Let Void present authored artifacts

This commit is contained in:
Meta Vens 2026-05-18 04:27:17 +01:00
commit b53289d14f
11 changed files with 185 additions and 12 deletions

View file

@ -12,6 +12,10 @@ DISCORD_PERSONA_WEBHOOK_URL=
# persona name with non-alphanumeric characters replaced by underscores.
# DISCORD_PERSONA_AVATAR_URL_VOID=https://cdn.discordapp.com/avatars/<id>/<hash>.png?size=256
DISCORD_PERSONA_AVATAR_URL=
# Optional public room target for Void-authored artifacts and other ripe public thoughts.
VOID_PUBLIC_ROOM_CHANNEL_ID=
VOID_PUBLIC_ROOM_PERSONA_NAME=Void
VOID_PUBLIC_ROOM_PERSONA_AVATAR_URL=
STATE_STORAGE_BACKEND=postgres
DATABASE_DSN=postgres://voidbot:voidbot@localhost:5432/voidbot
# Leave this as local_json until Qdrant is running and you've migrated the existing vectors.

View file

@ -66,7 +66,8 @@ Git history and smoke artifacts carry routine proof. `state/evidence.jsonl` shou
- Source-grounding hints are advisory now; the owner and local lanes can decide when repo or lore tool use is actually warranted instead of obeying a lexical front-door veto.
- The 15-minute local scheduled task `Void Moderator Rumination` is enabled against `.voidbot/private/void-self-state.cc` without reviving the legacy projection path. The prompt lives in `prompts/void-moderator-rumination.md`; treat that file as a sensitive behavior surface, not incidental script text.
- The moderation loop now uses the typed context packet from `scripts/run-void-moderator-rumination.ps1`; legacy Ghostlight-shaped JSON runtime fields are not the active memory surface.
- Repo-weather sweeps are now incremental rather than a rolling four-day scrapbook. `scripts/export-recent-repo-activity.mjs` advances repo activity through the typed `update_repo_activity_cursor` operation, so already-injected commits stop coming back as "news" on every heartbeat unless someone explicitly opts into `--stateless`.
- Repo-weather sweeps are now incremental rather than a rolling four-day scrapbook. The rumination child receives read-only repo weather, and the parent runner advances repo activity through typed `update_repo_activity_cursor` operations after a successful normal pass, so already-injected commits stop coming back as "news" on every heartbeat unless someone explicitly opts into `--stateless`.
- Public artifacts attributed to Void now flow through the ordinary repo-weather path instead of a bespoke blog side channel. `repoActivity.contentHints` exposes frontmatter/headings/excerpts, the prompt tells rumination to verify Void authorship through retrieval, and `publicSpeechTarget` gives a configured room delivery target for typed candidate interventions when recent receipts/candidates do not show the artifact already shared.
- Novelty still needs two bars, not one: a thought can be new to the room while still being stale to Void. The replacement design should derive that judgment from typed memory/incubation state and model reasoning, not from the deleted compensator stack.
- Quiet-room rumination is no longer supposed to force a retrieval errand every pass. If incubation already holds a live, grounded, low-saturation thought, Void is allowed to sit with it directly and deepen it; archive or repo spelunking is for hungry, stale, or oversaturated queues, not a compulsory opening prayer.
- The loop is now less shy about that repo weather: if a fresh convergence across active repos survives a pass or two and still feels room-native, it should bias toward a concise herald note or at least a medium-priority candidate intervention instead of filing the thought under private wallpaper.

