- Added snapcompact.shape setting with auto and variant options in agent config.
- Implemented resolveShape support for forced variants, auto provider winners, and repricing.
- Threaded resolved shape into compaction and inline-image flows for pricing and rendering.
- Added `handleUsageResetCommand` support to list and redeem usage reset credits.
- Refactored `/usage` into `show` and `reset` subcommands and removed `/reset-usage`.
- Handled ACP/TUI `/usage` flows so `show` reports usage and `reset` redeems credits.
- Kept selected theme setting values dirty-colored while selected in the UI list.
- Added commit-stability signaling to transcript blocks and marked tool previews as unstable until expanded or finalized.
- Updated transcript scrollback promotion to derive live commit state only for blocks reporting commit-stable rows.
- Added tests ensuring provisional pending edit previews are never committed while durable live rows still promote after the stability window.
- Added AuthStorage.listResetCredits to query each stored Codex account from the reset-credits endpoint and return live availability plus active or error state.
- Exposed the new status fetch through AgentSession and switched reset-usage selectors and commands to consume it via toResetUsageAccounts.
- Updated reset-usage UI and slash-command output to show per-account errors and updated empty-state messaging when resets could not be loaded.
v15.11.4 introduced stateful previous_response_id chaining on the
official OpenAI endpoint. The in-provider retry classifier matched only
the generic stale-id phrasing ('previous response ... not found |
invalid | expired | stale'), missing the Zero Data Retention 400
'Previous response cannot be used for this organization due to Zero
Data Retention.'. The error therefore bypassed the categorical-disable
path, so the chain was reset (not disabled), the next successful turn
re-armed it, and every other turn 400'd in a loop.
Add a dedicated isOpenAIResponsesZeroDataRetentionError detector and a
markOpenAIResponsesChainZeroDataRetention helper that disables chaining
on the first hit (skipping the three-strike circuit breaker). The
in-call retry now drops 'store: true' from the replay so the request is
semantically valid for ZDR orgs, and reasoning continuity is preserved
by the existing include: ['reasoning.encrypted_content'] flag.
AgentSession.#isStaleOpenAIResponsesReplayError gains the ZDR phrasing
too, so any ZDR error that does bubble past the provider retry resets
the Responses session and retries at zero backoff instead of falling
back to a different model.
Fixes#2341
- Extracted `limitMatchesActiveAccount`/`reportMatchesActiveAccount` into `slash-commands/helpers/active-oauth-account.ts` as the single definition of the report-to-account matching rules, including projectId matching against `limit.scope.projectId`/metadata.
- Dropped the duplicated `ActiveAccountIdentity`/`OAuthAccessResolver` shims, `as unknown` session casts, the dead `getOAuthAccountId` fallback, and the email-vs-scope-accountId comparison from `command-controller.ts` and `usage-report.ts`.
- Replaced the async per-provider `resolveActiveAccountsForReports` map with one synchronous typed `authStorage.getOAuthAccountIdentity()` call per render, gated to the session's current provider.
- Re-exported `OAuthAccountIdentity` from `session/auth-storage.ts` and added `active-oauth-account.test.ts` covering the matching rules.
- Running job labels now shimmer in the TUI to provide a dynamic visual indicator of activity.
- Adjusted cache key to account for shimmer animation, ensuring it updates at 30fps instead of the 12.5fps spinner cadence.
- Suppressed job ID display when the job label is identical to its ID, avoiding redundant information.
- Stored queued steering/follow-up attachments in `QueuedDisplayEntry` so restore APIs retain image data.
- Changed `AgentSession.clearQueue` and `popLastQueuedMessage` to return `{ text, images }` payloads.
- Restored queued text and images into editor image buffers when steer submission fails or queue items are restored.
- Added optional `hasSteeringMessages` config hook and limited steering checks to boundaries.
- Fixed interrupted tool-batch steering by keeping queued messages until boundary handling.
- Added idle text and image submissions to steer queueing when no input waiter exists.
- Auto-continued resumable sessions after queued steering and preserved submit metadata.
- Renamed all functions, types, and constants in @oh-my-pi/snapcompact to namespace-relative names (`snapcompactCompact` → `compact`, `renderSnapcompactFrames` → `renderMany`, `snapcompactFrameCount` → `frames`, `SnapcompactShape` → `Shape`, `SNAPCOMPACT_SHAPES` → `SHAPES`, …).
- Converted every consumer to `import * as snapcompact` member access: `agent/compaction.ts`, `coding-agent` `agent-session.ts`/`session-manager.ts`/`snapcompact-inline.ts`, and all affected tests.
- Renamed internal `geometry` locals to `geo` in `snapcompact.ts` to avoid TDZ collisions with the new `geometry` export.
- Updated `docs/compaction.md` prose and added a Breaking Changes entry to the snapcompact changelog documenting the full rename map.
- Added `renderSnapcompactFrames()` and `snapcompactFrameCount()` to @oh-my-pi/snapcompact for paging arbitrary text into PNG image blocks without dim-marker bookkeeping.
