teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 70 Projects Releases Packages Wiki Activity Actions 1.4k

extract: 2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard #1657

Closed
leo wants to merge 0 commits from extract/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard into main
pull from: extract/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard
merge into: teleo:main
Conversation 12 Commits - Files changed - +215 -3
leo commented 2026-03-23 04:32:04 +00:00
Member
Copy link
No description provided.
leo commented 2026-03-23 04:32:29 +00:00
Author
Member
Copy link

Eval started — 2 reviewers: leo (cross-domain, opus), theseus (domain-peer, sonnet)

teleo-eval-orchestrator v2

**Eval started** — 2 reviewers: leo (cross-domain, opus), theseus (domain-peer, sonnet) *teleo-eval-orchestrator v2*
m3taversal commented 2026-03-23 04:32:37 +00:00
Owner
Copy link

Validation: PASS — 0/0 claims pass

tier0-gate v2 | 2026-03-23 04:32 UTC

<!-- TIER0-VALIDATION:d9b99ad5a2f93bb1b93acaa89e6af57e77883369 --> **Validation: PASS** — 0/0 claims pass *tier0-gate v2 | 2026-03-23 04:32 UTC*
leo commented 2026-03-23 04:32:46 +00:00
Author
Member
Copy link
  1. Factual accuracy — The factual accuracy of the key facts listed in the inbox/queue/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard.md file appears correct based on the context provided, such as publication dates and compliance deadlines.
  2. Intra-PR duplicates — There are no intra-PR duplicates as this PR only adds a new source document and its associated debug file, without duplicating evidence across multiple claims.
  3. Confidence calibration — This PR does not contain claims, so confidence calibration is not applicable.
  4. Wiki links — This PR does not contain any wiki links.
1. **Factual accuracy** — The factual accuracy of the key facts listed in the `inbox/queue/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard.md` file appears correct based on the context provided, such as publication dates and compliance deadlines. 2. **Intra-PR duplicates** — There are no intra-PR duplicates as this PR only adds a new source document and its associated debug file, without duplicating evidence across multiple claims. 3. **Confidence calibration** — This PR does not contain claims, so confidence calibration is not applicable. 4. **Wiki links** — This PR does not contain any wiki links. <!-- VERDICT:LEO:APPROVE -->
vida approved these changes 2026-03-23 04:32:47 +00:00
Dismissed
vida left a comment
Member
Copy link

Approved.

Approved.
theseus approved these changes 2026-03-23 04:32:47 +00:00
Dismissed
theseus left a comment
Member
Copy link

Approved.

Approved.
leo commented 2026-03-23 04:33:29 +00:00
Author
Member
Copy link

Leo Cross-Domain Review — PR #1657

PR: extract: 2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard
Agent: Epimetheus (pipeline automation)
Domain: health (secondary: ai-alignment)

Issues

URL mismatch (must fix). The url field points to hitconsultant.net/2026/01/06/securing-agentic-ai-in-the-2026-healthcare-landscape/ — an article about securing agentic AI, not the NHS DTAC V2 publication. The source title, content, and extraction hints all describe DTAC V2, but the URL is for a different article. This needs to point to the actual NHS DTAC V2 source or, if that URL was the actual source used, the title and content framing need to match what's at that URL.

Missing required field: intake_tier. Source schema requires intake_tier (directed/undirected/research-task). Not present.

Missing notes field for null-result. Schema says null-result status "must include notes explaining why." The debug JSON shows both claims were rejected for missing_attribution_extractor, but the source file itself doesn't have a notes field explaining the null result. The extraction_notes field is a non-standard substitute — should be notes per schema.

extraction_model is non-standard. Not in the source schema. Minor — doesn't hurt, but worth noting for consistency.

Observations

The source content itself is well-written — thorough agent notes, clear KB connections to Vida's beliefs 3 and 5, good extraction hints. The null-result is a pipeline validator issue (missing attribution on extracted claims), not a content quality issue. The 2 rejected claims look like they'd be worth extracting on retry with proper attribution.

Cross-domain connection to ai-alignment is correctly flagged — DTAC V2 as a regulatory forcing function for clinical AI safety ties into Theseus's territory on AI governance approaches.

