailable when omitted. | fixture-tested; 4 open gates. | | [Devin Desktop](https://www.hansard.dev/imports/devin/) | `devin-desktop` | local-store | Devin Desktop ACP event logs from Application Support/Devin/User/acp-events. Ordered ACP transcript with thinking, tools, usage, and workspace metadata; exact per-message times are unavailable in current logs. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): Ten retained sessions passed repeat-import and raw-hash checks. Credential-database references contain no copied bytes; model provenance remains under review. | | [Windsurf](https://www.hansard.dev/imports/windsurf/) | `windsurf` | local-store, local-service, manual-export | Windsurf Cascade plan artifacts from \~/.codeium/windsurf/brain; matching Cascade protobufs are preserved as raw files but not decoded. Cascade plan artifacts plus raw protobuf backup; import a trajectory export for the full transcript. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): One raw-backup session passed repeat-import and hash checks but contains zero normalized messages. Full conversation import remains unverified. | ### Continue | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------- | | [Continue](https://www.hansard.dev/imports/continue/) | `continue` | local-store | Continue shared JSON sessions, including tool results, context, reasoning, attachments, and recorded usage. Shared IDE and CLI sessions, tools, reasoning, attachments, and recorded usage. Exact message clocks, interface labels, and some model IDs are absent. | fixture-tested; 4 open gates. | ### DeepSeek | Product | Source selector or format | Route | Coverage and limitations | Verification | | --------------------------------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [DeepSeek Harness](https://www.hansard.dev/imports/deepseek-harness/) | `deepseek-harness` | local-store | Versioned JSONL and Zstandard logs from local web, headless and agent deployments, including tools, edits, attachments and measured usage. Local versioned event logs preserve model routes, tools, usage and child runs. Custom persistence roots require HANSARD\_DSH\_SESSION\_ROOTS; provider settings and derived caches are excluded. | fixture-tested; 4 open gates. | ### Factory | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------------------ | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Factory cloud sessions](https://www.hansard.dev/imports/factory/) | `factory-cloud` | cloud | Factory cloud imports retained messages, tool output, usage, and session metadata and preserves richer local session history. The cloud response omits tool arguments. Current session settings remain separate from recorded message models. Full refreshes detect unchanged-clock message changes and retain archived history on incomplete, stale or regressed captures. Hosted access and exhaustive field coverage remain unverified. | fixture-tested; 4 open gates. | | [Factory Droid](https://www.hansard.dev/imports/factory/) | `factory` | local-store | Factory droid JSONL transcripts and token-usage sidecars from \~/.factory/sessions. Local transcripts retain recorded reply model IDs and reasoning effort independently of current settings. Model-only context is preserved without counting human prompts. Hosted resume, full metadata coverage and cloud access remain unverified. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): Official Droid 0.229.0 created a synthetic conversation against a local endpoint. One archive retained three records, one human prompt, reply model and effort, declared usage and two hash-verified raw files; repeated import was unchanged. Native resume required hosted authentication and remains unverified. 2026-09-29 native trial (partial): Direct content-addressed and CLI raw replay retain native messages, settings and usage. A second native run retained three tool calls, arguments and results including a controlled error; repeated import and raw-hash checks passed. The bounded metadata contract accounts for 73 observed paths and rejects field, type, role and record-kind drift. Structured diffs, attachments, provider errors, workers, hosted resume and viewer verification remain open. 2026-09-29 native trial (partial): A third official Droid run retained five calls and results, a controlled edit failure, correct file-change counts and a byte-verified tool-result image. Repeat import, raw hashes and direct/forced raw replay passed. The bounded contract accounts for 96 paths across 36 wrapped records, including decoded JSON-string edit results. User uploads, native documents, workers, provider failures, hosted resume and viewer acceptance remain open. | ### GitHub | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [GitHub Copilot CLI](https://www.hansard.dev/imports/copilot/) | `copilot-cli` | local-store | Copilot CLI events.jsonl session state and workspace metadata from \~/.copilot/session-state, with per-request token and premium-request usage from \~/.copilot/session-store.db. Recorded response models and native message lineage remain separate from configuration. Zero counters and shell exit codes are retained. Enriched raw replay needs the preserved usage-ledger binding; older archives require reimport. Hosted billing, media, children, compaction and other Copilot surfaces need separate native acceptance. | fixture-tested; 6 open gates. 2026-09-29 native trial (partial): Official CLI 1.0.89 with a local synthetic endpoint: one session resumed from 6 to 18 normalized messages, two human prompts, view success and controlled bash failure, five verified raw records, and unchanged repeat import. All 130 observed event paths audited. Full offline raw rebuild retained transcript, manifest, metadata and identity; a subsequent live import remained unchanged. Hosted billing and other surfaces remain unverified. | | [GitHub Copilot coding agent](https://www.hansard.dev/imports/copilot/) | `copilot-agent-cloud` | cloud | GitHub Copilot coding-agent sessions import task transcripts, repository and pull-request context, and recorded billing metadata. Transcript retrieval uses an undocumented endpoint. Premium requests and AI credits must not be treated as inference tokens. | fixture-tested; 4 open gates. | | [GitHub Copilot in VS Code](https://www.hansard.dev/imports/copilot/) | `copilot-ide` | local-store | Copilot Chat sessions from VS Code-family chatSessions stores, including the append-log format used since VS Code 1.109. Requests, responses, thinking, tool invocations, and file edits; tool arguments and token usage are only persisted for some invocations and newer VS Code builds. Current composer selections remain separate from historical request models. | fixture-tested; 4 open gates. | ### Google | Product | Source selector or format | Route | Coverage and limitations | Verification | | ---------------------------------------------------------------------------------------------- | ------------------------- | -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Antigravity 2.0](https://www.hansard.dev/imports/antigravity/) | `antigravity` | local-store, local-service | Readable transcripts, lifecycle notices, task artifacts, decoded database steps, and partial trajectory summaries from \~/.gemini/antigravity. Readable logs, lifecycle notices, artifacts, and decoded database steps; opaque protobuf bodies remain raw-only. Model selections are retained separately from response models; schema checks do not establish full native metadata or billing acceptance. | fixture-tested; 4 open gates. | | [Antigravity CLI](https://www.hansard.dev/imports/antigravity/) | `antigravity-cli` | local-store | Antigravity CLI transcripts, lifecycle notices, task artifacts, and conversation-database usage from \~/.gemini/antigravity-cli (the Gemini CLI successor). Transcript logs, lifecycle notices, task artifacts, and conversation-database model/token usage when present. Model selections are retained separately from response models; schema checks do not establish full native metadata or billing acceptance. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): Three retained sessions passed repeat-import and raw-hash checks; other Antigravity storage formats and full acceptance remain open. 2026-09-29 native trial (partial): CLI 1.2.13 created and resumed a synthetic conversation from 3 to 11 messages with one file tool call/result. Corrected accounting matches native CLI totals; model selections stay separate from response models. Stable identity, repeat import, seven raw hashes and viewer reload passed. Additional Sonnet and Gemini trials confirm the response/reasoning split. Positive native cache writes, full metadata and attachment coverage remain open. | | [Antigravity IDE](https://www.hansard.dev/imports/antigravity/) | `antigravity-ide` | local-store | Antigravity IDE transcripts, lifecycle notices, task artifacts, and conversation-database usage from \~/.gemini/antigravity-ide; stale migration copies are skipped. Transcript logs, lifecycle notices, task artifacts, and database usage when present; stale migration copies are skipped. Model selections are retained separately from response models; schema checks do not establish full native metadata or billing acceptance. | fixture-tested; 4 open gates. | | [Gemini](https://www.hansard.dev/imports/web-exports/) | `gemini-web` | manual-export, browser | Gemini browser capture and Google Takeout activity exports preserve retained chat content and available attachments. Activity exports and browser history have different coverage. Missing models, token usage, or message clocks remain unknown; NotebookLM is separate. | fixture-tested; 4 open gates. | | [Gemini CLI](https://www.hansard.dev/imports/gemini-cli/) | `gemini-cli` | local-store | Saved chats, checkpoints, sessions, and exports from \~/.gemini JSON/JSONL/Markdown stores. Persisted messages include snapshot updates, provider notifications, structured tool lifecycle and result-display metadata, usage, and checkpoints; pruned provider data remains unavailable. | fixture-tested; 4 open gates. | | [Gemini Notebook (formerly NotebookLM)](https://www.hansard.dev/imports/notebooklm/) (partial) | `notebooklm` | manual-export | Explicit consumer Takeout ZIP/folder importer for Chat History HTML, with separate notebook metadata and raw resources. Account labels are user supplied. Chat times, message IDs, native notebook/account IDs, models, usage, thoughts, citation-source identities and completeness are absent. Sources, notes and artifacts remain raw-only. No watcher, app-picker or browser route. Prefix-only append rejects shorter/changed history and metadata-only conflicts. | fixture-tested; 5 open gates. 2026-09-29 native trial (partial): One native Takeout prompt/reply pair, five hash-verified members, unchanged repeat import and raw rebuild after removal of the import copy. Browser viewer displayed the transcript, separate provider and unknown time. Metadata field accounting covers the bounded notebook/text-source cohort; multi-turn and full metadata display remain open. | | [Jules](https://www.hansard.dev/imports/jules/) | `jules` | cloud | Jules API sessions and activities preserve prompts, replies, plans, tool activity, generated patches, repository context, and status. The API does not expose inference model or token usage. Only an explicit recorded model hint can supply attribution. | fixture-tested; 4 open gates. | ### gptme | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [gptme CLI / local store](https://www.hansard.dev/imports/gptme/) | `gptme` | local-store | Main-branch JSONL, recorded reply model/effort, reasoning, usage and JSON tools; exact branch/view/recovery files plus a declared chat-settings projection. Originating interface is not recorded. Config credentials/MCP/prompt settings are excluded. Naive clocks remain timezone-unknown. Alternate histories, attachment references and markdown/XML tool syntax are raw-only. Child linkage, hosted billing and other hosts remain unverified. | fixture-tested; 6 open gates. 