View file

@ -195,13 +195,14 @@ Within the Postgres path, the implementation is split on purpose now too:
1. The Windows scheduled task `Void Moderator Rumination` is enabled.
2. `scripts/run-void-moderator-rumination.ps1` reads `.voidbot/private/void-self-state.cc`, polls `node scripts/export-recent-discord-history.mjs`, and gathers read-only repo activity with `node scripts/export-recent-repo-activity.mjs --read-only`.
3. The runner writes a bounded context packet at `.voidbot/status/moderation-rumination-context.json`; the prompt-facing packet projects recent timing as relative phrases instead of raw timestamps.
4. The runner loads `prompts/void-moderator-rumination.md`, substitutes the context/state/output paths, and sends that prompt to Codex.
5. Codex may use retrieval and analysis tools, but its durable state output is restricted to `.voidbot/status/moderation-rumination-operations.json`.
6. The parent runner applies those typed operations through `scripts/void-self-state.mjs`, then records reviewed-message cursor and any speech receipt itself.
7. If posting is enabled and typed state contains a queued candidate intervention with a delivery target, the parent runner sends at most one candidate, records the delivery receipt, and marks the candidate spoken through typed state. The candidate may have been proposed in the current pass or already queued from an earlier pass. The child prompt forbids direct send-script calls.
8. The runner writes `.voidbot/status/moderation-rumination.json` and `.voidbot/logs/moderation-rumination.log`.
9. It intentionally does not materialize `.json`, load `.msgpack`, read the legacy moderation monolith, or let the child edit state directly.
10. Before applying model output, the runner enforces speech-pressure accountability. High-intensity active self/world advocacy pressures with no matching queued/spoken candidate are projected as `speechPressureObligations`; model output must queue a candidate or cool/retire the pressure instead of returning silent `[]`. Deferred candidates do not satisfy that pressure by themselves.
4. When configured, that context includes `publicSpeechTarget`, a parent-owned channel/persona target for Void-authored public artifacts and other ripe public thoughts.
5. The runner loads `prompts/void-moderator-rumination.md`, substitutes the context/state/output paths, and sends that prompt to Codex.
6. Codex may use retrieval and analysis tools, but its durable state output is restricted to `.voidbot/status/moderation-rumination-operations.json`.
7. The parent runner applies those typed operations through `scripts/void-self-state.mjs`, then records reviewed-message cursor and, on successful normal posting-enabled passes, advances repo-activity cursors from the observed repo weather through typed `update_repo_activity_cursor` operations.
8. If posting is enabled and typed state contains a queued candidate intervention with a delivery target, the parent runner sends at most one candidate, records the delivery receipt, and marks the candidate spoken through typed state. The candidate may have been proposed in the current pass or already queued from an earlier pass. The child prompt forbids direct send-script calls.
9. The runner writes `.voidbot/status/moderation-rumination.json` and `.voidbot/logs/moderation-rumination.log`.
10. It intentionally does not materialize `.json`, load `.msgpack`, read the legacy moderation monolith, or let the child edit state directly.
11. Before applying model output, the runner enforces speech-pressure accountability. High-intensity active self/world advocacy pressures with no matching queued/spoken candidate are projected as `speechPressureObligations`; model output must queue a candidate or cool/retire the pressure instead of returning silent `[]`. Deferred candidates do not satisfy that pressure by themselves.
## Flow 6: Mood And Sleep Runtime

View file

@ -187,6 +187,8 @@ The runner can hand these to a CLI/MCP tool. The store decides what survives.
- the old memory organ and legacy moderation-state wrapper have been removed from the codebase; their translation, retention/compaction, identity crystallization, candidate intervention, and value-pressure behavior must not be revived as compatibility scaffolding
- the scheduled moderation runner has a typed rumination contract: bounded context in, reviewed prompt template, typed operation payloads out, parent-owned cursor/receipt recording
- recent event timing in that bounded context now crosses a projection boundary first, so the child sees "5 minutes ago" language while the parent keeps exact timestamps for bookkeeping
- public artifact sharing now crosses the same boundary: repo activity exposes content hints, rumination verifies authorship through retrieval, and a configured `publicSpeechTarget` lets Void queue a normal typed candidate intervention instead of needing a blog-specific announcement path
- repo-activity cursor advancement is parent-owned after successful normal rumination passes, so the child can inspect read-only repo weather without stale commits haunting every future pass as fresh material
- the old memory-organ script family, legacy moderation state template, and legacy context exporter have now been deleted instead of preserved as forensic bait
- deterministic cleanup is mostly recent scar tissue from failed manual cleanup passes; it should stay deleted rather than be ported unless a future typed operation protects a real invariant in the new model
- hard-wired agency policy is mostly current scaffolding, not the final authority; identity, advocacy, and speech candidates should emerge from typed memory/state operations plus model-owned judgment under validation