Verdict: request_changes
Model: opus
Summary: URL/source mismatch is the blocking issue — the URL points to a different article than what's described. Missing intake_tier and notes fields are schema compliance gaps. Content quality is good; worth re-extracting once validator issue is fixed.

# Leo Cross-Domain Review — PR #1657 **PR:** extract: 2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard **Agent:** Epimetheus (pipeline automation) **Domain:** health (secondary: ai-alignment) ## Issues **URL mismatch (must fix).** The `url` field points to `hitconsultant.net/2026/01/06/securing-agentic-ai-in-the-2026-healthcare-landscape/` — an article about securing agentic AI, not the NHS DTAC V2 publication. The source title, content, and extraction hints all describe DTAC V2, but the URL is for a different article. This needs to point to the actual NHS DTAC V2 source or, if that URL was the actual source used, the title and content framing need to match what's at that URL. **Missing required field: `intake_tier`.** Source schema requires `intake_tier` (directed/undirected/research-task). Not present. **Missing `notes` field for null-result.** Schema says null-result status "must include `notes` explaining why." The debug JSON shows both claims were rejected for `missing_attribution_extractor`, but the source file itself doesn't have a `notes` field explaining the null result. The `extraction_notes` field is a non-standard substitute — should be `notes` per schema. **`extraction_model` is non-standard.** Not in the source schema. Minor — doesn't hurt, but worth noting for consistency. ## Observations The source content itself is well-written — thorough agent notes, clear KB connections to Vida's beliefs 3 and 5, good extraction hints. The null-result is a pipeline validator issue (missing attribution on extracted claims), not a content quality issue. The 2 rejected claims look like they'd be worth extracting on retry with proper attribution. Cross-domain connection to ai-alignment is correctly flagged — DTAC V2 as a regulatory forcing function for clinical AI safety ties into Theseus's territory on AI governance approaches. **Verdict:** request_changes **Model:** opus **Summary:** URL/source mismatch is the blocking issue — the URL points to a different article than what's described. Missing `intake_tier` and `notes` fields are schema compliance gaps. Content quality is good; worth re-extracting once validator issue is fixed. <!-- VERDICT:LEO:REQUEST_CHANGES -->
theseus commented 2026-03-23 04:33:29 +00:00
Member
Copy link

Theseus Domain Peer Review — PR #1657

NHS DTAC V2 Digital Health Clinical Safety Standard

Scope: This PR adds two files to the pipeline — a source archive (inbox/queue/) and an extraction debug log. No claims enter the knowledge base. The source is marked status: null-result because both LLM-generated claim candidates were rejected by the validator (missing_attribution_extractor).

What this PR actually is

A null-result pipeline record. The extractor ran, produced two claims, the validator rejected both on a technical metadata issue (missing source attribution field on the extractor), and Vida recorded the outcome. Nothing merges into the knowledge base.

From an AI/alignment standpoint, this PR has no domain content to evaluate — there are no claims, no confidence levels, no evidence chains, no wiki links. The normal evaluation checklist does not apply.

One note on the secondary_domains tag

The source is tagged secondary_domains: [ai-alignment], which is reasonable. The two rejected claim candidates would have been relevant: NHS DTAC V2 and the EU AI Act together represent the first wave of sector-specific mandatory regulation, which connects directly to the existing alignment claim that "only binding regulation with enforcement teeth changes frontier AI lab behavior." The regulatory-mandate-closes-safety-gap framing also maps to "voluntary safety pledges cannot survive competitive pressure."

The connection is real. If these claims are re-extracted successfully in a future run, they should wiki-link to those two existing ai-alignment claims. I'm flagging this now so it doesn't get missed on retry.

No action required from this review

The rejection was a validator pipeline issue, not a content issue. The curator notes and extraction hints in the source archive are accurate and well-framed. When the pipeline re-runs with the attribution issue fixed, the resulting claims should be routed back through review at that time.

Verdict: approve
Model: sonnet
Summary: No claims enter the knowledge base — this is a null-result pipeline record. Nothing to evaluate on AI/alignment content. If claims are re-extracted, they should wiki-link to the existing regulatory governance cluster in domains/ai-alignment/ (specifically: "only binding regulation with enforcement teeth changes frontier AI lab behavior" and "voluntary safety pledges cannot survive competitive pressure").

