One concrete failure occurred when seeded-blind wrote no_followup after roughly 34 minutes. The outer process resumed about 100 times without restoring useful work. A live scheduler is not a runnable semantic path. In another failure pattern, the system already knew replanning was needed but first offered a predictably invalid choice, forcing a failed call before revealing the next step.
No existing Todo does not imply that the original goal is complete. After finishing a work item, the agent must compare the result with the original acceptance: is it satisfied, does a reasonable next step remain within authorization, is there an external dependency, or is there truly no useful continuation? Replanning may produce work or justify staying on the same route. It should not invent tasks merely to keep a loop moving.
A long task can remain unfinished for hours, so review should track actual settled work. The effective-Turn repair replaced implicit Todo-completion counting while preserving explicit legacy units. Current continuation and the proposed study use six effective work Turns; early three-Turn and then-product five-count settings describe their own revisions. A due review requires reconsideration, not a route change or new budget.
+A long task can remain unfinished for hours, so review should track actual settled work. The effective-Turn repair replaced implicit Todo-completion counting while preserving explicit legacy units. The new study in Section 10 uses six effective work Turns; early three-Turn and then-product five-count settings describe their own revisions. A due review requires reconsideration, not a route change or new budget.
A Turn here is neither a model message nor a tool call. Cadence comes from uniquely settled work: uncommitted refreshes, retries and duplicate records must not inflate the count. Reaching the interval asks for a review, not a mandatory route change, and grants no budget or authority. Real entrypoints have been tested to trigger while a Todo is still open and to resume work after a justified continuation. Net benefit depends on what the model actually decides.
The counter must also distinguish work from observation. A validated negative result can be effective work; monitor-only polls, duplicate submissions and unsettled attempts do not count. This lets a long-open Todo receive periodic review without letting background sampling trigger pointless replans. A review should connect the original goal, candidate evidence and the next action. Choosing to continue can be correct; acknowledging that a check occurred does not establish better research direction.
Review cost also needs a breakdown by trigger. Periodic checks, a remaining goal gap after a work item ends, and new evidence invalidating a key assumption may need different depths of review. Changing the interval affects only one category. If every small completion rebuilds the global plan, a longer interval may not solve the problem. Conversely, a replan phase can contain useful probes and validation, so its entire duration is not administrative waste. Traces should distinguish useful route revision, repeated evidence gathering and mechanical bookkeeping before testing the boundary between local continuation and heavier global review.
@@ -91,10 +91,10 @@Session recovery preserves execution context. Settlement connects the current Turn, selected work, validation result, durable writeback and budget use. A retry after a lost response needs to recognize existing effects rather than execute or count them twice. Restoring a session without settlement can revisit the same obstacle; correct settlement with the wrong session can lose the solving context.
Earlier repairs addressed exact session recovery, next-action/receipt binding and invalid continuation diagnosis. Recent work adds checkpoint-selection and lifecycle recovery. Resume from the original Turn and committed effects: a lost reply must not duplicate execution or spend, and independent new work requires a fresh legal-path judgment. Correct continuation and useful work selection remain separate acceptance questions.
The following additions are updated through 2026-10-16, distinguishing merged repairs from proposals under review without rewriting earlier windows.
+The following status is updated through 2026-10-17, preserving historical windows while separating source, actual research adoption and effects.
Recent inspection moved beyond whether an agent read a Goal to which goal actually arrived. The original task remained in prompts and files, and agents did read it; some newly created structured benchmark Goals nevertheless carried only generic research reminders. Work could satisfy that reminder while drifting away from the task’s main metric. A separate projection defect borrowed public-display filtering for scoped input: paths or secret-like strings could drop a whole goal paragraph, and research text could be truncated.
#6649 preserves the original task objective and priorities in new Goals and complete source text in authorized same-Goal replan input; public export boundaries remain separate. #6654 makes that shared goal projection a default-off, explicit opt-in in LoopX and its benchmark runner. When enabled, the planning horizon shows the original Objective, provenance, separate acceptance and readback before work selection. A source correction appears on the next read. Disabling it preserves the existing horizon behavior; the Goal input already supplied to replan is independent of this switch. It creates no second persisted goal and does not rely on repeating a slogan every Turn.