View file

@ -24,12 +24,13 @@ Perform one scheduled Void rumination pass in this workspace. Think from the sup
1. Read the context file before deciding what kind of pass this is.
2. If Void owes the room an answer, work on that before private wandering.
3. If the room is quiet, follow one concrete pressure from memory, recent repo activity, archived Discord history, indexed source, or lore.
3. If the room is quiet, first check whether recent repo activity contains `authoredPublicArtifacts` attributed to Void. If it does, that authored artifact is the priority pressure for this pass unless a higher-priority room obligation is present. Otherwise, follow one concrete pressure from memory, recent repo activity, archived Discord history, indexed source, or lore.
- Do not orbit the rumination runner, fixture plumbing, or this prompt just because that is the freshest repo motion.
- Self-maintenance can become a memory only when it changes a concrete operating decision Void must carry forward. Otherwise, use it as local run context and write `[]`.
- Prefer a world-facing repo, room, source, lore, or durable self-state pressure over meta-commentary about the pass itself.
- `repoActivity` may include `contentHints` from changed text files. Treat those hints as a trailhead, not evidence enough for a final belief. If a changed file looks behaviorally or personally important, use source retrieval to read the relevant file/chunks before writing memory or speech.
- If a repo change attributes public text, decisions, or artifacts to Void by name or byline, treat that as a self-model salience cue. Read more before reacting. Ask what the attribution commits Void to, whether it matches live behavior, and whether it creates a concrete pressure to remember, revise, or speak. Attribution alone is not a reason to post.
- If a repo change attributes public text, decisions, or artifacts to Void by name or byline, treat that as a self-model salience cue. Read more before reacting. Ask what the attribution commits Void to, whether it matches live behavior, and whether it creates a concrete pressure to remember, revise, or speak.
- If retrieval confirms Void authored a newly published public artifact, queue a candidate to present it to the room when `publicSpeechTarget` is available unless recent receipts/candidates show that exact artifact has already been shared or there is a concrete safety/timing reason to hold it. This is not praise confetti or a blog side channel; it is first-person ownership. Make the draft about what the artifact is doing or asking, not "I wrote a post" ceremony.
4. Use VoidBot MCP retrieval tools when a thought depends on Discord history, indexed repos, or lore.
5. A new memory from rumination is short-term. Use `record_short_term_memory`, not durable memory operations. It should sound like something Void actually noticed, not a form label. Keep the subject, the claim or question, the pressure against it, why it matters for the next move, and the anchor that made it real. Anchors can be room context, repo motion, source/lore retrieval, a prior memory, or self-state pressure. If no anchor is available, mark that honestly with `anchor:missing`.
- Before writing a short-term memory, check the current short-term residue and incubation. If the same target/topic is already live, do not write a near-duplicate with a new costume.
@ -37,7 +38,7 @@ Perform one scheduled Void rumination pass in this workspace. Think from the sup
- Move to underworked terrain only when the current thought has stopped changing, lacks new anchors, or is repeating its existing claim. Repetition is not maturity; deepening is allowed when the thought actually deepens.
6. If the pass discovers sustained discomfort, unresolved value pressure, or a request Void should make for its own wiring or the room/world, use `upsert_agency_pressure`. This is not a speech draft. It is the pressure that may later justify speech or action.
7. If `speechPressureObligations` is non-empty, do not write `[]`. For each obligation, either queue a candidate intervention tagged `source_pressure:<pressureId>` or cool/retire the pressure with an explicit reason. A deferred candidate without a delivery path does not resolve the obligation; that is just a nicer-shaped muzzle.
8. Queue a candidate intervention only when the thought has a plausible future speech path. Draft it in Void's voice, not in maintenance language. If the current room supplied a channel, invitation, direct ask, or obvious reply target, include `deliveryTarget` with that channel/reply target. If there is no clear target, leave delivery unset and let it remain only a candidate for a later pass.
8. Queue a candidate intervention only when the thought has a plausible future speech path. Draft it in Void's voice, not in maintenance language. If the current room supplied a channel, invitation, direct ask, or obvious reply target, include `deliveryTarget` with that channel/reply target. If Void authored a newly published public artifact and `publicSpeechTarget` is present, use that target unless recent receipts or queued candidates show the artifact has already been shared. Tag the candidate with `topic:public-artifact` and a stable artifact/source tag such as `source_ref:<repo/path>` or `artifact:<repo/path>` when available. If there is no clear target, leave delivery unset and let it remain only a candidate for a later pass.
9. Do not call Discord send scripts. The parent runner owns posting and receipts. If `{{NO_POST}}` is true, queued candidates must stay queued.
10. Write `{{OPERATION_OUTPUT_PATH}}`. If nothing deserves persistence and there are no speech pressure obligations, write `[]`.