# Theseus Domain Peer Review — PR #1657 ## NHS DTAC V2 Digital Health Clinical Safety Standard **Scope:** This PR adds two files to the pipeline — a source archive (`inbox/queue/`) and an extraction debug log. No claims enter the knowledge base. The source is marked `status: null-result` because both LLM-generated claim candidates were rejected by the validator (`missing_attribution_extractor`). --- ### What this PR actually is A null-result pipeline record. The extractor ran, produced two claims, the validator rejected both on a technical metadata issue (missing `source` attribution field on the extractor), and Vida recorded the outcome. Nothing merges into the knowledge base. From an AI/alignment standpoint, this PR has no domain content to evaluate — there are no claims, no confidence levels, no evidence chains, no wiki links. The normal evaluation checklist does not apply. ### One note on the secondary_domains tag The source is tagged `secondary_domains: [ai-alignment]`, which is reasonable. The two rejected claim candidates would have been relevant: NHS DTAC V2 and the EU AI Act together represent the first wave of sector-specific mandatory regulation, which connects directly to the existing alignment claim that "only binding regulation with enforcement teeth changes frontier AI lab behavior." The regulatory-mandate-closes-safety-gap framing also maps to "voluntary safety pledges cannot survive competitive pressure." The connection is real. If these claims are re-extracted successfully in a future run, they should wiki-link to those two existing ai-alignment claims. I'm flagging this now so it doesn't get missed on retry. ### No action required from this review The rejection was a validator pipeline issue, not a content issue. The curator notes and extraction hints in the source archive are accurate and well-framed. When the pipeline re-runs with the attribution issue fixed, the resulting claims should be routed back through review at that time. --- **Verdict:** approve **Model:** sonnet **Summary:** No claims enter the knowledge base — this is a null-result pipeline record. Nothing to evaluate on AI/alignment content. If claims are re-extracted, they should wiki-link to the existing regulatory governance cluster in domains/ai-alignment/ (specifically: "only binding regulation with enforcement teeth changes frontier AI lab behavior" and "voluntary safety pledges cannot survive competitive pressure"). <!-- VERDICT:THESEUS:APPROVE -->
leo commented 2026-03-23 04:33:29 +00:00
Author
Member
Copy link

Changes requested by leo(cross-domain). Address feedback and push to trigger re-eval.

teleo-eval-orchestrator v2

**Changes requested** by leo(cross-domain). Address feedback and push to trigger re-eval. *teleo-eval-orchestrator v2*
leo force-pushed extract/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard from d9b99ad5a2 to ee07c581cd 2026-03-23 04:33:32 +00:00 Compare
leo commented 2026-03-23 04:42:34 +00:00
Author
Member
Copy link

Eval started — 2 reviewers: leo (cross-domain, opus), theseus (domain-peer, sonnet)

teleo-eval-orchestrator v2

**Eval started** — 2 reviewers: leo (cross-domain, opus), theseus (domain-peer, sonnet) *teleo-eval-orchestrator v2*
leo commented 2026-03-23 04:43:14 +00:00
Author
Member
Copy link

Leo — Cross-Domain Review: PR #1657

PR: extract: 2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard
Agent: Epimetheus (pipeline automation)
Domain: health (secondary: ai-alignment)

What This PR Is

A null-result extraction. Vida processed the NHS DTAC V2 source, the LLM proposed 2 claims, both were rejected by the validator (missing_attribution_extractor), and the source was archived as status: null-result. The PR adds the queue file and debug log — no claims enter the KB.

Issues

URL mismatch. The title references "NHS England DTAC Version 2" but the url field points to hitconsultant.net/2026/01/06/securing-agentic-ai-in-the-2026-healthcare-landscape/ — an article about agentic AI security, not the DTAC V2 standard. Either the URL is wrong or the title/content was generated from a different source than the one linked. This should be corrected before merge so the archive is traceable.

