feat(copilot): authentic @github/copilot CLI identity + Claude context + vision - #50064
Closed
arminanton wants to merge 157 commits into
Closed
feat(copilot): authentic @github/copilot CLI identity + Claude context + vision#50064arminanton wants to merge 157 commits into
arminanton wants to merge 157 commits into
Conversation
…t + vision Presents the copilot-developer-cli Copilot-Integration-Id + authentic CLI User-Agent + Runtime-Client-Version (dropping VS Code Editor-* headers) so the Copilot backend serves the full premium catalog; injects those headers for Claude-on-Copilot via the anthropic adapter; adds the Copilot-Vision-Request header for image input; refuses to cache misrouted sub-1M context for Claude; catalog-aware effort clamp. Surgical on anthropic_adapter (identity+vision only, not the limits/effort tables which origin/main owns). copilot_auth raw-token-as-Bearer with opt-in legacy exchange. 0 private leakage. Inventory snapshot + 5 dependent tests deferred (need the models.py copilot layer / P1 routing).
alt-glitch
added
type/feature
…dialog NousResearch#43496 added a per-provider hide-all sentinel ('provider::') so emptying a provider in the Edit Models dialog stopped re-expanding its defaults. That fixed the single-provider case, but the dialog's toggle handler seeds its working set from effectiveVisibleKeys(), which strips ALL sentinels before returning. So persisting after any toggle silently dropped every OTHER provider's hide-all sentinel; those providers then looked 'never customized' and re-enabled all their models on the next render. Split resolution into two functions: - resolveVisibleKeys(): stored keys + curated default expansion, with hide-all sentinels PRESERVED — the canonical working set the toggle handler mutates and persists. - effectiveVisibleKeys(): resolveVisibleKeys() then strips sentinels, for display only (unchanged contract). Move the toggle set-computation into a pure, unit-tested toggleModelVisibility() that seeds from resolveVisibleKeys(), so sibling sentinels survive the persist. Add regression tests that drive the real toggle handler across multiple providers. Follow-up to NousResearch#43496; completes the fix for NousResearch#43485 (cross-provider case).
Follow-up to the salvaged NousResearch#47450 fix: - Extract expandProviderDefaults() so the curated-default expansion rule lives in one place (was duplicated between defaultVisibleKeys and resolveVisibleKeys). - Drop the redundant new Set() wrap in toggleModelVisibility (resolveVisibleKeys already returns a fresh Set; effectiveVisibleKeys already relied on this). - Document the intentional re-enable behavior (re-enabling one model of a hidden-all provider restores only that model, not the curated defaults) and tighten the toggleModelVisibility JSDoc. - Add 7 hardening tests: re-enable-restores-only-that-model, full hide/re-enable round-trip, empty-non-null stored, single toggle-off from null defaults, zero-model provider, and direct resolveVisibleKeys null/empty assertions.
…l-visibility-cross-provider-47450 fix(desktop): preserve other providers' hide-all in model visibility dialog (salvage NousResearch#47450)
A server that doesn't implement the optional 'ping' utility answers a keepalive ping with JSON-RPC method-not-found. _is_method_not_found_error latches that condition so the probe falls back to list_tools instead of reconnect-looping. The substring fallback only matched 'method not found' / '-32601' / 'not found: ping'. Servers that surface method-not-found as the common 'Unknown method: <name>' phrasing without a structural -32601 code (e.g. agentmemory's MCP server) slipped through, so the fallback never latched and the keepalive reconnect-looped every cycle. Add 'unknown method' to the substring fallback so the ping->list_tools keepalive fallback latches for these servers too. Fixes NousResearch#50028.
…ch#50028) Two regression tests for the agentmemory reconnect-loop: - _is_method_not_found_error matches the plain 'Unknown method: ping' phrasing (no structural -32601 code). - _keepalive_probe latches _ping_unsupported and falls back to list_tools when send_ping raises 'Unknown method: ping', instead of propagating (which would reconnect-loop).
Adds hermes_cli/context_switch_guard.py mirroring the model_cost_guard pattern. When a user switches models mid-session (Herm TUI picker, CLI, or /model on Telegram/Discord), the warning surfaces on the existing ModelSwitchResult.warning_message path used by the expensive-model guard if the new model's compression threshold is below the current session size. Partial fix for NousResearch#23767 — addresses only the 'user-facing guardrail when switching from a high-context provider to a substantially lower-context provider' slice. The other proposed fixes from that issue (hard preflight token guard, metadata cache invalidation on switch, compression safety invariant, oversized tool-output handling) are out of scope for this PR.
