Session workers now host a durable Harness over a per-session sqlite storage.
The server keeps each session in <sessionDir>/<id>/ with meta.json and
session.sqlite and never opens the storage itself. Workers hold retirement
while the Harness task graph has live tasks and resume interrupted work on
open.
Transcript serves the root conversation's durable view directly, Models
follows the conversation's agent document, and AgentController maps prompt,
steer, follow-up, queue cancellation, abort, and compaction onto the root
conversation, plus waitForPrompt. navigate, nextRun, and resume are dropped
(see experimental/services/README.md TODO). The durable TUI and the worker
share harness-setup.ts.
pi-server exports its own SessionMetadata and no longer depends on
pi-agent-core. Chord accepts readonly JSON types in service contracts without
walking them, which recursive JSON types like pi-ai's made too deep.
pi-agent-core now contains only Agent, the agent loop, the proxy stream, and
their types. Removed the harness, sessions and session storage, pico3, harness
tools, compaction, skills, prompt templates, telemetry schemas, search types,
and the uuidv7 and pi-telemetry re-exports, plus the ./node, ./harness/* and
./experimental/pico3 subpath exports. Durable sessions live in
@earendil-works/pi-durable.
Also removed packages/session-backends and the experimental mini and micro
coding-agent frontends, with their scripts and build configuration.
The user message's Markdown pads and colors its own background instead of
sitting in a Box that kept a second full-width copy of every line. The output
is identical.
Markdown holds its parsed tokens weakly: a token tree is about ten times its
source, and every transcript message keeps a Markdown component. The tokens
still survive bursts of re-renders such as theme previews. Markdown, Text, and
Box flatten their cached lines, which V8 otherwise keeps as trees of the
concatenated parts. A long assistant message keeps about a fifth of the heap.
A small local agent in src/experimental/durable: pi's model runtime, settings,
system prompt, theme, and interactive components over a durable Harness with
SQLite storage. Streaming, tools, steer and follow-up, abort, model and
thinking selection, compaction, --continue with recovery of interrupted turns,
a subagent tool with /agents to switch to and talk to subagents, and a live
/tasks panel from the task graph view. The tsconfig path for
@earendil-works/pi-durable/* resolves subpaths to source.
Package 22: runtime.now() and report() throw after the invocation ended; a
migration-only commit is published; a failed Harness.open closes without the
caller's context and rethrows the open error; ConversationWatch alias. Tests
for close joining non-cooperative code, cancelled close, queued operations at
the seal, progress calls and viewers on a paused Harness, the Chord guide, and
the spec's usage examples.
Package 23: Harness.taskGraph() and watchTaskGraph() mount every live task with
its owner edge, committed status, flags, and owned conversations, advanced from
commit publications. Example 24 prints the checkout's tree.
Close ends states and watches at its seal, joins non-cooperative code, and a
cancelled close cancels only its wait. Conversation.abort() starts scheduling.
New section 9.5 specifies Harness.taskGraph() and watchTaskGraph(). The Chord
guide uses real imports and documents shutdown order.
- Registry of named extensions (tools, sections, hooks, wraps, tasks) with install/uninstall;
defineExtension, defineTool, section, hook, wrapTool, wrapSection
- pi.agent document (model, thinking level, extensions, tools filter, instructions, cwd),
configure(), Conversation.agent()/configure(), agent option on root/createConversation/fork,
task-owned conversations copy their owner's agent
- Harness-wide HarnessSettings read at every use; env function built per use
- Hooks and the agent resolved per task phase; tool calls resolved with the tools filter applied
- ToolRegistration<TParameters, TDetails> types execute() args from parameters
- HarnessOptions.conversationCreated; Tx.submissionByRequest() and Tx.createSubmission()
- FileSystem.id; edit/write serialize per file system id and canonical path
- CodingTools extension (read, write, edit, bash)
- Examples 06-31 on the new API, README and CHANGELOG
Extensions installed by name, the rewindable pi.agent document with configure(),
Harness-wide live settings, env built per use, typed tool args with defineTool(),
HarnessOptions.conversationCreated, Tx submission methods, FileSystem.id for
edit/write serialization, and tool resolution with the tools filter applied.
- drop AsyncLocalStorage misuse guards from the Node adapter
- run calls immediately when the queue is idle; transactions publish their barrier before the callback starts
- SqliteStorage.close() waits for admitted multi-query reads and shares one close promise
Manual compact(), background and blocking threshold compaction, and overflow
compaction with one retry. Summaries are headed pi.compaction entries placed
through the inbox, or appended by a compaction the generation waits on; the
stale rule decides between concurrent summaries.
The subagent tool no longer offers wait, is not rerun after a crash (a repeated stop could stop newer work), reports each answer once even when several messages end in it, checks registry names as own properties, and its scenes cannot hang polling.
Tasks name their owner (conversation or task); a task waits on other tasks with a waiting state (failFast or allSettled) and runtime.outcomes(); a task that finishes while owned work is live holds completing until it drains; abort handlers run bottom-up; only live owners cascade. The generation owns its tool tasks and waits for them in a tools phase, replacing pi.post-tools and after. Adds Conversation.abort({ background: true }), example 24 (checkout with payments), and reworks example 23 into persistent subagents.