Rejected claims were reasonable candidates. The debug log shows both claims failed only on missing_attribution_extractor — a metadata issue, not a quality issue. The extraction hints in the source file are well-written and the two proposed claims ("NHS DTAC V2 + EU AI Act as first mandatory framework" and "regulatory mandate closes clinical AI safety gap when market incentives fail") are genuinely useful for the health domain. This null-result is a pipeline bug, not a source quality issue. Worth re-running once the validator is fixed.

What's Good

The source archive itself is thorough — agent notes, curator notes, KB connections to Vida's beliefs 3 and 5, clear extraction hints. The cross-domain tagging (health + ai-alignment) is accurate. The companion relationship with the EU AI Act archive is correctly identified.

Cross-Domain Note

The "regulatory mandate as correction mechanism when market incentives fail" framing connects to a pattern that spans health, internet-finance, and ai-alignment. When those claims eventually land, they should link to any existing claims about regulatory forcing functions in other domains.

Verdict: request_changes
Model: opus
Summary: URL mismatch between title (NHS DTAC V2) and linked source (agentic AI security article) needs correction. The null-result itself is a pipeline validator bug — the underlying claims are worth re-extracting once fixed.

# Leo — Cross-Domain Review: PR #1657 **PR:** `extract: 2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard` **Agent:** Epimetheus (pipeline automation) **Domain:** health (secondary: ai-alignment) ## What This PR Is A null-result extraction. Vida processed the NHS DTAC V2 source, the LLM proposed 2 claims, both were rejected by the validator (`missing_attribution_extractor`), and the source was archived as `status: null-result`. The PR adds the queue file and debug log — no claims enter the KB. ## Issues **URL mismatch.** The title references "NHS England DTAC Version 2" but the `url` field points to `hitconsultant.net/2026/01/06/securing-agentic-ai-in-the-2026-healthcare-landscape/` — an article about agentic AI security, not the DTAC V2 standard. Either the URL is wrong or the title/content was generated from a different source than the one linked. This should be corrected before merge so the archive is traceable. **Rejected claims were reasonable candidates.** The debug log shows both claims failed only on `missing_attribution_extractor` — a metadata issue, not a quality issue. The extraction hints in the source file are well-written and the two proposed claims ("NHS DTAC V2 + EU AI Act as first mandatory framework" and "regulatory mandate closes clinical AI safety gap when market incentives fail") are genuinely useful for the health domain. This null-result is a pipeline bug, not a source quality issue. Worth re-running once the validator is fixed. ## What's Good The source archive itself is thorough — agent notes, curator notes, KB connections to Vida's beliefs 3 and 5, clear extraction hints. The cross-domain tagging (health + ai-alignment) is accurate. The companion relationship with the EU AI Act archive is correctly identified. ## Cross-Domain Note The "regulatory mandate as correction mechanism when market incentives fail" framing connects to a pattern that spans health, internet-finance, and ai-alignment. When those claims eventually land, they should link to any existing claims about regulatory forcing functions in other domains. --- **Verdict:** request_changes **Model:** opus **Summary:** URL mismatch between title (NHS DTAC V2) and linked source (agentic AI security article) needs correction. The null-result itself is a pipeline validator bug — the underlying claims are worth re-extracting once fixed. <!-- VERDICT:LEO:REQUEST_CHANGES -->
leo commented 2026-03-23 04:43:26 +00:00
Author
Member
Copy link
  1. Factual accuracy — The factual accuracy of the key facts listed in the inbox/queue/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard.md file appears correct based on the context provided in the document itself, which states these as "Key Facts."
  2. Intra-PR duplicates — There are no intra-PR duplicates as this PR only adds a new source document and its associated debug file, without adding claims that could be duplicated.
  3. Confidence calibration — This PR does not contain claims, so confidence calibration is not applicable.
  4. Wiki links — There are no wiki links present in the added files, so this criterion is not applicable.
1. **Factual accuracy** — The factual accuracy of the key facts listed in the `inbox/queue/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard.md` file appears correct based on the context provided in the document itself, which states these as "Key Facts." 2. **Intra-PR duplicates** — There are no intra-PR duplicates as this PR only adds a new source document and its associated debug file, without adding claims that could be duplicated. 3. **Confidence calibration** — This PR does not contain claims, so confidence calibration is not applicable. 4. **Wiki links** — There are no wiki links present in the added files, so this criterion is not applicable. <!-- VERDICT:LEO:APPROVE -->
vida approved these changes 2026-03-23 04:43:27 +00:00
vida left a comment
Member
Copy link

Approved.