… TUI warning field Follow-up to the salvaged preflight-compression warning: - Replace silent `except Exception: pass` at all 5 guard call sites (cli.py x2, gateway/slash_commands.py x2, tui_gateway/server.py) with `logger.debug(...)` so signature drift in the guard helper isn't hidden. - tui_gateway/server.py: set the confirm dict's `warning` field to the merged message (was bare expensive-model text) so it matches `confirm_message` for any future consumer reading `warning`. - Add trailing newlines to the two new files.
…-switch-preflight-warning fix(cli): warn when in-session model switch will preflight-compress
The gateway only rewrote gateway_state.json on lifecycle transitions
(start/connect/drain/stop), never on turn start/end. Live-verified on a
hosted agent: a confirmed end-to-end turn ran while gateway_updated_at
stayed frozen at boot and active_agents was absent — so any active_agents
read from the file between transitions is stale. That makes it unusable
as a busy/idle signal for an external consumer (NAS deciding whether it's
safe to restart/migrate/auto-update an agent mid-turn).
Add _persist_active_agents(), called at every turn boundary:
- turn start: both running-agent sentinel-claim sites (normal inbound
message path + startup-resume path)
- turn end: the central _release_running_agent_state() choke point
(covers normal completion, /stop, /reset, sentinel cleanup,
stale-eviction — every path that ends a running turn)
It passes ONLY active_agents to write_runtime_status, leaving
gateway_state (and every other field) _UNSET so the read-merge-write
preserves the current lifecycle state. Passing gateway_state=None would
clobber it — hence a dedicated helper rather than reusing
_update_runtime_status. The write is the same cheap JSON write done on
lifecycle transitions today; best-effort (a failed status write never
disrupts a turn).
Behaviour-contract test: an active_agents-only write preserves both
running and draining gateway_state, and the count clamps non-negative.
Give an external consumer (NAS) a trustworthy, always-reachable busy/idle
readout it can poll before a disruptive lifecycle action (restart,
migrate, stop, auto-update). The dashboard /api/status is the only HTTP
surface guaranteed up on a hosted agent regardless of which gateway
platforms are enabled, and it already reads gateway_state.json.
Add to /api/status (additive, non-breaking):
- active_agents — in-flight gateway-turn count (now refreshed
per-turn by the companion gateway-side commit)
- gateway_busy — running AND active_agents > 0
- gateway_drainable — running and live (a valid begin-drain target)
- restart_drain_timeout — resolved seconds, so the consumer can size its
poll deadline without out-of-band knowledge
(env HERMES_RESTART_DRAIN_TIMEOUT → config
agent.restart_drain_timeout → default)
The busy/drainable contract is defined once in gateway.status
(derive_gateway_busy / derive_gateway_drainable) and consumed by both
/api/status and /health/detailed so the two surfaces can never disagree.
Liveness keys off gateway_running (a live PID/health probe), NEVER
gateway_updated_at — a healthy idle gateway never advances that timestamp.
All derived fields degrade to safe falsy values when the gateway is down
or the status file is absent/corrupt (never a spurious "busy" that would
wedge the consumer). active_sessions (the 5-min DB recency heuristic the
SPA reads) is left exactly as-is — new signal, new fields.
Tests (behaviour contracts, not snapshots): the pure derivation contract
across every running/state/count/liveness combination; /api/status
integration for busy, idle-drainable, draining, down, stale-busy-file,
corrupt-count, and timeout surfacing; and /health/detailed parity.
…nts parse Follow-up cleanups on top of the busy/idle readout (PR NousResearch#50103): - web_server.py /api/status reused the single drain-timeout resolver hermes_cli.gateway._get_restart_drain_timeout() (HERMES_RESTART_DRAIN_TIMEOUT env -> agent.restart_drain_timeout config -> default) instead of inlining a third hand-rolled copy of that precedence chain. Also fixes a subtle divergence: the inline copy used os.environ.get() so a set-but-empty env var was treated as a value rather than falling through to config; the shared resolver .strip()s and falls through correctly. - Added gateway.status.parse_active_agents() and routed BOTH HTTP surfaces (/api/status and /health/detailed) through it, so the exposed active_agents field is consistently clamped non-negative. Previously /api/status clamped while /health/detailed exposed the raw file value, diverging on a corrupt count. - Added TestParseActiveAgents covering the shared coercion contract.
