- Added `CompactionSummaryMessageOptions` interface to support optional fields and metadata in compaction summary messages.
- Included compaction method labels and before-after amount badge rendering in compaction views.
- Updated session maintenance and compaction methods to track and compute post-compaction token counts.
- Updated calls across agent and coding-agent packages to use the new compaction options object.
- Added preview title support and fallback handling across shape previews and status line segments.
- Refined session list sizing and line height budgets in the session selector component.
- Extracted session compaction method helpers and improved speculative compaction logic.
- Prevented armed LLM speculation results from overriding local snapshot compaction execution.
- Added theme icons and formatting for subscription status and advisor tracking across status lines and footers.
- Implemented `isAdvisorUsingSubscription` and `isUsingSubscription` methods to check active models against OAuth usage.
- Updated status line model segments to display the new advisor icon instead of text badges.
- Added comprehensive tests covering subscription and advisor costs across multiple font presets.
- Introduced embedded mode and context gauge render options for the status line alongside boundary calculation helpers.
- Added pluggable composer styles with a style registry supporting box, claude, pi, and borderless layout rendering.
- Extracted speculation lead resolution into a dedicated shared module and added theme symbol definitions.
- Expanded test coverage for status line context gauge modes, composer shape previews, and editor style assertions.
- Extract foreground wait, notice formatting, and settlement racing logic into a shared module.
- Update async job type definitions to support eval jobs alongside bash and task jobs.
- Add configuration settings for eval auto-background thresholds.
- Added compaction.asyncEnabled (Async Compaction, default on): when
context enters the pre-threshold band [threshold - lead, threshold)
with lead = clamp(threshold * 0.125, 8192, 32000), maintenance
speculatively summarizes in the background off a branch snapshot
(first configured LLM-backed method: remote, handoff, or soft) using
a side session id isolated from the live turn. Crossing the threshold
splices the armed result in instantly instead of blocking on a
summarization round-trip. Armed results are invalidated by branch
changes, reset boundaries, model switches that strand provider-native
replay payloads, and context growth past keepRecentTokens (which
re-speculates); extensions registering session_before_compact keep
exact blocking semantics (speculation disabled).
- Reworked handoff to commit in place: /handoff and the auto handoff
method now write the generated document as a regular compaction entry
on the current session (summary = document + <files> tag, cut from
prepareCompaction) instead of starting a new session. SessionHandoff
shrank to a document generator; session_before_switch/session_switch
no longer fire with reason "handoff"; mid-turn maintenance no longer
suppresses the handoff preference; overflow recovery can apply an
armed handoff result.
- Extracted the shared auto-compaction commit tail
(#commitAutoCompactionResult / #commitCompactionEntry) used by the
blocking production path, the armed speculative apply, manual
compaction, and manual handoff.
- Status line pulses the auto-compact icon while a speculation runs and
holds it in accent once a result is armed.
- Exported remotePreserveReusable from pi-agent-core/compaction for
apply-time validation of speculative remote results.
- Replaced legacy `compaction.strategy` and `remoteEnabled` settings with `compaction.methodOrder` across session maintenance, schema, and tests.
- Added automatic fallback mechanism to try subsequent compaction methods upon failure or unsupported model capabilities.
- Added mouse drag-and-drop reordering support and click handlers to multi-select settings submenus.
- Updated documentation and test suites to reflect ordered compaction strategy preferences and fallback chains.
- Added long-context pricing tiers and billing policies for subscription Codex models in the catalog.
- Introduced the `extendedContext` configuration setting to control premium long-context windows.
- Implemented runtime policy refresh and model re-binding when context settings change.
- Added comprehensive unit tests for pricing tiers, context capping, and policy toggling behavior.
- Replaced the `ctok` implementation with the `utok` universal tokenizer supporting multiple model families and UTF text encodings.
- Added tokenizer support and embedding data for Qwen3, DeepSeek V3, Kimi K2, and GLM-5 model variants.
- Added fixture generation scripts, vocabulary packers, and golden test suites for validating tokenization parity.
- Updated dependency requirements and Bazel workspace definitions for new crates and tools.
- Add `setPromptDropped` hook and `DroppedPrompt` type to return prompts that were cancelled during turn setup before dispatch.
- Restore dropped prompt text and image attachments to the interactive mode editor and remove the optimistic transcript row.
- Implemented the `ctok` Rust native tokenization engine with offline support for Claude V3, V47, V5, and V5Sonnet families.
- Replaced global token estimation with model-scoped `Tokenizer` instances and provider-anchored transcript accounting across packages.
- Added vocabulary generation scripts, test fixtures, and comprehensive unit tests for tokenizer routing and matching modes.
getContextBreakdown used message position (anchorIndex >= pending.cutoffCount) as a proxy for usage freshness. After a mid-run compaction rebased the in-flight snapshot, an in-flight provider response whose request predated the compaction landed past the rebase cutoff carrying pre-compaction usage, so it out-ranked the rebased estimate and reported the pre-compaction token count (~2.6x the real one). That phantom overflow tripped the "freed too little context to make progress" guard and drove the frame-rescue path on a byte-identical tokensBefore.