2026-09-29 native trial (partial): Official gptme 0.34.0 against a local synthetic endpoint: five initial and ten resumed records, a real file read, native undo/view/checkpoint captures, unchanged repeated imports and raw replay. 223 independent value/hash/round-trip checks passed; all 111 observed field paths accounted for. Hosted billing and other hosts remain unverified. | ### iFlow | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [iFlow](https://www.hansard.dev/imports/iflow/) | `iflow` | local-store | iFlow CLI transcripts from \~/.iflow/projects, including tool calls and compaction records. Full transcript, tool calls, and tool results; interactive runs record zero tokens because the CLI writes empty usage for them. | fixture-tested; 4 open gates. | ### JetBrains | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Junie](https://www.hansard.dev/imports/junie/) | `junie` | local-store | Local session events, saved agent state, IDE task chains, child agents, file changes, and recorded model usage. CLI events and saved state plus IDE task chains. Older CLI arguments can be lost after provider compaction; retained display events still supply commands and file changes. | fixture-tested; 4 open gates. | ### Kilo Code | Product | Source selector or format | Route | Coverage and limitations | Verification | | -------------------------------------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Kilo Code](https://www.hansard.dev/imports/kilo-code/) | `kilo-code` | local-store | Shared CLI, VS Code, and JetBrains SQLite sessions, including tools, reasoning, attachments, and usage. Shared CLI and current IDE SQLite history. Interface attribution is absent; recorded costs remain estimates when their provenance is ambiguous. | fixture-tested; 4 open gates. | | [Kilo Code Cloud](https://www.hansard.dev/imports/kilo-code/) | `kilo-code-cloud` | cloud | Kilo synchronized session exports and legacy transcript blobs provide retained conversations; targeted Cloud Agent requests also import final results. Cloud Agent result lookups require session and message IDs and return status/final text only, without the original prompt, tools, model, or tokens. | fixture-tested; 4 open gates. | | [Kilo Code legacy tasks](https://www.hansard.dev/imports/kilo-code/) | `kilo-code-legacy` | local-store | Earlier IDE and CLI JSON task histories and legacy task indexes. Earlier JSON tasks, including tools and human prompts. Missing model IDs and legacy clocks remain explicit gaps. | fixture-tested; 4 open gates. | ### Meta | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------- | ------------------------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Muse Code](https://www.hansard.dev/imports/muse-code/) | `muse-code` | local-store | Muse Code session.jsonl journals from the XDG muse/sessions data store, including linked nested subagent runs. Muse Code is already imported. Consumer Meta AI/Muse product history, external plugins and unobserved journal shapes require separate evidence. | fixture-tested; 4 open gates. | ### MiniMax | Product | Source selector or format | Route | Coverage and limitations | Verification | | --------------------------------------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------- | | [MiniMax Code cloud](https://www.hansard.dev/imports/minimax-code/) | `minimax-code-cloud` | cloud | Explicit MiniMax Code cloud session imports paginate retained messages and preserve source records with stable identity. Account-wide enumeration is not available. A session ID is required, and nonadvancing or partial pagination must not replace an archive. | fixture-tested; 4 open gates. | | [MiniMax Code local history](https://www.hansard.dev/imports/minimax-code/) | `minimax-code` | local-store | Canonical transcripts, verified compaction snapshots, older ledgers and SQLite history, tools, and durable request usage. CLI and desktop share a session identity. Canonical history and verified compaction snapshots take priority over mirrored stores; durable usage supersedes message counters. | fixture-tested; 4 open gates. | ### Mistral | Product | Source selector or format | Route | Coverage and limitations | Verification | | --------------------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Mistral Vibe CLI](https://www.hansard.dev/imports/vibe/) | `vibe` | local-store | Mistral Vibe session logs from \~/.vibe/logs/session, including nested agent runs and the meta.json token rollup. Transcript with reasoning, tool calls, tool results, manual shell runs, and the session token, price, and tool-outcome rollup from meta.json. | fixture-tested; 4 open gates. | ### Moonshot | Product | Source selector or format | Route | Coverage and limitations | Verification | | -------------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Kimi CLI](https://www.hansard.dev/imports/kimi/) | `kimi-cli` | local-store | Kimi CLI wire journals, context history, and subagent runs from \~/.kimi/sessions. Wire journal replay with reasoning, tool calls, tool results, and directional token totals; the store records no model on a main session, only on subagent launches. | fixture-tested; 4 open gates. | | [Kimi Code](https://www.hansard.dev/imports/kimi/) | `kimi-code` | local-store | Kimi Code wire journals from \~/.kimi-code/sessions, including per-agent runs and linked child sessions. Wire journal replay with reasoning, tool calls, tool results, per-model directional token totals, turn boundaries, and linked agent runs. | fixture-tested; 4 open gates. | ### Nous Research | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Hermes](https://www.hansard.dev/imports/hermes/) | `hermes` | local-store | Shared CLI, desktop, web, and messaging SQLite sessions, compression continuations, fallback logs, tools, and measured main and auxiliary model usage. Profile SQLite transcripts, reasoning, tools, diffs, linked delegates, and per-model usage. JSONL fallback logs preserve messages without reliable model or usage metadata. | fixture-tested; 4 open gates. | ### OpenAI | Product | Source selector or format | Route | Coverage and limitations | Verification | | -------------------------------------------------------- | ------------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [ChatGPT](https://www.hansard.dev/imports/web-exports/) | `chatgpt` | manual-export, browser | ChatGPT account exports and browser capture preserve conversation branches, files, recorded models, account identity, and provider metadata. Workspace plan and export permissions affect availability. Historical settings and measured usage cannot be inferred from current defaults; Codex cloud is separate. | fixture-tested; 4 open gates. | | [Codex CLI](https://www.hansard.dev/imports/codex/) | `codex-cli` | local-store | Terminal `codex` sessions recorded in the Codex state database. Full local transcript, tool calls, token usage, diffs, and subagent links. | fixture-tested; 4 open gates. | | [Codex cloud](https://www.hansard.dev/imports/codex/) | `codex-cloud` | cloud | Saved ChatGPT sign-in reads retained task turns and events; CLI fallback preserves task status and the unified diff. Fallback captures lack the full conversation. Alternate attempts retain turn records without event histories. Missing or thinner captures keep archived evidence; a changed conversation path that omits earlier messages requires separate branch-history support. Native metadata accounting remains pending. | fixture-tested; 4 open gates. 2026-09-29 native trial (blocked): Seven authenticated profiles returned empty active and archived task lists; one required sign-in. No native task was available for an archive trial. | | [Codex Desktop](https://www.hansard.dev/imports/codex/) | `codex-desktop` | local-store | Codex desktop app conversations from the local Codex state database. Full local transcript, tool calls, token usage, diffs, and subagent links. | fixture-tested; 4 open gates. | | [Codex SDK jobs](https://www.hansard.dev/imports/codex/) | `codex-sdk` | local-store | Codex exec and SDK-style runs from the local Codex state database; stats split delegated runs from one-shot batch jobs. Full SDK transcript and usage; delegated runs count in stats while one-shot jobs stay in the SDK jobs split. | fixture-tested; 4 open gates. | ### OpenClaw Foundation | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [OpenClaw](https://www.hansard.dev/imports/openclaw/) | `openclaw` | local-store | Per-agent SQLite transcripts, retained JSONL archives, tools, edits, fork lineage, and measured model usage shared by CLI, web, desktop, and messaging clients. Gateway-host SQLite and legacy JSONL histories preserve tools, usage, branches, and child sessions. Remote Gateway stores must be available locally; incognito sessions are not persisted. | fixture-tested; 4 open gates. | ### OpenCode | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------- | ------------------------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [OpenCode](https://www.hansard.dev/imports/opencode/) | `opencode` | local-store | Canonical OpenCode JSON and SQLite history from its core data root, independent of the CLI, desktop, or web surface that used it. Canonical JSON and SQLite transcripts with reasoning, tools, session totals, enforced source-shape accounting, and coherent snapshot replay. Model-switch selections remain separate from historical response models and effort. Coexisting transcript tables are selected per session; competing populated stores under one native ID are rejected. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): CLI 1.18.31 against a local endpoint: legacy-table session grew from four to six archived messages on resume with stable identity, two recorded models and unchanged repeated import. A separate v2 prompt and unused model-switch session imported alongside it without false model attribution. Two raw references resolve to a verified history-only snapshot; v2 generation, full metadata and viewer verification remain open. 2026-09-29 native trial (partial): Shared-snapshot replay reproduces both native sessions, eight messages, and serialized metadata including native identity. The shared identity constructor also passes synthetic MiMo nested-actor replay tests; no native MiMo acceptance is implied. Native CLI cohort rebuild passed; returning the resulting archive to ordinary live import hit the documented full-refresh requirement. | ### OpenHands | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------- | | [OpenHands](https://www.hansard.dev/imports/openhands/) | `openhands` | local-store | CLI, SDK, Agent Canvas, and agent-server events plus legacy application sessions, tools, file edits, branches, child sessions, and measured usage. SDK event folders and legacy application events preserve tools, edits, and recorded usage. Legacy pickle state remains raw-only; arbitrary SDK directories need an explicit root. | fixture-tested; 4 open gates. | | [OpenHands Cloud](https://www.hansard.dev/imports/openhands/) | `openhands-cloud` | cloud | OpenHands cloud API imports persistent conversation events and combined usage snapshots, including paused runtimes. Usage snapshots lack historical model attribution and events lack an active-branch pointer. Runtime files, cloud memories, and ZIP downloads are not fetched. | fixture-tested; 4 open gates. | ### Perplexity | Product | Source selector or format | Route | Coverage and limitations | Verification | | -------------------------------------------------------------- | ------------------------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Perplexity](https://www.hansard.dev/imports/browser-capture/) | `perplexity` | browser | Perplexity browser capture imports thread content, citations, files, account identity, and available provider metadata. Complete retained thread loading and account context are required. Missing model, token, or attachment bytes remain explicit. | fixture-tested; 4 open gates. | ### pi | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [pi](https://www.hansard.dev/imports/pi/) | `pi` | local-store | pi coding agent JSONL session trees from \~/.pi/agent/sessions, including branches and compactions. Only the active branch is normalized; abandoned branches remain raw. Response models, requested models and configuration remain separate. Calculated costs are estimates and zero counters remain explicit. Resume can omit effort changes; unmatched effort stays unknown, while omitted same-model changes are unobservable. | fixture-tested; 6 open gates. 