# 00 — Executive Summary (https://jackin.tailrocks.com/research/agents/session-capture/00-executive-summary/) ## Summary [#summary] Summarizes the session-capture market, common extraction model, coverage gaps, and implications for Déjà Vu. **Verification cutoff:** 2026-07-03. Scope per the research brief: how SpecStory works, what else exists, and what it means for jackin❯. This dossier is the evidence layer for the [Déjà Vu conversation-capture design](/research/agents/orchestration/conversation-capture/). ## Question and scope [#question-and-scope] What does the current session-capture landscape imply for the Déjà Vu design? ## Method [#method] This synthesis combines the SpecStory product and source audits, native agent-store inspection, the exporter and platform catalog, and the comparison matrix at the verification cutoff. ## Findings [#findings] ### The landscape in six sentences [#the-landscape-in-six-sentences] Session capture — persisting every AI coding conversation into durable, searchable artifacts — has one production-grade cross-agent implementation: **SpecStory**, whose open-source (Apache-2.0) Go CLI reads six agents' native on-disk stores via fsnotify, normalizes them into one schema, and renders markdown into `.specstory/history/` ([01](/research/agents/session-capture/01-specstory-product/), [02](/research/agents/session-capture/02-specstory-cli-internals/)). The entire market — SpecStory, the closed competitor Mantra, and \~40 OSS exporters/viewers — has converged on the same mechanism: **read the agent's own session files**; nobody PTY-scrapes, and hooks/OTel/wire-taps appear only as side channels ([11](/research/agents/session-capture/11-open-source-exporters/), [12](/research/agents/session-capture/12-platforms-and-observability/), [20](/research/agents/session-capture/20-comparison-matrix/)). Every agent jackin❯ runs persists a watchable local transcript except Amp, which requires live `--stream-json` capture — and the two agents nobody covers, Kimi and Grok, have useful native surfaces (versioned `wire.jsonl`; documented session dirs + ACP streams) ([10](/research/agents/session-capture/10-agent-session-stores/)). Capture itself is commoditized to $0 by its own vendor; value has moved up-stack to search, cross-agent resume, skill-mining (Lore), and turn↔code attribution (Mantra's git time-travel, SpecStory's provenance engine). SpecStory v2.0.0 provides cross-project **cross-agent resume** by reconstructing a session into a different agent's native format, validating demand for the cross-agent layer Déjà Vu targets. At the verification cutoff, **no product provides a cross-agent, host-side, purge-surviving archive**. ### Headline findings [#headline-findings] 1. **Déjà Vu's core bets are confirmed by the whole market.** Native-file reading first, vendor streams as hedge, screen-scrape used by literally nobody ([20 §mechanism scorecard](/research/agents/session-capture/20-comparison-matrix/)). 2. **SpecStory's implementation is a reusable blueprint, not just inspiration**: 58k LOC Apache-2.0 Go — provider SPI (11 methods), unified `SessionData` schema, disposable FTS5 index fingerprinted by size+mtime+version, full-rewrite idempotent markdown rendering, cross-agent reconstruction with `MigrationNote` ([02](/research/agents/session-capture/02-specstory-cli-internals/)). 3. **Best-case off-the-shelf coverage of jackin❯'s six agents is 2/6 (SpecStory) to 3/6 (claude-replay)**; zero tools cover Kimi or Grok — first-mover ground for jackin❯ ([20 §coverage](/research/agents/session-capture/20-comparison-matrix/)). 4. **OTel cannot cover the fleet**: only Claude/Codex/Gemini export it at all; for Amp, OpenCode, Kimi, Grok there is no telemetry channel — files and vendor APIs are the only fleet-wide capture path ([10](/research/agents/session-capture/10-agent-session-stores/)). 5. **The failure modes are documented, not hypothetical**: editor-update breakage, CPU-burning polls, silent incompleteness, un-gitignored transcripts leaking secrets — each with SpecStory issue numbers to design against ([01 §complaints](/research/agents/session-capture/01-specstory-product/)). 6. **jackin❯'s substrate advantage is real and already shipped**: agent homes are restored host-side under `~/.jackin/data//`, so capture for five of six agents is a read of paths jackin❯ already owns — while today `eject`/`prune` deletes those very histories ([30](/research/agents/session-capture/30-jackin-fit/)). ### What changes for Déjà Vu [#what-changes-for-déjà-vu] Confirmed: vector ranking, provider architecture, storage shape, market-gap claim. New inputs: the roster is six agents now (Grok added; several docs still say five); SpecStory shipped cross-agent resume ahead of plan — mechanism worth studying; attribution (turn↔git-state) has moved from "distant non-goal" to "two competitors are on it"; Kimi/Grok store layouts are now mapped externally but need in-container verification. Full delta in [30](/research/agents/session-capture/30-jackin-fit/). ## Implications for jackin❯ [#implications-for-jackin] Build Déjà Vu on native session stores with structured-stream capture for Amp, while keeping archive ownership, search, and retention on the host. ## Limitations and unknowns [#limitations-and-unknowns] Product capabilities and agent formats can drift after the verification cutoff; provider adapters need direct revalidation before implementation. ## Sources [#sources] * [SpecStory product evidence](/research/agents/session-capture/01-specstory-product/) * [SpecStory CLI internals](/research/agents/session-capture/02-specstory-cli-internals/) * [Agent session stores](/research/agents/session-capture/10-agent-session-stores/) * [Open-source exporters](/research/agents/session-capture/11-open-source-exporters/) * [Platforms and observability](/research/agents/session-capture/12-platforms-and-observability/) * [Comparison matrix](/research/agents/session-capture/20-comparison-matrix/) ## Related work [#related-work] * [Session-capture dossier](/research/agents/session-capture/) * [Déjà Vu conversation-capture design](/research/agents/orchestration/conversation-capture/)