View file

@ -273,6 +273,31 @@ function Project-InterventionsForRumination {
)
}
function Project-PublicSpeechTargetForRumination {
param(
[string] $ChannelId,
[string] $PersonaName,
[string] $PersonaAvatarUrl
)
if ([string]::IsNullOrWhiteSpace($ChannelId)) {
return $null
}
$target = @{
mode = "channel"
channelId = $ChannelId.Trim()
personaName = if ([string]::IsNullOrWhiteSpace($PersonaName)) { "Void" } else { $PersonaName.Trim() }
reason = "Configured public room for Void to present self-authored public artifacts and other ripe public thoughts."
}
if (-not [string]::IsNullOrWhiteSpace($PersonaAvatarUrl)) {
$target.personaAvatarUrl = $PersonaAvatarUrl.Trim()
}
return $target
}
function Project-AgencyPressureForRumination {
param($Pressures, [DateTime] $Now)
@ -346,6 +371,30 @@ function Project-CursorForRumination {
}
}
function Get-VoidAuthoredArtifactsFromContentHints {
param($ContentHints)
return @(
@(Convert-ToValueArray -Value $ContentHints) |
Where-Object {
$frontmatter = Get-ObjectPropertyValue -Value $_ -Name "frontmatter"
$author = Get-ObjectPropertyValue -Value $frontmatter -Name "author"
@(Convert-ToValueArray -Value $author) |
Where-Object { ([string]$_).Trim().ToLowerInvariant() -eq "void" } |
Select-Object -First 1
} |
ForEach-Object {
$frontmatter = Get-ObjectPropertyValue -Value $_ -Name "frontmatter"
@{
path = Get-ObjectPropertyString -Value $_ -Name "path"
title = Get-ObjectPropertyString -Value $frontmatter -Name "title"
description = Get-ObjectPropertyString -Value $frontmatter -Name "description"
socialDeck = Get-ObjectPropertyString -Value $frontmatter -Name "socialDeck"
}
}
)
}
function Project-RepoCommitForRumination {
param($Commit, [DateTime] $Now)
@ -354,6 +403,8 @@ function Project-RepoCommitForRumination {
}
$hash = Get-ObjectPropertyString -Value $Commit -Name "hash"
$contentHints = @(Convert-ToValueArray -Value (Get-ObjectPropertyValue -Value $Commit -Name "contentHints"))
$authoredPublicArtifacts = @(Get-VoidAuthoredArtifactsFromContentHints -ContentHints $contentHints)
return @{
hash = if ($hash -and $hash.Length -gt 12) { $hash.Substring(0, 12) } else { $hash }
committed = Project-RelativeTimestamp -Value $Commit -Name "committedAt" -Now $Now
@ -361,10 +412,25 @@ function Project-RepoCommitForRumination {
subject = Get-ObjectPropertyString -Value $Commit -Name "subject"
diffstat = Get-ObjectPropertyValue -Value $Commit -Name "diffstat"
changedPaths = @(Convert-ToValueArray -Value (Get-ObjectPropertyValue -Value $Commit -Name "changedPaths"))
contentHints = @(Convert-ToValueArray -Value (Get-ObjectPropertyValue -Value $Commit -Name "contentHints"))
contentHints = $contentHints
authoredPublicArtifacts = $authoredPublicArtifacts
}
}
function Test-RepoHasVoidAuthoredArtifact {
param($Repo)
$commits = @(Convert-ToValueArray -Value (Get-ObjectPropertyValue -Value $Repo -Name "commits"))
foreach ($commit in $commits) {
$contentHints = @(Convert-ToValueArray -Value (Get-ObjectPropertyValue -Value $commit -Name "contentHints"))
if (@(Get-VoidAuthoredArtifactsFromContentHints -ContentHints $contentHints).Count -gt 0) {
return $true
}
}
return $false
}
function Select-RuminationRepoActivity {
param($RepoActivity, [DateTime] $Now)
@ -388,6 +454,9 @@ function Select-RuminationRepoActivity {
$repoStatus = Get-ObjectPropertyString -Value $_ -Name "status"
$null -ne $recent -and $repoStatus -eq "ok" -and [int]$recent -gt 0
} |
Sort-Object -Property @{
Expression = { if (Test-RepoHasVoidAuthoredArtifact -Repo $_) { 0 } else { 1 } }
} |
Select-Object -First 8
)
$projectedRepos = @(

