AgentsSession capture

00 — Executive Summary

Native-store capture is the dominant mechanism, but no reviewed product provides jackin❯’s required cross-agent, host-side, purge-surviving archive.

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.

Question and scope

What does the current session-capture landscape imply for the Déjà Vu design?

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

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, 02). 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, 12, 20). 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). 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

  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).
  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).
  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).
  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).
  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).
  6. jackin❯'s substrate advantage is real and already shipped: agent homes are restored host-side under ~/.jackin/data/<container>/, so capture for five of six agents is a read of paths jackin❯ already owns — while today eject/prune deletes those very histories (30).

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.

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

Product capabilities and agent formats can drift after the verification cutoff; provider adapters need direct revalidation before implementation.

Sources

Session Capture Research

Dossier on coding-session capture mechanisms, products, native agent stores, market coverage, and jackin❯ integration options.

01 — SpecStory: Product, Business, Reception

SpecStory pairs an open CLI capture engine with closed editor and hosted surfaces, plus documented fidelity and privacy risks.

On this page

SummaryQuestion and scopeMethodFindingsThe landscape in six sentencesHeadline findingsWhat changes for Déjà VuImplications for jackin❯Limitations and unknownsSourcesRelated work