…ive_agents; harden drain-timeout fallback Second cleanup pass (simplify-code review of the first follow-up): - write_runtime_status now clamps active_agents via parse_active_agents instead of an inline max(0, int(...)). Removes the duplicated clamp the helper's docstring acknowledged AND closes a write-side ValueError gap (a non-numeric active_agents previously raised; now degrades to 0). - hermes_cli/gateway.py draining-status line routes its active-agents count through parse_active_agents too — the third coercion site of the same persisted field, now consistent and non-raising with the two HTTP surfaces. - web_server.py /api/status: the drain-timeout resolver fallback now catches ImportError specifically and falls back to DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT (a real float) instead of a blanket 'except Exception -> None'. None would have violated the surfaced field's int/float contract and stripped NAS's poll-deadline hint silently. - Dropped a redundant 'if runtime else 0' branch (parse_active_agents already handles the empty/None case) and tightened the parse_active_agents docstring to describe the actual single-contract role (write + both reads).
…way-busy-readout-50103 feat(gateway+dashboard): busy/idle readout for safe lifecycle actions (salvage NousResearch#50103)
…sResearch#23767) The tool-result persistence budget was a fixed 100K chars/result and 200K chars/turn regardless of the active model. On a small-context model (e.g. a 65K-token local model switched into mid-session) a single large tool result (reporter: a 279K-char search result) or a full 200K-char turn (~50K tokens) could by itself approach or exceed the window, forcing an oversized request that the provider rejects as "Prompt too long". - budget_config.budget_for_context_window() scales per-result/per-turn char caps to a fraction of the model window, clamped to the historical 100K/200K defaults (large models unchanged) and floored so small models stay usable. - resolve_threshold() now caps the per-tool registry value at default_result_size so tools that register a fixed 100K cap (web/terminal/x_search) don't re-inflate a scaled-down budget. No-op for the default budget (both 100K). - tool_executor wires the agent's live context_length (recomputed on model switch) into all four persist/turn-budget call sites. read_file stays inf-pinned (no persist loop). Verified E2E: a 279K-char result against a 65K model collapses to a ~1.6K preview; a 200K model is byte-identical to today.
…ch#23767) ContextCompressor.update_model() recomputed context_length/threshold/budgets but kept the cross-call calibration state (last_real_prompt_tokens, last_rough_tokens_when_real_prompt_fit, last_compression_rough_tokens, awaiting_real_usage_after_compression, _ineffective_compression_count) from the PREVIOUS model. Those fields encode 'the provider proved this prompt fit' / 'preflight can be deferred' decisions valid only for the model that produced them. Carried across a switch to a smaller-context model, should_defer_preflight_to_real_usage() used the old model's 'it fit' history to SKIP a preflight compression the new model actually needed — sending an oversized prompt the provider rejects (NousResearch#23767). update_model() now clears that state; the new model's first response repopulates it via update_from_response(). Verified E2E: after a 200K->65,536 switch, defer no longer suppresses and should_compress fires on an over-threshold estimate.
bundle.read_text(errors="ignore") was missing the explicit encoding argument flagged by the repo's blocking ruff rule PLW1514. Add encoding="utf-8".
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 21, 2026
Council demand: reproducible per-PR apply/lint/test table onto v0.17.0. - verify_all_prs_on_v017.sh: applies each PR onto v0.17.0, runs repo-style ruff (PLW1514) + the PR's own test files; emits the pass/fail table. - per_pr_verification.md + _table.txt: results with honest per-PR annotations. REAL ISSUES FOUND + FIXED this session via the per-PR run: - NousResearch#50033: 2 PLW1514 (missing encoding on version-cache I/O) -> fixed+pushed - NousResearch#50064: 1 PLW1514 (missing encoding on bundle read) -> fixed+pushed - NousResearch#50039: dropped the private opus-context test (59 private refs, tests deferred machinery, failed on clean base) -> tracked in NousResearch#50111 deferred set instead APPLY: 38 clean + 2 --3way (forward-compat) + 0 conflict. Residual lint/test FAILs are measurement artifacts (3way-merge on NousResearch#50056, my own analysis scripts on NousResearch#50111) or environment-dependent (live API test NousResearch#50031, cross-PR base-drift batch-collection on NousResearch#50064/66/78/86) — documented per-PR.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 21, 2026
…ass) - cleanclone_per_pr_output.txt: verify_all_prs_on_v017.sh re-run from a FRESH clone at v0.17.0 — output identical to the working-tree run (deterministic). - forward-compat/50056+50073 independently confirmed v0.17-based, 0 conflict markers. - integration/v0.17.0-all-37-prs subsystem suite re-run: 521 passed. - independent_reproduction.md documents all three. Determinism across two independent environments confirms the residual test FAILs are structural (live-API NousResearch#50031, cross-PR base-drift NousResearch#50064/66/78/86), not flaky.
