Review follow-ups (Codex on #6362, round 5):
- #computeSnapcompactRescueMaxFrames now subtracts the kept tail AFTER the
archive (plus the existing fixed-context reserves) so the budget mirrors
what #compactionCreatedHeadroom will measure, and returns 0 when not even
one frame fits — the rescue bails instead of appending a rebuild that can
never create headroom (and would wedge prepareCompaction behind its
last-entry guard once elide fixes the real tail).
- Dead-end warnings now stamp the branch's LATEST compaction entry: the
post-pass path no longer badges the entry the rescue just superseded, and
the no-preparation path badges the rebuilt entry when the rescue appended
without creating headroom.
Claude-Session: https://claude.ai/code/session_014rh4JyWFkxgMhgFaEf8VBY
Review follow-up (Codex on #6362, round 4): rebuilding a non-tail archive
appends the replacement compaction at the leaf, so the branch tail becomes a
compaction entry that prepareCompaction's last-entry guard can never
summarize past — even after elide shrinks the oversized kept tool result
that was the real culprit. The rescue now estimates the kept tail AFTER the
latest archive and bails when it alone exceeds the recovery band, leaving
that shape to the elide/image tiers.
Claude-Session: https://claude.ai/code/session_014rh4JyWFkxgMhgFaEf8VBY
Review follow-ups (Codex on #6362):
- #rescueSnapcompactFrameOverflow now returns the CompactionResult and emits
session_compact for the rebuilt entry, so extensions see the entry that is
actually active instead of (only) the one the rescue superseded.
- The no-preparation auto_compaction_end now carries that result instead of
{result: undefined, skipped: true} when the rescue rewrote history — the
TUI rebuilds the transcript on result, so a successful rescue is no longer
presented as a benign no-op.
Claude-Session: https://claude.ai/code/session_014rh4JyWFkxgMhgFaEf8VBY
Review follow-up (Codex on #6362): the rescue's replaceMessages() rebuild
drops the transient plan-reference message, so clear #planReferenceSent
(#1246) and reset advisor runtimes / todo phases exactly like the regular
compaction append path.
Claude-Session: https://claude.ai/code/session_014rh4JyWFkxgMhgFaEf8VBY
Route loadSessionMessagesReadOnly through transcript mode (collapsed to the
latest compaction) so history:// transcripts of on-disk sessions retain
failed/aborted assistant tails that the provider-context builder now drops.
Review follow-ups (Codex on #6362):
- The !preparation frame rescue now counts as complete only when the rebuild
actually created headroom; otherwise the elide/image tiers still run and the
no-progress warning stays — a frame-count shrink alone must not suppress it
when the oversized tail is a kept message/tool result the archive rescue
cannot touch.
- #computeSnapcompactRescueMaxFrames now applies the same MAX_FRAMES_DEFAULT /
maxFramesForDataBudget caps as #computeSnapcompactMaxFrames, so a
threshold-derived count can never exceed what the rebuilt prompt can attach.
Claude-Session: https://claude.ai/code/session_014rh4JyWFkxgMhgFaEf8VBY
A branch whose last entry is a snapcompact CompactionEntry billed past the
compaction threshold (FRAME_TOKEN_ESTIMATE x frames) dead-ended on every
resume: prepareCompaction returns undefined (nothing after the entry to
summarize), and the #4786 elide/image rescue tiers only inspect
"message"/"custom_message" entries, so a type:"compaction" tail escaped both
and the "Compaction freed too little context" warning re-fired forever.
Add a dedicated first rescue tier that rebuilds the SAME archive locally (no
LLM, no network) by re-running snapcompact.compact() over the entry's
carried-forward source text at a maxFrames derived from the trigger
threshold's recovery band instead of the window-fit budget: planArchive
truncates the oldest chars to fit, so the rebuilt entry genuinely shrinks.
Persisting through appendCompaction lets the write-time
superseded-compaction elision drop the stale frame payload from the JSONL,
and the pass skips the misleading no-progress warning.
Fixes the loop reported in
https://github.com/can1357/oh-my-pi/issues/4786#issuecomment-5056055342
Claude-Session: https://claude.ai/code/session_014rh4JyWFkxgMhgFaEf8VBY
- Implemented ModelRegistry.hasProvider to return true when a provider has live models, is discoverable, or is registered at runtime.