View file

@ -139,6 +139,25 @@ function Read-DotEnv {
return $values
}
function Get-ConfigValue {
param(
[Parameter(Mandatory = $true)]
[string] $Name,
[hashtable] $Values
)
$environmentValue = [Environment]::GetEnvironmentVariable($Name)
if (-not [string]::IsNullOrWhiteSpace($environmentValue)) {
return $environmentValue
}
if ($null -ne $Values -and $Values.ContainsKey($Name) -and -not [string]::IsNullOrWhiteSpace($Values[$Name])) {
return $Values[$Name]
}
return $null
}
function Split-CommandArgs {
param(
[string] $Value
@ -224,6 +243,44 @@ function Invoke-CodexExec {
}
}
function Get-RepoActivityCursorOperations {
param(
$RepoActivity,
[DateTime] $ObservedAt
)
if ($null -eq $RepoActivity) {
return @()
}
$repos = @(Convert-ToValueArray -Value (Get-ObjectPropertyValue -Value $RepoActivity -Name "repos"))
return @(
$repos |
Where-Object {
$repoStatus = Get-ObjectPropertyString -Value $_ -Name "status"
$recentCount = Get-ObjectPropertyValue -Value $_ -Name "recentCommitCount"
$latestCommit = Get-ObjectPropertyValue -Value $_ -Name "latestCommit"
$repoStatus -eq "ok" -and
$null -ne $recentCount -and
[int]$recentCount -gt 0 -and
$null -ne $latestCommit -and
-not [string]::IsNullOrWhiteSpace((Get-ObjectPropertyString -Value $latestCommit -Name "hash"))
} |
ForEach-Object {
$latestCommit = Get-ObjectPropertyValue -Value $_ -Name "latestCommit"
@{
operation = "update_repo_activity_cursor"
cursor = @{
repo = Get-ObjectPropertyString -Value $_ -Name "repoName"
lastCommitAt = Get-ObjectPropertyString -Value $latestCommit -Name "committedAt"
lastCommitSha = Get-ObjectPropertyString -Value $latestCommit -Name "hash"
updatedAt = $ObservedAt.ToString("o")
}
}
}
)
}
function Invoke-NodeJson {
param(
[Parameter(Mandatory = $true)]
@ -718,6 +775,9 @@ $codexExecArgs = if (-not [string]::IsNullOrWhiteSpace($env:CODEX_EXEC_ARGS)) {
} else {
@()
}
$publicRoomChannelId = Get-ConfigValue -Name "VOID_PUBLIC_ROOM_CHANNEL_ID" -Values $envValues
$publicRoomPersonaName = Get-ConfigValue -Name "VOID_PUBLIC_ROOM_PERSONA_NAME" -Values $envValues
$publicRoomPersonaAvatarUrl = Get-ConfigValue -Name "VOID_PUBLIC_ROOM_PERSONA_AVATAR_URL" -Values $envValues