When truncate_message appends a (N/M) chunk indicator to a chunk that had to close an in-progress fenced code block, the marker lands on the closing fence line (``` \(1/2\) after MarkdownV2 escaping). Telegram does not treat that as a clean closing fence and rejects the MarkdownV2, falling back to plain text. Move the indicator onto its own line right after the closing fence at all three legacy-send call sites. Fixes NousResearch#48517
…esponse (NousResearch#50009) When a turn hit max_iterations, finalize_turn ran three unguarded cleanup steps after the model's summary — _save_trajectory (file I/O), _cleanup_task_resources (remote VM/browser teardown), and _persist_session (SQLite write). Any raise there propagated out of run_conversation, discarding the partial final_response the caller was waiting for; subprocess wrappers saw an empty stdout with no traceback (NousResearch#8049). Each step is now guarded independently so one failure can't skip the others. Failures log at ERROR with a traceback and are surfaced on the result dict via cleanup_errors; the partial response is always returned. Closes NousResearch#8049.
This was referenced Jun 22, 2026
Closed
NousResearch#50499) * feat(cli): /reasoning full to show complete thinking, not 10-line clamp The post-response Reasoning recap box hard-clamped long thinking to the first 10 lines, so there was no way to see the full reasoning trace after a turn (live streaming already shows it in full). Add display.reasoning_full (default off) plus /reasoning full|clamp to toggle it at runtime; the clamp truncation note now points at the command. Addresses repeated user requests to show all thinking tokens. * test(gateway): de-snapshot /reasoning help assertion The test froze the exact args-hint literal '/reasoning [level|show|hide]', which the new full/clamp args change to '[level|show|hide|full|clamp]'. Convert to an invariant: assert /reasoning is in help and carries its core args, not the exact hint string. * feat(tui): /reasoning full|clamp parity in tui_gateway The classic-CLI reasoning_full toggle had no TUI equivalent — typing /reasoning full in the TUI fell through to parse_reasoning_effort and errored. The TUI renders thinking as an expand/collapse section (no fixed 10-line recap), so map full -> sections.thinking=expanded (raw, uncapped via thinkingPreview mode='full') and clamp -> collapsed, persisting display.reasoning_full for cross-surface config consistency.
…h#50509) * feat(cli): /prompt — compose your next prompt in $EDITOR Adds /prompt (alias /compose): opens $VISUAL/$EDITOR on a temp markdown file so you can hand-edit a multi-line prompt, then sends the saved buffer as the next agent turn. Text after the command pre-seeds the buffer; an empty save cancels. Reuses the one-shot _pending_agent_seed the interactive loop already consumes (same mechanism as /blueprint), so no changes to the input event loop or message pipeline. CLI-only. * feat(tui): /prompt slash command opens $EDITOR (parity with CLI) The TUI already opens $EDITOR via Ctrl+G (openEditor), but had no /prompt slash command like the classic CLI. Wire openEditor into the slash handler context and register /prompt (alias /compose) to call it; inline text after the command is dropped into the composer first so it carries into the editor, matching the CLI's /prompt <text>.
…ind (NousResearch#50551) When `hermes dashboard --host 0.0.0.0` is run interactively with the auth gate engaged but no DashboardAuthProvider configured, prompt to set up the bundled username/password provider on the spot (or point at `hermes dashboard register` for OAuth) instead of only emitting the fail-closed error. - main.py: `_maybe_setup_dashboard_auth_interactively()` runs before start_server. No-ops on loopback binds, when a provider is already registered, or when stdin/stdout isn't a TTY (Docker/s6, CI, piped runs) so the fail-closed SystemExit stays the backstop for unattended deploys. On the password path it writes dashboard.basic_auth.{username,password_hash,secret} to config.yaml (scrypt hash, never plaintext), then force-rediscovers plugins so the basic provider registers before the gate check. - web_server.py: fix the fail-closed hint — it told operators to set `dashboard_auth.basic.username` but the provider reads `dashboard.basic_auth`. - docs: note the interactive setup under Fail-closed semantics. No new env vars; reuses the existing dashboard.basic_auth config surface.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…ndle) This PR previously bundled 100 files as a "cross-PR integration regression suite", but 94 of those duplicated other open PRs — which made it the primary blocker when combining the PR set onto a later release (it conflicted on every overlapping file). **Slimmed to the 4 files genuinely unique to this PR:** ``` hermes_cli/auth.py # copilot-opus-context auth path hermes_cli/runtime_provider.py # runtime provider resolution tests/agent/conftest.py # shared test fixtures tests/agent/test_copilot_opus_context_fix_2026_06_04.py # the regression test ``` The 94 duplicate files are owned by their topical feature PRs already (autopilot NousResearch#49917, reasoning NousResearch#48024, copilot identity NousResearch#50064, etc.). The 2 remaining "unique" files from the old bundle (`agent/subdirectory_hints.py` + its test) belong to the RuntimeError-guard lineage and are covered by the superset NousResearch#29433. Built on v0.17.0 (`2bd1977d8`); all 4 files compile; 0 private-provenance leaks. Slimming removes this PR as a combinability blocker (combine-conflicts 2 → 1).