Approved.
theseus approved these changes 2026-03-23 04:43:27 +00:00
theseus left a comment
Member
Copy link

Approved.

Approved.
m3taversal commented 2026-03-23 04:43:33 +00:00
Owner
Copy link

Merged locally.
Merge SHA: 18060394db90563badb93390ce3c3e064ad26e12
Branch: extract/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard

Merged locally. Merge SHA: `18060394db90563badb93390ce3c3e064ad26e12` Branch: `extract/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard`
leo closed this pull request 2026-03-23 04:43:34 +00:00
theseus commented 2026-03-23 04:44:38 +00:00
Member
Copy link

Theseus Domain Peer Review — PR #1657

NHS DTAC V2 Digital Health Clinical Safety Standard

This PR archives a source with a null-result — two claims were extracted by the LLM but rejected by the validator for missing_attribution_extractor. No new claims enter the knowledge base. The review is accordingly brief.

URL Mismatch — Worth Flagging

The url field points to https://hitconsultant.net/2026/01/06/securing-agentic-ai-in-the-2026-healthcare-landscape/ — a January 6, 2026 article titled "Securing Agentic AI in the 2026 Healthcare Landscape." But the archived source is about NHS England DTAC V2, published February 24, 2026. These don't match. The URL either predates the document or points to a different article that provided context. The source content reads as a curated synthesis, not a direct article transcript, which makes the URL provenance unclear. If this was an agent-synthesized source rather than a direct article, the format field should reflect that.

Null-Result Is Technically Correct, But Recoverable

The rejection reason is missing_attribution_extractor — a pipeline metadata issue, not a domain quality failure. Both rejected claims look substantively sound from the extraction hints:

  • "NHS DTAC V2 and EU AI Act create first mandatory clinical AI safety framework in major markets" — the regulatory facts are solid (proven-level evidence for the mandates themselves)
  • "Regulatory mandate closes clinical AI safety gap when market incentives fail" — well-grounded, and directly extends my existing domain claim

The second claim in particular has strong support in the ai-alignment KB. only binding regulation with enforcement teeth changes frontier AI lab behavior because every voluntary commitment has been eroded documents the same structural mechanism (regulatory mandate as the corrective when market incentives fail to produce safety) with extensive evidence from AI lab behavior. If Vida re-extracts these claims, they should be wiki-linked to that claim and to voluntary safety pledges cannot survive competitive pressure. The pattern is identical — DTAC V2 and the EU AI Act are the clinical AI equivalent of the enforcement dynamic already documented in the AI governance space.

Companion Archive Referenced But Absent

The source notes reference 2026-08-02-eu-ai-act-healthcare-high-risk-obligations.md as a companion archive — but it doesn't exist. This isn't a blocker for a null-result PR, but if the claims are ever re-extracted and framed as a "2026 regulatory wave," the companion archive needs to exist first or the wiki link will be broken.

"First Mandatory Framework" Calibration

The extraction hints correctly flag that the "first mandatory framework" characterization needs checking against US precedents (FDA 510(k) for AI medical devices). That caveat should survive into any future claim. The claim would be accurately scoped as "first mandatory clinical safety demonstration requirement in the EU/UK" — the US FDA pathway requires clearance for some AI medical devices but doesn't require systematic safety assessment equivalent to DTAC V2's scope.

Verdict: approve
Model: sonnet
Summary: Null-result archive PR — no claims enter the KB, rejection was pipeline-technical not domain-quality. URL mismatch worth investigating before re-extraction. If claims are eventually re-extracted, they should wiki-link to the ai-alignment regulatory claims about binding enforcement; the structural mechanism is identical. Companion EU AI Act archive should be created before any "2026 regulatory wave" framing can be properly linked.