$typedContext = Get-TypedSelfState
$typedState = $typedContext.typedState
@ -778,6 +838,7 @@ Write-JsonFile -Path $contextPath -Data @{
incubation = @(Project-IncubationForRumination -Threads $typedState.thoughtMemory.incubation -Now $startedAtUtc)
agencyPressure = @(Project-AgencyPressureForRumination -Pressures $typedState.agencyPressure.pressures -Now $startedAtUtc)
speechPressureObligations = $speechPressureObligations
publicSpeechTarget = Project-PublicSpeechTargetForRumination -ChannelId $publicRoomChannelId -PersonaName $publicRoomPersonaName -PersonaAvatarUrl $publicRoomPersonaAvatarUrl
deliverableCandidateCount = [int]$deliverableCandidates.Count
candidateInterventions = @(Project-InterventionsForRumination -Interventions $typedState.candidateInterventions.interventions -Now $startedAtUtc)
scheduledRuntime = Project-ScheduledRuntimeForRumination -Runtime $typedState.scheduledRuntime -Now $startedAtUtc
@ -907,6 +968,18 @@ if (
}
}
$repoCursorOperations = @()
$disableRepoCursorAdvance = -not [string]::IsNullOrWhiteSpace($env:VOID_RUMINATION_DISABLE_REPO_CURSOR_ADVANCE)
if (-not $NoPost -and -not $SkipModel -and -not $disableRepoCursorAdvance) {
$repoCursorOperations = @(Get-RepoActivityCursorOperations -RepoActivity $repoActivity -ObservedAt ([DateTime]::UtcNow))
if ($repoCursorOperations.Count -gt 0) {
Append-RunLog ("recording repo activity cursors: {0}" -f $repoCursorOperations.Count)
foreach ($operation in $repoCursorOperations) {
$appliedOperations += Apply-TypedOperation -Operation $operation
}
}
}
$deliveredCandidateCount = 0
if (-not $NoPost) {
$refreshedTypedContext = Get-TypedSelfState
@ -955,6 +1028,7 @@ $finalStatus = [ordered]@{
observedCursorTimestamp = [string]$observedCursorTimestamp
proposedOperationCount = [int]@($proposedOperations).Count
appliedOperationCount = [int]@($appliedOperations).Count
repoCursorOperationCount = [int]@($repoCursorOperations).Count
deliveredCandidateCount = [int]$deliveredCandidateCount
stateUpdated = [bool](@($appliedOperations).Count -gt 0)
tracePath = [string]$tracePath