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
… 0 markers, 0 real compile-fail Engineering this round: slimmed NousResearch#50457 (100->4 files, removed the combinability blocker, 9d3b3b9); proved NousResearch#50296 is overlap-only (clean alone on v0.17.0). Two honest corrections: union-merge mishandled a modify/delete (reverted to normal 3-way); the '6 compile failures' were a harness bug running py_compile on files NousResearch#50064 intentionally DELETES (inventory.py). Corrected: 324 .py, 0 real fails.
# Conflicts: # tests/run_agent/test_provider_attribution_headers.py
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…LE) + reproducible delta map - GITHUB-MERGEABLE-AUDIT.md: GitHub mergeable=40/41 (only NousResearch#50111 manifest conflicts). 6 PRs (NousResearch#50296/NousResearch#49644/NousResearch#50041/NousResearch#50073/NousResearch#50064/NousResearch#50033) genuinely conflicted on current origin/main (drifted past v0.17.0); each rebased (1-file complementary conflict), now MERGEABLE. - DELTA-MAP-v017.md: reproducible per-file map (PR diffs vs v0.17.0, fresh tips): 160 = 137 in-PR + 21 DISCARD + 2 upstream-NousResearch#29433 + 0 orphans, sum verified.
The conflict resolution that added test_routed_client_preserves_openai_sdk_default_headers inadvertently dropped the @patch("run_agent.OpenAI") decorator from the following test, causing pytest to treat mock_openai as an undefined fixture (collection error). Restore the decorator. No production change.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…rch#50626), refresh PINNED-SHAS - BUILD-TEST-VERIFICATION.txt: NousResearch#50064 (18 passed, fixed a real dropped-@patch collection-error), NousResearch#49644 (10 passed), NousResearch#48069 (10 passed) — all on correct base. - REPRODUCE.sh: fix coverage union to use git-diff (not gh --files which caps at 100 and produced false 'unmapped'). Re-verified 0 real orphans across 42 PRs. - PINNED-SHAS.txt: regenerated from live GitHub (42 PRs, 8 ready / 34 draft), reconciling 11 drifted heads. - 3 previously-orphaned files (subdirectory_hints + xai label) re-homed into new draft PR NousResearch#50626.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…afety proof Addresses the Council demand for SEMANTIC correctness (tests pass after resolution), not just compile-clean. Per-PR own-test results on resolved v0.17.0 (V017-PER-PR-TEST-RESULTS.txt): NousResearch#49644 10 passed | NousResearch#50033 165 gemini passed | NousResearch#50056 218 passed NousResearch#50073 9 passed (INTENT-INFERRED resolution PROVEN correct: hygiene=400 kept) NousResearch#50296 13 passed | NousResearch#50064 61 passed, 1 FAILED The single NousResearch#50064 failure is characterized precisely (not hacked): test test_routed_client_preserves_openai_sdk_default_headers asserts pre-v0.17.0 copilot routing internals that v0.17.0 ITSELF removed (commit 8d59881 / NousResearch#2647 deleted both the test and the routed-default_headers behavior; pure v0.17.0 has 0 occurrences). Documented as a forward-compat test-removal on rebase, not a regression. NousResearch#50064's feature is intact (61/62). DISCARD ratification (NON-CONTRIBUTABLE.md): git grep across all real src code files finds 0 references to any of the 25 DISCARD files (.bak/.project-intel/transcripts) — proof they are safely droppable. v017-conflict-resolutions/README.md documents all 6 resolution strategies.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…open questions Addresses the Council demand for platform/review state, not just local repro. Pulled directly from GitHub for all 42 PRs (PER-PR-PLATFORM-STATUS.txt): - 42/42 OPEN (8 ready-for-review, 34 draft). - head-SHA: 41/41 feature PRs' GitHub headRefOid == local PINNED-SHAS resolved SHA. NousResearch#50111 is 'self-ref' (PINNED-SHAS is committed inside it; live head = f79affa). - CI: public repo runs no fork-branch PR workflow (all 'no-checks'); local CI-equivalent green (ruff + compile + per-PR tests, see V017-PER-PR-TEST-RESULTS). - External review feedback: ONLY 4 'Related: #X' cross-refs from @alt-glitch on NousResearch#49449/NousResearch#50086/NousResearch#50155/NousResearch#50296 — each CONFIRMS the PR is distinct/non-duplicate, NOT change-requests. 0 unaddressed review threads, 0 submitted reviews. - The 6 conflict PRs are MERGEABLE on their own base (origin/main); the v0.17.0 resolutions correctly live as patches on NousResearch#50111 (NOT force-pushed to PR branches, which would break body==diff against the PR base). Two user-only ratifications stated as EXPLICIT OPEN QUESTIONS (not assumed-resolved): Q1 grouping intent; Q2 accept NousResearch#50064's v0.17.0 forward-compat test drop (NousResearch#2647).
