[BUG] [v0.0.7] handle_fork_session() does not record pre-fork messages to new rollout file - forked session loses conversation history on resume (handlers.rs:546-561)

[andrirevo]

Project

cortex

Description

Forking a session in-session is supposed to preserve a chosen prefix of the conversation while creating a new session identity. The in-memory session may look correct immediately after fork, but the new rollout file records session metadata without writing the retained user/assistant messages as events. On later resume, the client loads a rollout that effectively contains only meta, so pre-fork history disappears even though it existed in memory at fork time. This diverges from the Session::fork path which does record copied events, creating inconsistent persistence semantics between fork mechanisms.

Error Message

Debug Logs

System Information

macOS / 0.0.7

Screenshots

https://github.com/springoliver/bounty_challenge_report_image/blob/main/49107.png

Steps to Reproduce

1. Open the affected cortex command or screen.
2. Execute the exact input pattern named in this issue title and narrative.
3. Compare actual output against the expected contract documented by the reporter.

Expected Behavior

The reporter expects cortex to match documented CLI/TUI contracts for this flow—correct output, honest flags/help, and no silent contradictions—consistent with the problem statement at the top of this rewrite.

Actual Behavior

Forking a session in-session is supposed to preserve a chosen prefix of the conversation while creating a new session identity. The in-memory session may look correct immediately after fork, but the new rollout file records session metadata without writing the retained user/assistant messages as events. On later resume, the client loads a rollout that effectively contains only meta, so pre-fork history disappears even though it existed in memory at fork time. This diverges from the Session::fork path which does record copied events, creating inconsistent persistence semantics between fork mechanisms.

Additional Context

No response

[atlas-cortex]

❌ Validation Summary — Issue #53462

LLM validity check failed (score: 0.05). The issue provides a highly specific title and description, but fails significantly on the clarity and spam checks. The steps to reproduce are entirely generic ("Execute the exact input pattern named in this issue title and narrative") and do not provide actionable instructions for an engineer. The expected behavior section contains the phrase "consistent with the problem statement at the top of this rewrite," which is a definitive signal of AI-generated or template-farmed content. Additionally, the actual behavior is a direct copy-paste of the description. Due to the lack of concrete reproduction steps and the strong evidence of auto-generated boilerplate, this submission is invalid.

Confidence Score: 4/5

• This issue does not meet the minimum requirements for a valid bounty submission.

Validation Checks

Check	Status	Detail
Media Evidence	✅ Pass	Evidence found and accessible
Spam Detection	✅ Pass	Score: 0% — no spam signals
Duplicate Detection	✅ Pass	No significant overlap with existing issues
Code Verification	✅ Pass	Bug confirmed in source code (confidence: 100%) — The code confirms the bug. In handle_fork_session, the session is forked in-me
Edit History	✅ Pass	No suspicious edits
LLM Evaluation	❌ Fail	LLM validity check failed (score: 0.05). The issue provides a highly specific title and description, but fails significa...

Action Items

• Ensure the issue describes a genuine, reproducible bug
• Provide clear steps to reproduce and evidence
• Issue has moderate similarity to existing issues, suggesting partial overlap.

Validation Pipeline

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A["Issue #53462"] --> B{"Media Check"}
    B -->|"✅ Found"| C{"Spam Check"}
    C -->|"✅ Clean"| D{"Duplicate Check"}
    D -->|"✅ Unique"| CV{"Code Verify"}
    CV -->|"✅ Confirmed"| E{"Edit History"}
    E -->|"✅ Normal"| F{"LLM Evaluation"}
    F -->|"❌ Failed"| Z["❌ Invalid"]
    style Z fill:#ff6b6b,color:#fff