Generation offers active registered tools through positional system entries and
hands a tool-calling answer to parallel or sequential pi.tool tasks and a
pi.post-tools task that applies addTools/terminate and continues the run. Tool
tasks validate, run beforeTool/afterTool, record intent with the replay policy,
publish bounded, sanitized, adaptively throttled progress in pi.live.tools, and
write results with a rendered diagnostics block. Hook dispatch with conversation
and subtree scopes, prepareArguments, HarnessOptions.env, and read/bash/edit/write
tools in pi-durable/tools. The env shell now streams raw output and spills past
thresholds; its bounded capture and publisher are removed.
Durable generation imports retry helpers from pi-ai/utils/retry; examples use
pi-ai/models and pi-ai/providers/faux. Entry graph budgets and an import
footprint test guard the models entry.
Submissions with request-ID deduplication and handles, the pi.live run
control and presentation document, the built-in pi.generation task
(system prompt preparation, streamed durable partials, retries, deferred
polling, abort), typed entry tokens, stream options and retry policy,
TaskRuntime reads, Tx.settleSubmission, registry conversation setups,
Storage.scanSubmissions, Harness.inspect, and byTaskId attribution.
Waiting calls enable scheduling. The scratch tour is split into
test/examples.
pi.live turn control and generation presentation, built-in entry kinds,
pi.generation checkpoint and phases, typed entry tokens, built-in tasks in
the registry, TaskRuntime reads, stream options and retry policy config,
Harness hook for scheduler-written outcomes, and createConversation without
input.
Adds defineTask, registry-resolved phase handlers, and a scheduler that
decides every task transition in one callback on the Session line:
reservation with migration, dependencies, precedence rules in a step
before each phase, handover to replaced definitions, direct-task abort
(mark, signal, join, fresh abort invocation), orphaning of blocked tasks,
open reconciliation, and close that joins invocations without writing
outcomes. runtime.commit() callbacks return the typed next state; Tx no
longer exposes setTask. Adds Harness.resume, getTask, waitForTask,
abortTask, and task-aware waitForIdle; RegistryReader.subscribe wakes
the scheduler.
Implements Pico5 Package 13: Harness.open over a Session with an application-owned
registry (tools, tool wrappers, hooks, tasks, system prompt sections; batched
publication, stable keyed order), lazy root creation with init, atomic
create/fork with init, conversation-bound commits, fork-aware entries, model
context derivation, and the built-in ConversationConfig document.
Fixes cached documents skipping migration when accessed with another definition
version. Rewrites the Pico5 spec and handoff to the registry/system-prompt
design and removes the superseded live-registries proposal.
Storage reports replayed deltas after the selected base; Session tracks the
count across adopted writes so checkpoint predicates can bound replay.
Also adds internal reserved-root creation and conversation-bound commit
defaults for the upcoming Harness.
Replace the alternate tracker implementations with the optimized immutable overlay, validate draft placements as strict JSON, and document the ownership contract. Consolidate tracker tests and benchmarks around the canonical implementation.
Name the Astra-immutable-optimized Chord Delta tracker as the Packages 6-7
prerequisite, include the minimal generic Tx table surface in that
milestone, and revoke drafts at callback settlement. Drop the Chord
prerequisite from Package 11 because the existing replicated-state source
contract already matches. Specify that tool stream() never spills; tools
spill through their execution environment.
Port and extend the agent environment tests for NodeExecutionEnv, output
capture, adaptive publishing, and truncation, including exact-byte
truncation, flushing, line-reader cancellation, spill backpressure, and
Buffer-free UTF-8 counting.
Fix truncation reporting when bytes and lines are both exceeded, when only
bytes are exceeded at the line cap, and when small limits trim multi-byte
edge characters. Report the full size of oversized newline-terminated tail
lines. Resolve durable test imports from source so tests run unbuilt.
Set Pico tool output defaults to 50 KiB and 2,000 lines.
Make SessionManager projections authoritative for provider requests, add append-only context edits and actionable turn boundaries, and preserve existing queue scheduling during continuation and recovery.
Keep clone and GC regressions plus a standalone traversal benchmark. Archive the discarded graph experiment and baseline comparisons in durable docs, including the remaining transient-memory and traversal-speed costs.
- Envelope carries a contiguous per-watch revision; storage Seq stays internal;
Chord bridge publishes off the line through a bounded ordered adapter
- Namespaces reach the view only through a declared view projection; memos and
slot working state are never in the view
- memoOnce uses property presence; memos are coordination/evidence, not
exactly-once; idempotency key before the effect
- Hooks bound to their namespace token; BeforeToolApi.waiting(ctx) is async;
memo keys are (task, namespace, name)
- Reload: quiescent hold/reload/release, otherwise suspend/reopen; no handler
withdrawal machinery in v1; Namespace.unregister
- pi.* entry names reject except pi.notice; config reset is an operation;
generation failures run the final boundary and start successors
Mario Zechner