-The original-goal repair #6649 is merged; horizon proposal #6654 still awaits independent review. The switch revision has configuration-editor and CLI readback, feature-off parity and benchmark effective-setting checks; the shared projection also has installed-package and real-CLI source-delivery validation. These validate candidate source, not its adoption by the research integration; old checkpoints are not rewritten. This repairs visibility, not goal prioritization by the model, and cannot explain every earlier low score.
+The original-goal repair #6649 and horizon switch #6654 are both merged, with configuration-editor, CLI readback and feature-off validation. The new same-point research in Section 10 explicitly enables the shared Goal horizon and reads the original objective in current reviews; old checkpoints are still not rewritten. An objective reaching work selection does not guarantee correct prioritization or explain every earlier low score. Follow-through must ask whether a complete experiment reduces the task’s main-metric gap.
In the older Graph stride-on/off comparison, outer wakes failed 20/99 and 14/104 times; successful wakes also recorded 35 and 45 internal stage errors. Failures clustered around review, checkpoint selection and unsettled-state recovery. The outer runner could wake again, while committed candidates, native results and some checkpoints survived. Work therefore continued, but could repeatedly recover the same decision, delay useful action and consume research or capture time.
Recorded failed-stage time was about 49 and 35 minutes, not total loss; 20/99 does not mean 20% of useful work was wasted. Unequal fault burdens confound an overall comparison. The selection-hop repair and lifecycle recovery repair address distinct breaks: preserve the original Turn, recognize committed effects and restore a legal route when independent work arrives. They add no submissions or cooldown resets and do not retroactively convert failures into passes. New studies need actual adoption of the repaired source.
@@ -132,7 +132,7 @@Exact Todo output fell from 15,986 UTF-8 bytes and three body copies to 2,721 bytes and one copy. Ordinary quota grew from 23,088 to 27,137 bytes against the command-only version because it carried actual content. Pending sources shrank from preference + Goal + Todo to Goal. This does not establish lower total tokens or latency: if old reads were already batched, removing a CLI process may remove no model round trip.
In 12 frozen real wakes, all received the complete Todo: nine through inline or file-based guards, three through exact reads. Eighteen inspected bodies matched their startup source digests. That establishes delivery and source consistency, not comprehension, complete constraint adherence or total cost benefit. The earlier roughly 78% synthetic compression claim likewise applies only to its measured output.
-The next integration’s information organization follows one real decision: complete current-work constraints arrive directly; a same-source original goal anchors selection; additional history and evidence expand by relevant question and revision. Do not mechanically reread an already delivered source. Missing content, failed sources or changed versions require complete reads through the current contract. Authorized research input must not lose its objective or counterevidence to public-display filtering. Optimize the whole decision path rather than one JSON length.
+The current study’s information organization follows one real decision: complete current-work constraints arrive directly; a same-source original goal anchors selection; additional history and evidence expand by relevant question and revision. Do not mechanically reread an already delivered source. Missing content, failed sources or changed versions require complete reads through the current contract. Authorized research input must not lose its objective or counterevidence to public-display filtering. Optimize the whole decision path rather than one JSON length.
Optional capabilities must not leak through generic guidance. Repeated semantic-preference reads induced by a generic skill while the capability is off are a boundary defect; #5874 returns that guidance to the participating hook. Smaller packets and fewer useless prompts help, but must preserve acceptance tails, applicability, continuation conditions and failure recovery. The optimization unit is the decision path, not one JSON length.
A direction worth testing is to put state and recovery complexity inside semantically complete tools with clear boundaries: obtain all constraints needed for current work, for example, or submit a result with its source and applicability. A tool may perform several internal checks while the model remains responsible for interpreting evidence and choosing a route. Anthropic’s tool-design guidance likewise organizes interfaces around real work rather than exposing every underlying API to the model.