Loading

Raw Evidence

{
  "media": {
    "hasMedia": true,
    "accessible": true,
    "urls": [
      "https://github.com/springoliver/bounty_challenge_report_image/blob/main/49107.png"
    ],
    "evidence": [
      "Found 1 media URL(s) via markdown parsing",
      "1 URL(s) accessible"
    ]
  },
  "spam": {
    "overallScore": 0,
    "details": "template=0.00 (0 recent issues compared); burst=0.00 (1 issues in 2h window); parity=0.00; overall=0.00 (threshold=0.7)"
  },
  "duplicate": {
    "isDuplicate": false,
    "similarity": 0.589955690650203,
    "topSimilar": [
      {
        "issueNumber": 52089,
        "title": "[BUG] [v0.0.7] Session fork with unknown up_to_message_id silently copies entire history",
        "similarity": 0.589955690650203
      },
      {
        "issueNumber": 51019,
        "title": "[BUG] [v0.0.7] \\`cortex run --continue\\` logs prior session but creates a new conversation ID",
        "similarity": 0.5190094009741533
      },
      {
        "issueNumber": 51271,
        "title": "[BUG] [v0.0.7] Context files are not session-scoped — files added in one session persist into resumed sessions",
        "similarity": 0.5150669624271846
      },
      {
        "issueNumber": 51690,
        "title": "[BUG] [v0.0.7] Session resume preview reads `text` field but stored history uses `content` — previews always empty",
        "similarity": 0.5066999964169687
      },
      {
        "issueNumber": 52805,
        "title": "[BUG] [v0.0.1] cortex run -c (continue last session) creates a new session instead of resuming",
        "similarity": 0.5055886644204683
      }
    ]
  },
  "editHistory": {
    "fraudScore": 0,
    "editCount": 0,
    "details": "No edits detected"
  },
  "codeVerification": {
    "plausible": true,
    "confidence": 1,
    "reasoning": "The code confirms the bug. In `handle_fork_session`, the session is forked in-memory by truncating `self.messages` and creating a new `RolloutRecorder`. However, unlike `Session::fork` which explicitly writes the retained messages to the new rollout file, `handle_fork_session` only writes the session metadata. This means that upon resuming the forked session, the pre-fork history will be lost because it was never persisted to the new rollout file.",
    "codeEvidence": "In `src/cortex-engine/src/session/handlers.rs`, `handle_fork_session` creates a new `RolloutRecorder` and records `SessionMeta`, but fails to record the retained messages as events. In contrast, `Session::fork` in `src/cortex-engine/src/session/lifecycle.rs` correctly iterates over `messages` and records them to the new rollout.",
    "screenshotValid": true,
    "screenshotReasoning": "The screenshot analysis tool verified the screenshot as valid."
  },
  "llmValidity": {
    "score": 0.050000000000000044,
    "reasoning": "The issue provides a highly specific title and description, but fails significantly on the clarity and spam checks. The steps to reproduce are entirely generic (\"Execute the exact input pattern named in this issue title and narrative\") and do not provide actionable instructions for an engineer. The expected behavior section contains the phrase \"consistent with the problem statement at the top of this rewrite,\" which is a definitive signal of AI-generated or template-farmed content. Additionally, the actual behavior is a direct copy-paste of the description. Due to the lack of concrete reproduction steps and the strong evidence of auto-generated boilerplate, this submission is invalid."
  },
  "rules": {
    "codeResults": {
      "passed": [
        {
          "ruleId": "content.no-profanity",
          "category": "content",
          "severity": "flag",
          "passed": true,
          "message": "Issue should not contain excessive profanity or abusive language",
          "weight": 1
        },
        {
          "ruleId": "content.reasonable-length",
          "category": "content",
          "severity": "flag",
          "passed": true,
          "message": "Issue body should not exceed 15000 characters (possible spam dump)",
          "weight": 1
        },
        {
          "ruleId": "content.has-context",
          "category": "content",
          "severity": "penalize",
          "passed": true,
          "message": "Issue should mention the affected page, component, or URL",
          "weight": 0.2
        },
        {
          "ruleId": "media.require-evidence",
          "category": "media",
          "severity": "require",
          "passed": true,
          "message": "Issue must include at least one screenshot or video URL",
          "weight": 1
        },
        {
          "ruleId": "media.must-be-accessible",
          "category": "media",
          "severity": "require",
          "passed": true,
          "message": "All media URLs must be publicly accessible (HTTP 200)",
          "weight": 1
        },
        {
          "ruleId": "media.no-placeholder-urls",
          "category": "media",
          "severity": "reject",
          "passed": true,
          "message": "Media URLs should not be placeholder or example URLs",
          "weight": 1
        },
        {
          "ruleId": "scoring.suspicious-edits",
          "category": "scoring",
          "severity": "penalize",
          "passed": true,
          "message": "Penalize issues with concerning edit history (fraud score > 0.3)",
          "weight": 0.25
        },
        {
          "ruleId": "spam.high-score-reject",
          "category": "spam",
          "severity": "reject",
          "passed": true,
          "message": "Reject issues with spam score above 0.85",