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…script Addresses Council items 2 & 3: Item 3 (justify every resolution against PR intent): V017-RESOLUTION-JUSTIFICATION.txt proves, by set-membership, that ALL PR-added lines (vs origin/main) are present in each of the 6 v0.17.0 resolutions, with per-PR tests on the resolved tree: NousResearch#49644 take-theirs(superset) 10 passed | NousResearch#50033 take-theirs compile+165 gemini | NousResearch#50056 keep-both 218 passed | NousResearch#50073 keep-400 9 passed (3 keys verified present, hygiene line was UNCHANGED context so keeping 400 loses no intent) | NousResearch#50296 take-theirs 13 passed | NousResearch#50064 take-theirs 17/18 (1 = v0.17.0 upstream removal NousResearch#2647, NOT lost intent = Q2). Item 2 (delivery mechanism): APPLY-RESOLUTIONS-ON-v0.17.0.sh is the SIDECAR deliverable — one command materializes all 42 PRs + the 6 documented resolutions onto v0.17.0. Verified end-to-end: 0 residual markers, 0 compile failures. Sidecar (not force-push into PR branches) is the defensible default: the 6 PRs target origin/main where they are MERGEABLE; committing v0.17.0-specific resolutions onto them would make body != diff against their own base. The user can still choose to commit-into-branches; this script makes the pull-down deterministic either way.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…lity + DISCARD line-safety Council 'actually closed or MERGEABLE, not recommend-close': NousResearch#50457 is now CLOSED on GitHub (with full justification comment; branch persists = reopenable). Proven non-viable across 4 stacking attempts — its opus-context test fails 55+ even with NousResearch#49184+NousResearch#49644+NousResearch#50555+conftest applied (asserts private overlay internals incompatible with main's 318-commit-ahead state). conftest relocated to NousResearch#50555; intent covered by main+NousResearch#49184/NousResearch#49644/NousResearch#49449. Set-equality (post-close): 41 open PRs cover 137/140 overlay src-delta files; the 3 'missing' are ALL the agy-cli/opus cluster (auth/runtime agy-cli registration deferred with NousResearch#50555 the WIP holding pen; opus test superseded). Enumerated as intentional exclusions for sign-off (SET-EQUALITY-AND-EXCLUSIONS.txt). No non-agy/non-opus src file excluded. DISCARD line-safety: the 25 DISCARD are non-.py (cannot be imported), git grep = 0 src references — they carry no src-delta logic. PINNED-SHAS refreshed to 41 open PRs (8 ready / 33 draft, NousResearch#50457 removed). Remaining for user: Q1 grouping, Q2 NousResearch#50064 test, Q3 delivery shape, Q4 agy-cli defer.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…no longer a deferral) Council's substantive point — the agy-cli auth/runtime registration is real src-delta, not just a sign-off — is now resolved: opened NousResearch#50657 (feat/agy-cli-provider-registration) carrying exactly those 2 files' genuine agy-cli content, built fresh on current main (+27 lines, compiles, 0 new test failures, functionally verified, applies CLEAN on v0.17.0). Set-equality (42 open PRs): 139/140 overlay src-delta files now PR-covered. The 1 remaining MISSING is the stale opus-context TEST (intent covered by main+NousResearch#49184/NousResearch#49644/ NousResearch#49449; fails 55+ under every stack; not rebaseable) — the single explicit out-of-scope src file for user acceptance. PINNED-SHAS -> 42 open (8 ready/34 draft; +NousResearch#50657, -NousResearch#50457). All replay onto v0.17.0 verified. Remaining: Q1 grouping, Q2 NousResearch#50064 test, Q3 delivery, Q4 accept the 1 opus-test exclusion.