Keep-alive subagents are handed to AgentLifecycleManager.adopt, which stores
their reviver closure in the process-global #adopted map. The closure is
defined inside runSubagent's scope, which also captures the live AgentSession
(extension-runner callbacks, buildSubagentSessionOptions), so its lexical
environment pins the whole session graph. park() disposes and detaches the
session but leaves the adoption record indefinitely, and #doDispose never
dropped the in-memory transcript, session-manager entries, or the raw-SSE
debug buffer (whose trimmed records retain slice() views of full wire frames),
so every completed subagent's heavy state leaked for the process lifetime.
dispose() is terminal and every revival path reopens from disk, so #doDispose
now sheds retained conversation memory via agent.reset(),
RawSseDebugBuffer.clear(), and SessionManager.releaseRetainedEntries(). The
adoption record can still reference the session, but only as a husk.
Fixes#8003
- Separated deterministic replacement generation, placeholder derivation,
placeholder-range scanning and message-tree transforms out of the 2647-line
module; obfuscator.ts now holds the types and SecretObfuscator.
- ephemeralPlaceholderKey stays a single instance and both global regexes stay
beside the code that resets their lastIndex, so placeholder stability and
the security argument in the moved comments are preserved verbatim.
- Repointed every importer at the real modules rather than leaving a re-export
shim; the public ./secrets barrel exports the same 15 names as before.
- A provider-supplied retry-after now bypasses the transient rate/concurrency
heuristic window instead of being overridden by it (regression from the
subscription-cap retry change).
- Updated event-controller/ui-helpers test doubles for provenance-gated
renderer selection (hasBuiltInTool), aggregated retryErrors on
auto_retry_end, and Bedrock override compat gaining streamIdleTimeoutMs.
A cooldown-expiry model revert runs at a turn boundary. The user-prompt
path reverts then re-checks accumulated context against the restored
model via runPrePromptCompactionIfNeeded, but the automatic
agent.continue() path (#scheduleAgentContinue) reverted and issued the
next request with no such check. When a transient failure had fallen
back to a larger-window model and the conversation then grew past the
original model's window, restoring the primary once its cooldown expired
sent a predictably oversized request to the smaller model.
maybeRestoreRetryFallbackPrimary now reports whether it actually
switched, and the auto-continue path runs the same post-revert
context-fit maintenance (compaction/promotion) the prompt path already
runs, but only when a revert occurred.
Fixes#7952
The handoff catch in session-handoff.ts and the /handoff handler in
command-controller.ts mapped any error named AbortError to "Handoff
cancelled" regardless of whether the handoff signal was actually
aborted. Providers throw name-AbortError errors on non-user conditions
(stalls, idle timeouts, nested resolution failures), so a genuine
generation failure surfaced as a user cancellation and hid the cause.
Only report "Handoff cancelled" when handoffSignal.aborted is set;
re-throw the real error otherwise. The controller now trusts the
normalized "Handoff cancelled" message and drops its own AbortError
check so re-thrown provider failures render as "Handoff failed: ...".
Fixes#7903
The isAwaitingUserAnswer guard that suppresses the todo completion reminder while the agent waits on a user question only recognized English question words and pronouns. A '？'/'?'-terminated Chinese, Japanese, Korean, or Spanish prompt went undetected, so the <system-reminder> interrupted the pause and the model misread it as the user's answer.
isQuestionPromptLine now also treats a question-mark-terminated line containing any non-ASCII character as a pending user question.
Fixes#7803
The per-turn systemPrompt returned by before_agent_start was applied only to the agent state, so any base-prompt rebuild firing in the prompt window (context-overflow compaction/promotion, memory promotion, MCP/RPC tool refresh, hindsight MM-TTL refresh) re-pushed the rebuilt base via setSystemPrompt and silently dropped the override before the request.
SessionTools now tracks the active per-turn override and re-applies it on every base rebuild during the turn, clearing it when the turn ends.
Fixes#7755
- Bounded rewind report recovery to messages created after the active checkpoint.
- Added resumed-context regression coverage for late stale rewind results.