- Replaced AgentSession's internal provider check with #isKnownProvider that delegates to the new hasProvider method, updating related fallback logic.
- Exposed the active retry fallback selector from live agent sessions.
- Rendered fallback rows with an explicit marker and resolved provider/model.
- Added an end-to-end fallback-to-Agent-Hub regression assertion.
Fixes#6316
Emitted session_shutdown after model rendering and centralized managed timer cleanup across one-shot listings and agent sessions.
Added regression coverage for the extension shutdown lifecycle.
Fixes#6297
clampTimeout resolved the per-tool default (bash 300s) whenever the agent
omitted `timeout` and only enforced the tool's own min/max, so the
tools.maxTimeout global ceiling — applied solely in sdk.ts on explicitly
numeric args — was bypassed on the common default-fallback path.
Thread maxTimeout into clampTimeout so the resolved effective timeout,
including the default path, is capped before the per-tool floor/ceiling
apply. Explicit values below the cap still win; maxTimeout <= 0 stays
no-cap. Applied at every call site (bash, eval, browser, debug, lsp,
fetch, and the session-level bash executor), and the bash clamp notice
now names the global ceiling when it is the binding limit.
Fixes#6294
- Carried startup-selected fallback role and primary selector into AgentSession.
- Continued remaining role fallback entries after the startup fallback fails.
- Added regression coverage for chained startup failover.
Fixes#6283
A non-retriable provider error on the continuation turn after a failed
tool result ended the run, but #persistSessionMessageIfMissing dropped
the empty error turn as reload poison, so the session JSONL stopped at
the last tool result and the provider errorMessage was lost with no
durable record of why the run stopped. When retry, model fallback, and
compaction all decline the turn, the non-retry terminal error tail now
persists it via the same helper the retry-lifecycle dead-ends use; the
empty turn stays off the wire on reload via the transform-messages
empty-assistant filter, matching the existing retry-exhaustion path.
Fixes#6249
The agent_end handler only recorded stopReason/provider/model at debug and dropped errorMessage/errorStatus/errorId, so a session dying repeatedly on provider stream failures left no actionable trace in the main log. Extract logProviderTurnError and emit one warn-level entry carrying provider, model, errorMessage, errorStatus, and errorId when a turn ends in stopReason:error.
Fixes#6177
Short-circuited session_stop emission when an abort or disposal is already in progress, avoiding extension work whose result cannot be used.
Added deterministic coverage for an abort racing the final settle pass.
Fixes#6134
A stream that stalls or aborts mid-tool-call ends the assistant turn with
stopReason error/aborted, then appends a synthetic tool_result per un-run
tool call to keep the provider's tool_use/tool_result pairing intact. That
placeholder trailed the failed turn, so AgentSession.retry() — which only
inspected the last message and required role assistant — short-circuited to
false and /retry printed 'Nothing to retry'.
retry() now walks back over trailing synthetic tool results (details
__synthetic true) before the assistant + stopReason check, stripping both
the placeholders and the failed turn. Only synthetic results are skipped, so
a turn whose tools actually ran stays non-retryable. Adds an exported
isSyntheticToolResultMessage guard in agent-loop.ts.
Fixes#6056
- Stopped asynchronous tool-result handling from overwriting newer todo state.
- Added an AgentSession regression for six exclusive completion calls.
Fixes#6148
Installed the normal plan proposal handler in print mode, persisted the resolved plan artifact, and silently stopped the completed planning turn for later review.
Shared plan proposal validation with interactive mode and added regression coverage.
Fixes#6017
Main renamed/refactored #tryShakeRescueForDeadEnd + #emitShakeRescueNotice into
the tiered #rescueCompactionDeadEnd (elide, then image drop, notices emitted
internally), so a textually-clean merge of this branch left calls to undefined
private methods. Re-express the !preparation rescue through the new API:
progress = prepareCompaction succeeding on the rewritten branch, skipElide when
falling through from a shake pass (the image tier still gets a chance), and
historyRewritten flagged whenever a tier freed content even without progress.
Restore the baseline dead-end remedy text (image drop is automated now, so the
manual /shake images suggestion is stale) and align the rescue-refit regression
test with main's continuation gating (auto-continue after compaction now
requires an active goal or queued work).
can1357