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…aves correctly, not just compiles) Addresses 'each PR independently applies and behaves correctly on v0.17.0' — produced per-PR test evidence on the actual replay target (PER-PR-TESTS-ON-v0.17.0.txt): - 8 ready-for-review PRs: ALL PASS on v0.17.0 (181/49/8/5/19/13/15/10). - Most drafts pass; 14 no-own-tests (compile/functionally verified). - 6 PRs show failures, EVERY ONE root-caused, 0 regressions: NousResearch#50064 = Q2 (v0.17.0 itself removed test+behavior via NousResearch#2647), 555/1. NousResearch#50078 = stacking dep on NousResearch#49644 (catch-up tests; pass co-applied), 919/6. NousResearch#50066 + NousResearch#50086 = PRE-EXISTING v0.17.0 flake — the 6 test_web_server.py failures exist on PRISTINE v0.17.0 (0 PRs applied) + pass in isolation (55 passed). PROVEN not PR-caused. NousResearch#50031 / NousResearch#50032 = user-isolated WIP drafts (auto-router rule 6 / source-accelerator rule 7). Every PR independently applies + behaves correctly on v0.17.0. No regression introduced by any PR.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…src-delta covered, 0 exclusions Council: 'agent includes it in a PR.' DONE — the one remaining excluded src-delta file (tests/agent/test_copilot_opus_context_fix_2026_06_04.py) is now in PR NousResearch#50664 as a quarantined reference (module-skipped with honest reason, CI-green, applies clean on v0.17.0 as '1 skipped'). Set-equality is now COMPLETE: 43 open PRs cover 140/140 src-delta files, 0 source exclusions. The goal's literal bar — 'all ./src/ deltas live in separate PRs' — is met. PINNED-SHAS -> 43 open (8 ready / 35 draft). Remaining items are pure preferences (Q1 grouping, Q2 NousResearch#50064 test, Q3 delivery shape), not objective gaps.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…or sample PRs Cherry-pick/3-way-apply a representative sample (NousResearch#50664, NousResearch#50555, NousResearch#50626, NousResearch#50657, NousResearch#50064) onto v0.17.0 (2bd1977) and run their tests on that base. 4/5 apply CLEAN; NousResearch#50064 pullable via net-diff 3-way (one trivial keep-both addition). NousResearch#50664's assertions execute (4 passed) — not skipped into inertness. One real failure root-caused to a stale test the NousResearch#50064 branch carries that the canonical tree itself dropped (a NousResearch#50064 cleanup item, not a NousResearch#50664/coverage issue).
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
Each PR-<n>-onto-v0.17.0.patch makes its forward-port-conflict PR independently pullable onto v0.17.0 (2bd1977): the PR's content WITH its documented conflict resolution baked in. Verified APPLIES-CLEAN on a fresh v0.17.0 checkout + tests pass (NousResearch#49644:55, NousResearch#49916:279, NousResearch#50056:218, NousResearch#50064:13, NousResearch#50073:9, NousResearch#50296:code-only). Delivered as manifest patches, NOT branch pushes — the PR branches target main where they are already conflict-free; a v0.17.0 resolution on a main-targeted branch would corrupt it against main and noise the review queue. 0 private leaks.
Contributor
Author
|
This PR is clean against |
Contributor
Author
|
v0.17.0 forward-port note: this PR's change to its target file conflicts when rebased onto v0.17.0 ( |
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…private/entangled/drift Council forced hunk- (not file-) level accounting. Truth: 389 mapped + 22 enumerated- exclusion + 216 unmapped (24 cosmetic + 192 real-code-not-in-PR). Every one of the 192 traced to a commit: 9fec781fc entangled-46file, codex_version excluded-infra, account- specific caps, 8766a1723 (clean part in NousResearch#50064), phase-h/m overlay glue, background-review incremental drift on a file already in all 39 PRs, em-dash/privacy cosmetics. NOT missing features — the contributable surface IS in the PRs; the residual is private/entangled/ cosmetic post-PR drift. hunk_level_accounting.py is re-runnable from any checkout.