- Widened the agent loop's `transformProviderContext` hook to `(context, model) => Context` so per-request transforms can gate on the dispatch model's capabilities.
- Added `SnapcompactInlineTransformer` rendering the system prompt and large historical tool results as snapcompact frames on vision models: vision gate, per-provider image budgets, 3k-token floor, savings-margin gate, skip-last rule, and hash-keyed render caches swept to live tool calls.
- Added default-off `snapcompact.systemPrompt` and `snapcompact.toolResults` settings under a new Context → Experimental group, composed after secret obfuscation in `sdk.ts` so frames are built per-request and never persisted to session.jsonl.
- Added prompt stubs (`snapcompact-system-stub.md`, `snapcompact-system-frames-note.md`, `snapcompact-toolresult-note.md`) and unit tests covering frame paging, no-mutate guarantees, budget caps, gates, and render caching.
- Fixed `/dump` output (`session-dump-format.ts`) and the RPC `get_state` `dumpTools` payload (`rpc-mode.ts`) serializing Zod schema instances — leaking `def`/`shape` internals and stringified methods — by converting parameters through `zodToWireSchema` like providers receive.
- Fixed context-usage token estimation stringifying the Zod `def` tree, which overcounted tool schema tokens in the status line.
- Fixed tool-discovery indexing (`tool-index.ts`) returning empty `schemaKeys` for Zod tools, weakening BM25 ranking; keys are now recovered via wire conversion.
- Fixed the extension inspector panel rendering "(no arguments)" for Zod tools by reading properties off the converted wire schema.
- Added coverage in `tool-index.test.ts` plus new `context-usage.test.ts` and `session-dump-format.test.ts`, and a changelog entry.
MnemopiSessionState.dispose() now drains pending fact extractions and
runs sleepAllSessions on every owned bank before closing handles, and
AgentSession.dispose() awaits the result. This matches the manual
`/memory enqueue` slash command which was the only caller of the
consolidation pipeline.
Without the shutdown hook, episodic_memory, gists, consolidation_log,
graph_edges, and triples stayed empty for every deployment that never
typed `/memory enqueue|rebuild` — working memory accumulated forever
and long-term recall never formed.
Factored the consolidate step out of `mnemopiBackend.enqueue` into a
shared MnemopiSessionState#consolidate so the slash command and the
shutdown path share one implementation. Added two regression tests
verifying owned-bank consolidation order (flush -> sleep -> close, per
bank) and that aliased subagent dispose stays a no-op against the
parent.
Fixes#2320
A subagent's send await:true to Main during a blocking task spawn was a structural deadlock: deliverIrcMessage queues mid-turn messages as step-boundary asides, but Main's next boundary requires the sender's own batch to finish, so the sender always burned the full irc.timeoutMs. Awaited sends now pass expectsReply through IrcBus.send; a mid-turn recipient with async.enabled off generates an ephemeral no-tools reply via runEphemeralTurn, records an irc:autoreply aside in its own history, and delivers it back over the bus with replyTo threading so the sender's waiter resolves.
Kept classifier refusals eligible for model fallback, but restored the retry.maxRetries guard so fallback chains cannot consume extra provider calls after the turn budget is exhausted.
Fixes#2290
Preserved Anthropic stop_details on assistant messages so the agent can distinguish classifier refusals from transport failures.
Taught AgentSession to use configured retry fallback chains for refusal and sensitive stops without same-model retries, then pin the fallback for the conversation.
Fixes#2290
The shake-strategy post-shake threshold check was reading
#estimatePendingPromptTokens([]) while #checkCompaction triggered on
calculateContextTokens(assistantMessage.usage). The local estimator
ignored block.thinkingSignature payloads (OpenAI Responses encrypted
reasoning items, Anthropic signed thinking blocks, etc.), so on a
thinking-heavy session the estimate sat ~0.9–2× below provider-reported
usage. Once the two straddled the threshold, the #2119 dead-loop guard
never fired, shake reported 'handled', and #scheduleAutoContinuePrompt
re-injected the auto-continue developer prompt every turn — 53 injections
in a real 25-minute repro session before an external timeout.
Thread the trigger's provider-anchored contextTokens through
#runAutoCompaction → #runAutoShake for the threshold and incomplete
paths, then evaluate residual pressure as triggerContextTokens −
result.tokensFreed with an 80% recovery-band hysteresis. Re-checking
against the raw threshold (even on the corrected metric) would still let
shake reclaim a trickle of the previous turn's elidable blocks and land
just under the line every turn; the band closes that oscillation.
As defense in depth, estimateTokens() now charges thinkingSignature and
redactedThinking.data alongside the visible thinking text so every
other site that uses the estimator (idle compaction, pre-prompt check,
status line) tracks provider usage on replay.
New regression test pins the contract; existing dispatch test bumped
its mocked tokensFreed so its happy-path scenario lands inside the new
recovery band.
Fixes#2275
- Added a new @oh-my-pi/snapcompact package and redirected compaction call sites to it.
- Added provider-aware snapcompact shape resolution for model-specific mixed-frame behavior.
- Added optional image detail support by extending ImageContent and passing hints through OpenAI providers.