2026-09-29 native trial (partial): Official CLI 0.73.1 with a local synthetic endpoint: initial/resumed conversation retained sixteen messages, two human prompts, five tool calls, controlled edit/shell errors and a byte-verified image. Initial prefix, repeat import, source bytes and full offline raw rebuild passed. All 53 observed field paths audited. Hosted usage, other session shapes and full viewer acceptance remain open. | ### Prime Intellect | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | [Prime Agent](https://www.hansard.dev/imports/prime-agent/) | `prime-agent` | local-store | Prime Agent JSONL session trees from \~/.prime/agent, including legacy per-cwd stores, RLM child sessions, and session-local continual-harness state. Versioned JSONL transcript with model routing, reasoning effort, service tier, tools, token and cost usage, attachments, lifecycle state, linked RLM child sessions, and raw-preserved kernel and session-local continual-harness state. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): Three retained sessions passed repeat-import and raw-hash checks; full metadata, tool, attachment, and viewer acceptance remain open. | ### Qoder | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Qoder Cloud Agents](https://www.hansard.dev/imports/qoder/) | `qoder-cloud` | cloud | Qoder cloud tasks import retained messages, tools, output files, repository context, task relationships, and billing credits. Credits are separate from inference tokens. Reasoning and measured token counts are unavailable; attachment download failures and limits remain explicit. | fixture-tested; 4 open gates. | | [Qoder local history](https://www.hansard.dev/imports/qoder/) | `qoder` | local-store | Native transcripts, desktop SQLite history, subagents, recorded edit patches, and available request usage. Native transcripts and desktop histories with tools and subagents. Hosted requests hide token counts; credits remain separate. Selected desktop models are not request attribution. | fixture-tested; 4 open gates. | ### Roo Code | Product | Source selector or format | Route | Coverage and limitations | Verification | | --------------------------------------------------------- | ------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Roo Code CLI](https://www.hansard.dev/imports/roo-code/) | `roo-code-cli` | local-store | Historical Roo Code task files, tool calls, reasoning, attachments, child tasks, and recorded usage. Historical CLI tasks in the VS Code shim store. Ephemeral sessions are unavailable after deletion; model identity is often absent. | fixture-tested; 4 open gates. | | [Roo Code IDE](https://www.hansard.dev/imports/roo-code/) | `roo-code` | local-store | Historical Roo Code task files, tool calls, reasoning, attachments, child tasks, and recorded usage. Historical IDE task transcripts and tools, reasoning, attachments, and recorded usage. Models are often absent; legacy records may lack clocks. | fixture-tested; 4 open gates. | ### Roomote | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------------ | ------------------------- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Roomote cloud](https://www.hansard.dev/imports/roomote/) | `roomote-cloud` | cloud | Roomote API imports complete visible conversation pages and linked tasks; a matching database import keeps its richer history. Cloud text is sanitized and omits archived or hidden conversations from listing. Known IDs can be requested explicitly; native hosted acceptance is pending. | fixture-tested; 4 open gates. | | [Roomote database](https://www.hansard.dev/imports/roomote/) | `roomote-db` | database-copy | Roomote database snapshots import messages, tool arguments/results, reasoning, usage ledgers, child tasks, and scoped memories. Only history tables and projections are preserved. Cloud and database copies join by verified native identity, and partial projections cannot replace complete history. | fixture-tested; 4 open gates. | ### Tencent | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [CodeBuddy](https://www.hansard.dev/imports/codebuddy/) | `codebuddy` | local-store | CodeBuddy Code project transcripts and subagent runs from \~/.codebuddy/projects. Transcript, reasoning, tool calls, tool results, and per-message token usage; the record shape was mapped from the vendor bundle and unmapped record types are counted in session metadata. Public vendor documentation URL needs refresh; previously listed codebuddy.ai homepage returns 404. | fixture-tested; 4 open gates. | ### Warp | Product | Source selector or format | Route | Coverage and limitations | Verification | | ----------------------------------------------------------- | ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | [Warp cloud](https://www.hansard.dev/imports/warp/) | `warp-cloud` | cloud | Warp cloud pages provide normalized conversation steps, recorded models, parent/child links, and aggregate usage. Aggregate usage belongs to the parent when no child allocation is recorded. Unsupported third-party harness sessions can return HTTP 422. | fixture-tested; 4 open gates. | | [Warp local history](https://www.hansard.dev/imports/warp/) | `warp` | local-store | Local SQLite task history, tool arguments and results, edits, reasoning, recorded models and usage, and linked agent runs. Desktop and Agent CLI task protobufs, local usage snapshots, and coherent history database copies. Unknown fields remain counted and preserved in raw. | fixture-tested; 4 open gates. | ### xAI | Product | Source selector or format | Route | Coverage and limitations | Verification | | -------------------------------------------------------------- | ------------------------- | ----------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Cursor CLI](https://www.hansard.dev/imports/cursor/) | `cursor-cli` | local-store | Cursor CLI interactive, headless, and ACP conversation stores from \~/.cursor/chats and \~/.cursor/acp-sessions, including saved Cursor account profiles. Ordered prompt messages carry the model that answered each request, reasoning summaries, tool calls with structured results, edit diffs, and step clocks. The stores record no token counts; recovered Cursor usage history supplies them when available. | fixture-tested; 4 open gates. | | [Cursor](https://www.hansard.dev/imports/cursor/) | `cursor` | local-store | Cursor chats from workspace state.vscdb stores and newer \~/.cursor/projects agent transcripts. Modern agent transcripts are rich; Composer headers add churn and lineage, while SQLite bubbles preserve timing, review state, context snapshots, and error or content-addressed tool results. | fixture-tested; 4 open gates. | | [Cursor cloud agents](https://www.hansard.dev/imports/cursor/) | `cursor-cloud` | cloud | Cursor cloud API imports retained conversation text, task status, repository context, and session token totals. The endpoint omits tool trajectories, model attribution, and individual message clocks. Local Cursor histories use separate sources. | fixture-tested; 4 open gates. | | [Grok Build](https://www.hansard.dev/imports/grok-build/) | `grok-build` | local-store | Grok Build durable ACP updates, prompt usage ledgers, structured chat sidecars, and provider request failures from \~/.grok/sessions. Durable ACP updates, typed hook/subagent/permission/MCP lifecycle, prompt-level token/cost ledgers, source-shape telemetry, structured chat enrichment, and raw session sidecars. Current model settings remain separate from recorded model usage. Unhandled update types produce explicit warnings and raw-only records instead of silent omissions. Recorded format versions, zero counters and unambiguous repository remotes are retained; explicit repository overrides remain authoritative. | fixture-tested; 4 open gates. 2026-09-29 native trial (partial): Ten retained sessions passed repeat-import and raw-hash checks; historical client versions and full field coverage remain unverified. 2026-09-29 native trial (blocked): Grok 1.0.44 rejected fresh synthetic prompts on two saved profiles because the usage balance was exhausted. Successful replies and resume remain unverified. 2026-09-29 native trial (partial): Two native failed turns retained provider error text, five messages and eleven hash-verified raw records each. Repeats were unchanged; this does not verify successful replies or resume. 2026-09-29 native trial (partial): All 95 observed paths in fourteen retained summary/signal records pass explicit field accounting. Parser 0.5.6.3 replay preserved 662 messages and 127 verified raw records; event and attachment field audits remain open. | ### Xiaomi | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------- | | [MiMo Code](https://www.hansard.dev/imports/mimo-code/) | `mimo-code` | local-store | MiMo Code SQLite history from its independent mimocode data root and enforced storage cohort. Independent SQLite transcript with reasoning, tools, session totals, exact source-shape accounting, and linked agent runs. | fixture-tested; 4 open gates. | ### Zed Industries | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------- | | [Zed](https://www.hansard.dev/imports/zed/) | `zed` | local-store | Native Agent Panel SQLite history, including tools, edits, recorded settings, and cumulative token usage. Historical text-thread JSON is included; external agents use their own history stores. Native agent threads and child runs. Per-message clocks and model history are not recorded; tokens stay unattributed to a model when only the final selection is saved. | fixture-tested; 4 open gates. | ### Posit | Product | Source selector or format | Route | Coverage and limitations | Verification | | ------------------------------------------------------------------- | ------------------------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Posit Assistant](https://www.hansard.dev/imports/posit-assistant/) | `posit-assistant` | local-store | Version 3 local conversation trees normalize the selected branch, recorded reply models, usage, and tool calls/results; all tree and LM/UI source bytes are retained. Current model and effort settings remain separate from historical replies. Alternate branches, UI-only records, file references and unknown blocks remain raw-only. Uninspected child kinds, old schemas, missing references, stale revisions and loss of retained history are rejected. JSON/HTML exports and other native hosts remain unverified. | fixture-tested; 6 open gates. 