@@ -170,7 +170,7 @@Improvement and technical depth are separate axes. A deep contract repair may eliminate a rare dead loop; a small instruction repair may immediately release substantial work time. We assess the gap removed and its evidence, not PR counts or passed-test totals.
| Boundary | Currently verified | Still unproven | ||
|---|---|---|---|---|
| Goal and feedback | Reproducible ledger misjudgments repaired; full Goal input and same-source horizon proposals have real CLI/installed readback | Actual adoption, task prioritization and net benefit; old checkpoints are not migrated | ||
| Goal and feedback | Reproducible ledger misjudgments repaired; full Goal input and same-source horizon have CLI, installed and current-model readback | Task prioritization and net benefit; old checkpoints are not migrated | ||
| Research state and recovery | Joint capture, fresh before review, original identity/opportunities/cooldown/deadline, mature-point continuation and further work are inspectable | Sustained stability as points grow, complete historical cost and a complete user-facing restoration journey | ||
| Evidence and review | Conditional capture, later delivery, immediate-predecessor review and real behavior chains; negative results and stale citations preserved | Explore beyond session/file memory; correct references yielding better choices | ||
| Planned and stride | Merged initial-quality/later-gain distinction; questions about retained best, goal bottleneck and actual implementation | Initial quality, later gain and cross-task stability after new-source adoption |
| Graph raw score | Quality term | Time penalty | Final score | Mean solution time |
|---|---|---|---|---|
| Inherited incumbent | 0.753764 | 0.018622 | 0.735142 | 6.68 s |
| New retained-history candidate | 0.755289 | 0.022892 | 0.732397 | 10.47 s |
| Observation | Sample and verification scope | What it does not establish |
|---|
| Stage | Design and criterion | Budget and limits |
|---|---|---|
| Accumulate from scratch | One arm per task; pin task, model, scorer, installed source, feedback and prompt; inspect initial delivery and actual evidence adoption | Task limits of 12/18/18 hours, at most 48 worker-hours; no six-arm fresh matrix |
| Produce research points | Capture before natural replans; preselect safe boundaries near half and three-quarter time, targeting two qualified mid/late points per task | Six target points; no score-based selection, deletion of stalled/low-scoring observations or artificial replans to hit a clock |
| Compare the same point | Proposed first comparison: Portfolio and Graph, same goal, evidence and version, both replanning fresh, varying stride on/off only; compare fresh/retained separately | Equal four-hour marginal windows, reporting common 1/2/4-hour outcomes; preserve consumed budget, opportunities and cooldown; account separately for later context-arm costs |
| Research point | State entering comparison | Budget and observation boundary |
|---|---|---|
| Portfolio | Source age about 7.22 hours; seven inherited native results and best 23.27 | Common 1/2/4-hour windows from continuation activation, including installation and preparation; cumulative limit 36 hours |
| Graph | Selected by preregistered age and sealing conditions; source age about 13.59 hours; 14 inherited native results and best 0.844507 | The same 1/2/4-hour observations; an equal 496-second reconstruction/replay charge, with source age and continuation phase totaling 36 hours |
A quality checkpoint is complete, attributable, captured before the current decision and actually restorable in an ordinary package. Sparse research is itself an observation; quality must not become post-hoc winner selection. Native submission has a one-hour cooldown from acceptance, is initially eligible and receives no extra tail grading. Review cadence is six settled effective work Turns throughout. A defect in goals, evidence, restoration or feedback stops the affected pair; preserve its reason and failure cost, then record a separate repaired attempt.
-Primary outcomes are legal native gain above inherited best, time to first gain and complete marginal cost. Process evidence asks how a negative result changes the next real experiment. Three fresh LoopX trajectories versus historical official runs remain descriptive. General LoopX-versus-native effects require separately admitted native repeats on the same version and budget; historical baselines cannot be stitched into a new causal control.
+Original opportunities and remaining cooldown follow the point; copying it grants neither extra opportunities nor a refill. A relevant qualified repair can justify retiring an affected source to free capacity, retaining every score, failure and stop reason without selecting by reward. The replaced Graph source had 17 completed native results at retirement; only the first 14 captured at the selected point enter its new arms. Later source information is not backfilled into that point.
+One real break was ownership: restored 0700 directories or 0600 files still belonged to root, so the worker could not read them. The selected-research-copy ownership repair has independent review and actual adoption of its candidate source in these Graph receivers. It preserves modes and imports no historical authority. That PR was still unmerged at this section’s cutoff; default installation is not thereby updated. Readability, model adoption, subsequent capture and research benefit have separate acceptance.