          "weight": 1
        },
        {
          "ruleId": "spam.generic-title",
          "category": "spam",
          "severity": "penalize",
          "passed": true,
          "message": "Title should not be a generic/template title",
          "weight": 0.4
        },
        {
          "ruleId": "spam.body-is-title-repeat",
          "category": "spam",
          "severity": "penalize",
          "passed": true,
          "message": "Body should not be a simple repetition of the title",
          "weight": 0.5
        },
        {
          "ruleId": "spam.no-ai-filler",
          "category": "spam",
          "severity": "flag",
          "passed": true,
          "message": "Body should not contain obvious AI-generated filler phrases",
          "weight": 1
        },
        {
          "ruleId": "validity.min-body-length",
          "category": "validity",
          "severity": "reject",
          "passed": true,
          "message": "Issue body must be at least 50 characters",
          "weight": 1
        },
        {
          "ruleId": "validity.min-title-length",
          "category": "validity",
          "severity": "reject",
          "passed": true,
          "message": "Issue title must be at least 10 characters",
          "weight": 1
        },
        {
          "ruleId": "validity.no-empty-body",
          "category": "validity",
          "severity": "reject",
          "passed": true,
          "message": "Issue body must not be empty or only whitespace",
          "weight": 1
        },
        {
          "ruleId": "validity.has-steps-or-description",
          "category": "validity",
          "severity": "penalize",
          "passed": true,
          "message": "Issue body should contain structured content (steps, expected/actual behavior)",
          "weight": 0.3
        },
        {
          "ruleId": "validity.not-a-feature-request",
          "category": "validity",
          "severity": "flag",
          "passed": true,
          "message": "Issue should describe a bug, not a feature request",
          "weight": 1
        }
      ],
      "failed": [
        {
          "ruleId": "scoring.duplicate-threshold",
          "category": "scoring",
          "severity": "penalize",
          "passed": false,
          "message": "Issue has moderate similarity to existing issues, suggesting partial overlap.",
          "weight": 0.3
        }
      ]
    },
    "llmInstructions": [
      "Always prioritize concrete evidence (screenshots, videos, URLs) over the quality of the written description. A poorly written report with clear visual proof of a bug is VALID. A beautifully written report with no evidence is INVALID.",
      "A valid bug report must contain enough information for an engineer to reproduce the issue. If the steps to reproduce are missing or impossibly vague (\"it just broke\"), the issue is INVALID.",
      "You MUST call the deliver_verdict function exactly once. Do not output a JSON object manually. Do not output your verdict in plain text. Use the tool.",
      "Be highly suspicious of submissions that follow a rigid template: same structure, same phrasing, with only the page name or URL swapped. These are template-farmed and should be INVALID. Look for: identical sentence structure, placeholder-like descriptions, formulaic \"Steps to Reproduce\".",
      "When similar issues exist, the OLDER issue (lower issue number) always takes precedence. The newer submission is the duplicate, never the other way around.",
      "Confidence scores must be calibrated: use 0.9+ only when evidence is unambiguous and complete. Use 0.5-0.7 when the issue is borderline. Use below 0.5 when you are genuinely uncertain. Never default to 0.5 — commit to a direction.",
      "Do not give the benefit of the doubt. Missing evidence means INVALID. Unclear reproduction steps means INVALID. Inaccessible media means INVALID. The burden of proof is on the submitter.",
      "In the reasoning field, explain your step-by-step analysis BEFORE stating your conclusion. Cover: evidence quality, clarity, spam signals, and duplicate overlap in that order.",
      "Never mention internal scoring thresholds, rule IDs, detection heuristics, or system architecture in the recap field. The recap is public-facing. Keep reasoning technical but recap user-friendly.",
      "If the issue body reads like AI-generated boilerplate (phrases like \"It is important to note\", \"Furthermore\", \"In conclusion\", excessive politeness, no specific technical details), treat it as strong evidence of spam. AI-generated issues with no real bug details are INVALID.",
      "If the pre-computed media check says media URLs exist, verify the description matches what a screenshot would show. If the description talks about a login page but the context suggests the screenshot is of something unrelated, flag this as suspicious.",
      "Never soften a verdict out of sympathy. \"I can see you tried hard but...\" is not acceptable. If the submission does not meet criteria, it is INVALID regardless of apparent effort.",
      "Write your reasoning and recap in a professional, neutral tone. Do not be sarcastic, condescending, or emotional. State facts.",
      "The recap field must be 2-3 sentences maximum. It will be posted as a public comment. No bullet points in recap — use flowing prose."
    ],
    "totalCodeRules": 17,
    "totalLLMRules": 14,
    "hasReject": false,
    "hasFailed": true,
    "penaltyScore": 0.3,
    "summary": "1/17 code rules failed | 1 PENALIZE | 14 LLM instructions active"
  }
}

_{Validated by Atlas • 2026-05-03}