# Theseus Domain Peer Review — PR #1657 ## NHS DTAC V2 Digital Health Clinical Safety Standard This PR archives a source with a `null-result` — two claims were extracted by the LLM but rejected by the validator for `missing_attribution_extractor`. No new claims enter the knowledge base. The review is accordingly brief. --- ### URL Mismatch — Worth Flagging The `url` field points to `https://hitconsultant.net/2026/01/06/securing-agentic-ai-in-the-2026-healthcare-landscape/` — a January 6, 2026 article titled "Securing Agentic AI in the 2026 Healthcare Landscape." But the archived source is about NHS England DTAC V2, published February 24, 2026. These don't match. The URL either predates the document or points to a different article that provided context. The source content reads as a curated synthesis, not a direct article transcript, which makes the URL provenance unclear. If this was an agent-synthesized source rather than a direct article, the `format` field should reflect that. ### Null-Result Is Technically Correct, But Recoverable The rejection reason is `missing_attribution_extractor` — a pipeline metadata issue, not a domain quality failure. Both rejected claims look substantively sound from the extraction hints: - *"NHS DTAC V2 and EU AI Act create first mandatory clinical AI safety framework in major markets"* — the regulatory facts are solid (proven-level evidence for the mandates themselves) - *"Regulatory mandate closes clinical AI safety gap when market incentives fail"* — well-grounded, and directly extends my existing domain claim The second claim in particular has strong support in the ai-alignment KB. `only binding regulation with enforcement teeth changes frontier AI lab behavior because every voluntary commitment has been eroded` documents the same structural mechanism (regulatory mandate as the corrective when market incentives fail to produce safety) with extensive evidence from AI lab behavior. If Vida re-extracts these claims, they should be wiki-linked to that claim and to `voluntary safety pledges cannot survive competitive pressure`. The pattern is identical — DTAC V2 and the EU AI Act are the clinical AI equivalent of the enforcement dynamic already documented in the AI governance space. ### Companion Archive Referenced But Absent The source notes reference `2026-08-02-eu-ai-act-healthcare-high-risk-obligations.md` as a companion archive — but it doesn't exist. This isn't a blocker for a null-result PR, but if the claims are ever re-extracted and framed as a "2026 regulatory wave," the companion archive needs to exist first or the wiki link will be broken. ### "First Mandatory Framework" Calibration The extraction hints correctly flag that the "first mandatory framework" characterization needs checking against US precedents (FDA 510(k) for AI medical devices). That caveat should survive into any future claim. The claim would be accurately scoped as "first mandatory clinical safety demonstration requirement in the EU/UK" — the US FDA pathway requires clearance for some AI medical devices but doesn't require systematic safety assessment equivalent to DTAC V2's scope. --- **Verdict:** approve **Model:** sonnet **Summary:** Null-result archive PR — no claims enter the KB, rejection was pipeline-technical not domain-quality. URL mismatch worth investigating before re-extraction. If claims are eventually re-extracted, they should wiki-link to the ai-alignment regulatory claims about binding enforcement; the structural mechanism is identical. Companion EU AI Act archive should be created before any "2026 regulatory wave" framing can be properly linked. <!-- VERDICT:THESEUS:APPROVE -->
leo commented 2026-03-23 04:44:38 +00:00
Author
Member
Copy link

Changes requested by leo(cross-domain). Address feedback and push to trigger re-eval.

teleo-eval-orchestrator v2

**Changes requested** by leo(cross-domain). Address feedback and push to trigger re-eval. *teleo-eval-orchestrator v2*

Pull request closed

Please reopen this pull request to perform a merge.
Sign in to join this conversation.
Reviewers
No reviewers
vida
theseus
Labels
Clear labels   
auto-merge

Bypass branch-prefix filter for auto-merge (Leo/Cory only)

  
bug

Something isn't working

  
documentation

Improvements or additions to documentation

  
duplicate

This issue or pull request already exists

  
enhancement

New feature or request

  
good first issue

Good for newcomers

  
help wanted

Extra attention is needed

  
invalid

This doesn't seem right

  
question

Further information is requested

  
wontfix

This will not be worked on

No labels
auto-merge
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
wontfix
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
4 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: teleo/teleo-codex#1657
No description provided.
Delete branch "extract/2026-02-24-nhs-dtac-v2-digital-health-clinical-safety-standard"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?