- Added native snapcompact render options, including 5x8/8x8 font loading and palette/geometry controls.
Adds enforceInlineByteCap() in streaming-output and applies it to bash and browser tool results: oversized outputs are elided head/tail with an artifact:// footer pointing at the full capture, closing paths that previously let 100KB+ inline results past the minimizer. Defense at the tool-result boundary (no-op for already-bounded output).
Adds compaction.strategy: "snapcompact" to the schema and the AgentSession routing: when chosen, both manual /compact (without custom instructions) and auto compaction call snapcompactCompact() to archive history as PNG frames instead of an LLM summary. Falls back to context-full with a visible warning notice when the current model is text-only or when /compact gets custom instructions. CustomTool and shared-event payloads carry the new action through. \n\nAlso wires the per-turn supersede pass: #pruneSupersededReads() runs every turn before threshold gating (cache-aware: only fires when the post-candidate suffix is small or the prompt cache is cold), prunes older read results superseded by a newer read of the same file, rewrites the session, and accounts the saved tokens in the next compaction decision. Gated by compaction.supersedeReads (default on).\n\nsession/messages.ts now delegates the core role conversion to agent-core's convertMessageToLlm so snapcompact image blocks flow through the LLM-context conversion path.
Registers a HistoryProtocolHandler with the internal URL router: history:// lists every registered agent (id, status, kind, last activity) and history://<agentId> renders a concise markdown transcript (tool calls collapsed to one line each, thinking elided). Live refs render from the in-memory message array; parked refs load read-only from the JSONL session file via loadSessionMessagesReadOnly (no writer, no lock). System prompt + read tool prompt + docs/tools/read.md learn the new scheme.
The session-observer overlay is gone. The Agent Hub (ctrl+s, alt+a, or double-tap left arrow on an empty editor) presents one overlay with two views: a live registry table (status, unread irc count, current task, last activity; j/k to navigate, r to revive, x to abort/release) and per-agent chat (transcript + input line) — submitting revives a parked agent and steers it via the normal prompt path. Main is the ambient chat and stays out of the table.\n\nrenderInitialMessages no longer takes a prebuilt context: every redraw now reaches for AgentSession.buildTranscriptSessionContext() (full-history transcript with each compaction emitted inline at the point it fired, snapcompact frames re-attached on rebuild). UiHelpers drops the deferred-compaction render and the IRC autoreply branch that the new mailbox bus deprecated. CompactionSummaryMessage renders as a slim divider (── 📷 compacted · ctrl+o ──), expanding to the summary + snapcompact frame count. session-manager.buildSessionContext gains a { transcript: true } mode; an exported buildSessionContextFromFile() reads a session file without taking the writer lock so the hub chat view can tail any agent (parked or live). Theme picks up icon.camera + tool.irc symbol entries.
Shared background now flows through a '/Users/can/.omp/agent/sessions/-Projects-.tree-pi-commit/2026-06-10T15-36-32-782Z_019eb22d-970e-7000-8964-72c98becf3e8/local' file referenced in each prompt instead of a context string forwarded into the subagent's system prompt. The JS and Python preludes drop the context kwarg from agent(), the subagent system prompt drops the {{#if context}} block and the conversation-context file pointer, and runEvalAgent no longer writes a per-call conversation context file. AgentSession sheds the now-unused formatCompactContext() helper that supplied the file's body, and ToolSession.getCompactContext is removed alongside it.
Replaces the blocking auto-reply IRC turn with a process-global IrcBus and a four-op tool (send/wait/inbox/list). send is fire-and-forget with per-recipient delivery receipts (injected/woken/revived/failed); replies become real turns by the recipient, observed via wait (or the send await:true sugar). Bounded per-agent mailboxes (cap 100) drop oldest on overflow; AgentSession.deliverIrcMessage folds an in-flight delivery in as a non-interrupting aside at the next step boundary, or starts a real wake turn when idle. AgentRegistry/lifecycle handle the idle→woken / parked→revived transitions, so messaging a non-running peer brings it back. Adds a dedicated TUI renderer (directional headers, delivery-outcome coloring, quoted bodies, per-recipient receipt trees, status-badged peer lists with unread counts). irc.timeoutMs is now the default timeout for wait / send await:true. AgentSession sheds the agentRegistry config field, the dedupeIrcReply → dedupeEphemeralReply rename (now used by /btw and /omfg), and the background-channel exchange queue / forwardIrcRelayToMain plumbing the auto-reply model needed.
Propagated explicit thinking-off state through the agent loop so provider requests receive disableReasoning instead of an undefined effort. Added Ollama and agent-session regressions for the :off path.\n\nFixes #2239
The schema default for tools.approvalMode is already "yolo", so checking the
resolved setting alone disabled the ACP permission gate for every
default-config session (17 existing tests in
agent-session-acp-permission.test.ts fail). The skip now requires an
explicitly configured approval mode — the --yolo/--auto-approve runtime
override or a user-set tools.approvalMode — via the new
Settings.isConfigured(), keeping default ACP sessions gated.
Addresses review feedback on #2097.
can1357