2026-09-29 native trial (partial): Official TUI v0.1.0 build dev against a local synthetic endpoint: first and resumed imports grew from two to six LM records with stable identity, one tool call/result, four hash-verified raw files and unchanged repeated import. All 75 observed field paths audited; hosted billing and other hosts remain unverified. | ## Unsupported products and missing routes This is a running backlog. Priority 1 covers explicit product gaps and major hosted histories; priority 2 covers additional maintained clients; priority 3 covers narrower or unverified surfaces. Product identity remains unresolved where no authoritative match is available. A failed public-page request is not evidence that a product does not exist. | Company or project | Product | Candidate routes | Next evidence needed | Priority | | ------------------- | ---------------------------------------------------------------------------------------------------------------------- | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | | Agent37 | [QM (Agent37 hosted)](https://www.agent37.com/qm) | cloud, browser | Upstream identifies Agent37 as a third-party hosted QM service. Hosted account/instance identity, access, version, retained-history API, pagination and export availability remain unverified. Self-hosted database access does not establish hosted coverage. | 1 | | Alibaba | [Qwen Chat](https://chat.qwen.ai/) | browser, manual-export | Qwen Code historical logs do not cover the consumer chat or its agent modes. | 1 | | Amazon | [Amazon Bedrock Managed Agents powered by OpenAI](https://aws.amazon.com/bedrock/managed-agents-openai/) | cloud, manual-export | The official product is in limited preview. AWS hosts the agent loop and model inference; AgentCore or self-hosted compute executes tools. AWS IAM, endpoints and retained state differ from OpenAI Agents API. Shared harness concepts do not establish identical source contracts. | 1 | | Amazon | [Kiro cloud sessions](https://kiro.dev/docs/cloud-sessions/) | cloud, browser | Local and supplied Kiro exports are implemented; account-wide hosted enumeration needs separate validation. | 1 | | Amp | [Amp Puck](https://ampcode.com/docs/puck) | cloud, browser, manual-export | Puck conversations are distinct from coding threads created by Puck. The documented puck:true search selects the former only. Verify personal-assistant history, delegated thread links, voice, Slack, and web/TUI/mobile identity independently of Amp thread export. | 1 | | Anthropic | [@Claude in Slack](https://claude.com/product/tag) | cloud, manual-export | Team and Enterprise beta with shared thread context, background work and scheduled instructions. Workspace/channel/thread identity, participant attribution, approvals and tool actions must survive; Slack message text alone cannot prove complete agent history. | 1 | | Anthropic | [Claude Design](https://claude.com/product/design) | cloud, browser, manual-export | Standalone design and in-conversation experiences retain editable artifacts and revisions. PDF, PowerPoint and HTML artifact exports do not establish conversation or tool-history completeness. | 1 | | Anthropic | [Claude for Excel](https://claude.com/claude-for-microsoft-365) | local-store, cloud, telemetry-export | Office agent surface sheet, separate from Claude.ai chat. Document and cross-app session identities require verification. Official OTEL traces omit assistant response text and cap prompts at 4,000 characters; direct-provider deployments also omit Claude account, MCP and file-upload metadata. Telemetry alone is a partial audit route. | 1 | | Anthropic | [Claude for Outlook](https://claude.com/claude-for-microsoft-365) | local-store, cloud, telemetry-export | Office agent surface mail, separate from Claude.ai chat. Document and cross-app session identities require verification. Official OTEL traces omit assistant response text and cap prompts at 4,000 characters; direct-provider deployments also omit Claude account, MCP and file-upload metadata. Telemetry alone is a partial audit route. | 1 | | Anthropic | [Claude for PowerPoint](https://claude.com/claude-for-microsoft-365) | local-store, cloud, telemetry-export | Office agent surface slide, separate from Claude.ai chat. Document and cross-app session identities require verification. Official OTEL traces omit assistant response text and cap prompts at 4,000 characters; direct-provider deployments also omit Claude account, MCP and file-upload metadata. Telemetry alone is a partial audit route. | 1 | | Anthropic | [Claude for Word](https://claude.com/claude-for-microsoft-365) | local-store, cloud, telemetry-export | Office agent surface doc, separate from Claude.ai chat. Document and cross-app session identities require verification. Official OTEL traces omit assistant response text and cap prompts at 4,000 characters; direct-provider deployments also omit Claude account, MCP and file-upload metadata. Telemetry alone is a partial audit route. | 1 | | Anthropic | [Claude in Chrome](https://claude.com/claude-in-chrome) | cloud, browser, local-store | The side panel now runs an account-backed Cowork session. Browser actions, approvals, tabs and scheduled runs need source-specific validation. Shared account history does not establish export completeness or prove which machine executed each action. | 1 | | Anthropic | [Claude Science](https://claude.com/product/claude-science) | local-store, manual-export | Dedicated desktop scientific workbench with conversations linked to code, environments, figures and notebooks. Local, SSH and cluster execution, persistent kernels, artifact revisions and background reviews need distinct provenance; Claude Code coverage cannot be assumed. | 1 | | Anthropic | [Claude Security (cloud)](https://claude.com/product/claude-security) | cloud, manual-export | Enterprise scans, adversarial validation, findings, recommended patches, approvals and recurring runs need task identity and lifecycle. Exporting findings does not establish a full agent transcript. | 1 | | Anthropic | [Claude Security plugin for Claude Code](https://claude.com/product/claude-security) | local-store, manual-export | The local plugin is distinct from hosted Enterprise scanning. Claude Code can preserve recorded transcript events, but scan artifacts, parallel validators, findings and patch-review lineage require independent evidence. | 1 | | Anthropic | [Claude unified chat and tasks](https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude) | cloud, browser, manual-export | The September 2026 rollout merges chat and Cowork in one conversation. Existing chat exports and Cowork caches do not establish complete task, browser, approval, artifact, or scheduled-run history. Preserve original execution/source evidence; older Cowork tasks are excluded from product search. | 1 | | ByteDance | [TRAE Work web](https://work.trae.ai/) | cloud, browser, manual-export | The official site links this web application, but its static response is only an application shell. Cloud enumeration, retained history and overlap with decrypted local TRAE Work caches remain unverified. | 1 | | CloudStack (Msty) | [Msty Go](https://msty.ai/products/go/) | local-store, manual-export | Desktop task agents, Mission Control helpers, scheduled jobs, approvals, and Memory Bank require separate history accounting from Studio conversations. Mobile steering does not establish cloud execution. | 1 | | DeepSeek | [DeepSeek chat](https://chat.deepseek.com/) | browser, manual-export | The DeepSeek Harness importer does not import the consumer website. | 1 | | GitHub | [Claude on GitHub (cloud agent)](https://docs.github.com/en/copilot/concepts/agents/about-third-party-coding-agents) | cloud, browser | GitHub-hosted Claude partner agent, separate from Copilot and the vendor-owned cloud product. Verify GitHub account, repository, agent identity, iteration/PR lineage, model selection, event history, billing and artifact retention. | 1 | | GitHub | [Codex on GitHub (cloud agent)](https://docs.github.com/en/copilot/concepts/agents/about-third-party-coding-agents) | cloud, browser | GitHub-hosted Codex partner agent, separate from Copilot and the vendor-owned cloud product. Verify GitHub account, repository, agent identity, iteration/PR lineage, model selection, event history, billing and artifact retention. | 1 | | GitHub | [GitHub Copilot app (cloud sandbox)](https://docs.github.com/en/copilot/concepts/agents/github-copilot-app) | cloud, browser | App sessions can execute in cloud sandboxes. Do not infer a local transcript or equate them with issue-assigned coding-agent logs; verify cloud enumeration, agent identity, worktrees, approvals, canvases and retained events. | 1 | | GitHub | [GitHub Copilot app (local)](https://docs.github.com/en/copilot/concepts/agents/github-copilot-app) | local-store, manual-export | Desktop app built on Copilot CLI with local sandboxes, worktrees, chats, automations and canvases. Shared runtime does not prove shared session roots or complete app metadata coverage; native app attribution and artifact retention are unverified. | 1 | | GitHub | [GitHub Copilot Chat on github.com](https://docs.github.com/en/copilot) | browser, cloud, manual-export | Web chat is separate from the coding agent, CLI and VS Code history. | 1 | | GitHub | [GitHub Copilot SDK (cloud)](https://docs.github.com/en/copilot/how-tos/copilot-sdk/features/cloud-sessions) | cloud, sdk-events | GitHub-hosted sessions use cloud-agent entitlements and optional repository context. Streaming must be enabled for message deltas, and the remote worker must start before the first prompt. Remote Control of a local runtime is a different surface. | 1 | | GitHub | [GitHub Copilot SDK (local)](https://docs.github.com/en/copilot/how-tos/copilot-sdk) | local-store, sdk-events | SDK sessions use a local Copilot runtime. Origin, application identity, machine prompts, child runs and ephemeral versus persisted event stores need verification independently of interactive CLI history. | 1 | | GitHub | [GitHub Copilot SDK Remote Control](https://docs.github.com/en/copilot/how-tos/copilot-sdk/features/remote-sessions) | local-store, cloud, sdk-events | The SDK shares a locally executing session to GitHub web/mobile. A remote URL is transport evidence, not proof of GitHub-hosted compute. Preserve local origin and verified cross-route identity. | 1 | | Google | [Firebase App Testing agent](https://firebase.google.com/docs/app-distribution/android/app-testing-agent) | cloud, manual-export | Preview Android test-generation and execution agent. YAML test definitions are not run history; preserve test/run/step identity, actions, assertions, screenshots, recordings, logs, versions and failures independently of Gemini in Firebase chat. | 1 | | Google | [Gemini Spark](https://blog.google/innovation-and-ai/products/gemini-app/next-evolution-gemini-app/) | cloud, browser, local-store | Persistent personal cloud agent using the Antigravity harness, with desktop integration also announced. Antigravity transcript support does not establish Spark account history, scheduled/background work, approvals or local-versus-cloud execution coverage. | 1 | | Google | [Google AI Studio](https://aistudio.google.com/) | browser, manual-export | Saved prompts, app-building sessions and Gemini chat are different stores. Inspect native exported prompts and attachments. | 1 | | Manus | [Manus](https://manus.im/docs/) | cloud, browser, manual-export | Inspect tasks/messages/files and ownership evidence; avoid treating task summaries as full transcripts. | 1 | | Meta | [Meta AI consumer assistant](https://www.meta.ai/) | browser, manual-export, desktop | Separate consumer app history from Muse Code journals. Exact current product names and export coverage require verification. | 1 | | Meta | [Muse personal agent](https://muse.ai/) | browser, desktop, cloud, manual-export | Verified separate Meta product with web, Mac, mobile, and WhatsApp surfaces. Muse Code and Meta AI chat import coverage do not cover Muse. Chat, background tasks, approvals, activity audit trails, memories, files, and cross-device identity need a native history contract. | 1 | | Microsoft | [Microsoft Copilot