Assistant context snapshots now carry a monotonic compaction epoch, bumped in rebaseAfterCompaction and stamped at message-record time. A post-cutoff anchor whose epoch predates the pending snapshot's epoch is no longer trusted over the rebased estimate.
Fixes#8887
- Kept the shared cursor/interaction-query module as the single handler and deleted the duplicate local implementation in cursor.ts
- Added the named webFetchRequestQuery approval case (field 9 is named under the regenerated proto)
- Preserved the deliberate no-fake-VM-success semantics for setupVmEnvironmentArgs (review of #8047)
- Updated the field-9 regression test to assert the named decode of the raw same-field reply, which also pins the LEN-prefix wire framing
- Add the `providers.cacheRetention` setting to control prompt-cache retention options per request.
- Forward configured cache retention preferences through the settings-aware stream function.
- Update documentation and test coverage for long cache retention behaviors.
A session that crossed a provider boundary compacted 90 times in three days
without ever succeeding: every attempt asked the summarizer to read the whole
re-expanded span in one call (2.33M tokens on 08-15, 3.03M by 08-17, against a
1M cap), and every rejection was retried ten times.
Three independent defects:
1. `generateSummary` serialized the entire span into one prompt with no budget
check. It now plans windows that fit the summarizer's context and folds them
with the update prompt that iterative compaction already uses, so a stranded
boundary is recovered instead of rejected. A provider that rejects a window
the catalog said would fit (claude-sonnet-4-5 advertises 1M but is
beta-gated to 200k on OAuth credentials) halves what was actually sent and
re-plans, because only the rejection knows the real cap.
2. `TRANSIENT_TRANSPORT_PATTERN` matched bare status codes, so the random id in
the `raw-http-request=.../1787022540720-3o503gxo48bvb.json` pointer omp
appends to its own errors classified a deterministic 400 as a transient 503.
Statuses are now word-boundaried, matching AUTH_FAILURE_PATTERN.
3. Neither retry layer vetoed ContextOverflow, so one failure became up to 30
identical calls (10 outer x 3 oneshot). A oneshot replays a fixed prompt, so
an input that does not fit never fits; both layers now fail fast to the next
candidate.
The boundary scan that decides which compaction entry a model can actually read
is extracted as `findReadableCompactionIndex`, since the fold and
`prepareCompaction` both need it.
Verified by replaying the session that failed: 7,096 messages summarize in 3
calls with a largest prompt of 773,705 tokens under the real 1M cap, and in 15
calls with a largest prompt of 196,148 tokens under a simulated 200k cap.
Persistence is lazy: getSessionFile() returns an allocated path from the
start, but the JSONL is only materialized once an assistant message (or an
explicit ensureOnDisk()) crosses the persistence gate. The shutdown banner
printed the resume hint based solely on the path, so any session that ended
before the first assistant message advertised a copy-pasteable command that
always fails with Session not found.
Gate the hint on the new SessionManager#isSessionOnDisk() (file exists in
the active storage backend) and add unit tests.
Fixes#8860
A boolean latch survived /new and unnamed session switches, so the
replacement session skipped titling and could inherit the previous
skill's title. Bind the latch and the apply check to the originating
session id.
maybeStartTitleGeneration used to fire again for every untitled skill
prompt, so a queued /skill: during the first title request could race
and rename the session. Latch until the first request settles.
Session titles ignored /skill:<name> <args> because the invocation is a
custom skill-prompt, not a user turn. Feed the chip or reconstructed
/skill line into first-title generation and replan context, never the
expanded SKILL.md body.
The idle watchdog aborts the request signal and cursor.ts closes
the Connect stream, so there is no in-flight server exec to race.
Unmarked MCP/todo blocks can continue once every emitted call has
a matching result, same as HTTP/2 RST.
A ThinkingLoop abort is the loop guard asking for a same-model resample
(it injects a thinking-loop-redirect notice that only makes sense on the
model that looped), not a provider failure. #handleRetryableError routed
it through the generic retryable-error branch, so on attempt 1 it called
noteRetryFallbackCooldown + #tryRetryModelFallback and could switch to
another family from retry.fallbackChains while parking the original
selector on a 5-minute cooldown. A healthy Grok 4.6 planning turn got
replaced by whatever the chain listed next.
Carve ThinkingLoop out of the model-fallback branch and out of the
Fireworks Fast->base degrade so the loop guard always re-samples the same
model; the retry budget still bounds a genuinely stuck stream.
Fixes#8760
prepareCompaction walked the branch from the last compaction and ignored reset_boundary markers, so /compact (and auto-compaction) resurrected pre-/clear turns into the summary even though buildSessionContext already starts the model context after the boundary.
Model reset_boundary as a first-class agent-core session entry and start the summarization window after the latest boundary, dropping the superseded pre-reset compaction summary. A boundary before the last compaction stays superseded by it.
Fixes#8718
can1357