dev/nisse
2
1 Fork 0
Code Issues 23 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Put work items in the state store, and bind the log to them (M1.1)
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m14s
Details

Browse Source 
Development Plan M1.1, as discussed.

- Schema v4: a work_items table (id, scope, title, status, outcome,
  position, data) and an agent row whose active_item points at one
  (NULL: idle). Canonical events and intents carry their work item, and
  events their actor. Older stores are refused with a clear message:
  there was no production data, so no migration (the mechanism stays).
- The log is reached through a Transcript bound to one work item and
  one actor: store.transcript(item, actor) reads only that item and
  writes with both. The planner, executor, delegation and expert desk
  get one per call from the orchestrator instead of holding the store,
  so a component can neither read another task's events (the planner
  read every earlier task's, #78) nor write without attribution.
  store.all_events() is kept for readers that span items (evaluation
  capture, dumps). Intents are begun through the transcript or with
  work_item=, so each belongs to its item.
- The orchestrator opens a work item on 'use', closes it with its
  outcome (completed or abandoned), and carries what the operator said
  while idle into the new item as copies with their origin, so a task
  sent before 'use' is still planned from (D1). control.py keeps its
  state machine through get_state()/transition(), now over the active
  work item, until M2.6 retires it.
- nisse_dev.dump shows work items and each event's item and actor.

Tests: test_work_items.py (scoping, attribution, intent ownership,
restart, outcomes, carried messages, a second task never seeing the
first); the suites updated for the per-call transcript.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
This commit is contained in:
dongarandClaude Opus 5.5 committed 2026-10-01 23:20:29 +00:00
1 parent 3cf4cefacd
commit 83804fe02a
40 files changed
+1026 -363
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