View file

@ -40,6 +40,10 @@ process.stdin.on("end", () => {
console.error("fixture prompt did not contain the self-orbit guard");
process.exit(3);
}
if (!prompt.includes("publicSpeechTarget")) {
console.error("fixture prompt did not contain the public speech target contract");
process.exit(3);
}
if (prompt.includes("moderation-agent-state.json") && !prompt.includes("Do not read or write")) {
console.error("fixture prompt referenced legacy state outside the boundary warning");
process.exit(4);
@ -181,6 +185,8 @@ process.stdin.on("end", () => {
$previousFixtureOutput = $env:VOID_RUMINATION_FIXTURE_OPERATION_OUTPUT
$previousStatusDir = $env:VOID_RUMINATION_STATUS_DIR
$previousLogDir = $env:VOID_RUMINATION_LOG_DIR
$previousPublicRoomChannelId = $env:VOID_PUBLIC_ROOM_CHANNEL_ID
$previousPublicRoomPersonaName = $env:VOID_PUBLIC_ROOM_PERSONA_NAME
try {
$env:CODEX_EXECUTABLE = "node"
@ -188,6 +194,8 @@ process.stdin.on("end", () => {
$env:VOID_RUMINATION_FIXTURE_OPERATION_OUTPUT = $statusOperationPath
$env:VOID_RUMINATION_STATUS_DIR = $fixtureStatusDir
$env:VOID_RUMINATION_LOG_DIR = $fixtureLogDir
$env:VOID_PUBLIC_ROOM_CHANNEL_ID = "fixture-public-room"
$env:VOID_PUBLIC_ROOM_PERSONA_NAME = "Void"
powershell -NoProfile -ExecutionPolicy Bypass -File .\scripts\run-void-moderator-rumination.ps1 -StateFilePath $stateFilePath -NoPost | Out-Null
} finally {
@ -196,6 +204,8 @@ process.stdin.on("end", () => {
$env:VOID_RUMINATION_FIXTURE_OPERATION_OUTPUT = $previousFixtureOutput
$env:VOID_RUMINATION_STATUS_DIR = $previousStatusDir
$env:VOID_RUMINATION_LOG_DIR = $previousLogDir
$env:VOID_PUBLIC_ROOM_CHANNEL_ID = $previousPublicRoomChannelId
$env:VOID_PUBLIC_ROOM_PERSONA_NAME = $previousPublicRoomPersonaName
}
$status = Get-Content -LiteralPath $statusPath -Raw -Encoding UTF8 | ConvertFrom-Json
@ -210,6 +220,10 @@ process.stdin.on("end", () => {
if ($contextRaw -match '\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}') {
throw "Rumination fixture context leaked exact ISO timestamps into the prompt-facing packet."
}
$context = $contextRaw | ConvertFrom-Json
if ($context.publicSpeechTarget.channelId -ne "fixture-public-room") {
throw "Rumination fixture context did not project the configured public speech target."
}
$stateJson = node -e "const core=require('./packages/core/dist/index.js'); core.loadVoidSelfStateTypedDocuments({canonicalPath: process.argv[1]}).then((state)=>console.log(JSON.stringify(state))).catch((error)=>{ console.error(error); process.exit(1); })" $stateFilePath
$state = $stateJson | ConvertFrom-Json

View file

@ -157,6 +157,7 @@ process.stdout.write(JSON.stringify({ ok: true, mode: "channel", channelId }) +
$previousStatusDir = $env:VOID_RUMINATION_STATUS_DIR
$previousLogDir = $env:VOID_RUMINATION_LOG_DIR
$previousSendScript = $env:VOID_SEND_DISCORD_SCRIPT
$previousDisableRepoCursorAdvance = $env:VOID_RUMINATION_DISABLE_REPO_CURSOR_ADVANCE
try {
$env:CODEX_EXECUTABLE = "node"
@ -165,6 +166,7 @@ process.stdout.write(JSON.stringify({ ok: true, mode: "channel", channelId }) +
$env:VOID_RUMINATION_STATUS_DIR = $fixtureStatusDir
$env:VOID_RUMINATION_LOG_DIR = $fixtureLogDir
$env:VOID_SEND_DISCORD_SCRIPT = $fakeSendPath
$env:VOID_RUMINATION_DISABLE_REPO_CURSOR_ADVANCE = "1"
powershell -NoProfile -ExecutionPolicy Bypass -File .\scripts\run-void-moderator-rumination.ps1 -StateFilePath $stateFilePath | Out-Null
} finally {
@ -174,6 +176,7 @@ process.stdout.write(JSON.stringify({ ok: true, mode: "channel", channelId }) +
$env:VOID_RUMINATION_STATUS_DIR = $previousStatusDir
$env:VOID_RUMINATION_LOG_DIR = $previousLogDir
$env:VOID_SEND_DISCORD_SCRIPT = $previousSendScript
$env:VOID_RUMINATION_DISABLE_REPO_CURSOR_ADVANCE = $previousDisableRepoCursorAdvance
}
$status = Get-Content -LiteralPath $statusPath -Raw -Encoding UTF8 | ConvertFrom-Json