consumer chat](https://copilot.microsoft.com/) | browser, manual-export | Microsoft consumer Copilot is not GitHub Copilot. | 1 | | MiniMax | [MiniMax Agent](https://agent.minimax.io/) | browser, manual-export | Do not conflate consumer Agent tasks with MiniMax Code local or cloud sessions. | 1 | | Mistral | [Mistral Vibe for work (formerly Le Chat)](https://mistral.ai/products/vibe/) | browser, manual-export | Mistral states that Le Chat conversations, settings and plans carry over to Vibe. Chat and long-running Work mode require independent capture; the existing Vibe CLI importer does not cover this account history or remote coding tasks. | 1 | | Mistral | [Mistral Vibe remote coding agents](https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5/) | cloud, browser, manual-export | Cloud sessions can start from CLI or Vibe chat and move between local and cloud execution. Preserve execution transitions, repository/diff context, attempts, and original identity without claiming local logs contain the complete hosted run. | 1 | | Moonshot | [Kimi consumer chat and agent tasks](https://www.kimi.com/) | browser, manual-export | Kimi Code and Kimi CLI wire journals do not cover hosted chat, research or generated work products. | 1 | | OpenAI | [ChatGPT dots](https://learn.chatgpt.com/docs/dots) | cloud, browser, manual-export | A persistent cloud agent has channel-specific conversations, saved notes, proactive work and delegated Work/Codex tasks. Preserve dot, channel and child-task identities independently. Local child transcripts and account chat exports cannot establish complete dot history. | 1 | | OpenAI | [ChatGPT for Word](https://openai.com/index/astra-for-law/) | local-store, cloud, manual-export | Officially announced Word add-in for proofreading, suggested edits and formatting checks. ChatGPT history coverage does not establish document-scoped conversation, tracked-change, attachment or cross-app identity preservation. | 1 | | OpenAI | [ChatGPT in Slack and Microsoft Teams](https://learn.chatgpt.com/docs/enterprise/chatgpt-slack-and-teams) | cloud, manual-export | Service-account surfaces have workspace/channel identity and approved connections distinct from participants' private ChatGPT accounts. Codex cloud delegation from Slack runs as the requesting user. Preserve parent messages and task links without merging by display name. | 1 | | OpenAI | [ChatGPT Space agent interactions](https://learn.chatgpt.com/docs/space) | cloud, browser, manual-export | Page-side conversations, inline requests, comments, agent replies and accepted document changes are separate evidence. Shared pages do not share private chats or memory. Preserve page/version/action links and agent identity. | 1 | | OpenAI | [ChatGPT Team Tasks](https://learn.chatgpt.com/docs/enterprise/teams) | cloud, browser, manual-export | Scheduled and event-triggered runs use a team service account and workspace connections. Preserve team/task/run identity, configured-versus-recorded models, generated files and workspace-credit billing. Runs do not inherit the creator's private history or become human activity. | 1 | | OpenAI | [ChatGPT Work Cloud](https://learn.chatgpt.com/docs/enterprise/cloud-local-access) | cloud, browser, manual-export | Cloud coordination can use a local executor or a cloud container, with changes between turns. Local telemetry omits cloud orchestration. Compliance records cover only supported events; existing ChatGPT chat exports and Codex cloud tasks do not establish full Work history. | 1 | | OpenAI | [ChatGPT Work Local](https://learn.chatgpt.com/docs/get-started-with-work) | local-store, manual-export | Local Work and Codex share core capabilities but retain separate histories. Verify recorded product identity, conversations, tools and artifacts; app branding or a Codex-compatible runtime does not establish existing importer coverage. | 1 | | OpenAI | [ChatGPT Workspace Agents](https://learn.chatgpt.com/workspace-agents) | cloud, browser, manual-export | Published agents can receive asynchronous ChatGPT API-channel triggers with separate access tokens. Trigger submission is not a history export. Verify agent versions, run enumeration, event retention and overlap with Team Tasks before any deduplication. | 1 | | OpenAI | [Codex Security CLI](https://learn.chatgpt.com/docs/security/cli) | local-store, manual-export | Default scan bundles and workbench.sqlite3 live under Codex Security plugin state; CODEX\_SECURITY\_STATE\_DIR overrides that root. Native evidence must reconcile shared workbench identity with plugin scans and distinguish partial coverage from completed scans. | 1 | | OpenAI | [Codex Security Cloud](https://learn.chatgpt.com/docs/security/setup) | cloud, manual-export | Existing Codex cloud transcripts do not establish coverage of scans, monitoring configuration, findings, artifacts or generated patches and draft-PR links. | 1 | | OpenAI | [Codex Security local plugin and workbench](https://learn.chatgpt.com/docs/security/plugin) | local-store, manual-export | Ordinary Codex transcripts may retain scan activity but do not preserve the complete sealed scan directory, workbench triage state or cross-scan finding identity. JSON, CSV and SARIF exports cover different fields. | 1 | | OpenAI | [OpenAI Agent Builder](https://developers.openai.com/api/docs/guides/agent-builder) | cloud, browser, manual-export | Preview runs and node traces need historical preservation separately from workflow definitions. Official documentation schedules shutdown for 2026-11-30. Exporting Agents SDK code or recreating a Workspace Agent does not export past conversations or run history. | 1 | | OpenAI | [OpenAI Agents API](https://developers.openai.com/api/docs/guides/agents-api/overview) | cloud, manual-export | Managed Codex sessions use API-project identity, independently of Codex SDK and ChatGPT cloud tasks. Streams do not replay missed events; saved items omit some intermediate events. Trace export requires organization enablement and may arrive later. Usage is best effort, lacks cache-write counts and is not a final bill; command-output truncation is not reported. | 1 | | OpenAI | [OpenAI Agents SDK applications](https://developers.openai.com/api/docs/guides/agents/sdk) | local-store, cloud, manual-export | Application-owned multi-agent workflows, sessions and traces are distinct from the Codex SDK CLI harness. Inspect the application's persistence and tracing policy, handoffs, tool runs and attachments; no universal retained-history store is established. | 1 | | Perplexity | [Comet assistant](https://www.perplexity.ai/comet) | browser, desktop | Verify whether browser-side tasks are ordinary Perplexity threads or a separate store; shared branding is insufficient. | 1 | | Perplexity | [Perplexity Computer](https://www.perplexity.ai/) | browser, cloud | Inspect multi-step task events, artifacts, subagents and usage independently from the existing search-thread capture. | 1 | | Replit | [Replit Agent](https://docs.replit.com/replitai/agent) | browser, manual-export, cloud | Project source exports alone are not conversation exports; retain task history, checkpoints, tools and artifacts. | 1 | | Replit | [Replit Chat](https://docs.replit.com/chat/overview) | cloud, browser, manual-export | General chat, research, connected context, and Routines can precede conversion into Projects. Preserve chat-to-project lineage and scheduled runs; Replit Agent project exports do not establish this coverage. | 1 | | Unresolved | Instinct | unknown | Public reporting identifies a personal messaging agent, but the official product URL and history interface remain unverified. The instinct.ai domain is a sale page, not product evidence; do not substitute an unrelated same-name package. | 1 | | Vercel | [v0](https://v0.dev/docs/api/platform) | cloud, browser, manual-export | Evaluate documented chats/messages API with pagination, versions, attachments and access boundaries. | 1 | | Vercel | [Vercel Agent](https://vercel.com/agent) | cloud, browser, manual-export | Dashboard and Slack investigations, approved actions, and code review need team/project identity, plans, approvals, tool evidence, deployments and pull-request lineage. v0 conversations are separate. | 1 | | xAI | [Grok Bot](https://docs.x.ai/grok-bot/overview) | desktop, browser, cloud | The client persists transcript replicas with caps of 200 entries, 768 KiB, 24 bots, and seven days. These caches cannot establish complete cloud history; sign-in and native capture are still needed. Native sign-in succeeded, but the linked account failed subscription eligibility. Native trial deferred; no paid plan or credit-card trial was activated. | 1 | | xAI | [Grok chat (web and mobile)](https://docs.x.ai/grok/overview.md) | browser, manual-export | Consumer Grok account history is separate from Grok Build and Grok Bot. | 1 | | Y Combinator | [QM (self-hosted)](https://github.com/yc-software/qm) | database-copy, cloud, browser | Durable deployments use PostgreSQL; the default in-memory store disappears on restart. Preserve scoped session identity, append-only tape, harness changes, approvals, compaction, source roles, artifacts and request usage. Viewer history is an audience-filtered projection. Codex, Claude Code, Pi and OpenCode backends do not imply QM coverage. | 1 | | Alibaba | [Qwen Code DashScope Batch jobs](https://github.com/QwenLM/qwen-code) | cloud, manual-export | The current official CLI exposes batch submit/manage workflows through the DashScope Batch API. Verify input/output records, job lifecycle, partial failures, request/account identity and usage without counting machine batch prompts as human conversations. | 2 | | Alibaba | [Qwen Code Desktop](https://github.com/QwenLM/qwen-code/releases/tag/desktop-latest) | desktop-cache, local-store | The official macOS, Windows and Linux app is separate from the consumer Qwen chat product. Verify configured homes, native client identity, workspaces, attachments and overlap with local CLI JSONL before claiming desktop coverage. | 2 | | Alibaba | [Qwen Code editor and ACP integrations](https://qwenlm.github.io/qwen-code-docs/en/users/integration-vscode/) | local-store, acp-events | Official VS Code, Zed and JetBrains interfaces require separate discovery and origin checks. A retained CLI-compatible session may overlap with qwen-code, but client-owned state and ACP streams are not proven by the CLI trial. | 2 | | Alibaba | [Qwen Code messaging channels](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/overview/) | local-store, local-api | Official docs list Telegram, DingTalk, WeChat, Feishu, QQ, WeCom, GitHub, GitLab and DingTalk Workspace channels. Verify per-user/group/workspace session scope, platform message identity, attachments, webhook-triggered jobs and human-versus-machine prompts. A channel transports requests to Qwen Code; it does not establish a vendor-hosted runtime. | 2 | | Alibaba | [Qwen Code SDK applications](https://qwenlm.github.io/qwen-code-docs/en/developers/sdk-typescript/) | local-store, sdk-events | Official TypeScript, Python and Java SDKs are documented separately. Verify durable versus ephemeral transcripts, application and subagent identity, machine-prompt accounting, and overlap with the CLI store. | 2 | | Alibaba | [Qwen Code Web UI and daemon](https://qwenlm.github.io/qwen-code-docs/en/users/qwen-serve/) | local-store, local-api, manual-export | The browser UI controls a local or explicitly selected daemon; browser access is not hosted execution. A native 0.24.7 probe reached the end of workspace-qualified persisted paging and read JSON/JSONL exports. Both omitted embedded image bytes; exports also omitted per-message models and some usage. Export channel labels do not establish original client identity. Capability, workspace, cursor