Fixes#7739
The ExtensionAPI getAllTools() wired to session.getAllToolNames(),
returning bare tool-name strings. Upstream @earendil-works/pi-coding-agent
promises ToolInfo[] with sourceInfo, so extensions loaded through the
legacy-pi shim (e.g. gentle-pi) crashed on t.sourceInfo.source at every
session start.
Added SourceInfo/ToolInfo types plus SessionTools.getAllToolInfos(), which
returns { name, description, parameters, sourceInfo } and classifies each
tool as builtin/mcp/sdk/extension. Rewired every getAllTools action site
(interactive, acp, print/rpc, subagent executor) and the example extension.
Fixes#7732
- Implemented in-house, zero-dependency utility modules in `pi-utils` covering DOM manipulation, markdown parsing, templating, browser automation helpers, and terminal buffers.
- Migrated packages across the repository to consume the new internal utilities and `omptype` schema validators instead of external dependencies.
- Removed multiple external runtime and development dependencies including Zod, Marked, LRU cache, Turndown, and Puppeteer browser packages.
Registered live session resume commands with postmortem handling so a
fatal rejection or exception identifies every recoverable agent before
cleanup. Escaped terminal control characters in recovery output.
The 17.2.9 revert (172ce9b) restored the legacy path-based session
directory names but removed all migration, including the reverse path.
Sessions written under the short-lived hashed scheme (17.2.5-17.2.8,
`<scope>-<readable>-<sha256>`) were left orphaned, so `omp -r`
current-folder scope reported no sessions.
computeDefaultSessionDir now reconstructs the hashed dir name for the
cwd and performs a one-way best-effort migration into the legacy name,
alongside the existing legacy-absolute migration.
Fixes#7677
Reset-window rotation requires account-specific wording; concurrency caps require an actual cap signal; credential removal gated on AuthFailed without UsageLimit so a valid-but-blocked 403 credential is retained.
(cherry picked from commit 2f72752c2586352a4f7e9e814af1cdb0cf192af4)
Account-reset hint evaluated before short retry hints; account-scoped caps rotate on status 403 or undefined (Devin statusless trailer); statusless concurrency caps marked transient; transient same-model retries use the concurrency backoff.
Refuted: quota-worded concurrency caps were already excluded from rotation before the usage-limit text match.
(cherry picked from commit f2b9a18d715ddbcb6ae703670f2212da36bb2826)
A classifier refusal returned before the `onTurnError` hook that owns
model fallback, so `AdvisorRuntime` treated one provider's policy verdict
as terminal: `Refusal (cyber)` on the advisor model disabled the advisor
outright even with a fallback chain configured. Its only recovery was
stripping echoed primary reasoning and resending once, which does nothing
for a refusal about the content itself.
Route a refusal that outlives the strip through the same hook the generic
failure path uses, mirroring its epoch guard, session-transition requeue,
and requeue-on-recovery. The cascade walks the chain to exhaustion and
only reports the advisor unavailable once the host runs out of candidates,
matching what turn-recovery already allows for the primary.
Each cascade visits a model at most once. A switch re-arms
`#includeThinking` through `#syncModelIdentity`, so chain keys that point
back at each other (A to B, B to A) would otherwise strip-and-resend
against the same pair forever. A successful turn or a reset starts a
fresh walk.
Also stop `/advisor status` throwing when a live advisor has no roster
entry: `formatAdvisorStatus` guarded only the inactive case before
dereferencing `stats.advisors[0]`, and `#ensureAdvisors` clears
`#advisorStatuses` before repopulating it, so a status call landing in
that window hit `undefined.contextWindow`.
Made text replay safety depend on whether the active output sink has committed streamed text.
Kept tool calls, images, and server tools replay-unsafe while covering text and JSON print policies plus a transient socket-close recovery.
Fixes#7625
Align isUnexpectedStopCandidate with #isEmptyAssistantStop: only a signed (non-whitespace thinkingSignature) thinking-only stop is a candidate. Unsigned thinking-only stops stay with the empty-stop retry path and its cap, so unexpected-stop classification no longer re-handles a turn the empty-stop cap already gave up on.
Fixes#7499
roboomp