Return persisted planning acceptance or refusal inside the investigation turn.
Keep model judgment separate from action authority and preserve accepted action
identity across provider failures. Enforce actor/request idempotency atomically
and retain complete approval and independent verification context.
Preserve unknown disk evidence, stream whitespace and historical resolution
timestamps. Keep conversation scrolling inside its own panel. Record real-model,
disposable-lab and browser qualification with explicit population limits.
Refs #1782
Let the configured model choose investigation steps within explicit budgets.
Keep canonical planning, permissions and independent verification authoritative,
and preserve streamed conclusions in conversation history.
Expose recorded action outcomes so cached inventory cannot stand in for an
approval or execution receipt. Retain full plan context and make the exact
action review reachable from Assistant, including on narrow screens.
Refs #1782
The three deep-dive documents describe enumerations and tuned constants that
live in code. Prose cannot notice when a fifth state or an eighth signal type
is added next to it, so the documents would have rotted silently.
These guards derive the truth from the source rather than asserting literal
strings. A test that only checks the document contains RESOLVING keeps
passing when a new state appears, which is the drift actually worth catching.
Covered, in both directions where the set is enumerable. Session states and
tool kinds against internal/ai/chat/fsm.go and the ToolCallKind String
method. Patrol signal types and the five tuned signal thresholds against
internal/ai/patrol_signals.go. The investigation attempt limit and cooldown
against internal/ai/findings.go. The look-before-asking bound and the tool
concurrency cap against internal/ai/chat/agentic.go. Identifiers named in the
structured errors section against the declared error codes and tool names.
Error codes are checked document to code only. The document names a
representative sample rather than all 45 declared codes, so requiring the
reverse would force a table that churns on every addition while catching
nothing a reader cares about. A rename or removal still fails.
Writing the guard immediately found a real mistake in the document it
guards. ErrCodeFSMBlocked is FSM_BLOCKED, not fsm_blocked as the prose
claimed, corrected here.
Each guard was verified to fail by adding a fifth session state, adding a
signal type, and changing a threshold, then confirming the failure named the
document and the value.
Contract-Neutral: test and documentation only
AI.md, AI_AUTONOMY.md and PULSE_PRO.md linked nine times into
docs/architecture/, which .gitignore marks as not for public release. The
targets were never missing, they were deliberately unpublished, so every one
of those links was dead for anybody but the maintainer.
Write the three promised documents against the code and publish them under
docs/ where the rest of the shipped set lives.
PATROL_ARCHITECTURE.md covers a run end to end. The interesting part is that
deterministic signal detection runs after the model, not before, so unmatched
signals catch what the model failed to file. Signal types, the thresholds
those signals derive from your own alert settings, and every condition in
Finding.ShouldInvestigate are documented from internal/ai/patrol_signals.go
and internal/ai/findings.go.
ASSISTANT_SAFETY.md documents the session state machine in
internal/ai/chat/fsm.go, its four states, the tool classification it runs on,
and its invariants. No write without a validated target, no second write
before the first is verified, no final answer about an unverified change, and
no attempt count that wears the gate down.
ASSISTANT_ARCHITECTURE.md covers the agentic loop around that machine, the
three-phase pipeline, why only execution parallelises and at what cap, the
read-before-write batch that must stay ordered, the look-before-asking gate
and its bound, and the stable error codes.
Also removed two older pointers into the same private directory, in API.md
and UPGRADE_v6.md, and the two references to ENTITLEMENT_MATRIX.md in
PULSE_PRO.md. That file exists locally and is a monetization document, so
publishing it is not a documentation decision.
Unresolvable intra-doc links are now 2 of 218, both internal release-control
documents deliberately withheld from the shipped set.
Contract-Neutral: documentation only
rcourtman