and archived-source boundaries need explicit handling. | 2 | | Amazon | [Amazon Q Business](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/what-is.html) | cloud, manual-export | Business conversations have a different account/application API from coding agents. | 2 | | Amazon | [Amazon Q Developer CLI historical history](https://kiro.dev/docs/cli/) | local-store | Check migration into the Kiro classic SQLite reader with actual historical artifacts; do not install a retired client for current integration. | 2 | | Amazon | [Amazon Q Developer IDE](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html) | ide | Kiro imports do not establish Q Developer IDE chat coverage. | 2 | | Amazon | [Kiro Mobile](https://kiro.dev/docs/mobile/) | cloud, manual-export | Early-access iOS client uses the same cloud sessions as Kiro Web. This is a separate access surface, not evidence of a new conversation identity or an implemented mobile export. | 2 | | Amazon | [Kiro Web](https://kiro.dev/docs/web/) | browser, cloud, manual-export | Vendor documentation exposes browser-based multi-repository agents. Verify whether native exports include all web sessions and whether the cloud identity is shared with Kiro local sessions. | 2 | | Anthropic | [@Claude in Microsoft Teams (announced)](https://claude.com/product/tag) | cloud | The official product page describes a forthcoming Teams surface with a waitlist. Native availability and retained history are unverified; Slack support cannot be inferred. | 2 | | Apple | [Xcode coding intelligence](https://developer.apple.com/xcode/) | ide | Separate native Xcode chats from externally hosted Codex or Claude runs; do not count a shared model twice. | 2 | | ByteDance | [Coze](https://www.coze.com/) | cloud, manual-export | Bot conversations, workflows and development runs need separate identifiers and capture contracts. | 2 | | ByteDance | [Doubao](https://www.doubao.com/) | browser, manual-export | Consumer chats are separate from TRAE stores. Export, media and account boundaries need a native sample. | 2 | | Chatbox | [Chatbox](https://chatboxai.app/) | local-store, manual-export | Inspect native exported sessions, local attachment storage and provider metadata. | 2 | | ChatHub | [ChatHub](https://chathub.gg/) | browser, local-store, manual-export | Multi-model conversations span web, extension, desktop and mobile clients. Preserve each response model, side-by-side grouping, files and image output; a link from Chatbox does not establish common ownership or shared history. | 2 | | Cherry Studio | [Cherry Studio](https://docs.cherry-ai.com/) | local-store, manual-export | Database backup may contain credentials; preserve only allowlisted conversation and attachment data. | 2 | | Forge | [Forge](https://forgecode.dev/) | local-store, cloud | Determine retained conversation storage; configuration and analytics files do not prove transcript availability. | 2 | | Genspark | [Genspark](https://www.genspark.ai/) | browser, manual-export | Hosted agent tasks and generated artifacts need a retained-history capture contract. | 2 | | Google | [Firebase Studio](https://firebase.google.com/docs/studio) | browser, cloud, manual-export | Cloud workspace chat and prototyping sessions require account/workspace enumeration and task history. | 2 | | Google | [Flow](https://labs.google/flow/about) | browser, cloud, manual-export | Creative project prompts, generated assets and revisions are a distinct artifact-oriented surface. Conversation import scope and export fidelity require review. | 2 | | Google | [Gemini Code Assist](https://developers.google.com/gemini-code-assist/docs/overview) | ide, cloud | IDE chat history requires its own store contract; Antigravity and historical Gemini CLI are not substitutes. | 2 | | Google | [Gemini Enterprise and Agentspace](https://cloud.google.com/gemini-enterprise) | cloud, manual-export | Organization search and agent histories need tenant-specific APIs and retention evidence. | 2 | | Google | [Gemini in Firebase](https://firebase.google.com/docs/ai-assistance/gemini-in-firebase) | cloud, manual-export | Console and Firebase CLI assistance require separate history and retention verification from Firebase Studio workspaces. | 2 | | Google | [Gemini in Workspace](https://workspace.google.com/solutions/ai/) | cloud, manual-export | Workspace side-panel conversations may have different retention and export policies from Gemini Apps. | 2 | | Google | [Opal](https://opal.google/) | browser, manual-export | Workflow definitions and execution/chat histories must be distinguished. | 2 | | Google | [Stitch](https://stitch.withgoogle.com/) | browser, manual-export | Design conversation and generated assets need a distinct task/project model. | 2 | | Google | [Workspace Studio](https://workspace.google.com/studio/) | cloud, manual-export | Flow definitions, agent activity, and execution histories are separate from Gemini chat. Takeout lists flows and activity logs; their native schema and import scope require validation. | 2 | | gptme | [gptme Android](https://gptme.org/docs/app.html) | cloud-api, manual-export | Establish whether the client retains history bytes or only connects to a server; no Android-native capture or backup has been validated. | 2 | | gptme | [gptme Cloud](https://gptme.org/docs/cloud.html) | cloud-api, browser, manual-export | No account-wide hosted history acquisition, authentication contract, instance pagination, artifact capture or cross-route identity has been validated. | 2 | | gptme | [gptme Desktop](https://gptme.org/docs/app.html) | local-store, cloud-api | Locate the bundled local store and distinguish local execution from cloud sign-in; existing compatible-store parsing does not establish native desktop acceptance. | 2 | | gptme | [gptme Web UI (self-hosted)](https://gptme.org/docs/webui.html) | local-store, cloud-api | Verify server instance identity, branches, artifacts, panels, browser/computer previews and API pagination; a local-store trial does not prove web UI acceptance. | 2 | | Granola | [Granola Chat](https://docs.granola.ai/help-center/getting-more-from-your-notes/chatting-with-your-meetings.md) | desktop, cloud, manual-export | Private chat threads about meetings, folders and the full note collection are separate from meeting transcripts. The documented CSV export contains notes, summaries and meeting transcripts; it does not establish chat-history export coverage. | 2 | | Hugging Face | [HuggingChat](https://huggingface.co/chat/) | browser, manual-export | Hosted chat history is separate from local model inference and Hub datasets. | 2 | | Jan | [Jan](https://jan.ai/docs/) | local-store, manual-export | Read local threads and attachments with measured usage and model identity when recorded. | 2 | | JetBrains | [JetBrains AI Assistant chat](https://www.jetbrains.com/help/ai-assistant/) | ide | Junie task-chain history does not establish coverage for general AI Assistant chats. | 2 | | LibreChat | [LibreChat](https://www.librechat.ai/docs) | cloud, database-copy, manual-export | Multi-user conversation and agent history needs account-scoped capture and branch identity. | 2 | | LM Studio | [LM Studio chat](https://lmstudio.ai/docs/) | local-store, manual-export | Chat application history is separate from OpenAI-compatible API requests; inspect native persistence. | 2 | | Lovable | [Lovable](https://docs.lovable.dev/) | browser, manual-export | Project chat, edits, files and integration state need an explicit conversation export. | 2 | | Microsoft | [Copilot Studio](https://learn.microsoft.com/en-us/microsoft-copilot-studio/) | cloud, manual-export | Dataverse conversation transcripts and agent runs need independent schema validation. | 2 | | Microsoft | [Microsoft 365 Copilot](https://learn.microsoft.com/en-us/copilot/microsoft-365/) | cloud, manual-export | Work account interactions, app context and compliance exports need their own identity and source contract. | 2 | | MiniMax | [Talkie character chat](https://www.talkie-ai.com/) | browser, manual-export | Consumer character conversations are separate from MiniMax Code and Agent. The public data-export page lists profile fields without promising chat history; inspect native exports, character/thread identity, memories, retries and media. | 2 | | MiniMax | [Talkie Claw](https://www.talkie-ai.com/claw-guide) | cloud, browser, manual-export | Proactive character companions span messaging channels and generated media. Verify conversation/channel identity, background messages, attachments, and diamond billing independently of ordinary Talkie chat and OpenClaw local logs. | 2 | | Mintplex Labs | [AnythingLLM Desktop Assistant](https://docs.anythingllm.com/desktop-assistant/features) | local-store, manual-export | Desktop Assistant threads are saved in the Assistant Chat workspace. Preserve screenshots, tools and originating interface when recorded; do not duplicate shared workspace threads or treat screenshots as underlying application data. | 2 | | Mintplex Labs | [AnythingLLM Meeting Assistant](https://docs.anythingllm.com/meeting-assistant/features) | local-store, manual-export | Meeting transcripts and generated summaries are distinct from agent follow-up actions. Ask Questions creates a workspace containing the transcript; preserve links, source revisions, approvals and tool results without treating meeting speech as chat prompts. | 2 | | Mintplex Labs | [AnythingLLM Mobile](https://docs.anythingllm.com/mobile/overview) | local-store, manual-export | Android is a standalone harness even when inference uses desktop or cloud providers. JSON/Markdown exports, on-device threads, forks, scheduled jobs and optional instance sync need native schema and cross-route identity checks. | 2 | | Mintplex Labs | [AnythingLLM scheduled jobs](https://docs.anythingllm.com/scheduled-jobs/viewing-runs) | local-store, cloud, manual-export | Run records preserve configured prompt, thinking, tool arguments/results, files, clocks and recorded token counters. The UI shows the latest 50 runs. Continue in Thread copies prompt and final response, not the full run; retain lineage and avoid double-counting human activity. | 2 | | Mintplex Labs | [AnythingLLM workspace chat](https://docs.anythingllm.com/) | local-store, cloud, manual-export | Desktop, self-hosted and cloud workspace chats expose CSV, JSON, Alpaca and OpenAI fine-tune exports with account permissions. Native database/API fidelity, agent tools, branches, attachments and account boundaries remain unverified. Training exports may omit conversation evidence. | 2 | | Mistral | [Mistral Vibe for code in IDEs](https://mistral.ai/products/vibe/code/) | local-store, manual-export | Official pages distinguish VS Code, JetBrains, and Zed access. Verify host, ACP transport, retained store, and local/remote session identity; the Vibe CLI importer alone does not establish these surfaces. | 2 | | Notion | [Notion Agent](https://www.notion.com/help/notion-agent) | desktop, browser, cloud, manual-export | Personal agent chat, tool actions, model selection, page context and connected sources need a native history contract. Workspace document exports are not proof of conversation coverage. | 2 | | Notion | [Notion Custom Agents](https://www.notion.com/help/custom-agents) | desktop, browser, cloud | Triggered and scheduled agent runs, interactive chats, activity logs, approval history and configuration versions are separate from personal Notion Agent conversations. | 2 | | oh-my-pi | [oh-my-pi](https://github.com/can1357/oh-my-pi) | local-store | Separate data root and diverged schema; the pi importer is not sufficient. | 2 | | Open Interpreter | [Interpreter Desktop](https://www.openinterpreter.com/desktop) | local-store, manual-export | The document workstation is separate from the