​

Session Management & Compaction (Deep Dive)

• Session routing (how inbound messages map to a sessionKey)
• Session store (sessions.json) and what it tracks
• Transcript persistence (*.jsonl) and its structure
• Transcript hygiene (provider-specific fixups before runs)
• Context limits (context window vs tracked tokens)
• Compaction (manual + auto-compaction) and where to hook pre-compaction work
• Silent housekeeping (e.g. memory writes that shouldn’t produce user-visible output)

• /concepts/session
• /concepts/compaction
• /concepts/session-pruning
• /reference/transcript-hygiene

​

Source of truth: the Gateway

• UIs (macOS app, web Control UI, TUI) should query the Gateway for session lists and token counts.
• In remote mode, session files are on the remote host; “checking your local Mac files” won’t reflect what the Gateway is using.

​

Two persistence layers

1. Session store (sessions.json)
   • Key/value map: sessionKey -> SessionEntry
   • Small, mutable, safe to edit (or delete entries)
   • Tracks session metadata (current session id, last activity, toggles, token counters, etc.)
2. Transcript (<sessionId>.jsonl)
   • Append-only transcript with tree structure (entries have id + parentId)
   • Stores the actual conversation + tool calls + compaction summaries
   • Used to rebuild the model context for future turns

​

On-disk locations

• Store: ~/.fased/agents/<agentId>/sessions/sessions.json
• Transcripts: ~/.fased/agents/<agentId>/sessions/<sessionId>.jsonl
  • Telegram topic sessions: .../<sessionId>-topic-<threadId>.jsonl

​

Store maintenance and disk controls

• mode: warn (default) or enforce
• pruneAfter: stale-entry age cutoff (default 30d)
• maxEntries: cap entries in sessions.json (default 500)
• rotateBytes: rotate sessions.json when oversized (default 10mb)
• resetArchiveRetention: retention for *.reset.<timestamp> transcript archives. Defaults to the same value as pruneAfter; false disables cleanup.
• maxDiskBytes: optional sessions-directory budget
• highWaterBytes: optional target after cleanup (default 80% of maxDiskBytes)

1. Remove oldest archived or orphan transcript artifacts first.
2. If still above the target, evict oldest session entries and their transcript files.
3. Keep going until usage is at or below highWaterBytes.

fased sessions cleanup --dry-run
fased sessions cleanup --enforce

​

Task/cron sessions and run logs

• cron.sessionRetention (default 24h) prunes old isolated task/cron run sessions from the session store (false disables).
• cron.runLog.maxBytes + cron.runLog.keepLines prune ~/.fased/cron/runs/<jobId>.jsonl files. Defaults are 2_000_000 bytes and 2000 lines.

​

Session keys (sessionKey)

• Main/direct chat (per agent): agent:<agentId>:<mainKey> (default main)
• Group: agent:<agentId>:<channel>:group:<id>
• Room/channel (Discord/Slack): agent:<agentId>:<channel>:channel:<id> or ...:room:<id>
• Task/cron: cron:<job.id>
• Webhook: hook:<uuid> (unless overridden)

​

Session ids (sessionId)

• Reset (/new, /reset) creates a new sessionId for that sessionKey.
• Daily reset defaults to 4:00 AM local time on the gateway host. It creates a new sessionId on the next message after the reset boundary.
• Idle expiry uses session.reset.idleMinutes or legacy session.idleMinutes. It creates a new sessionId when a message arrives after the idle window. When daily + idle are both configured, whichever expires first wins.
• Thread parent fork guard uses session.parentForkMaxTokens with default 100000. It skips parent transcript forking when the parent session is already too large, so the new thread starts fresh. Set 0 to disable.