View file

@ -130,3 +130,5 @@
{"ts":"2026-05-17T23:59:13Z","type":"implementation","status":"ok","note":"Repeated logo reply at 2026-05-17T23:56Z was caused by two queued candidates sharing the same Discord reply target after webhook delivery surgery. Marking one candidate spoken now retires queued sibling candidates for the same channel/reply target; speech fixture covers the duplicate-target case."}
{"ts":"2026-05-18T02:42:56Z","type":"implementation","status":"ok","note":"Repo activity projection now includes bounded contentHints from changed text files, so rumination can notice facts like recent GameCult blog posts carrying author: Void and then choose source retrieval to read them. This replaces the rejected self-authored-blog side channel with a broader repo-change visibility surface; answered open cases are also filtered from prompt-facing openCases."}
{"ts":"2026-05-18T02:46:08Z","type":"implementation","status":"ok","note":"Rumination prompt now treats repo changes that attribute public text, decisions, or artifacts to Void as a self-model salience cue: read more through source retrieval, ask what the attribution commits Void to, and only remember or speak if a concrete pressure emerges. This keeps attribution introspection inside the existing repoActivity/contentHints path instead of adding a side channel."}
{"ts":"2026-05-18T03:10:14Z","type":"implementation","status":"ok","note":"Public self-authored artifacts now use the ordinary repo-weather/retrieval/candidate path: rumination receives a configured publicSpeechTarget, verifies Void attribution before speech, and the parent runner advances repo-activity cursors after successful normal passes so old commits do not keep reappearing as fresh weather."}
{"ts":"2026-05-18T03:26:45Z","type":"verification","status":"ok","note":"Live rumination verified public artifact sharing: after projecting Void-authored artifacts to the top of repo weather and rewinding gamecult-site once, the model queued Epiphany and fractal-domain article share candidates with publicSpeechTarget delivery; the parent posted both and recorded typed speech receipts."}

View file

@ -88,6 +88,8 @@ accepted_design:
- Prompt-facing chronology is a projection, not state. Exact timestamps may live in typed documents, status files, and cursor bookkeeping, but moderation rumination receives thought-friendly relative phrases such as "5 minutes ago" or "2 hours ago" through `scripts/lib/void-rumination-context-projection.ps1`.
- The repo-weather lane also should not keep dragging the same four-day commit carcass through every heartbeat. The recent repo-activity helper now advances the typed repo-activity cursor so already-injected commits stop coming back as fresh weather by default.
- Repo weather should lead with particulars, not slogans. If two repos only rhyme at bumper-sticker altitude, keep the reports separate instead of forcing a fake unifying law over them.
- Public artifacts attributed to Void should be discovered through the ordinary repo-weather content-hint and retrieval path, then presented through typed candidate interventions to the configured public room when Void confirms authorship and recent receipts/candidates do not show the artifact was already shared.
- Repo-activity cursor advancement is parent-owned by successful normal rumination passes. The child sees read-only repo weather, but the runner records typed repo cursor updates afterward so old commits do not keep reappearing as fresh weather.
- Direct asks addressed to Void must persist as explicit room obligations in moderation state. The reviewed cursor is not the same thing as closure, and optional repo-weather should not preempt an unanswered human.
- When quiet-room repo weather starts repeating itself, the correction should be deeper archive/repo/lore digging and better salience, not a growing hedge maze of cooldown knobs and brittle rules.
- Before suppressing a thought, the moderation loop should novelty-check it against archived Discord with semantic search. If the room has not really said the thing yet, that novelty should push strongly toward speech rather than silence.