docs(tally): 2026H2 improvement plan, prompt playbook & GTM/research companions#84
Merged
Conversation
lamemustafa
force-pushed
the
docs/tally-2026h2-plan
branch
from
July 23, 2026 20:26
361b45c to
bfce9be
Compare
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: bfce9be4b2
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
lamemustafa
added a commit
that referenced
this pull request
Jul 23, 2026
Four P2 internal-consistency fixes from the automated review of PR #84: - Absence-of-ceremony grep: scope to code + evidence/ADR docs, not the roadmap/playbook .md files (which legitimately name FIXTURE_CANARY). - Full-fidelity voucher profile: allocate V4; V3 (bridge.tally.vouchers/3) is already the selected-read schema pinned by a CHECK in migration 0007. - Outbox state machine: add CONFIRMED_WITH_DIVERGENCE as a distinct terminal state (was required by the readback step but missing from the transition set). - Crash test: replace bare `kill -9` with an OS-agnostic injected crashpoint (+ taskkill on Windows), since the compatibility matrix targets Windows. - Propagate V4 through the Phase 2 review/preservation references. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b6b1111c7d
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
…search companions Land the Tally research + planning deliverables into the repo as the current execution authority, superseding the write-disabled / data-minimised posture of the original research plan where they conflict. New docs (docs/tally/): - IMPROVEMENT_PLAN_2026H2.md — market research, phase roadmap (unseal → full-fidelity reads → Drift Sentinel → write substrate → product loop), rulings, wedge + proof points. - PROMPT_PLAYBOOK.md — per-phase implementation / adversarial-review / rectification / change-preservation prompts + orchestrator loop. Adds a Phase-1 task to implement the missing profile-specific `Unsupported` compatibility signature. - MARKET_RESEARCH_ADDENDUM.md — expanded landscape (Zoho/Munim/Open/EnKash/GST connectors/Tally-native remote), cited competitor pricing, public-record UX teardown of the four leading flows. - GO_TO_MARKET_AND_PRICING.md — open-core boundary, per-firm pricing (corrected to the CA-practice norm), deadline-aware support SLA, cold-start strategy, GTM. - LICENSED_LAB_QUALIFICATION_CHECKLIST.md — per-version probes that must produce compatibility receipts (write grammar, Edit Log attribution, auto-numbering, gateway security, encoding). - EXECUTION_LOG.md, BACKLOG.md — orchestrator working files. Amendments: - TALLY_INTEGRATION_RESEARCH_AND_CODEX_PLAN.md — supersession header noting which sections the 2026H2 plan replaces (writes, data minimisation, batch size). - README.md — point to the new plan set first. - compatibility-surface.json / -matrix.json — reseal after the legacy-doc header edit (hash-pinned file); gate + matrix-markdown checks pass. No code or behaviour change; docs and compatibility evidence pins only. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Four P2 internal-consistency fixes from the automated review of PR #84: - Absence-of-ceremony grep: scope to code + evidence/ADR docs, not the roadmap/playbook .md files (which legitimately name FIXTURE_CANARY). - Full-fidelity voucher profile: allocate V4; V3 (bridge.tally.vouchers/3) is already the selected-read schema pinned by a CHECK in migration 0007. - Outbox state machine: add CONFIRMED_WITH_DIVERGENCE as a distinct terminal state (was required by the readback step but missing from the transition set). - Crash test: replace bare `kill -9` with an OS-agnostic injected crashpoint (+ taskkill on Windows), since the compatibility matrix targets Windows. - Propagate V4 through the Phase 2 review/preservation references. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
lamemustafa
force-pushed
the
docs/tally-2026h2-plan
branch
from
July 24, 2026 04:22
b6b1111 to
a42f56f
Compare
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
…rocess Three findings from the re-review of PR #84 (PROMPT_PLAYBOOK.md): - P1: OutcomeUnknown recovery must run the full field-level readback diff and resolve to CONFIRMED or CONFIRMED_WITH_DIVERGENCE — a key+fingerprint match alone can report a divergent write as clean. - P1: never re-dispatch on an inconclusive probe. A crash + foreign narration/ fingerprint edit makes a real prior write match neither probe; treating that as absent duplicates the voucher. Require an unambiguous absence proof, else stay OUTCOME_UNKNOWN / MANUAL. - P2: route confirmed non-security defects through the repo's AGENTS.md process (Bug issue + dedicated Rectify PR with root-cause + regression check), security-sensitive ones via SECURITY.md — in both the rectification and orchestrator prompts. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Lands the Tally research + planning deliverables into the repo as the current execution authority. Docs and compatibility-evidence pins only — no code or behaviour change.
The direction: move Bridge from a read-only evidence console to a marketable, full-CRUD, two-way Tally integration for CA/CS firms, keeping the Truth Layer as the differentiator (substance behind workflows, not a destination screen). See IMPROVEMENT_PLAN_2026H2.md.
New docs (
docs/tally/)Unsupportedcompatibility signature (the compatibility README notes none exists today).Amendments
TALLY_INTEGRATION_RESEARCH_AND_CODEX_PLAN.md— supersession header naming the sections the 2026H2 plan replaces (writes-disabled, data-minimisation, batch size).README.md— point to the new plan set first.compatibility-surface.json/-matrix.json— resealed after the legacy-doc header edit (the doc is hash-pinned).Validation
bridge-tally-compatibility -- gate …→compatibility_gate_passed:unknown_claims=11:evidenced_claims=0✅bridge-tally-compatibility -- check-matrix-markdown …→compatibility_matrix_markdown_current✅Rollback
Revert this commit; docs-only, no schema or behaviour impact.
🤖 Generated with Claude Code