​

Session store schema (sessions.json)

• sessionId: current transcript id (filename is derived from this unless sessionFile is set)
• updatedAt: last activity timestamp
• sessionFile: optional explicit transcript path override
• chatType: direct | group | room (helps UIs and send policy)
• provider, subject, room, space, displayName: metadata for group/channel labeling
• Toggles:
  • thinkingLevel, verboseLevel, reasoningLevel, elevatedLevel
  • sendPolicy (per-session override)
• Model selection:
  • providerOverride, modelOverride, authProfileOverride
• Token counters (best-effort / provider-dependent):
  • inputTokens, outputTokens, totalTokens, contextTokens
• compactionCount: how often auto-compaction completed for this session key
• memoryFlushAt: timestamp for the last pre-compaction memory flush
• memoryFlushCompactionCount: compaction count when the last flush ran

​

Transcript structure (*.jsonl)

• First line: session header (type: "session", includes id, cwd, timestamp, optional parentSession)
• Then: session entries with id + parentId (tree)

• message: user/assistant/toolResult messages
• custom_message: extension-injected messages that do enter model context (can be hidden from UI)
• custom: extension state that does not enter model context
• compaction: persisted compaction summary with firstKeptEntryId and tokensBefore
• branch_summary: persisted summary when navigating a tree branch

​

Context windows vs tracked tokens

1. Model context window: hard cap per model (tokens visible to the model)
2. Session store counters: rolling stats written into sessions.json. These power chat status, Agent > Sessions, and fallback usage display.

• The context window comes from the model catalog (and can be overridden via config).
• contextTokens in the store is a runtime estimate/reporting value; don’t treat it as an exact limit.

​

Compaction: what it is

• The compaction summary
• Messages after firstKeptEntryId

​

When auto-compaction happens (Pi runtime)

1. Overflow recovery: the model returns a context overflow error → compact → retry.
2. Threshold maintenance: after a successful turn, when:

• contextWindow is the model’s context window
• reserveTokens is headroom reserved for prompts + the next model output

​

Compaction settings (reserveTokens, keepRecentTokens)

{
  compaction: {
    enabled: true,
    reserveTokens: 16384,
    keepRecentTokens: 20000,
  },
}

• If compaction.reserveTokens < reserveTokensFloor, Fased bumps it.
• Default floor is 20000 tokens.
• Set agents.defaults.compaction.reserveTokensFloor: 0 to disable the floor.
• If it’s already higher, Fased leaves it alone.

​

User-visible surfaces

• Chat /status (current session)
• Agent > Sessions (session list, last activity, transcript metadata, and protected delete actions)
• Usage page (token usage history; session counters are only a fallback when no better usage record exists)
• fased status (CLI)
• fased sessions / sessions --json
• Verbose mode: 🧹 Auto-compaction complete + compaction count

​

Silent housekeeping (NO_REPLY)

• The assistant starts its output with NO_REPLY to indicate “do not deliver a reply to the user”.
• Fased strips/suppresses this in the delivery layer.

​

Pre-compaction “memory flush” (implemented)

1. Monitor session context usage.
2. When it crosses a “soft threshold” (below Pi’s compaction threshold), run a silent “write memory now” directive to the agent.
3. Use NO_REPLY so the user sees nothing.

• enabled (default: true)
• softThresholdTokens (default: 4000)
• prompt (user message for the flush turn)
• systemPrompt (extra system prompt appended for the flush turn)

• The default prompt/system prompt include a NO_REPLY hint to suppress delivery.
• The flush runs once per compaction cycle (tracked in sessions.json).
• The flush runs only for embedded Pi sessions (CLI backends skip it).
• The flush is skipped when the session workspace is read-only (workspaceAccess: "ro" or "none").
• See Memory for the workspace file layout and write patterns.

​

Troubleshooting checklist

• Session key wrong? Start with /concepts/session and confirm the sessionKey in chat /status or Agent > Sessions.
• Store vs transcript mismatch? Confirm the Gateway host and the store path from fased status.
• Compaction spam? Check:
  • model context window (too small)
  • compaction settings (reserveTokens too high for the model window can cause earlier compaction)
  • tool-result bloat: enable/tune session pruning
• Silent turns leaking? Confirm the reply starts with NO_REPLY exactly, and confirm the build includes the streaming suppression fix.