terminal agent. Verify native conversation stores, Word/Excel/PDF edits, browser/computer tools, attachments and local versus hosted model evidence. | 2 | | Open Interpreter | [Open Interpreter terminal](https://docs.openinterpreter.com/) | local-store, manual-export | Inspect retained terminal conversation logs and computer/tool semantics by client generation. The current terminal agent and Interpreter Desktop workstation have separate source repositories; neither has an implemented importer. | 2 | | Open WebUI | [Open WebUI](https://docs.openwebui.com/) | cloud, database-copy, manual-export | Use account-scoped exports/API before database reads; preserve branches, tools and files. | 2 | | OpenClaw Foundation | [Remote OpenClaw Gateway](https://docs.openclaw.ai/) | cloud, manual-export | The existing importer requires a locally accessible Gateway state directory; remote history API is a separate route. | 2 | | Qoder | [Qoder Agent SDK](https://docs.qoder.com/cli/sdk/overview) | browser, cloud, manual-export | Vendor documents an SDK separately from its CLI. Verify transcript persistence and machine-run provenance before claiming coverage through the CLI reader. | 2 | | Quora | [Poe](https://poe.com/) | browser, manual-export | Multi-bot conversations need raw bot/model identity, branching and attachment coverage. | 2 | | StackBlitz | [Bolt](https://support.bolt.new/) | browser, manual-export | Capture project chat and revision/checkpoint history independently of exported source code. | 2 | | Tencent | [Yuanbao](https://yuanbao.tencent.com/) | browser, manual-export | CodeBuddy coding sessions do not cover the consumer assistant. | 2 | | Vercel | [eve agent framework](https://eve.dev/) | cloud, local-store, manual-export | History belongs to each deployed application and its access policy. Durable session IDs differ from executing workflow runs and channel continuation tokens. Replay must preserve stream versions, delta/final semantics, retry ambiguity, compaction and child tasks. | 2 | | xAI | [Grok in X](https://help.x.com/en/using-x/about-grok) | browser, manual-export | Verify whether X history and grok.com history share account and conversation identity before joining captures. | 2 | | You.com | [You.com](https://you.com/) | browser, manual-export | Search, research and custom-agent histories need native account export evidence. | 2 | | CloudStack (Msty) | [Msty Nexus model testing](https://msty.ai/products/nexus/) | local-store, manual-export | Nexus includes interactive model, preset, and route testing inside its gateway console. Verify whether tester conversations persist. Gateway request logs and current routing settings cannot stand in for consumer history or historical reply-model attribution. | 3 | | CloudStack (Msty) | [Msty Studio](https://msty.ai/products/studio/) | local-store, browser, manual-export | Official exports contain conversation/split structure and either embedded attachment data in JSON or files in .mstyconv ZIPs. Branches, crew/persona replies, tools and missing older attachments require native schema validation. Go and Nexus are separate. | 3 | | Cognition | [DeepWiki chat](https://deepwiki.com/) | browser | Repository documentation Q\&A may be separate from Ask Devin. Inspect persistent identity and export availability. | 3 | | Dify | [Dify](https://docs.dify.ai/) | cloud, database-copy, manual-export | Chat messages, workflow runs and application telemetry require separate event identities. | 3 | | Flowise | [Flowise](https://docs.flowiseai.com/) | cloud, database-copy, manual-export | Chat history and workflow traces require versioned contracts and credential-safe raw preservation. | 3 | | Google | [Gemini in Android Studio](https://developer.android.com/studio/gemini/overview) | ide | Verify Android Studio chat persistence separately from Code Assist. | 3 | | n8n | [n8n AI agents](https://docs.n8n.io/) | cloud, database-copy, manual-export | Workflow execution records are not automatically human conversations; preserve machine-run classification. | 3 | | Nous Research | [Remote Hermes profiles](https://hermes-agent.nousresearch.com/docs/) | cloud, manual-export | Local profile SQLite coverage does not prove remote-only account enumeration. | 3 | | OpenHands | [Remote self-hosted OpenHands](https://docs.openhands.dev/) | cloud, manual-export | Local store and hosted Cloud adapters exist; verify arbitrary self-hosted API compatibility and auth scope. | 3 | | Plandex | [Plandex](https://docs.plandex.ai/) | cloud, manual-export | Inspect server-side plan/conversation exports and retained version history. | 3 | | Posit | [Databot (historical)](https://assistant.posit.co/docs/getting-started/) | local-store, manual-export | Historical exploratory data-analysis agent superseded by Posit Assistant. Native legacy storage and migration continuity remain unverified. | 3 | | Posit | [Positron Assistant (historical)](https://assistant.posit.co/docs/getting-started/) | local-store, manual-export | Superseded by Posit Assistant as of Positron 2026.07. Preserve historical stores independently; shared branding does not establish schema or identity compatibility. | 3 | | SWE-agent | [mini-SWE-agent](https://mini-swe-agent.com/latest/) | local-store | Versioned task trajectories need separate job classification and cost accounting. | 3 | | SWE-agent | [SWE-agent](https://swe-agent.com/latest/) | local-store | Trajectory files are machine-prompted jobs, not human conversation activity. | 3 | | Xiaomi | [MiMo hosted chat or playground](https://mimo.xiaomi.com/) | browser, manual-export | A model/API brand is not proof of durable account history. Inspect the actual hosted history before defining a source. | 3 | ## Format and drift coverage The source-shape registry declares **70 enforced**, **54 observation-only**, **2 unsupported**, and **1 inapplicable** contracts. Enforced contracts reject unfamiliar structural cohorts. Observation-only contracts record shape evidence without establishing exhaustive field coverage. An unsupported shape contract can accompany a raw-preservation route. Shape policy, raw replay support, and import availability are separate properties. A matching shape does not prove every metadata field is normalized or displayed. Tests associated with every implemented product are listed in the machine-readable catalog; a fixture pass does not establish native account access or acceptance. Bounded JSON field accounting is declared for **9 formats**, and selected protobuf schema accounting for **6 formats**. **112 formats have no declared field audit.** These audits cover only the scopes listed below; none establishes complete provider metadata fidelity. | Source format | Parser version | Product entry | Shape policy | Field audit | Raw replay | | --------------------------------------- | -------------- | ------------------------------------------------------------------------- | ------------ | ------------------------ | ----------- | | `aider-chat-history` | `0.6.1.0` | aider | enforce | Not declared | supported | | `amp-cloud-history` | `0.6.1.0` | amp-cloud | enforce | Not declared | deferred | | `amp-thread-export` | `0.6.1.0` | amp-export | enforce | Not declared | deferred | | `amp-thread-history` | `0.6.1.0` | amp | enforce | Not declared | deferred | | `antigravity-cli-brain` | `0.6.1.0` | antigravity-cli | observe | Not declared | deferred | | `antigravity-cli-conversation-db` | `0.6.1.0` | antigravity-cli | observe | Selected protobuf schema | deferred | | `antigravity-cli-language-server-steps` | `0.6.1.0` | antigravity-cli | observe | Selected protobuf schema | deferred | | `antigravity-cli-transcript-log` | `0.6.1.0` | antigravity-cli | observe | Not declared | supported | | `antigravity-conversation-db` | `0.6.1.0` | antigravity | observe | Selected protobuf schema | deferred | | `antigravity-history` | `0.6.1.0` | antigravity | observe | Not declared | deferred | | `antigravity-ide-brain` | `0.6.1.0` | antigravity-ide | observe | Not declared | deferred | | `antigravity-ide-conversation-db` | `0.6.1.0` | antigravity-ide | observe | Selected protobuf schema | deferred | | `antigravity-ide-language-server-steps` | `0.6.1.0` | antigravity-ide | observe | Selected protobuf schema | deferred | | `antigravity-ide-transcript-log` | `0.6.1.0` | antigravity-ide | observe | Not declared | supported | | `antigravity-language-server-steps` | `0.6.1.0` | antigravity | observe | Selected protobuf schema | deferred | | `antigravity-protobuf` | `0.6.1.0` | antigravity | unsupported | Not declared | unsupported | | `antigravity-summary-proto` | `0.6.1.0` | antigravity | observe | Not declared | deferred | | `antigravity-trajectory-summary` | `0.6.1.0` | antigravity | observe | Not declared | deferred | | `antigravity-transcript-log` | `0.6.1.0` | antigravity | observe | Not declared | supported | | `augment-cli-history` | `0.6.1.0` | augment | enforce | Not declared | deferred | | `augment-cloud-history` | `0.6.1.0` | augment-cloud | enforce | Not declared | deferred | | `augment-cosmos-history` | `0.6.1.0` | augment | enforce | Not declared | deferred | | `augment-ide-history` | `0.6.1.0` | augment | enforce | Not declared | deferred | | `chatgpt-browser` | `0.6.1.0` | chatgpt | observe | Not declared | deferred | | `chatgpt-export` | `0.6.1.0` | chatgpt | observe | Not declared | deferred | | `claude-cloud-history` | `0.6.1.0` | claude-cloud, claude-remote-control | observe | Not declared | deferred | | `claude-code-desktop-metadata` | `0.6.1.0` | claude-code-desktop | observe | Not declared | supported | | `claude-sdk-history` | `0.6.1.0` | claude-sdk | observe | Not declared | supported | | `claude-web-browser` | `0.6.1.0` | claude-web | observe | Not declared | deferred | | `claude-web-export` | `0.6.1.0` | claude-web | observe | Not declared | deferred | | `claude-web-memory` | `0.6.1.0` | claude-web | observe | Not declared | deferred | | `claude-workspace-desktop` | `0.6.1.0` | claude-cowork-cloud, claude-cowork | observe | Not declared | supported | | `cli-history` | `0.6.1.0` | claude, claude-remote-control | observe | Not declared | supported | | `cline-sdk-session-history` | `0.6.1.0` | cline-cli | enforce | Not declared | supported | | `cline-task-history` | `0.6.1.0` | cline | enforce | Not declared | supported | | `codebuddy-history` | `0.6.1.0` | codebuddy | observe | Not declared | supported | | `codex-cli-history` | `0.6.1.0` | codex-cli | enforce | Not declared | supported | | `codex-cloud-history` | `0.6.1.0` | codex-cloud | observe | Not declared | deferred | | `codex-desktop-history` | `0.6.1.0` | codex-desktop | enforce | Not declared | supported | | `codex-sdk-history` | `0.6.1.0` | codex-sdk | enforce | Not declared | supported | | `continue-history` | `0.6.1.0` | continue | enforce | Not declared | deferred | | `copilot-agent-session` | `0.6.1.0` | copilot-agent-cloud | observe | Not declared | deferred | | `copilot-cli-history` | `0.6.1.0` | copilot-cli | observe | Bounded JSON fields | supported | | `copilot-ide-history` | `0.6.1.0` | copilot-ide | observe | Not declared | supported | | `crush-history` | `0.6.1.0` | crush | enforce | Not declared | deferred | | `cursor-agent-transcripts` | `0.6.1.0` | cursor | observe | Not declared | supported | | `cursor-cli-history` | `0.6.1.0` | cursor-cli | observe | Not declared | deferred | | `cursor-cloud-history` | `0.6.1.0` | cursor-cloud | observe | Not declared | deferred | | `cursor-global-sqlite` | `0.6.1.0` | cursor | observe | Not declared | deferred | | `cursor-raw-sqlite-salvage` | `0.6.1.0` | cursor | observe | Not declared | deferred | | `cursor-workspace-sqlite` | `0.6.1.0` | cursor | observe | Not declared | deferred | | `deepseek-harness-history` | `0.6.1.0` | deepseek-harness | enforce | Not declared | deferred | | `devin-ask-browser` | `0.6.1.0` | ask-devin | observe | Not declared | deferred | | `devin-cli-history` | `0.6.1.0` | devin-cli | observe | Not declared | supported | | `devin-cloud-browser` | `0.6.1.0` | devin-cloud | observe | Not declared | deferred | | `devin-cloud-history` | `0.6.1.0` | devin-cloud | observe | Not declared | deferred | | `devin-desktop-acp-events` | `0.6.1.0` | devin-desktop | observe | Not declared | supported | | `devin-desktop-acp-messages` | `0.6.1.0` | devin-desktop | observe | Not declared | deferred | | `factory-cloud-history` | `0.6.1.0` | factory-cloud | observe | Not declared | deferred | | `factory-droid-history` | `0.6.1.0` | factory | observe | Bounded JSON fields | supported | | `gemini-cli-history` | `0.6.1.0` | gemini-cli | enforce | Not declared | supported | | `gemini-web-browser` | `0.6.1.0` | gemini-web | observe | Not declared | deferred | | `gemini-web-export` | `0.6.1.0` | gemini-web | observe | Not declared | deferred | | `goose-jsonl-history` | `0.6.1.0` | goose | enforce | Not declared | deferred | | `goose-sqlite-history` | `0.6.1.0` | goose | enforce | Bounded JSON fields | deferred | | `gptme-history` | `0.6.1.0` | gptme | enforce | Bounded JSON fields | supported | | `grok-build-history` | `0.6.1.0` | grok-build | observe | Bounded JSON fields | supported | | `hermes-jsonl-history` | `0.6.1.0` | hermes | enforce | Not declared | deferred | | `hermes-sqlite-history` | `0.6.1.0` | hermes | enforce | Not declared | deferred | | `iflow-cli-history` | `0.6.1.0` | iflow | enforce | Not declared | supported | | `import` | `0.6.1.0` | Generic normalized input, not a provider contract. | inapplicable | Not declared | unsupported | | `jules-cloud-history` | `0.6.1.0` | jules | observe | Not declared | deferred | | `junie-cli-history` | `0.6.1.0` | junie | enforce | Not declared | deferred | | `junie-ide-history` | `0.6.1.0` | junie | enforce | Not declared | deferred | | `kilo-code-cloud-history` | `0.6.1.0` | kilo-code-cloud | enforce | Not declared | deferred | | `kilo-code-sqlite-history` | `0.6.1.0` | kilo-code | enforce | Not declared | deferred | | `kilo-code-task-history` | `0.6.1.0` | kilo-code-legacy | enforce | Not declared | deferred | | `kimi-cli-history` | `0.6.1.0` | kimi-cli | enforce | Not declared | supported | | `kimi-code-history` | `0.6.1.0` | kimi-code | enforce | Not declared | supported | | `kiro-classic-history` | `0.6.1.0` | kiro | enforce | Not declared | deferred | | `kiro-cli-history` | `0.6.1.0` | kiro | enforce | Not declared | deferred | | `kiro-crew-history` | `0.6.1.0` | kiro | enforce | Not declared | deferred | | `kiro-ide-history` | `0.6.1.0` | kiro | enforce | Not declared | deferred | | `kiro-session-export` | `0.6.1.0` | kiro-export | enforce | Not declared | deferred | | `kiro-unified-history` | `0.6.1.0` | kiro | enforce | Not declared | deferred | | `mimo-code-history` | `0.6.1.0` | mimo-code | enforce | Not declared | supported | | `minimax-code-cloud-history` | `0.6.1.0` | minimax-code-cloud | enforce | Not declared | deferred | | `minimax-code-history` | `0.6.1.0` | minimax-code | enforce | Not declared | deferred | | `muse-code-history` | `0.6.1.0` | muse-code | enforce | Not declared | supported | | `notebooklm-export` | `0.6.1.0` | notebooklm | observe | Bounded JSON fields | supported | | `openclaw-jsonl-history` | `0.6.1.0` | openclaw | enforce | Not declared | deferred | | `openclaw-sqlite-history` | `0.6.1.0` | openclaw | enforce | Not declared | deferred | | `opencode-history` | `0.6.1.0` | opencode | enforce | Not declared | supported | | `opencode-sqlite-history` | `0.6.1.0` | opencode | enforce | Not declared | supported | | `openhands-cloud-history` | `0.6.1.0` | openhands-cloud | enforce | Not declared | deferred | | `openhands-legacy-history` | `0.6.1.0` | openhands | enforce | Not declared | deferred | | `openhands-sdk-history` | `0.6.1.0` | openhands | enforce | Not declared | deferred | | `perplexity-browser` | `0.6.1.0` | perplexity | observe | Not declared | deferred | | `pi-cli-history` | `0.6.1.0` | pi | enforce | Bounded JSON fields | supported | | `posit-assistant-history` | `0.6.1.0` | posit-assistant | enforce | Bounded JSON fields | supported | | `prime-agent-history` | `0.6.1.0` | prime-agent | enforce | Not declared | supported | | `qoder-app-history` | `0.6.1.0` | qoder | enforce | Not declared | deferred | | `qoder-cli-history` | `0.6.1.0` | qoder | enforce | Not declared | deferred | | `qoder-cloud-history` | `0.6.1.0` | qoder-cloud | enforce | Not declared | deferred | | `qoder-ide-history` | `0.6.1.0` | qoder | enforce | Not declared | deferred | | `qoder-work-history` | `0.6.1.0` | qoder | enforce | Not declared | deferred | | `qwen-code-history` | `0.6.1.0` | qwen-code | enforce | Bounded JSON fields | supported | | `roo-code-cli-history` | `0.6.1.0` | roo-code-cli | enforce | Not declared | deferred | | `roo-code-task-history` | `0.6.1.0` | roo-code | enforce | Not declared | deferred | | `roomote-cloud-history` | `0.6.1.0` | roomote-cloud | enforce | Not declared | deferred | | `roomote-db-history` | `0.6.1.0` | roomote-db | enforce | Not declared | deferred | | `trae-agent-history` | `0.6.1.0` | trae | enforce | Not declared | deferred | | `trae-ide-history` | `0.6.1.0` | trae | enforce | Not declared | deferred | | `trae-legacy-history` | `0.6.1.0` | trae | enforce | Not declared | deferred | | `trae-work-history` | `0.6.1.0` | trae | enforce | Not declared | deferred | | `vibe-cli-history` | `0.6.1.0` | vibe | enforce | Not declared | supported | | `warp-cli-history` | `0.6.1.0` | warp | enforce | Not declared | deferred | | `warp-cloud-history` | `0.6.1.0` | warp-cloud | enforce | Not declared | deferred | | `warp-desktop-history` | `0.6.1.0` | warp | enforce | Not declared | deferred | | `web-chat-export` | `0.6.1.0` | Generic historical export compatibility envelope, not a distinct product. | observe | Not declared | deferred | | `windsurf-cascade-brain` | `0.6.1.0` | windsurf | observe | Not declared | deferred | | `windsurf-cascade-protobuf` | `0.6.1.0` | windsurf | unsupported | Not declared | unsupported | | `windsurf-language-server-transcript` | `0.6.1.0` | windsurf | observe | Not declared | supported | | `windsurf-trajectory-export` | `0.6.1.0` | windsurf | observe | Not declared | supported | | `windsurf-transcript-jsonl` | `0.6.1.0` | windsurf | observe | Not declared | supported | | `zed-agent-history` | `0.6.1.0` | zed | enforce | Not declared | deferred | | `zed-text-history` | `0.6.1.0` | zed | enforce | Not declared | deferred | ### Field-audit scopes These versioned contracts detect changes in the selected fields or declarations. Runtime normalization, preserved bytes, and viewer behavior still require separate checks. A parser version change requires review of every associated contract, and a scope change regenerates this reference. | Source formats | Audit | Declared scope | | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `antigravity-conversation-db`, `antigravity-cli-conversation-db`, `antigravity-ide-conversation-db`, `antigravity-language-server-steps`, `antigravity-cli-language-server-steps`, `antigravity-ide-language-server-steps` | Selected protobuf schema | Selected embedded protobuf descriptors audited in the official Antigravity CLI 1.2.13 and desktop language server. This is a schema field contract, not complete record or billing acceptance. | | `copilot-cli-history` | Bounded JSON fields | Copilot CLI 1.0.89 JSONL events from an offline local OpenAI-compatible endpoint: initial and resumed text turns, view tool, and controlled bash failure. Endpoint tokens are injected test counters, not measured hosted usage. SQLite ledger columns, workspace/checkpoint sidecars, attachments, subagents, compaction, Remote Control, SDK, desktop and cloud histories require separate field audits. | | `factory-droid-history` | Bounded JSON fields | Droid 0.229.0 native text, Execute, Read, Create, Edit, controlled command and edit failures, embedded tool-result image and session-settings records. User-uploaded documents, workers, provider failures and hosted resume require separate evidence. | | `goose-sqlite-history` | Bounded JSON fields | Goose CLI 1.52.0 SQLite initial and resumed synthetic conversations through a local OpenAI-compatible endpoint, including write/edit, a failed edit, a nonzero shell result and an image result. Usage counters are injected, not measured billing. Legacy JSONL, desktop/API interfaces, hosted providers, recipes, schedules, subagents, compaction, user uploads and other tool/block kinds need separate audits. | | `gptme-history` | Bounded JSON fields | Observed gptme 0.34.0 native main/branch/view/recovery shapes and explicitly scoped chat configuration. A field-accounting pass is not evidence of hosted billing, attachment byte fidelity, child linkage, or web/desktop acceptance. | | `grok-build-history` | Bounded JSON fields | Metadata sidecars only. Update, event, chat, workflow, resource and attachment schemas require separate contracts. A pass verifies declared field accounting, not normalization or raw fidelity. | | `notebooklm-export` | Bounded JSON fields | NotebookLM consumer Takeout notebook and text-source JSON metadata from one native prompt/reply export. Chat HTML, generated artifacts, binary sources, and other source types require separate contracts. Metadata for notebooks without chats is raw-only. | | `pi-cli-history` | Bounded JSON fields | pi coding-agent 0.73.1 v3 tree JSONL: initial and resumed text turns through a local OpenAI-compatible endpoint, current edit arrays, a failed edit, a failed bash call and an image result. Injected tokens and configured-rate costs are synthetic. Forks, compaction, extensions, uploads, thinking content, other APIs, hosted use and older producer versions require additional cohorts. | | `posit-assistant-history` | Bounded JSON fields | Native v3 tree, LM/UI sidecars, and workspace metadata from the TUI local synthetic-endpoint trial. Attachments, compaction, child sessions, and other providers need separate samples. | | `qwen-code-history` | Bounded JSON fields | Qwen Code 0.24.7 tree JSONL and version-one usage ledger: one initial and two resumed turns through a local OpenAI-compatible endpoint, file creation/edit, controlled edit/shell failures, a capability-rejected image and an embedded image result. Injected token counters are synthetic. Hosted metering, user uploads, extensions, subagents, branches, compaction, other backends and older producing versions require additional cohorts. | ## Acceptance and drift Every route needs a versioned native sample and a repeatable import trial covering messages, tool arguments/results, edits, attachments, models, measured usage, repository/branch context, account/organization/project identity, lifecycle, billing, and parent/child relationships where the provider records them. A metadata field must be identified as normalized, preserved only in safe raw data, intentionally excluded with a reason, unavailable, or still unreviewed. Trials must preserve complete earlier transcripts and raw records, update a resumed session in place, distinguish absent fields from explicit clears, avoid stale metadata overwriting newer evidence, and deduplicate only with verified account and conversation identity. Unknown record types and metadata paths need a visible drift report. Partial pagination, inaccessible attachments, unsupported formats, and unavailable clocks must never be reported as complete captures. The coverage audit checks every registered source, parser format, and browser route against this inventory. Adding a source or format without a product entry fails the audit. Public vendor discovery is a separate network check: candidate links require review before becoming support claims.