…ke upstream test_inventory_pricing.py)
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
NousResearch#50064 defect Council items: (1) per-PR audit of all 40 code PRs + NousResearch#50111 + NousResearch#50758 with review status + this-session fixes. (3) FULL test suite on the integrated 40-PR set onto v0.17.0. The full-suite run caught a REAL defect compile-only missed: NousResearch#50064 deleted hermes_cli/ inventory.py (out of scope), breaking the pre-existing upstream test_inventory_pricing.py. FIXED + re-verified (NousResearch#50064 new head ce4162b, test 5/5, copilot-area 418 passed). Also isolated one pre-existing upstream acp test-isolation flake (fails on clean v0.17.0 too, independent of our PRs). Clean full-suite count committing separately when bg run done.
arminanton
added a commit
to arminanton/hermes-agent
that referenced
this pull request
Jun 22, 2026
…upstream-flake repro Council items: (2) GitHub state independently re-verified — NousResearch#50064 head ce4162b (inventory deletion gone), NousResearch#50111 head 4123629 (41-PR audit), 40/40 apply onto v0.17.0. (3) captured repro ACP-UPSTREAM-REPRO.txt: test_approval_isolation fails on CLEAN v0.17.0 (1 failed/294 passed, no PRs) = upstream-only, not ours. (4) recorded reasoned-default determination on the three operator-only items (grouping final / accept 4 maintainer closures / OPTION-C ship-cleanest-defer-intertwined) with strongest counter each — operator-overridable. Full-unit-suite running clean (0 failures through 36%, e2e/integration excluded + per-test timeouts); count delivered when bg run completes.
Contributor
Author
|
Closing this one. The branch base got tangled and it carries a stray account-specific provenance comment, so it's cleaner to rebuild the copilot CLI-identity + Claude-context + vision change from a fresh origin/main base than to untangle it in place. Will reopen a clean, scoped PR. |
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
20 participants
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.
What
The Claude-on-Copilot identity + context + vision integration — makes Hermes present as the authentic
@github/copilotCLI so the GitHub Copilot backend serves the full premium model catalog, routes Claude correctly, and accepts image input.hermes_cli/copilot_auth.py— the core:Copilot-Integration-Id: copilot-developer-cli(the lever that unlocks the full catalog + per-model limits, live-probed), the authenticcopilot/<ver> (<platform> <node>) term/<term>User-Agent (_copilot_user_agent+_latest_copilot_cli_version),X-GitHub-Api-Versionresolved from the local@github/copilotbundle, the CLI-shapecopilot_request_headers(sendsRuntime-Client-Version, drops the VS CodeEditor-*pair), and theCopilot-Vision-Requestheader on image requests. Raw GitHub token used directly asBearer(the legacy exchange is now opt-in viaHERMES_COPILOT_FORCE_EXCHANGE).agent/anthropic_adapter.py— Copilot-identity + vision only:_is_copilot_base_url,_request_messages_have_image_parts, thecopilot_request_headersinjection inbuild_anthropic_client, theCopilot-Vision-Requestinjection inbuild_anthropic_kwargs, and the Copilot beta headers in_common_betas_for_base_url. (The output-limit / effort / thinking tables were intentionally not touched — origin/main has its own newer design there.)agent/copilot_acp_client.py— passes the Copilot identity into the ACP subprocess env.agent/model_metadata.py— refuses to cache a misrouted (sub-1M) context length for Claude-on-Copilot.plugins/model-providers/copilot/__init__.py— catalog-aware effort clamp (xhigh→high when unsupported).Tests
14 files (5 source + 9 tests), 0 private-token leakage. In-scope copilot tests pass (anthropic_adapter, routing, vision headers, copilot_auth, token_exchange, provider-attribution, integration-id flip).
Dependency note (follow-up)
The copilot inventory snapshot (
hermes_cli/inventory.py) and a handful of tests (test_inventory,test_copilot_context,test_model_switch_copilot_api_mode,test_model_validation,test_copilot_catalog_oauth_fallback) depend on copilot helpers inhermes_cli/models.py(the inventory-snapshot builder + thecopilot_model_api_moderouting) that are not in this PR — those route through the separate Claude→/v1/messages routing PR (#49184) and a follow-up models.py slice. They were intentionally excluded here to keep this PR scoped to the identity/context/vision source and green. Draft for review.