nisse-dev/src/nisse_dev/executor.py
+24 -18
View File
@@ -19,7 +19,7 @@ from nisse_dev.canonical import PlanSubmitted, StoredEvent, ToolCall, ToolResult
from nisse_dev.delegation import Delegation
from nisse_dev.expert import ASK_EXPERT_TOOL, BudgetExhausted, ExpertDesk
from nisse_dev.llm import LLMClient, LLMError, RoleMap
from nisse_dev.state import StateStore
from nisse_dev.state import Transcript
from nisse_dev.tools import EXECUTOR_TOOLS, MUTATING_TOOLS, ToolOutcome, Workspace
EXECUTOR_SYSTEM = """You are nisse-dev's executor, doing mechanical work.
@@ -76,7 +76,6 @@ class LLMExecutor:
def __init__(
self,
client: LLMClient,
store: StateStore,
roles: RoleMap,
workspace: Workspace,
*,
@@ -88,7 +87,6 @@ class LLMExecutor:
cancel: Cancel | None = None,
) -> None:
self._client = client
self._store = store
self._roles = roles
self._workspace = workspace
self._max_turns = max_turns
@@ -113,7 +111,7 @@ class LLMExecutor:
self._notify(f"turn {turn + 1}: {summary}")
def _escalate(
self, milestone: int, failures: int, last_failure: str
self, transcript: Transcript, milestone: int, failures: int, last_failure: str
) -> ExecutorOutcome | None:
"""Hand the sub-task to a stronger model, per L9.
@@ -134,7 +132,9 @@ class LLMExecutor:
"above. Finish this sub-task, staying inside the approved plan."
)
result = self._delegate.run(
brief=brief, branch=f"delegation/milestone-{milestone}-{failures}"
transcript.as_actor("helper"),
brief=brief,
branch=f"delegation/milestone-{milestone}-{failures}",
)
if result.usable:
return None
@@ -153,13 +153,16 @@ class LLMExecutor:
return [*EXECUTOR_TOOLS, FINISH_TOOL]
return [*EXECUTOR_TOOLS, ASK_EXPERT_TOOL, FINISH_TOOL]
def _consult(self, arguments: dict[str, Any]) -> ToolOutcome:
def _consult(
self, transcript: Transcript, arguments: dict[str, Any]
) -> ToolOutcome:
assert self._expert is not None
question = str(arguments.get("question", "")).strip()
if not question:
return ToolOutcome("ask_expert needs a question", success=False)
try:
return ToolOutcome(self._expert.ask(question).render(), success=True)
answer = self._expert.ask(transcript.as_actor("expert"), question)
return ToolOutcome(answer.render(), success=True)
except BudgetExhausted as exc:
# Not an error the model should route around: it is the signal
# that it is circling and should get on with the work or fail.
@@ -167,7 +170,7 @@ class LLMExecutor:
except LLMError as exc:
return ToolOutcome(f"the expert did not answer: {exc}", success=False)
def _scope(self) -> tuple[str | None, int]:
def _scope(self, transcript: Transcript) -> tuple[str | None, int]:
"""The approved plan, and where this milestone's events begin.
The most recent plan in the log is the approved milestone plan: no
@@ -177,7 +180,7 @@ class LLMExecutor:
context window cannot afford and the plan already distils.
"""
latest: StoredEvent | None = None
for stored in self._store.read_events():
for stored in transcript.read():
if isinstance(stored.event, PlanSubmitted):
latest = stored
if latest is None:
@@ -185,9 +188,11 @@ class LLMExecutor:
assert isinstance(latest.event, PlanSubmitted)
return latest.event.plan, latest.id
def run(self, milestone: int) -> ExecutorOutcome:
def run(self, transcript: Transcript, milestone: int) -> ExecutorOutcome:
"""Run a milestone of the work item whose transcript this is, writing
as the executor (L6, L7)."""
model = self._roles.resolve("executor")
plan, after = self._scope()
plan, after = self._scope(transcript)
system = (
f"{EXECUTOR_SYSTEM}\n\n{self._workspace.describe()}"
f"\n\nYou are executing milestone {milestone}."
@@ -209,7 +214,7 @@ class LLMExecutor:
return ExecutorOutcome("stopped", f"before turn {turn + 1}")
try:
produced = self._client.complete(
self._store.read_events(after=after),
transcript.read(after=after),
tools=tools,
model=model,
system=system,
@@ -219,7 +224,7 @@ class LLMExecutor:
calls: list[ToolCall] = []
for event in produced:
self._store.append_event(event)
transcript.append(event)
if isinstance(event, ToolCall):
calls.append(event)
@@ -235,7 +240,7 @@ class LLMExecutor:
self._report(turn, calls)
for index, call in enumerate(calls):
if self._cancel.requested:
skip_calls(self._store, calls[index:])
skip_calls(transcript, calls[index:])
return ExecutorOutcome("stopped", f"during turn {turn + 1}")
if call.tool == "finish":
if not did_work and not finish_refused:
@@ -248,7 +253,7 @@ class LLMExecutor:
"making any change",
)
else:
self._store.append_event(
transcript.append(
ToolResult(
call_id=call.call_id,
result="milestone finished",
@@ -256,7 +261,7 @@ class LLMExecutor:
)
)
skip_calls(
self._store,
transcript,
calls[index + 1 :],
"not run: finish had already ended the milestone",
)
@@ -274,12 +279,12 @@ class LLMExecutor:
success=False,
)
elif call.tool == "ask_expert":
outcome = self._consult(call.arguments)
outcome = self._consult(transcript, call.arguments)
else:
if call.tool in MUTATING_TOOLS:
did_work = True
outcome = self._workspace.dispatch(call.tool, call.arguments)
self._store.append_event(
transcript.append(
ToolResult(
call_id=call.call_id,
result=outcome.result,
@@ -298,6 +303,7 @@ class LLMExecutor:
# Escalating to the human is the fallback when there
# is no delegate, not the intended path.
escalation = self._escalate(
transcript,
milestone,
consecutive_failures,
outcome.result,