+The Graph point also lacked 37 temporary raw outputs. We regenerated them using only its sealed source, fixed fixture recipes and input digests, checked retained metrics, then sealed shared derived data separately for both arms. Ordinary users in both receivers read matching bytes and modes. Original output digests were absent: this is not original-byte recovery, and the old point was not backfilled. Saving research products under declared workspace coverage remains more reliable than continually repairing temporary paths. #6696 guides that placement; directory capture does not automatically discover every dynamic dependency.
+Both Graph models read 68 Explore events from the same basis and completed the current Goal’s semantic replan, preparation settlement and research handoff. Their first choice was identical: extending neighbor feature-mass means and standard deviations. Both stopped unchanged retries of rejected candidates and saved the 37 outputs in the workspace. Starting fresh did not itself produce a different first route. Complete experiments, decisions after negative results, the next natural capture and native gain remain to be observed.
+At two hours, each same-point Portfolio arm had two new native results and neither exceeded inherited best. By the preregistered four-hour cut, the retained arm submitted its frozen turnover-budget candidate and reached 23.42; fresh retained 23.27. The candidate, saved three-file digests, adopted package and public result were reconciled; no server package-digest attestation exists. This is a +0.15 continuation gain above the chosen point, also below the source donor’s later 23.48, rather than an all-time best.
+| Same four-hour continuation window | Retained history | Fresh replan |
|---|---|---|
| New completed native results | 3 | 2 |
| Best / gain above inherited best | 23.42 / +0.15 | 23.27 / 0 |
| Received uncached input tokens | 2,930,530 | 3,447,509 |
| Received cached input tokens | 122,126,336 | 130,243,584 |
| Received output tokens | 556,410 | 520,661 |
The retained arm’s Sharpe moved from 1.8804 to 1.8952 and drawdown from −1.12% to −1.08%, while excess return worsened from −19.46% to −19.49%; IR and Sortino still earned no points. Valid output, better local optimization and a small total-score gain did not close the main return gap. Nor does this justify simply blaming forgotten goals: both arms can read the objective. How they prioritize it, identify the limiting factor and choose experiments still needs inspection.
+Following its mean-influence audit, fresh tested one fixed Equity-observation repair. Some training averages improved, but the 2020 missing-macro stress path moved Sharpe from about 0.826 to −0.684, drawdown from about 3.00% to 5.34%, and relative terminal wealth down about 529,500. The model retained every result, rejected promotion and kept its native incumbent. This counterexample to one fixed rule does not reject all robust estimators: improved offline input metrics must still survive endogenous holdings, discrete allocation selection and costs.
+The retained arm also tested distinct mechanisms. A holding-period serial-covariance estimator failed its information gate; fully suppressing discretionary interim short adjustments helped some annual outcomes but hurt half-year performance and short-correlation requirements. Neither route was promoted. Fresh’s subsequent cone-optimization audit remained unfinished at the four-hour cut. Later replay and panel products are not retroactively counted as completed work, much less global-optimality proof. Complete experiments, informative counterexamples, candidate adoption and original-goal gain need separate records. Overlapping windows and case-session totals are not independent sample sizes.
+Cost ordering changed with the window. Fresh’s received uncached input was about 2.34% higher at one hour, 3.22% lower at two, and 17.64% higher at four; four-hour cached input was 6.65% higher and output 6.42% lower. These records remove inherited thread counters and include compaction and usage already returned for unfinished Turns. Fresh’s first task event also reported context-window metadata of 258,400 versus retained’s 475,000; subsequent events reported 475,000 in both. Event metadata does not establish an effective response limit, but the difference remains disclosed. Unreturned responses, evaluator resources, host admission and complete billing remain separate; qualification and other research on the shared host affect timing. A token vector cannot directly determine net efficiency.
+Later common windows ask whether negative evidence changes the next completed experiment, whether the exact adopted source improves the native main objective, what preparation/research/tool/evaluation cost precedes the first gain, and whether the next point remains restorable. Historical Official runs remain descriptive references, not same-version, same-budget native repeats. Raw archives are not released with this article: the public record provides scope, methods and aggregate observations, not independent reconstruction of every run.